每天自动聚合 AI 领域最新动态
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): compl...
Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadrat...
Reinforcement learning has helped AI agents solve increasingly difficult tasks, but high rewards do not always reflec...
Reproducibility is essential for scientific research, yet prior work shows that LLM outputs vary with hardware and ba...
Host-resident layer streaming enables full-parameter LLM fine-tuning beyond GPU memory, but data-parallel ranks compe...
Transformer language models build predictions through successive residual updates, but how their representations beco...
How many tokens from its context does a language model actually use, and what determines that number? We study this q...
Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear littl...
Language models can now prove theorems, but people still decide which problems to pursue. We ask whether a model's in...
Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, yet how RL reshap...
On-policy self-distillation (OPSD) trains a student to match a privileged teacher distribution along its own sampled ...
We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models. LoopVL...