每天自动聚合 AI 领域最新动态
Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating ...
Many robot manipulation videos do not indicate whether the task was successfully completed. RoboJev-27B is an open-we...
Referring expression grounding in overhead imagery requires oriented bounding boxes rather than horizontal ones, sinc...
Animals have a remarkable capacity for autonomy---driven by intrinsic motivation---without external sensory cues or e...
Online scene change detection requires integrating incoming observations to determine which regions have changed rela...
Catastrophic forgetting in continual learning (CL) manifests not only as accuracy degradation but also as explanation...
An agent that truly knows and acts on behalf of its user has been a long-standing promise of AI assistants. Computer-...
Reasoning language models generate thousands of tokens per answer, and generation speed is limited by memory bandwidt...
Existing interpretability tools do not test whether a representation keeps the same content when only the phrasing ch...
Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step...
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent exec...
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a...