每天自动聚合 AI 领域最新动态
Recent advances in image generation have demonstrated the potential of unified multimodal models that integrate under...
Real-time video editing requires low-latency causal generation with bounded computational resources while preserving ...
Tool-Integrated Reasoning (TIR) enables LLMs to solve complex tasks through iterative tool interactions. However, exi...
Captions serve as a primary supervision signal for both multimodal understanding and text-to-image generation. Howeve...
Language remains an outlier in generative modeling: while images, video, and audio are increasingly modeled in contin...
Omni-modal large language models (Omni-LLMs) have achieved remarkable performance on audio-visual understanding tasks...
Large language model agents have shown strong potential in complex interactive tasks, yet their reinforcement learnin...
Recursive self-improvement requires agents to turn accumulated experience into better future behavior. Personal AI ag...
Industrial recommenders increasingly adopt the pretrain-then-transfer paradigm, yet behavioral distribution drift rai...
Large Language Model (LLM) agents have seen rapid adoption in software engineering. As agents take a greater role in ...
Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environm...
World Action Models (WAMs) have emerged as a promising paradigm by jointly modeling robot actions and future visual d...