arXiv
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the fronti...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms
Language-model agents increasingly face long-horizon tasks with evolving state, interdependent decisions, and delayed...
HuggingFace
Hunyuan-A13B Technical Report
We present Hunyuan-A13B, an open-source large language model based on a Mixture-of-Experts architecture. It contains ...
HuggingFace
PACT: From Credit Assignment to Critic Alignment
Reinforcement learning has become a central component of large language model (LLM) post-training, yet token-level cr...
HuggingFace
RewardVerse: Rubric-Guided Policy Optimization for Video Reward Modeling
Reinforcement learning (RL) is vital for optimizing video generation models, with a robust reward model (RM) serving ...
HuggingFace
SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue
Long-term conversational memory in multi-party settings requires more than retrieving relevant content from long-term...
HuggingFace
MemBodied: Recurrent Associative Memory for Vision-Language-Action Models
Vision-Language-Action models provide a strong foundation for general-purpose robot control, yet a vast majority of p...
HuggingFace
StudentBench: AI and human tutoring yield equivalent GRE learning gains
Artificial intelligence offers an unprecedented opportunity to augment human capabilities, yet progress at the fronti...
HuggingFace
EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
We study coding agents for long-horizon, dexterous robotics and ask whether their solutions can provide scalable supe...
HuggingFace
Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents
Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory a...
HuggingFace
HappyWorld-Bench
Evaluating world models requires assessing both the quality of the worlds they generate and their consistency and res...
HuggingFace
Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoni...