10 papers
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
Haozhe Liu, Tian Ye, Sensen Gao +11
As coding agents move from supervised code completion to unattended, around-the-clock exploration, their work expands from isolated predictions into long trajectories of reasoning,…
Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification
Haopeng Li, Yitong Li, Junsong Chen +8
Diffusion transformers are essential for high-fidelity video generation, but long token sequences make attention a dominant inference bottleneck. Training-free dynamic sparse atten…
Motion4Motion: Motion Transfer Across Subjects at Inference
Ling-Hao Chen, Zixin Yin, Duomin Wang +2
This work explores the motion transfer from one video to another, which is crucial in animation for diverse characters. Previously, video motion transfer has been largely explored…
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
Peiwen Zhang, Yufan Deng, Shangkun Sun +11
Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tuned models…
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Juncheng Ma, Jianxin Bi, Yufan Deng +19
Embodied foundation models are expected to benefit from data scaling like large language models, but face a much tighter data bottleneck. Teleoperated real-robot trajectories remai…
UniVerse-1: Unified Audio-Video Generation via Stitching of Experts
Duomin Wang, Wei Zuo, Aojie Li +7
We introduce UniVerse-1, a unified, Veo-3-like model capable of simultaneously generating coordinated audio and video. To enhance training efficiency, we bypass training from scrat…
LazyDrag: Enabling Stable Drag-Based Editing on Multi-Modal Diffusion Transformers via Explicit Correspondence
Zixin Yin, Xili Dai, Duomin Wang +4
The reliance on implicit point matching via attention has become a core bottleneck in drag-based editing, resulting in a fundamental compromise on weakened inversion strength and c…
Training-Free Text-Guided Color Editing with Multi-Modal Diffusion Transformer
Zixin Yin, Xili Dai, Ling-Hao Chen +7
Text-guided color editing in images and videos is a fundamental yet unsolved problem, requiring fine-grained manipulation of color attributes, including albedo, light source color,…
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation
Youliang Zhang, Zhaoyang Li, Duomin Wang +6
The rapid development of large-scale models has catalyzed significant breakthroughs in the digital human domain. These advanced methodologies offer high-fidelity solutions for avat…
Taming Teacher Forcing for Masked Autoregressive Video Generation
Deyu Zhou, Quan Sun, Yuang Peng +8
We introduce MAGI, a hybrid video generation framework that combines masked modeling for intra-frame generation with causal modeling for next-frame generation. Our key innovation,…