数据来源：ArXiv Domain LLM Domain Papers1. When Agent Governance HelpsAbstract:No specification says how a governed autotelic AI agent organization, where agents pursue self-generated goals inside guardrails, should be designed and evaluated. We answer in two parts. First, we synthesize the Governed Autotelic Multi-Agent Product Organization (GAMPO) framework from a document-based qualitative evidence synthesis of 321 sources, integrating agency, agile, platform, and governance theory into a runnab ...

数据来源：ArXiv Domain LLM Domain Papers1. X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative DecodingAbstract:This paper investigates collaborative speculative decoding (CoSD), a distributed large language model (LLM) inference framework in which an on-device small language model (SLM) drafts candidate tokens and a server LLM verifies them. Existing CoSD methods assume a shared vocabulary between the SLM and the LLM and incur substantial communication load because residual ...

数据来源：ArXiv Domain LLM Domain Papers1. Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model ImprovementAbstract:Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-horizon, end-to-end autonomous research program on BabyLM 2026 Strict-Small, within 10 million corpus words and 100 million cumulative word presentations. Three stages connected frontier advancement, princi ...

数据来源：ArXiv Domain LLM Domain Papers1. Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model ImprovementAbstract:Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-horizon, end-to-end autonomous research program on BabyLM 2026 Strict-Small, within 10 million corpus words and 100 million cumulative word presentations. Three stages connected frontier advancement, princi ...

数据来源：ArXiv Domain LLM Domain Papers1. Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model ImprovementAbstract:Learning from limited text requires models to use context, generalize to new inputs, and retain useful capabilities. Qiushi Engine conducted a long-horizon, end-to-end autonomous research program on BabyLM 2026 Strict-Small, within 10 million corpus words and 100 million cumulative word presentations. Three stages connected frontier advancement, princi ...

数据来源：ArXiv Domain LLM Domain Papers1. R2VC: Modular Fact-Checking with Retrieval, Verification, and Confidence CalibrationAbstract:Large language models are increasingly used for automated fact checking, but end-to-end prompting often entangles evidence retrieval, reasoning, and uncertainty estimation, making failures difficult to diagnose and confidence difficult to trust. We present R2VC, a modular retrieve, reason, verify, calibrate architecture for evidence-grounded fact checking with cita ...

数据来源：ArXiv Domain LLM Domain Papers1. Few-Shot Degradation Is Not What It Seems: Behavioral Evidence, Representation Analysis, and a Random-Text Control Across 12 Models, 2 Tasks, and 2 ArchitecturesAbstract:Few-shot prompting sometimes degrades language models instead of helping them, but why this happens is unknown. We evaluate 12 open-weight models on two Ukrainian tasks news classification and legal case outcome prediction and find that the effect is strongly task-dependent: the same model ...

数据来源：ArXiv Domain LLM Domain Papers1. Token Merging for Multilingual Speech Recognition: A Systematic Study Across Model Scale and Fine-TuningAbstract:Leading multilingual speech recognition models like Whisper transcribe diverse, low-resource languages without language-specific training but are computationally expensive to deploy. Token merging mitigates this inefficiency by dynamically combining redundant features, shortening the sequence length during inference without requiring retraining. ...

数据来源：ArXiv Domain LLM Domain Papers1. Enhancing Extubation Failure Prediction with LLM-Derived Features from Respiratory Therapy Clinical NotesAbstract:Invasive mechanical ventilation is a lifesaving therapy, but timely, safe discontinuation is essential to preventing extubation failure (EF) and related risks to health. We present a novel approach to EF prediction that leverages features classified in free-text respiratory therapy notes using a large language model and logistic regression pipe ...

数据来源：ArXiv Domain LLM Domain Papers1. Modality Discrepancy Transformer for Ambivalence and Hesitancy RecognitionAbstract:Ambivalence and hesitancy (A/H) are affective states in which individuals express contradictory signals across facial, vocal, and linguistic channels. Automatically recognising A/H in clinical videos requires detecting cross-modal disagreement — the signal that standard fusion methods suppress. Based on the conflict-aware multimodal fusion framework of Bekhouche et al., we p ...

数据来源：ArXiv Domain LLM Domain Papers1. Modality Discrepancy Transformer for Ambivalence and Hesitancy RecognitionAbstract:Ambivalence and hesitancy (A/H) are affective states in which individuals express contradictory signals across facial, vocal, and linguistic channels. Automatically recognising A/H in clinical videos requires detecting cross-modal disagreement — the signal that standard fusion methods suppress. Based on the conflict-aware multimodal fusion framework of Bekhouche et al., we p ...

数据来源：ArXiv Domain LLM Domain Papers1. Do small language models know what they don’t know?Abstract:We explore whether entropy-based confidence signals can be leveraged to improve the accuracy of Small Language Models (SLMs) with fewer than 3 billion parameters, running entirely on consumer hardware. We evaluate seven distinct approaches, including token-level entropy early stopping, semantic entropy estimation, and uncertainty-aware routing to larger expert models, across 7 model pairs and 5 st ...

数据来源：github.com/trending global Languageszhaoxuya520/reverse-skillReverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing + On-demand toolchain bootstrapping + Self-evolving knowledge base Supports Claude Code, Kiro, Cursor, Cline, and other AI coding clients 逆向/渗透/安全技能路由包 - AI 自动路由 + 按需自举工具链 + 自动进化经验库 | 支持 Claude Code / Kiro / Cursor / Cline 等代码 AI 客户端 ⭐ Stars: 10733 🍴 Forks: 0 📝 Language: PowerShell different-ai/openworkThe open-sour ...

数据来源：github.com/trending global Languagesmicrosoft/AI-For-Beginners12 Weeks, 24 Lessons, AI for All! ⭐ Stars: 57225 🍴 Forks: 0 📝 Language: Jupyter Notebook paperswithbacktest/awesome-systematic-tradingA curated list of awesome libraries, packages, strategies, books, blogs, tutorials for systematic trading. ⭐ Stars: 12245 🍴 Forks: 0 📝 Language: Python usekaneo/kaneo🎯 All you need. Nothing you don’t. Open source project management that works for you, not against you. ⭐ Stars: 5689 🍴 ...

数据来源：github.com/trending global Languagesmicrosoft/AI-For-Beginners12 Weeks, 24 Lessons, AI for All! ⭐ Stars: 59048 🍴 Forks: 0 📝 Language: Jupyter Notebook usekaneo/kaneo🎯 All you need. Nothing you don’t. Open source project management that works for you, not against you. ⭐ Stars: 6156 🍴 Forks: 0 📝 Language: TypeScript lyogavin/airllmAirLLM 70B inference with single 4GB GPU ⭐ Stars: 25671 🍴 Forks: 0 📝 Language: Jupyter Notebook iv-org/invidiousInvidious is an alternative front- ...