每天自动聚合 AI 领域最新动态
Single-image 3D scene construction is a fundamental problem in 3D vision. Recent methods such as SAM-3Dfy enable end-...
Music source separation (MSS) has been conventionally addressed by discriminative methods. Recently, flow matching ha...
Building virtual embodied agents that operate in open-ended games like human players is a long-standing goal requirin...
World Models (WMs) can support Multimodal Agents (MAs) through simulated experience, while Agent trajectories can inf...
We introduce TWIG (Tree-structured Weights with Inherited Gates), a representation in which every weight of a neural ...
The rapid growth of microdramas has increased demand for high-quality script production. Long-form microdrama script ...
Location encoders map geographic coordinates to high-dimensional descriptors through contrastive alignment with paire...
In a hierarchical multi-agent system, a Leader assigns tasks and subagents carry them out. Jointly training the Leade...
On-policy self-distillation enables post-training foundation models without relying on stronger external teachers. Ho...
Developing general-purpose algorithms with global asymptotic convergence guarantees for Nash equilibria of general-su...
Developing general-purpose algorithms with global asymptotic convergence guarantees for variational inequalities (VIs...
Language models can make personalized recommendations from rich item content, user history, and feedback. However, ev...