数据来源：HuggingFace Papers Latest Papers1. OPRD: On-Policy Representation DistillationAbstract:On-policy distillation (OPD) supervises the student only in output space by matching next-token probabilities. This output-only paradigm has two limits: (1) sampling variance from Monte Carlo KL estimates over large vocabularies (e.g., Qwen’s ~150k tokens) persists throughout training, and (2) it treats the teacher as a black-box, discarding all intermediate hidden states after the LM head. We propose O ...

数据来源：HuggingFace Papers Latest Papers1. Code2LoRA: Hypernetwork-Generated Adapters for Code Language Models under Software EvolutionAbstract:Code language models need repository-level context to resolve imports, APIs, and project conventions. Existing methods inject this knowledge as long inputs (retrieved through RAG or dependency analysis) or through per-repository fine-tuning and LoRA — costly at repository scale and brittle to evolving codebases. We introduce Code2LoRA, a hypernetwork fram ...

数据来源：HuggingFace Papers Latest Papers1. dots.tts Technical ReportAbstract:We present this http URL, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning ...

数据来源：HuggingFace Papers Latest Papers1. Your UnEmbedding Matrix is Secretly a Feature Lens for Text EmbeddingsAbstract:Large language models exhibit impressive zero-shot capabilities across a wide range of downstream tasks. However, they struggle to function as off-the-shelf embedding models, leading to suboptimal performance on massive text embedding benchmarks. In this paper, we identify a potential cause underlying this deficiency. Our motivation stems from an unexpected observation: text e ...

数据来源：HuggingFace Papers Latest Papers1. What Should Agents Say? Action-state Communication for Efficient Multi-Agent SystemsAbstract:Multi-agent systems (MAS) built on large language models are typically organized around roles, pipelines, and turn schedules, while the content that agents pass to one another is often left as unconstrained natural language. However, this free-form communication can rapidly inflate token usage, consume the shared context window, and ultimately affect both system ...

数据来源：HuggingFace Papers Latest Papers1. ICA Lens: Interpreting Language Models Without Training Another DictionaryAbstract:Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard tool for this purpose, but using them as the default first lens often requires training, storing, and evaluating large overcomplete dictionaries. This bottleneck limits rapid exploration and rai ...

数据来源：HuggingFace Papers Latest Papers1. EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic EnvironmentsAbstract:Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introdu ...

数据来源：HuggingFace Papers Latest Papers1. When is Your LLM Steerable?Abstract:Activation steering offers a lightweight approach to control language models’ behavior at inference time, but whether it succeeds or fails heavily depends on the prompt, concept, model, and steering configuration. Finding the regime and boundaries of successful steering typically requires expensive grid searches and post-hoc evaluation of full autoregressive rollouts. In this work, we investigate whether steerability c ...

数据来源：HuggingFace Papers Latest Papers1. Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level PerformanceAbstract:While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we ...

数据来源：HuggingFace Papers Latest Papers1. Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level PerformanceAbstract:While 10B-level industrial foundation models have pushed the boundaries of image inpainting, their prohibitive computational costs severely hinder practical deployment. Constructing a highly optimized task-specific specialist offers a promising solution; however, extreme structural compression inevitably triggers a severe representation bottleneck. To conquer this, we ...

数据来源：HuggingFace Papers Latest Papers1. PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language ModelsAbstract:Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks. However, most existing MLLMs rely on autoregressive generation, which limits their efficiency for perception tasks that require captioning multiple regions. In this work, we propose PerceptionDLM, a multimodal diffusion language model optimized for efficient p ...

数据来源：HuggingFace Papers Latest Papers1. PlanBench-XL: Evaluating Long-Horizon Planning of LLM Tool-Use Agents in Large-Scale Tool EcosystemsAbstract:LLM agents increasingly operate in large tool ecosystems, where real-world tasks require discovering relevant tools, inferring implicit sub-goals, and adapting to dynamic environments over long horizons. However, existing benchmarks rarely evaluate planning under retrieval-limited tool visibility. To address this gap, we introduce PlanBench-XL, an ...

数据来源：HuggingFace Papers Latest Papers1. DanceOPD: On-Policy Generative Field DistillationAbstract:Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. However, these capabilities are rarely naturally aligned and often conflict. For instance, editing tends to degrade T2I performance, while global and local editing interfere with each other. Consequently, effectively composing these capabilities has be ...

数据来源：HuggingFace Papers Latest Papers1. AsyncOPD: How Stale Can On-Policy Distillation Be?Abstract:On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is becoming increasingly important for large language model (LLM) post-training. Like reinforcement learning (RL), however, OPD faces an on-policy systems bottleneck, as rollouts can dominate training time for reasoning workloads. Asynchronous training pipelines can alleviate this bottleneck by decoup ...

数据来源：HuggingFace Papers Latest Papers1. SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot TasksAbstract:Speech and audio generation is often needed in animation dubbing, audio drama, movies, advertising, games, podcasts, and short-video production. In these scenarios, creators may need to design voices without reference recordings, control speaker styles with natural language, support acoustic scenes with environments and audio effects, and later reuse the ...