每天自动聚合 AI 领域最新动态
Robots operating in the physical world will increasingly need to coordinate with other robots, particularly in manipu...
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object ...
Quasi-Newton (QN) methods have long been among the most effective methods for large-scale unconstrained convex optimi...
Molecular learning models are strongly shaped by their underlying representations. Yet standard sequential and graph ...
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated t...
Discrete diffusion language models offer a compelling alternative to autoregressive generation for tasks demanding bi...
Several state-of-the-art methods for online reinforcement learning in continuous control improve policies using actio...
We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their po...
High-resolution 3D generation increasingly relies on voxel latents and multi-stage pipelines that first predict activ...
What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ...
Building reliable robot capabilities across diverse tasks requires substantial human effort to develop and maintain s...
LLMs are increasingly applied to cybersecurity workflows, where they are expected to translate analysts' intent into ...