每天自动聚合 AI 领域最新动态
A trainable input embedding table assigns each vocabulary item an independently adjustable vector. We investigate whe...
Bidirectional video diffusion models denoise entire videos in parallel, yet when trained on effectively unlimited in-...
In response to the growing demand for long sequences in agentic and reasoning use cases, many state-of-the-art LLMs c...
Cross-lingual contrastive learning has been a core component of multilingual encoder training, but the ability to exp...
On-policy reinforcement learning has become a central paradigm for improving the reasoning abilities of large languag...
Many useful language-model tasks cannot be evaluated by exact outcome verification. Rubric-based reinforcement learni...
In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to over...
Training large language models (LLMs) is resource-intensive, and adapting them for diverse deployment scenarios with ...
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factori...
Large language models (LLMs) have become increasingly capable problem solvers, but being able to solve a problem is n...
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implemen...
Sensors are useful not only for understanding the world but also for deciding what to do next. Existing sensor models...