每天自动聚合 AI 领域最新动态
Training-free block-sparse attention can accelerate video transformers, but row-wise attention concentration does not...
We introduce Hydra-0, a generalist world model conditioned on action flow, which represents robot actions as pixel mo...
Population-level behavior in large-language-model (LLM) agents cannot be characterized by single-agent benchmarks. We...
We present PhysCaP, a Physics-Informed Code-as-Policy agent for active perception in robotic manipulation. While visi...
Game world models have recently demonstrated promising capabilities in generating visually coherent and action-contro...
Recently, there has been a great deal of research into improving AI methods and their application. The main focus is ...
Persistent memory makes false information durable: once a false statement is stored, it can be retrieved into future ...
The Traveling Salesman Problem (TSP) is one of the most extensively studied NP-hard optimization problems. Genetic Al...
Sequential recommendation predicts the next item from a user's interaction history, but not every interaction is equa...
Question answering (QA) over long, connected documents remains challenging because relevant evidence may span multipl...
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safet...
Skills play different roles as an agent's policy evolves: they should first provide learnable knowledge, then support...