每天自动聚合 AI 领域最新动态
Correcting health misinformation in dialogue requires more than producing a factual rebuttal: users differ in what th...
This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare fi...
Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypo...
Predicting robot videos requires both precise motion reasoning and preservation of high-frequency appearance, yet mon...
AI coding agents, software tools that automate development tasks through reasoning and tool use, are increasingly ext...
When training Mixture-of-Experts (MoE) language models with expert parallelism, all-to-all token dispatch and combine...
Neural operators provide fast surrogate models for approximating operators between function spaces, but their predict...
We investigate whether automatic speech recognition (ASR) errors in user input can lead to unsafe outputs from Embodi...
Texture image classification plays a significant role in computer vision applications, including industrial inspectio...
Recent advances in generative AI allow users to create 3D models from text or images. However, these models prioritiz...
A code world model accepted by a sampling gate can be exactly right on everything the gate can see and arbitrarily wr...
Recent generative approaches to geometry estimation adapt pretrained image diffusion models and treat the task as ima...