10 papers
VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio Generation
Yinming Huang, Shuyuan Tu, Xi Yan +5
Using reinforcement learning to post-train joint video-audio generation models requires a reward signal. Existing methods construct this reward by combining metrics for individual…
Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation
Shuyuan Tu, Qi Tian, Zihan Yang +9
Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cau…
Unify Robot Actions in Camera Frame
Sicheng Xie, Lingchen Meng, Zijie Diao +9
Cross-embodiment robot learning requires a unified action representation with consistent semantics across robot platforms. Existing representations suffer from platform-specific in…
Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference
Jiaqi Leng, Shuyuan Tu, Haidong Cao +4
Human preference alignment presents a critical yet underexplored challenge for diffusion models in text-to-3D generation. Existing solutions typically require task-specific fine-tu…
Emotion-LLaMAv2 and MMEVerse: A New Framework and Benchmark for Multimodal Emotion Understanding
Xiaojiang Peng, Jingyi Chen, Zebang Cheng +11
Understanding human emotions from multimodal signals poses a significant challenge in affective computing and human-robot interaction. While multimodal large language models (MLLMs…
ArcFlow: Unleashing 2-Step Text-to-Image Generation via High-Precision Non-Linear Flow Distillation
Zihan Yang, Shuyuan Tu, Licheng Zhang +3
Diffusion models have achieved remarkable generation quality, but they suffer from significant inference cost due to their reliance on multiple sequential denoising steps, motivati…