Existing 3D talking avatar methods mainly rely on parametric face models including 3DMM or FLAME, whose compact motion representations limit their ability to synthesize extreme expressions and to model accessories such as headwear. We introduce AudioLift, a two-stage framework that uses generated multi-view videos as t...
Zhuo-Yuan Jiang, Weijie Lyu, Xiao-Yuan Wang et al.· 0 citations
Reinforcement learning (RL) is promising for spatial text-to-image generation, but existing work largely focuses on policy optimization, assuming accurate rewards and effective online rollouts. We observe in-domain gains with out-of-domain degradation, exposing two limitations: unreliable spatial rewards in open-world...
Xiaofeng Tan, Jia-Xin Lin, Haobo Yuan et al.· 1 citation
Learning Reference Coordinate Frames for Perspective Taking is introduced, a framework that trains VLMs to construct and use explicit reference frames for viewpoint-dependent reasoning and consistently improves over its backbone and achieves strong performance against existing open-source methods.
Bang Xiao, Wen-Qi Jia, Ozgur Kara et al.· 0 citations
DG-Mem is proposed, a dual-grained agentic memory framework that augments a frozen MLLM with a non-parametric, externally stored memory built once from training-time rollouts and consulted read-only at test time, and improves consistently over no-memory and competitive memory baselines.
Jie-Ke Wang, Tian-Cheng Shen, Yibo Yang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.