每天自动聚合 AI 领域最新动态
LLM agents will increasingly act in socially structured settings where role, audience, and relational context can sha...
Understanding and reasoning over long contexts has become a key requirement for deploying large language models (LLMs...
Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs onl...
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repa...
LLMs memorize sensitive training data, including personally identifiable information (PII), creating a pressing need ...
As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting acr...
Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amoun...
Conventional reinforcement learning strategies for visual generation typically employ sample-wise reward functions, y...
Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repa...
Vision-Language Models (VLMs) have demonstrated immense promise in Spatio-Temporal Video Grounding (STVG). However, c...
Continual post-training enables foundation models to acquire new knowledge while preserving existing capabilities. Re...
We present WorldDirector, a highly controllable video world model framework designed for persistent dynamic object me...