arXiv
Discriminative World Models for Web Agents
Recent web agents use world models for test-time action selection by sampling candidate actions, predicting the resul...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Cliff: Learning Process Rewards from the First Mistake
Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for large language model (LL...
HuggingFace
Kirin: Animal Motion Generation from In-the-Wild Video
Understanding animal motion is fundamental to modeling animal behavior and biomechanics, yet progress in this area la...
HuggingFace
Post-Training Language Models for Gold-Medal Performance in Coding Competitions
Competitive programming has become a key test of large language model reasoning, with international competitions such...
HuggingFace
On the Design Fundamentals of Pixel Text Representation Learning
Text-rich visual inputs require models that can read, retrieve, and compress language directly in pixel space, yet ex...
HuggingFace
Language Models Can Control Their Own Attention
Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to fi...
HuggingFace
EarlyEval: Cheaper Agent Evaluation via Early Outcome Prediction
Evaluating LLM agents is essential for guiding their development, yet it has grown prohibitively expensive: a single ...
HuggingFace
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Autonomous agents are beginning to carry out machine-learning (ML) research end to end. These agents combine a model ...
HuggingFace
S3Gym: Can LLMs Turn Self-Testing and Self-Judging into Self-Improvement?
Large language models (LLMs) increasingly interact with external environments and accumulate substantial behavioral e...
HuggingFace
Aspire: Can Models Self-Evolve from Vague Goals?
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at re...
HuggingFace
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
As agents move from research prototypes to deployed tools, their capability increasingly depends on model-external ex...
HuggingFace
Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers
Historical newspapers are an abundant record of public life, but their dense, irregular and sometimes noisy layouts m...