每天自动聚合 AI 领域最新动态
Recent advances in video generation allow robots to learn manipulation trajectories from generated videos. However, t...
Direct preference alignment methods are widely used to align large language models (LLMs) with human preferences beca...
Two dominant tokenisation algorithms are used by modern language models: byte-pair encoding (BPE) and UnigramLM. Thes...
Coding agents are typically evaluated with desired behavior specified through issues or instructions. In practical we...
In collaborative tasks with asymmetric information, participants coordinate their understanding through interaction. ...
3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot in...
Scientific code repositories encode decades of human knowledge in executable models, methods, and tools. Yet fragment...
Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior ...
Diffusion Transformers deliver state-of-the-art video generation, but their long spatiotemporal sequences make attent...
Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended. Ru...
Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing ne...
We introduce Zing-0.5, a 5B autoregressive world model designed for playability: users can explore generated worlds, ...