ArXiv Domain 2026-10-15
数据来源：ArXiv Domain
LLM Domain Papers
1. PsyBer-Agent: A Psychology-Driven User Agent for Recommender Systems
Abstract:Evaluating recommender systems before deployment requires simulators that remain realistic over long, closed-loop interaction cycles. Current LLM-based agents generally function as surface imitators that generate realistic short-term responses but fail to capture the underlying user dynamics such as fatigue, affect, and shifting preferences. We propose PsyBer-Agent, a psychology-inspired simulator that models these dynamics through its Psy-Engine. This engine represents each user with three evolving, model-defined latent states. To calibrate simulated behavior against real interaction logs, we align log-conditioned reference trajectories with simulator-generated latent-state trajectories via Unbalanced Gromov—Wasserstein optimal transport. This approach provides structured supervision for a lightweight policy without the computational burden of fine-tuning the backbone LLM. We also introduce WebSim and the PsyBer Benchmark, which encompass multimodal scenarios and seven recommender backbones. Our framework evaluates behavioral fidelity, latent-state consistency, robustness, and responses to social-cue perturbations. On the tested horizons, PsyBer-Agent shows lower behavioral discrepancy than the prompt-only simulators while maintaining stable performance under large-scale concurrent simulation for up to 5M queued simulation tasks under bounded concurrency. Code is available in the supplementary material and at: PsyBer-Agent: this https URL, WebSim Platform: this https URL.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.13989 (HTTP 429)
Authors: Chong Zhang, Qijie Shen, Haichao Zhang, Can Wang, Xiaobo Jin, Jia Wang
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.13989.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.13989
Published: 2026-10-15T01:49:16.022Z
2. Loose Lips: Understanding Privacy Leakage in Agentic Dialogue
Abstract:As LLM agents are increasingly deployed in high-stakes enterprise settings, understanding how they handle sensitive information in agentic dialogue has become critical. Privacy leakage in such settings requires reasoning about whether information flows respect the contextual norms under which they originated. We extend CIMemories to CIMEMORIES DIALOGUE, a benchmark of 4,410 two-agent dialogue instances grounded in Contextual Integrity theory. Using this benchmark, we systematically evaluate 7 open-weight models from the Qwen3 and Llama 3.1 families across conversation lengths of 1 and 6 turns under three prompting conditions. We find that task capability and privacy leakage are fundamentally coupled: more capable models are systematically leakier, with no model in our evaluation able to decouple the two. Thinking models consistently leak more than their non-thinking counterparts, a pattern we attribute to the extended reasoning surface created by chain-of-thought. Leakage compounds with conversation length, rising up to 3x from 1 to 6 turns. Our results suggest that the coupling between task capability and privacy leakage is not an artifact of misconfiguration but a structural feature of current agentic systems.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14071 (HTTP 429)
Authors: Soumya Sharma, Ayana Hussain, Heber Hwang Arcolezi, Ulrich Aïvodji, Spandana Gella, Adriana Romero-Soriano, Golnoosh Farnadi
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14071.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14071
Published: 2026-10-15T01:49:16.022Z
3. Is the Future Predictable? Modeling Future Predictability for Reliable Temporal Reasoning
Abstract:Large language models (LLMs) remain unreliable when reasoning about the future. Existing models often overlook the difference among future states, committing to specific answers even when the queried facts are inherently volatile. To capture this challenge, we introduce ChronoRegime, a future-oriented temporal reasoning task that requires models to determine whether historical temporal evidence justifies commitment to a future answer. Furthermore, we propose Confidence-Aware Temporal Reasoning (CTR), a framework that estimates future predictability from temporal dynamics and regulates answer commitment accordingly. Rather than performing unconditional forecasting, CTR commits only when the reconstructed evidence supports the target future state. Across multiple LLMs, CTR improves strict overall accuracy by 6.7 percentage points and reduces hallucination rates by 18.4 percentage points on average over the plain QA baseline. These results demonstrate that explicit predictability assessment is an effective mechanism for safer and more reliable temporal reasoning under future uncertainty.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14073 (HTTP 429)
Authors: Yongyi Huang, Huaping Zhang, Wenyao Cui, Qiuchi Li, Lei Li, Baohua Zhang
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14073.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14073
Published: 2026-10-15T01:49:16.022Z
4. Fin_Agent at FinEval 2026: Task-Aware Methods for Multilingual Financial NLP
Abstract:We present Fin_Agent, our submission to the FinEval 2026 shared task on multilingual fi nancial language understanding. Our sys tems address Greek financial named-entity recognition, Japanese implicit communication recognition, and multilingual financial ques tion answering. For Greek NER, we com bine annotation-aware numeric rules with zero shot Qwen2.5-32B classification, achieving 0.9521 public F1 and 0.8884 private F1. For Japanese implicit communication, an inter pretable cue-based ordinal scorer achieves 98.0% test accuracy. For multilingual financial QA, BGE-M3retrieval with Qwen3-32B gen eration achieves 0.3023 and 0.3419 ROUGE-1 F1 on the public and private splits. Key limita tions include dataset-specific rules, handcrafted cues, and limited supervision. Implementa tion code is available this https URL Rashidnira/finagent-fineval-2026.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14101 (HTTP 429)
Authors: Mohotarema Rashid, Tanzina Hossain, Xiaoying Song, Lingzi Hong
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14101.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14101
Published: 2026-10-15T01:49:16.022Z
5. Does System One Transfer? Calibrated Typed-Decision Models, Label Budgets, and Translation for Indonesian Regional Languages
Abstract:Calibrated typed-decision (“System One”) models return a label and a probability in a single forward pass at a small fraction of the cost of large language models (LLMs), yet their evaluation has been almost entirely English. We report a pre-registered evaluation of the commercial Jev model and the open Laya-multilingual model on Indonesian regional languages, using the parallel NusaX sentiment (12 languages) and NusaTranslation sentiment and emotion (7 languages) test sets. Jev is more often correct on sentences that are lexically closer to Indonesian in all three datasets, and presenting the human Indonesian translation instead raises its accuracy by up to 37.2 points, most in languages distant from Indonesian. Its expected calibration error does not grow on regional languages, but its ability to rank its own errors degrades in all three datasets. Retrained classifiers need more than 500 labels per language to match zero-shot Jev in 9 of 10 NusaX regional languages. A confidence-gated cascade that sends Jev’s 10-30% least confident decisions to a local IndoBERT classifier matches or exceeds the better of the two systems, and routing to an LLM instead matches that LLM at 24-77% lower API cost. Of six further commercial LLMs (three Claude and three GPT models), five are 4-14 points more accurate than Jev, at several hundred times the API cost where it is reported, while the smallest (Claude Haiku) is less accurate. We release the pre-registration, code and all predictions.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14112 (HTTP 429)
Authors: Romi Fadli, Rusdah, Wahyu Ramadani Putri Utami, Zulfa Malika Amana
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14112.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14112
Published: 2026-10-15T01:49:16.022Z
6. Next-Concept Modeling: Fast, Parallel Coarse-to-Fine Text Generation
Abstract:Diffusion language models (DLMs) offer parallel sampling for faster generation than autoregressive models, an increasingly important advantage as inference becomes a dominant computational workload. However, DLMs degrade quickly with fewer sampling steps, process the full sequence at every step, and require many passes over the dataset to reach good quality. We introduce Next-Concept Modeling (NCM), a two-stage, coarse-to-fine framework: a multiscale residual VQ-VAE encodes text into a hierarchy of discrete codes, and a transformer generates one level at a time, predicting all codes within a level in parallel. At matched parameter scales, NCM achieves better generative perplexity than the strongest DLM baseline on LM1B while running $21\times$ faster. On OpenWebText, NCM is competitive with the strongest DLM while running $10\times$ faster; on XSum, it matches the strongest DLM’s ROUGE-L while being $31\times$ faster. On the reasoning task of Sudoku, NCM outperforms autoregressive and diffusion baselines across all difficulty levels, using fewer function evaluations. On the reasoning task of Sudoku, NCM outperforms autoregressive and diffusion baselines across all difficulty levels, using fewer function evaluations.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14162 (HTTP 429)
Authors: Hermann Kumbong, Ishan S. Khare, Iddah Mlauzi, Andrew Woen, Charles Ding, E. Kelly Buchanan, Simran Arora, Azalia Mirhoseini, Christopher Ré
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14162.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14162
Published: 2026-10-15T01:49:16.022Z
7. Modeling the Arrival Time of Information-Bearing Events in Natural Language
Abstract:Understanding how information is distributed over time is fundamental to modeling natural language. While existing empirical studies primarily rely on post-hoc analysis of information-theoretic metrics, such as surprisal, little is known about the generation processes under the surface. We propose a novel approach for addressing this gap using the tool of neural temporal point processes (TPPs) by modeling the key information-bearing events in text sequences with learnable event intensity functions. Our model takes the history of event intervals and the contextual semantic representations from LLMs as input, and predicts the future arrival times for two types of events: new-word and high-surprisal-token. The experimental results reveal an interesting distinction in event intensities: LLMs tend to produce new words at significantly higher rates than humans, while high-surprisal tokens do not exhibit the difference. A decaying pattern of intensity over time is found in new-word events for both humans and LLMs, but not in high-surprisal-token events. Our findings revisit and extend previous studies that use simpler methods; provide supplementary evidence for theories about constrained context representation inherent in human language production; and find a new angle to view human and LLM generation differences.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14212 (HTTP 429)
Authors: Leyi Lao, Yulin Ou, Yang Xu, Hao An
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14212.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14212
Published: 2026-10-15T01:49:16.022Z
8. Agentic Data Engineering for LLMs: System Design and a Controlled Empirical Study
Abstract:LLM data engineering requires iterative experimentation to determine how data selection, rewards, and curricula affect model learning, making it a natural setting for AI-for-AI (AI4AI) research. Can agents use experimental feedback to progressively improve strategies, and do the resulting strategies improve target-model performance on held-out data? We study how agents use experimental feedback to develop data-engineering strategies under fixed training and evaluation protocols. Our Agentic Data Engineering (ADE) framework lets agents pursue, revise, or combine research directions using cumulative findings. Strategies are selected by in-loop scores and evaluated on held-out benchmarks. Across four tasks-math and code data selection, math reward design, and math curriculum learning-selected strategies achieve absolute gains over generic baselines of up to 13.34% on AIME25 Pass@32 and 5.85% averaged across four held-out benchmarks under fixed training conditions. In-loop scores improve over successive experiments, while held-out trajectories show that later in-loop gains do not always improve generalization. Comparisons of research organization and feedback access favor combining evidence analysis with cumulative findings. Research trajectories show how earlier findings inform strategy revisions and combinations across research directions.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14238 (HTTP 429)
Authors: Ruomeng Ding, Qianli Shen, Zhaoyang Han, Meixin Chen, Daoyuan Chen, Yaliang Li
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14238.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14238
Published: 2026-10-15T01:49:16.022Z
9. The Thinking Leakage in Reinforcement Learning for LLMs
Abstract:Hybrid reasoning models such as the Qwen3 series switch between a THINK mode and a NO-THINK mode through a few chat-template tokens. A popular recipe trains such models with reinforcement learning in NO-THINK mode and reports improved reasoning performance. We provide evidence that much of this gain can be explained by thinking leakage: the gain comes largely from partially reactivating the reasoning abilities of the original model’s THINK mode instead of learning enhanced reasoning behavior. We train Qwen3-1.7B, 4B, and 8B with GRPO in NO-THINK mode. As accuracy improves, responses become longer and more reflective, are increasingly judged by the original model to resemble its own thinking, and the model’s internal activations shift toward its THINK mode. We then investigate at the level of weights, activations, and attention heads: scaling the RL update further elicits THINK-mode behavior and approaches THINK-mode accuracy but does not exceed it; in Qwen3-8B, replacing a low-dimensional THINK-related activation subspace of the RL-trained model with its original-model value removes most of the RL gain, and the reverse exchange transfers a considerable fraction of the gain to the original model; and the RL-induced shift passes through the attention heads that read the empty think block. We further identify a possible mechanism in the GRPO training signal: responses favored by the advantage-weighted update are more THINK-like, and a gradient step computed from this signal moves the model toward its THINK state. Thus, gains in NO-THINK mode can largely reflect reactivation of reasoning abilities already present in the original model.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14270 (HTTP 429)
Authors: Wenxuan Zhu, Shuming Liu, Bang An, Aznaur Aliev, Bing Li, Yibo Yang, Bernard Ghanem
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14270.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14270
Published: 2026-10-15T01:49:16.022Z
10. ASSET: Adaptive Speech Segmentation via Reinforcement Learning
Abstract:Speech large language models (LLMs) are often built using pretrained acoustic encoders as an audio interface to an LLM decoder. However, LLMs scale poorly with input sequence length, while acoustic encoders tend to produce substantially longer sequences than typical textual inputs. This motivates learning to compress encoder outputs while preserving task-oriented information. To this end, we introduce ASSET, a reinforcement learning (RL)-based framework that learns to adaptively compress encoder outputs by first partitioning them into variable-duration segments and then pooling each segment into a continuous audio token. We use group-relative policy optimization (GRPO) to train a segmenter with task performance feedback and a token-rate penalty. In automatic speech recognition (ASR) experiments, ASSET achieves performance comparable to a transcript-assisted character-boundary oracle with approximately 25% fewer audio tokens on English LibriSpeech, while improving on a phone-boundary oracle at a similar token rate on Mandarin AISHELL. Exploratory experiments on non-ASR tasks further illustrate how learned segmentation changes when the framework is adapted to tasks beyond transcription.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14309 (HTTP 429)
Authors: Cihan Xiao, Yuan Tseng, Matthew Wiesner, Desh Raj, Leibny Paola Garcia Perera, Sanjeev Khudanpur, David Harwath
Categories: cs.CL
PDF URL: https://arxiv.org/pdf/2610.14309.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14309
Published: 2026-10-15T01:49:16.022Z
Agent Domain Papers
1. Artificiality’s First Exam: An LLM-Referenced C-test for Supraintelligence
Abstract:Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or saturates soon. How can we then evaluate machines that may become more capable than the current machines and the people who write the tests? One answer to the question hinges on inverse problems, inductive inference questions for which difficulty depends on the complexity of the underlying mechanism, given the observations and the previous knowledge. Levin’s Kt, a computable variant of Kolmogorov complexity, puts a theoretical upper bound to that difficulty, balancing the simplest representation encoding for the mechanism and the logarithm of the time steps to run that mechanism. Previous tests derived from Levin’s Kt, such as the original C-test, are based on minimalistic Universal Turing Machines (UTM), capable of very limited representations and no previous knowledge. Reasoning large language models (LLM) are UTMs that capture a compendium of human culture as knowledge, using prompts as natural language programs. This paper presents the first test based on Levin’s Kt with LLMs as representational machines. Fresh test items can be produced at high difficulties, estimated in a ratio scale measured in bits, before any human or frontier model can solve them. We formalise the measure, devise a lightweight generation and certification pipeline, explore the effect of the power of the reference machine and the gap between examiner and examinee. We produce a first battery of certified items administered to twelve LLMs. The resulting agent characteristic curves decrease with difficulty, down to the uncharted high-difficulty region, the supra-intelligence window of items we can certify, yet beyond generations of frontier intelligence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14005 (HTTP 429)
Authors: Jose Hernandez-Orallo
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14005.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14005
Published: 2026-10-15T01:49:30.977Z
2. The Silent Failures in Agentic Data Science
Abstract:Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14115 (HTTP 429)
Authors: Xue Li, Hongqian Xia, Daniel Gomm, Aécio Santos, Cornelius Wolff, Madelon Hulsebos
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14115.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14115
Published: 2026-10-15T01:49:30.977Z
3. ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Abstract:The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both agent-free and agent-based task validation; Training, which updates the agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the agent’s rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and ClawGym-Bench. The iteratively refined tasks are further transferred to smaller-scale Qwen3.5-4B and 9B models with gains across all benchmarks, validating data quality independently of the loop model.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14118 (HTTP 429)
Authors: Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14118.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14118
Published: 2026-10-15T01:49:30.977Z
4. Correction Training for Diffusion Models
Abstract:Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier steps, something it has never seen at training time. This might be one reason diffusion models often struggle without additional help, such as CFG. We introduce a correction step for diffusion models which attempts to reduce this training-inference gap. The corrector takes the base model’s prediction as input and is trained against the same ground-truth target. This makes correction an explicit learning task, with training inputs provided by the base model. During sampling, at each denoising step, we iteratively refine the denoiser’s clean-sample prediction. This allows us to correct predictions at intermediate denoising steps, preventing early artifacts from persisting into the final sample. Although the corrector is trained only on predictions from the base denoiser, it can be applied repeatedly to its own outputs at inference for better results. This simple framework leads to substantial improvement in sample quality while largely preserving diversity. We evaluate our method across DiT, SiT, and JiT. Our method substantially improves upon previously reported FID scores for unguided generation and, notably, unconditional generation, where producing high-quality samples without guidance has been particularly challenging. Our method achieves performance competitive with classifier-free guidance (CFG), and combining correction with CFG further improves diversity and reduces oversaturation typical of CFG. Finally, we show that the additional inference cost of correction can be amortized by distilling the refined predictions back into the base diffusion model, retaining the quality gains without additional inference-time overhead.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14136 (HTTP 429)
Authors: Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14136.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14136
Published: 2026-10-15T01:49:30.977Z
5. Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Abstract:Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary check. We present Long-Horizon-Terminal-Bench 2.0 (LHTB 2.0), an extension of Long-Horizon-Terminal-Bench that preserves its 46 original tasks while correcting task and evaluation-infrastructure defects and extending 31 tasks. LHTB 2.0 contains 77 tasks across 13 domains and eight task types. The extended tasks are produced through a systematic reconstruction-task pipeline. We start from a working scientific or engineering artifact, then use a parameterized reference implementation to generate multiple scenarios, reveal six as behavioral evidence, hold out three for evaluation, and use dense progress ladders to reward partial progress while preventing memorization of public outputs. We also extend the evaluation horizon from 90 minutes to three hours and record verifier checkpoints every 30 minutes, enabling direct measurement of sustained progress within a run. Across 1,145 scored model-task runs from 15 frontier models, GPT-6-astra leads with dense mean reward 0.69 and 37 tasks at R at least 0.95, followed by GPT-5.6-sol with dense mean reward 0.67 and 32 tasks at the same threshold. On the 30 reconstruction tasks, binary verifier scores average 0.221, whereas dense ladder scores average 0.653, showing that outcome-only evaluation discards substantial intermediate progress. LHTB 2.0 provides a broader, hardened, and process-aware testbed for studying reliable agent execution over hours.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14146 (HTTP 429)
Authors: Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu, Tong Zheng, Ninghao Liu, Lichao Sun, Haitao Mi, Leowei Liang
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14146.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14146
Published: 2026-10-15T01:49:30.977Z
6. VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation
Abstract:VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine through standardized, high-quality datasets and multi-institutional collaboration across academic and non-academic sectors. This framework addresses the gap between AI advances in human medicine and the fragmented state of veterinary AI development.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14149 (HTTP 429)
Authors: Katherine J. Koebel, Renata Ivanek, Parminder Basran, Jennifer Sun, Casey Cazer, Gayatri Anil, Tommaso Banzato, Liz Barton, Dottie Cimino Brown, Leszek Bukowski, Marta Castelhano, Simon Coghlan, Christopher De Sa, Nikki Dutta, Hala Ghali, Julio Giordano, Joshua Glass, David C. Hogg, Nicholas Hollingshead, Adam Kiehl, Ziang Liu, Monica Meduri, Param Mohapatra, Kim Nayyer, Amelia Nelson, Peter-John Mantyla Noble, Christopher Pinard, Beryl Rabindran, Scott Ross, Ron Seccia, Moira Sheehan, Fei Wang, Tracy L. Webb, Kilian Q. Weinberger, Heather M. Whitney, Chen Xin
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14149.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14149
Published: 2026-10-15T01:49:30.977Z
7. Unconstrained CTI-REALM with Open-Weights
Abstract:Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and far more expensive closed frontier models. We study that choice on CTI-REALM (arXiv:2603.13517), a benchmark in which an agent turns a threat-intelligence report into a working detection by querying a live telemetry store. We evaluate twenty-six models, nineteen open-weight and seven closed, under a common harness, scorer and panel of LLM judges. Our main finding is that an open-weight model can match the strongest closed models at less than a tenth of their cost, provided it is given enough turns. The benchmark’s published limit on agent messages is a confound: a task that exhausts the limit scores zero on every checkpoint, including those it had already passed, so results at that limit partly measure which models finish in time. At the published limit the leading open-weight and closed models cannot be distinguished. With the limit relaxed, the models it was truncating recover, and the highest rewards belong to open-weight models. Among the leading models, price is a poor guide to capability: models with similar rewards differ in cost by more than an order of magnitude. Because the benchmark’s checkpoint scores largely record what an agent did or mentioned, we also introduce stage-level metrics that score what the agent submits, by executing its detection queries in the telemetry store and judging its outputs against the answer key. Rather than combining them into one more overall reward, we show that different models lead different stages, which suggests routing each stage of the workflow to the model that performs it best rather than choosing a single model by its overall score. We also report how many tokens each model generates, and find that the share of output spent on thinking does not track the reward.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14180 (HTTP 429)
Authors: Sahil Garg, Ruhi Gottumukkala, Vishal Agarwal, Shubham Vishwakarma
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14180.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14180
Published: 2026-10-15T01:49:30.977Z
8. Visualizing the World Model in an Agent’s Value Function
Abstract:Could model-free reinforcement learning algorithms actually be learning a model of the environment? In this work, we apply counterfactual interventions which hold everything about a state fixed, besides a targeted change, to explore if the value function of a Proximal Policy Optimization agent forms a world model of the Crafter environment. Despite only being trained to optimize reward, we discover that the value function learns concepts such as the rules governing when a diamond is collectible, water and food having an impact on health, heuristics regarding inventory, and more. Finally, we discuss the safety implications of our visualizations and some shortcomings of current reinforcement learning agents that will prevent us from building truly advanced machine intelligence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14186 (HTTP 429)
Authors: Shawheen Naderi, Fatemeh Akherati, Yubei Chen
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14186.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14186
Published: 2026-10-15T01:49:30.977Z
9. Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models
Abstract:Explaining a vision—language model (VLM) prediction requires tracing training-example influence to the multimodal evidence that mediates it, yet existing attribution methods largely operate only at the sample level. Recent latent-mediated influence methods provide feature-level attribution in language models, but lack the multimodal and spatial structure needed to ground influence in VLMs. We introduce MOSAIC (Multimodal Orthogonalized Sparse Autoencoders for Influence Characterization). It learns a shared sparse image—text latent space whose concepts are 1) sparse within each modality, 2) supported on contiguous image regions, 3) aligned to the phrases that describe them, and 4) approximately decorrelated. It then applies EK-FAC to decompose training-example influence through these concepts and localize their contributions to specific text phrases and image regions. We evaluate MOSAIC on Qwen and Gemma across captioning, chest X-ray understanding, and visual question answering. The learned features are more localized and coherent without degrading task behavior, and ablating influence-ranked latents changes model outputs more than ablating latents ranked by activation or frequency. We find that visual evidence can substantially reorganize training-data attribution while preserving more of the shared latent structure. MOSAIC thus connects where model behavior comes from with what multimodal evidence carries that influence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14190 (HTTP 429)
Authors: Laura Yao, Shixing Yu, Jie Peng, Promit Ghosal, Kyra Gan, Tianlong Chen
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14190.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14190
Published: 2026-10-15T01:49:30.977Z
10. Should SLMs be in the Driver’s Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs
Abstract:The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the user. Agents powered by models small enough to run on edge devices keep that data local, but yield far worse results. A third option is to have cloud models write a program that devices execute: the data stays local, but as the program is written before any data is seen, it fails whenever a step depends on interpreting content that appears only at run time. We explore an intermediate architecture, in which the cloud-written program defers bounded questions over user data to a small local model through an ordinary function call. On AppWorld this improves the success rate of a code-only agent in all six combinations of backbone model and test partition we evaluate, by up to 14.9pp, recovering a substantial part of the gap to a cloud-hosted ReAct loop while keeping user data on the device.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14209 (HTTP 429)
Authors: Boris Radovič, Marco Canini, Veljko Pejović
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14209.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14209
Published: 2026-10-15T01:49:30.977Z
Evaluation Domain Papers
1. Artificiality’s First Exam: An LLM-Referenced C-test for Supraintelligence
Abstract:Under the accelerated pace of AI development, any benchmark whose difficulty is calibrated with humans or current AI systems becomes circular, or saturates soon. How can we then evaluate machines that may become more capable than the current machines and the people who write the tests? One answer to the question hinges on inverse problems, inductive inference questions for which difficulty depends on the complexity of the underlying mechanism, given the observations and the previous knowledge. Levin’s Kt, a computable variant of Kolmogorov complexity, puts a theoretical upper bound to that difficulty, balancing the simplest representation encoding for the mechanism and the logarithm of the time steps to run that mechanism. Previous tests derived from Levin’s Kt, such as the original C-test, are based on minimalistic Universal Turing Machines (UTM), capable of very limited representations and no previous knowledge. Reasoning large language models (LLM) are UTMs that capture a compendium of human culture as knowledge, using prompts as natural language programs. This paper presents the first test based on Levin’s Kt with LLMs as representational machines. Fresh test items can be produced at high difficulties, estimated in a ratio scale measured in bits, before any human or frontier model can solve them. We formalise the measure, devise a lightweight generation and certification pipeline, explore the effect of the power of the reference machine and the gap between examiner and examinee. We produce a first battery of certified items administered to twelve LLMs. The resulting agent characteristic curves decrease with difficulty, down to the uncharted high-difficulty region, the supra-intelligence window of items we can certify, yet beyond generations of frontier intelligence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14005 (HTTP 429)
Authors: Jose Hernandez-Orallo
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14005.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14005
Published: 2026-10-15T01:49:43.767Z
2. The Silent Failures in Agentic Data Science
Abstract:Large language models have significantly lowered the barrier to writing code. Naturally, this has also led to the development of data science agents that promise automating the design and execution of data science from task formulation to model development. Existing evaluations of agentic data science (agentic DS) assess downstream predictive performance and code correctness, providing preliminary insight in agentic DS capabilities. We argue that these evaluations overlook the fundamental principles of data science: methodological data science- and domain knowledge. As such, only assessing downstream performance masks methodological failures such as data leakage and inappropriate validation, limiting the development of robust agentic DS systems. In this paper, we evaluate agentic DS beyond accuracy from three different angles: 1) a large-scale analysis of failure modes in common agentic DS frameworks and models across 220 data science tasks, 2) a reusable and extensible test suite with curated data science tasks that test for six specific failures in a controlled manner, and 3) a qualitative assessment of agentic DS pipelines against expert solutions on Kaggle competitions. We find that the majority of agentic solutions contain at least one failure mode despite the complexity of agentic harness or model capacity. Moreover, we identify a positive correlation between the occurrence of data leakage failures and predictive performance, confirming the necessity to evaluate agents beyond accuracy. Our qualitative analysis shows that DS agents generally lack problem solving creativity and domain knowledge, compared to competition-winning data scientists. We believe that principled failure mode analysis, as presented here, should be integral part of agentic DS evaluations, and that the insights we surface will be key in developing trustworthy agentic DS pipelines.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14115 (HTTP 429)
Authors: Xue Li, Hongqian Xia, Daniel Gomm, Aécio Santos, Cornelius Wolff, Madelon Hulsebos
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14115.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14115
Published: 2026-10-15T01:49:43.767Z
3. ClawLoop: Self-Improving Agents via Harness-Native Training Loop
Abstract:The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents operate in sandbox workspaces and interact directly with file systems and shells. While numerous post-training pipelines exist for tool-use agents, their counterparts for harness-based agents remain scarce and are predominantly one-shot and teacher-dependent: a stronger external model synthesizes tasks and collects trajectories, the target agent is trained once, and evaluation results are consumed by human researchers rather than fed back into the loop. Such pipelines are inherently bounded by the capability of the external model and the scope of human prior, leaving no room for self-improvement. To address these limitations, we propose ClawLoop, a framework that enables self-improving without any external teacher model and with minimal prior dependencies. ClawLoop composes three phases into a self-sustaining cycle: Task Synthesis, which generates a diverse pool of training tasks via two complementary construction routines, applies diagnosis-conditioned difficulty growth followed by both agent-free and agent-based task validation; Training, which updates the agent via SFT and/or RL; and Diagnosis and Feedback, which analyzes the agent’s rollout behaviors to produce a capability analysis report that will be used as feedback for task synthesis in the next iteration. Using Qwen3.6-27B as the loop model, ClawLoop yields consistent improvements on SkillsBench, Claw-Eval-Live, and ClawGym-Bench. The iteratively refined tasks are further transferred to smaller-scale Qwen3.5-4B and 9B models with gains across all benchmarks, validating data quality independently of the loop model.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14118 (HTTP 429)
Authors: Hansi Yang, Linji Hao, Hongyan Hao, An Wang, Han Wu, Qi Gu, Xunliang Cai
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14118.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14118
Published: 2026-10-15T01:49:43.767Z
4. Correction Training for Diffusion Models
Abstract:Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed from its own imperfect predictions from the earlier steps, something it has never seen at training time. This might be one reason diffusion models often struggle without additional help, such as CFG. We introduce a correction step for diffusion models which attempts to reduce this training-inference gap. The corrector takes the base model’s prediction as input and is trained against the same ground-truth target. This makes correction an explicit learning task, with training inputs provided by the base model. During sampling, at each denoising step, we iteratively refine the denoiser’s clean-sample prediction. This allows us to correct predictions at intermediate denoising steps, preventing early artifacts from persisting into the final sample. Although the corrector is trained only on predictions from the base denoiser, it can be applied repeatedly to its own outputs at inference for better results. This simple framework leads to substantial improvement in sample quality while largely preserving diversity. We evaluate our method across DiT, SiT, and JiT. Our method substantially improves upon previously reported FID scores for unguided generation and, notably, unconditional generation, where producing high-quality samples without guidance has been particularly challenging. Our method achieves performance competitive with classifier-free guidance (CFG), and combining correction with CFG further improves diversity and reduces oversaturation typical of CFG. Finally, we show that the additional inference cost of correction can be amortized by distilling the refined predictions back into the base diffusion model, retaining the quality gains without additional inference-time overhead.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14136 (HTTP 429)
Authors: Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14136.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14136
Published: 2026-10-15T01:49:43.767Z
5. Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
Abstract:Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its final state passes a binary check. We present Long-Horizon-Terminal-Bench 2.0 (LHTB 2.0), an extension of Long-Horizon-Terminal-Bench that preserves its 46 original tasks while correcting task and evaluation-infrastructure defects and extending 31 tasks. LHTB 2.0 contains 77 tasks across 13 domains and eight task types. The extended tasks are produced through a systematic reconstruction-task pipeline. We start from a working scientific or engineering artifact, then use a parameterized reference implementation to generate multiple scenarios, reveal six as behavioral evidence, hold out three for evaluation, and use dense progress ladders to reward partial progress while preventing memorization of public outputs. We also extend the evaluation horizon from 90 minutes to three hours and record verifier checkpoints every 30 minutes, enabling direct measurement of sustained progress within a run. Across 1,145 scored model-task runs from 15 frontier models, GPT-6-astra leads with dense mean reward 0.69 and 37 tasks at R at least 0.95, followed by GPT-5.6-sol with dense mean reward 0.67 and 32 tasks at the same threshold. On the 30 reconstruction tasks, binary verifier scores average 0.221, whereas dense ladder scores average 0.653, showing that outcome-only evaluation discards substantial intermediate progress. LHTB 2.0 provides a broader, hardened, and process-aware testbed for studying reliable agent execution over hours.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14146 (HTTP 429)
Authors: Zongxia Li, Zhongzhi Li, Yucheng Shi, Ruhan Wang, Junyao Yang, Chengsong Huang, Zhichao Liu, Xiyang Wu, Anhao Li, Yue Yu, Ergan Shang, Fuxiao Liu, Tong Zheng, Ninghao Liu, Lichao Sun, Haitao Mi, Leowei Liang
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14146.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14146
Published: 2026-10-15T01:49:43.767Z
6. VETNET: Assembling Benchmark Datasets for AI-Driven Veterinary Innovation
Abstract:VETNET represents an ecosystem of live benchmark datasets and evaluation frameworks designed to accelerate AI-driven innovation in animal science and veterinary medicine through standardized, high-quality datasets and multi-institutional collaboration across academic and non-academic sectors. This framework addresses the gap between AI advances in human medicine and the fragmented state of veterinary AI development.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14149 (HTTP 429)
Authors: Katherine J. Koebel, Renata Ivanek, Parminder Basran, Jennifer Sun, Casey Cazer, Gayatri Anil, Tommaso Banzato, Liz Barton, Dottie Cimino Brown, Leszek Bukowski, Marta Castelhano, Simon Coghlan, Christopher De Sa, Nikki Dutta, Hala Ghali, Julio Giordano, Joshua Glass, David C. Hogg, Nicholas Hollingshead, Adam Kiehl, Ziang Liu, Monica Meduri, Param Mohapatra, Kim Nayyer, Amelia Nelson, Peter-John Mantyla Noble, Christopher Pinard, Beryl Rabindran, Scott Ross, Ron Seccia, Moira Sheehan, Fei Wang, Tracy L. Webb, Kilian Q. Weinberger, Heather M. Whitney, Chen Xin
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14149.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14149
Published: 2026-10-15T01:49:43.767Z
7. Unconstrained CTI-REALM with Open-Weights
Abstract:Organisations that want language-model agents for security work face a choice between open-weight models, which they can run and audit themselves, and far more expensive closed frontier models. We study that choice on CTI-REALM (arXiv:2603.13517), a benchmark in which an agent turns a threat-intelligence report into a working detection by querying a live telemetry store. We evaluate twenty-six models, nineteen open-weight and seven closed, under a common harness, scorer and panel of LLM judges. Our main finding is that an open-weight model can match the strongest closed models at less than a tenth of their cost, provided it is given enough turns. The benchmark’s published limit on agent messages is a confound: a task that exhausts the limit scores zero on every checkpoint, including those it had already passed, so results at that limit partly measure which models finish in time. At the published limit the leading open-weight and closed models cannot be distinguished. With the limit relaxed, the models it was truncating recover, and the highest rewards belong to open-weight models. Among the leading models, price is a poor guide to capability: models with similar rewards differ in cost by more than an order of magnitude. Because the benchmark’s checkpoint scores largely record what an agent did or mentioned, we also introduce stage-level metrics that score what the agent submits, by executing its detection queries in the telemetry store and judging its outputs against the answer key. Rather than combining them into one more overall reward, we show that different models lead different stages, which suggests routing each stage of the workflow to the model that performs it best rather than choosing a single model by its overall score. We also report how many tokens each model generates, and find that the share of output spent on thinking does not track the reward.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14180 (HTTP 429)
Authors: Sahil Garg, Ruhi Gottumukkala, Vishal Agarwal, Shubham Vishwakarma
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14180.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14180
Published: 2026-10-15T01:49:43.767Z
8. Visualizing the World Model in an Agent’s Value Function
Abstract:Could model-free reinforcement learning algorithms actually be learning a model of the environment? In this work, we apply counterfactual interventions which hold everything about a state fixed, besides a targeted change, to explore if the value function of a Proximal Policy Optimization agent forms a world model of the Crafter environment. Despite only being trained to optimize reward, we discover that the value function learns concepts such as the rules governing when a diamond is collectible, water and food having an impact on health, heuristics regarding inventory, and more. Finally, we discuss the safety implications of our visualizations and some shortcomings of current reinforcement learning agents that will prevent us from building truly advanced machine intelligence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14186 (HTTP 429)
Authors: Shawheen Naderi, Fatemeh Akherati, Yubei Chen
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14186.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14186
Published: 2026-10-15T01:49:43.767Z
9. Cross-Modal Latent Influence: Patch-Level Training Sample Attribution for Vision-Language Models
Abstract:Explaining a vision—language model (VLM) prediction requires tracing training-example influence to the multimodal evidence that mediates it, yet existing attribution methods largely operate only at the sample level. Recent latent-mediated influence methods provide feature-level attribution in language models, but lack the multimodal and spatial structure needed to ground influence in VLMs. We introduce MOSAIC (Multimodal Orthogonalized Sparse Autoencoders for Influence Characterization). It learns a shared sparse image—text latent space whose concepts are 1) sparse within each modality, 2) supported on contiguous image regions, 3) aligned to the phrases that describe them, and 4) approximately decorrelated. It then applies EK-FAC to decompose training-example influence through these concepts and localize their contributions to specific text phrases and image regions. We evaluate MOSAIC on Qwen and Gemma across captioning, chest X-ray understanding, and visual question answering. The learned features are more localized and coherent without degrading task behavior, and ablating influence-ranked latents changes model outputs more than ablating latents ranked by activation or frequency. We find that visual evidence can substantially reorganize training-data attribution while preserving more of the shared latent structure. MOSAIC thus connects where model behavior comes from with what multimodal evidence carries that influence.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14190 (HTTP 429)
Authors: Laura Yao, Shixing Yu, Jie Peng, Promit Ghosal, Kyra Gan, Tianlong Chen
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14190.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14190
Published: 2026-10-15T01:49:43.767Z
10. Should SLMs be in the Driver’s Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs
Abstract:The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the user. Agents powered by models small enough to run on edge devices keep that data local, but yield far worse results. A third option is to have cloud models write a program that devices execute: the data stays local, but as the program is written before any data is seen, it fails whenever a step depends on interpreting content that appears only at run time. We explore an intermediate architecture, in which the cloud-written program defers bounded questions over user data to a small local model through an ordinary function call. On AppWorld this improves the success rate of a code-only agent in all six combinations of backbone model and test partition we evaluate, by up to 14.9pp, recovering a substantial part of the gap to a cloud-hosted ReAct loop while keeping user data on the device.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14209 (HTTP 429)
Authors: Boris Radovič, Marco Canini, Veljko Pejović
Categories: cs.AI
PDF URL: https://arxiv.org/pdf/2610.14209.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14209
Published: 2026-10-15T01:49:43.767Z
VLM Domain Papers
1. How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings
Abstract:Positional embeddings encode the spatial position of each image patch in a Vision Transformer (ViT), allowing the model to distinguish different spatial arrangements of visual content. However, we know little about how the choice of embedding shapes a vision transformer’s internal representation. In this work, we show that Absolute Positional Embeddings (APE) and Rotary Positional Embeddings (RoPE) encode spatial position through different internal mechanisms: APE stores position in explicit features, while RoPE builds it inside attention and rebuilds it when it is withheld. Specifically, in APE models, sparse autoencoders recover causal row- and column-specific features, whereas interventions on RoPE reveal distinct rotary components that separately encode row and column information. Additionally, causal interventions selectively disabling RoPE’s row or column rotations show that decodable row and column information can be independently removed and, once rotations are restored, partly reconstructed, in part by axis-specialized attention heads. Both mechanisms are causally important for classification: permuting APE’s positional features across patches reduces top-1 accuracy by 24—31 points, and ablating the rotations of RoPE’s primary rebuilding head reduces it more than ablating those of any other head. Our findings show that the choice of positional encoding fundamentally changes how spatial information is organized and processed inside Vision Transformers. More broadly, our work demonstrates how mechanistic analysis can reveal how models construct, reconstruct, and maintain structured representations, providing a basis for targeted interventions in vision models.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.13992 (HTTP 429)
Authors: Mahmoud Mannes, Nikhil Maturi, Parva Mehta, Jiwon Jeong, Aravind Singaram Kannappan
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.13992.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.13992
Published: 2026-10-15T01:49:57.677Z
2. SharedSAE: a unified sparse dictionary across u-net blocks and denoising time for diffusion models
Abstract:Concept representations in diffusion models drift across network depth and denoising time, yet existing sparse autoencoders offer only per-block or per-timestep dictionaries, leaving no single feature dictionary for localization and intervention in the network. We present Shared Sparse Autoencoder (SharedSAE), which learns one sparse dictionary shared across four U-Net attention blocks and all 50 denoising steps of SDXL 1.0. A block-specific low-rank input adapter aligns the residual distribution of each block before the shared encoder, and a temporal conditioning module with a shared timestep branch and a block-timestep correction branch absorbs temporal non-stationarity. Despite spanning both axes, Shared SAE preserves a coherent dictionary structure. Built on the shared dictionary, localized feature suppression reduces the number of NudeNet-positive generations in the I2P detector-positive subset from 139 to 1. Tracing sparse features across the trajectory further reveals that concept representations are redistributed across U-Net blocks during generation, shifting from the earliest downsampling block toward intermediate and later blocks as denoising proceeds. SharedSAE thus provides a unified, interpretable, and intervention-ready representation space for diffusion models, enabling concept analysis and erasure at any covered block and denoising step.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.13997 (HTTP 429)
Authors: Longhao Lei, Lan Yao
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.13997.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.13997
Published: 2026-10-15T01:49:57.677Z
3. Pristine Models
Abstract:Training on broad, unfiltered data enables high-quality image generation, but can also teach models concepts that should not be generated; restricting the training data ensures safety, but reduces quality because examples containing unsafe concepts also provide useful knowledge that is not itself unsafe. Existing approaches largely address this trade-off post hoc through concept unlearning, which can lead to catastrophic forgetting as the number of concepts to remove grows. We instead ask whether unsafe concept knowledge can be compartmentalized during pretraining so that access to it can be disabled at inference. We introduce Pristine Models, a novel text-to-image generation architecture with an attention mechanism that encourages the separation of safe and unsafe knowledge into independently parameterized branches. The branch-specific parameters are learned during training, while the unsafe branch can be detached at inference. On ImageNet, Pristine Models enable safer generation while retaining much of the utility of full-data pretraining, achieving higher image quality and better text alignment than training only on safe data or applying post-hoc concept removal. We further scale our approach to CC12M, demonstrating that it remains effective in a substantially larger and more diverse open-world pretraining setting.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14091 (HTTP 429)
Authors: Anirudh Sundara Rajan, Krishna Kumar Singh, Richard Zhang, Yong Jae Lee
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14091.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14091
Published: 2026-10-15T01:49:57.677Z
4. Human Pose Estimation by Probabilistic Mixtures of Gaussian and Uniform Distributions
Abstract:Despite advancements in sub-pixel decoding, modern Human Pose Estimation (HPE) architectures remain constrained by deterministic coordinate extraction from discrete heatmaps, which systematically fails under dense occlusions and Out-of-Distribution (OoD) ambiguities. To address these limitations, we propose a post-hoc continuous probabilistic framework that intercepts raw heatmaps and models them as a Gaussian Mixture Model (GMM) augmented with a spatially agnostic uniform distribution, requiring no architectural modifications or retraining. This continuous representation allows us to comprehensively explore the distinct contributions of density modeling to HPE. We show that the spatial expectation of our fitted GMM achieves precision parity with leading sub-pixel decoders without heuristic post-processing. Leveraging this continuous space, our test-time augmentation aggregates probability distributions rather than discrete activations, mitigating multi-scale heatmap poisoning. Furthermore, because our multimodal GMM parameterization isolates competing spatial hypotheses, it naturally interfaces with geometric regularizers such as Markov Random Fields. However, our analysis exposes the inherent vulnerabilities of 2D kinematic priors under perspective foreshortening and visual degradation. Crucially, this density formulation yields significant improvements in uncertainty quantification: our calibrated geometric covariance volume outperforms standard peak-intensity heuristics in OoD anomaly detection under severe occlusion. For in-distribution calibration, dynamically fusing our geometric metric via Adaptive Softmax reduces or matches baseline Area Under the Sparsification Error (AUSE) across benchmarks and degradation levels. Finally, we establish that this continuous parameterization is extensible to multi-view 3D architectures, bypassing the $\mathcal{O}(N^3)$ voxel memory bottleneck.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14093 (HTTP 429)
Authors: Santiago Reina Alguacil, Ezequiel López Rubio
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14093.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14093
Published: 2026-10-15T01:49:57.677Z
5. Scenes as an Attack Surface: Uncovering Scene-Grounded Safety Failures in MLLMs
Abstract:Existing jailbreak attacks have exposed serious safety weaknesses in multimodal large language models (MLLMs). Most prior attacks rely on specially constructed visual inputs to carry or support harmful intent. In this paper, we uncover a different vulnerability: task-relevant scene semantics alone can shift an MLLM from refusal to compliance, even when the visual input introduces no additional attack instructions and the original task intent remains unchanged. We formalize this failure as a scene-grounded visual safety vulnerability and introduce SceneSafetyBench to investigate it across eight risk categories and nine white- and black-box MLLMs. Our analysis reveals that this failure is associated with how task-relevant visual evidence influences downstream safety representations, suggesting that visual grounding alone cannot fully explain the observed safety shift. Building on this finding, we propose Scene-Grounded Attacks (SGA), which preserve the original task while constructing validated scene-grounded queries and combining their independent responses. Across nine target MLLMs, SGA achieves an average attack success rate (ASR) of 86.17%, outperforming the strongest baseline by 8.55 percentage points and achieving the highest ASR on eight models. Our results identify scene semantics as an overlooked attack surface in MLLMs and highlight a growing tension between stronger visual grounding and robust multimodal safety alignment.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14094 (HTTP 429)
Authors: Tongxi Wu, Yuyang Cheng, Jiacheng Xian, Hu Huang, Zhihao Wu, Menglin Yang, Jian Zhang, Yang Gao
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14094.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14094
Published: 2026-10-15T01:49:57.677Z
6. TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback
Abstract:Classifier-free guidance (CFG) typically applies a shared scale to all latent tokens, although their velocity predictions evolve differently during sampling. We introduce Trajectory-Adaptive Classifier-Free Guidance (TrajCFG), a training-free method for flow-matching models that adapts token-wise guidance using historical changes in guided velocity direction. TrajCFG maps this feedback to bounded scales, assigning stronger guidance to larger directional changes and weaker guidance to more consistent directions. It combines adjacent-step and interval-normalized longer-span feedback, reusing standard CFG predictions without additional model evaluations. Controlled diagnostics and ablations examine the roles of directional feedback, token-wise allocation, and history-span fusion. Experiments on text-to-video, image-to-video, text-to-audio-video, text-to-image, and image-to-3D generation show improvements over base samplers across multiple backbones. For text-to-video generation, TrajCFG improves VBench Total scores by 0.30-0.75 points over the strongest evaluated baseline on each of three backbones. These results support historical directional feedback as a broadly applicable signal for fine-grained guidance allocation. The project page is available at this https URL.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14153 (HTTP 429)
Authors: Jingyu Liu, Hao Jiang, Yikang Ding, Huafeng Shi, Xu Yang, Xiaoqiang Liu, Guoxin Zhang, Pengfei Wan, Kun Gai
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14153.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14153
Published: 2026-10-15T01:49:57.677Z
7. Video-Arena: A Scalable Agentic Video Benchmark for Spatiotemporal Capability
Abstract:Understanding and tracking a dynamic world are fundamental to visual intelligence. Existing video benchmarks provide limited insight into whether models can maintain a coherent understanding of evolving world state. Building such a benchmark from real-world videos is challenging because the underlying world state is partially observable, making annotations hard to obtain. To close this gap, we introduce Video-Arena, a benchmark that turns competitive games into scalable, verifiable tests of how well models understand evolving world states from videos. Specifically, inspired by how humans understand dynamic events, we evaluate spatiotemporal world state understanding and tracking through three task categories: perceiving critical events, interpreting state updates, and tracking the resulting states. Our pipeline can generate videos and aligned reference labels from game records at scale. To keep evaluation affordable and reproducible, we curate a golden set of 180 tasks across 9 games and run evaluations under two protocols: native visual understanding and tool-assisted agentic analysis. The best-performing systems achieve F1 scores of and under the two protocols, respectively. The result highlights that native models struggle to perceive events reliably, while tool-assisted systems improve event recovery but still struggle to interpret state updates and track the resulting states consistently over time. Our project page is in this https URL
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14158 (HTTP 429)
Authors: Kuan Zhang, Yukun Chen, Zhihao Yang, Yue Su, Xiangnan Wu, Zirong Chen, Run Luo, Tao Tan, Yinhe Zheng, Yiming Li
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14158.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14158
Published: 2026-10-15T01:49:57.677Z
8. Token-Budgeted Candidate Retrieval for 3D Scene-Grounded VLMs: Category Names vs. Pairwise Geometry
Abstract:Under a fixed context budget, which objects and relations should a 3D scene-grounded VLM see first? On ScanNet indoor referring benchmarks (Dai et al., 2017), matching the query to object category names outperforms pairwise geometry scoring at every reported K. The gaps are largest at high recall. Analytic pairwise cues beat per-object cue scoring and query-agnostic kNN graphs, including on paraphrases. MiniLM and BGE-small still score higher on those splits. We evaluate token-budgeted candidate retrieval with axis-aligned boxes, a token-ratio metric, training-free baselines, two small encoders that match q to each object’s category name, and QCRR (Query-Conditioned Relation Retrieval), a deterministic pairwise-geometry scorer. Across ScanRefer gt_val plus a custom 20% scan-id split of Nr3D and Sr3D (35,504 queries; not official ReferIt3D val), additive noun matching reaches R@10 0.864 on ScanRefer against QCRR’s 0.626; MiniLM and BGE-small reach 0.911 to 0.913 on ScanRefer and 0.941 to 0.947 on Nr3D. A corrected 3DGraphLLM harness (native Acc@0.25 0.67 on the full graph, n=300 ScanRefer queries) shows that context selection changes downstream accuracy under a matched object budget (Random 0.44, QCRR 0.56, MiniLM 0.67, oracle 0.70). Semantic retrieval beats hand-designed geometry on that harness. We will release the protocol, retriever implementations, and per-query outputs so new selectors can be swapped in without rewriting the analysis.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14207 (HTTP 429)
Authors: Michał Zakrzewski, Mariia Shpir, Taras Rumezhak
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14207.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14207
Published: 2026-10-15T01:49:57.677Z
9. CAPTOR: a vision-language foundation model for Chest-Abdomen-Pelvis Oncologic CT
Abstract:Purpose : To develop and evaluate CAPTOR, a deep-learning vision-language foundation model for oncologic chest-abdomen-pelvis (CAP) CT interpretation. Materials & Methods : CAPTOR (Chest-Abdomen-Pelvis foundaTion model for Oncologic Radiology) is a contrastive vision-language model, trained using a pretraining strategy for oncologic CAP CT (in single- or multiple-series acquisitions), on a multicenter retrospective dataset from North America, Europe and Asia, predominantly from tumor lesion examinations. CAPTOR was compared with state-of-the-art CT foundation models on three downstream tasks: disease detection, survival prediction using TumorImagingBench and image retrieval. Classification and retrieval were both evaluated on held-out internal and public test sets, stratified by anatomical coverage and indication. Bootstrap resampling was used to estimate confidence intervals, and pairwise comparisons were performed using permutation tests. Results : CAPTOR was trained and tested on 25,512 and 10,794 CT-report pairs respectively. TumorImagingBench datasets comprised between 134 and 421 studies each. CAPTOR outperformed all baseline models, on the classification task, on the CAP subset (AUC 0.767, 95%CI: 0.734-0.793, vs. 0.695, 95%CI: 0.645-0.736 for the next-best, p<0.001) and oncologic subset (AUC 0.784, 95%CI: 0.759-0.805, vs. 0.734, 95%CI: 0.703-0.767 p<0.001), ranked first on three of the four oncologic prognostic benchmarks, and achieved superior retrieval performance on CAP and oncologic subsets. Conclusion : A foundation model trained on oncology-enriched CAP CT data outperformed relevant state-of-the-art models in its target clinical context, underscoring the importance of clinically aligned pretraining. We release our preprocessing, training and inference code : this https URL and model weights : this https URL
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14226 (HTTP 429)
Authors: Séléna Jean-Mactoux, Sophie Loizillon, Ghina Jardali, Amandine Crombé, Nathalie Lassau, Alexandre Bône
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14226.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14226
Published: 2026-10-15T01:49:57.677Z
10. Latent World Action Model for GUI Agents
Abstract:Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-perceiving them for action selection. However, this two-stage paradigm faces two key challenges in GUI environments: (L1) the high computational cost of pixel reconstruction and (L2) the need to reconstruct large and diverse appearance-level details beyond what is required for action selection. In practice, this screen-generation objective can induce an identity shortcut problem, where future-state prediction largely preserves the current state rather than capturing action-induced changes. In this work, we reformulate GUI world modeling by shifting the prediction target from full-screen reconstruction to action-induced future information in latent space. Concretely, we leverage a large multimodal model as the latent world model, whose shared representations support two dedicated heads for both action selection and predictive transition modeling. The action head directly translates these latent representations into action selection, while the transition head captures action-conditioned future information. To mitigate the identity shortcut, we further introduce an action-aware contrastive objective that encourages the transition representations to capture discriminative action-induced changes. Extensive experiments across offline and online GUI settings show that our method achieves up to 31.9% and 40.6% relative gains in success rate over pixel-space world models, respectively, while substantially reducing inference latency by up to 98.9%. Our code is available at this https URL.
中文摘要
翻译失败: Translation limit exceeded. Please try it again later.
Response status: 401 (Unauthorized)
Response body : “{\”ShowCaptcha\”:false}”
LLM Analysis
LLM Analysis Failed: Error: Kimi内容未就绪或抓取失败: 2610.14228 (HTTP 429)
Authors: Seungjun Yu, Hojun Choi, Seojeong Park, Jaeyo Shin, Hyunjung Shim
Categories: cs.CV
PDF URL: https://arxiv.org/pdf/2610.14228.pdf
CoolPaper URL: https://papers.cool/arxiv/2610.14228
Published: 2026-10-15T01:49:57.677Z