每天自动聚合 AI 领域最新动态
Deep research (DR) agents address open-ended information needs through multi-step reasoning, long-horizon web search,...
Recent video super-resolution (VSR) models achieve efficient one-step generation through diffusion distillation. Howe...
A robot needs a world model that predicts how its actions will change the scene and a policy that chooses those actio...
Reinforcement Learning (RL) has emerged as a key driver for LLM reasoning. This capability is equally pivotal in long...
On-policy distillation (OPD) trains students using teacher feedback on their own sampled responses, yet how prompt ch...
On-policy distillation (OPD) provides teacher supervision on student-generated trajectories, but a single trajectory ...
Large Language Models (LLMs) have been used for novel discovery of algorithms, theorems, drugs, and other tasks throu...
A benchmark score compares a system output against a reference, and methodological attention falls almost entirely on...
Creativity benchmarks for large language models (LLMs) vary widely in task and metric design. This raises the questio...
Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned on...
Vision-language models (VLMs) are increasingly trained to generate structured outputs like points and bounding boxes ...
World action models (WAMs) aim to answer a coupled physical question: given a task instruction, what motion should th...