每天自动聚合 AI 领域最新动态
Reinforcement Learning (RL) has demonstrated significant gains in image captioning, yet it is still limited in encour...
The European Union (EU) has emerged as a leading regulatory body in the development of sustainability and privacy reg...
We formalize the Steiner Traveling Salesman Problem (Steiner-TSP) on Graphs of Convex Sets (GCS), which seeks a minim...
Deep-learning models of anatomy can be numerically plausible yet anatomically impossible, and they generalize poorly ...
Contextualization is essential for production automatic speech recognition (ASR) systems, where user-provided phrases...
For sixty years, machine verification has been a major cost overhead, affordable only for exceptional artifacts. Here...
In professional life sciences workflows, scientists routinely interpret visual artifacts (gel blots, microscopy image...
We develop a new direct accelerated Newton method for minimizing convex functions with Lipschitz continuous Hessian. ...
Deploying vision-language models (VLMs) on mobile devices is challenging due to their significant memory and compute ...
Hybrid-thinking multimodal large language models (MLLMs) allow a single model to alternate between deliberative think...
With large pretrained models, existing methods have effectively improved instruction-based video editing. However, mo...
Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safet...