6 papers
TempAct: Advancing Temporal Plausibility in Autoregressive Video Generation via Planner-Executor RL
Jing Wang, Xiangxin Zhou, Jiajun Liang +5
Autoregressive (AR) video diffusion models enable low-latency streaming generation by synthesizing videos chunk by chunk with cached visual context, but this chunk-wise formulation…
HairOrbit: Multi-view Aware 3D Hair Modeling from Single Portraits
Leyang Jin, Yujian Zheng, Bingkui Tong +3
Reconstructing strand-level 3D hair from a single-view image is highly challenging, especially when preserving consistent and realistic attributes in unseen regions. Existing metho…
Steering Video Diffusion Transformers with Massive Activations
Xianhang Cheng, Yujian Zheng, Zhenyu Xie +2
In this work, we study the role of Massive Activations (MAs), which are rare, high-magnitude spikes confined to a few fixed hidden dimensions in video diffusion transformers (DiTs)…
AnyCrowd: Instance-Isolated Identity-Pose Binding for Arbitrary Multi-Character Animation
Zhenyu Xie, Ji Xia, Michael Kampffmeyer +9
Controllable character animation has advanced rapidly in recent years, yet multi-character animation remains underexplored. As the number of characters grows, multi-character refer…
ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting
Zehua Ma, Hanhui Li, Zhenyu Xie +4
Generating 3D content from a single image remains a fundamentally challenging and ill-posed problem due to the inherent absence of geometric and textural information in occluded re…
GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated Clipping
Jing Wang, Jiajun Liang, Jie Liu +10
Recently, GRPO-based reinforcement learning has shown remarkable progress in optimizing flow-matching models, effectively improving their alignment with task-specific rewards. With…