每天自动聚合 AI 领域最新动态
Remote sensing foundation models (RSFMs) are commonly evaluated using aggregate metrics, which can hide systematic pe...
Reinforcement learning based post training of diffusion models, such as Denoising Diffusion Policy Optimization (DDPO...
Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately...
Autoregressive transformers remain comparatively weak for protein sequence and structure generation. We study the rol...
Generative models of human-object interaction are bounded by the data that exists: everyday activities involve severa...
Modern information systems, including many agentic workflows, use dense retrieval to explore large amounts of unstruc...
Real-world users often exhibit highly heterogeneous preferences over multiple objectives for LLM responses. A lightwe...
Jev-style decision models return categorical probability distributions over predefined options without generating fre...
Learned image compression achieves competitive rate-distortion performance, but very-low-bitrate reconstruction remai...
A typed decision model answers a fixed question about an input by returning a probability for each of several caller-...
A language model can give a correct answer more probability than any single incorrect answer and still usually sample...
Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples ...