每天自动聚合 AI 领域最新动态
Reinforcement Learning (RL) policies often degrade in unfamiliar environments because they lack explicit deliberation...
Segment Anything Model 3 (SAM 3) provides a strong frozen backbone for concept-prompted segmentation, but applying it...
Public AI evaluations are often read as terminal leaderboards, yet the underlying evidence is a selective time series...
We introduce TuneJury, an open, instance-level pairwise reward model for text-to-music that predicts a music preferen...
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approac...
Remote sensing vision-language models have advanced Earth observation understanding, but most existing work remains c...
Simple linear and frequency-domain models remain surprisingly competitive in long-horizon time-series forecasting, an...
Oppenheim and Lim (1981) showed that natural images stay recognizable when reconstructed from their Fourier phase alo...
Standard accuracy benchmarks are designed to test how closely large language models (LLMs) approach correct answers, ...
A content-moderation system can score well on every standard accuracy metric and still cause real harm, if its mistak...
DreamX-World 1.0 is a general-purpose interactive text/image-to-video world model for controllable long-horizon gener...
Diffusion transformers have demonstrated remarkable generative capabilities, yet the rich perceptual representations ...