每天自动聚合 AI 领域最新动态
Many long-horizon agents compact their context on a global rule, usually a token budget, blind to what the agent was ...
Egocentric human data offer a path to scaling robot learning beyond costly robot demonstrations, yet the embodiment g...
Sequential recommenders typically use a fixed slate size even though the number of useful alternatives changes within...
Recent advances in world models have enabled increasingly realistic visual synthesis. However, these generated enviro...
Self-improving policies continually expose new failure patterns, changing what their judges must be able to verify. H...
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted ...
Large language models (LLMs) can solve many narrow tasks, but querying them separately for millions of related instan...
Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is n...
World models offer a data-driven alternative to traditional simulators for robotics, with applications spanning polic...
Scientific research often begins by synthesizing ideas from a set of related papers to identify gaps and formulate ne...
Existing methods for 4D hand-object reconstruction often rely on costly per-sequence optimization, while generative a...
Tool-using agents make consequential changes to external state, yet correct outcomes do not guarantee that their acti...