每天自动聚合 AI 领域最新动态
Multi-object tracking in sports broadcasts is hard for two reasons: athletes move fast and change direction abruptly,...
AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing th...
Relational learning typically predicts from a database state, but decision making asks a different question: how will...
Text-based world models have recently shown potential to simulate complex RL environment state transitions for a dive...
Reasoning over long document contexts remains a challenge for large language models (LLMs). Standard retrieval method...
Creative intent in video editing can be expressed through text instructions (e.g., "remove the people"), image refere...
Web application development often proceeds through successive requests that extend an existing implementation. Yet we...
Enhancing the agentic capabilities of Large Language Models (LLMs) to tackle complex software engineering (SWE) and g...
Knowledge distillation (KD) frameworks place teacher and student on the same GPUs, so per-GPU memory limits the teach...
Whole-body tracking has become the interface through which operators drive humanoid robots, yet the references it con...
Comparing financial disclosures across languages requires identifying shared accounting concepts and recovering all n...
We seek a hierarchical resolution of residual error under a composite learning objective as a principled mechanism fo...