每天自动聚合 AI 领域最新动态
Test-time scaling has emerged as a key inference strategy for reasoning models, where a model generates a large numbe...
Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effec...
Recent advances in video generation have made synthetic videos increasingly realistic, placing greater demands on rel...
Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with pai...
Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a pr...
Recursive self-improvement (RSI) describes a system that improves not only its behavior but also the process by which...
AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gra...
World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spat...
This paper studies category-level RGB-D object pose estimation, which recovers an object's 3D rotation and translatio...
High-quality image editing requires precise modification of target regions while preserving the content of unrelated ...
Tool-using voice agents often leave users waiting after speech ends, even when actionable information arrives earlier...
LLM routing dynamically selects and coordinates heterogeneous language models across diverse tasks. However, existing...