每天自动聚合 AI 领域最新动态
World-action models (WAMs) couple predictive visual modeling with action generation, typically relying on iterative d...
Natural language autoencoders translate a language model's internal activations into readable explanations. Explainin...
Language-model agents increasingly use tools to act on external systems. Earlier actions can alter files, permissions...
An agent that uses tools typically responds to what the user explicitly asks, yet completing the task may require inf...
Pixel-space diffusion Transformers (DiTs) directly operate on high-dimensional visual data, yet their hidden represen...
Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think...
Active test-time adaptation (ATTA) improves robustness under distribution shift by updating a deployed model during i...
Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to...
To serve as real-world personal assistants, streaming video models need persistent memory that retains past experienc...
Connectionist temporal classification (CTC) naturally supports offline and streaming speech recognition with utteranc...
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inferenc...
Long-horizon camera-controlled video generation requires recovering previously observed content from an ever-growing ...