40 papers
Towards Practical 20 kbps Generative Video Compression via Adaptive Tokenization and Entropy Modeling
Jiancheng Zhao, Jixiang Luo, Haibin Huang +2
Video compression at ultra-low bitrates remains challenging due to the loss of perceptually important details under limited bit budgets. Recent generative video compression methods…
Generator-Aligned Reward Modeling with Target-Aware Bounded Optimization for Visual Generation
Ziqiao Weng, Yuanzhi Liang, Haibing Huang +2
Post-training aims to enhance desired attributes in visual generative models while preserving their general generation capabilities. Reward-guided post-training faces two challenge…
FutureDuet: Decoupling Observation Access from Future Supervision in World Action Models
Jie Wu, Yuzhi Huang, Junqi Liu +5
World Action Models (WAMs) augment robot action generation with future visual supervision. Existing WAMs commonly fuse main and wrist observations into one visual stream and train…
Uncertainty DMD: Restoring Diversity in Few-Step Autoregressive Video Distillation
Zixuan Duan, Xunzhi Xiang, Yabo Chen +6
Few-step distillation improves the efficiency of autoregressive (AR) video generation, but often causes diversity collapse: under the same prompt, different noise samples tend to p…
Dreaming in Flow: Bidirectional Self-Refinement for Unified Multimodal Models
Ke Hao, Yuanzhi Liang, Tingxi Chen +5
Unified multimodal models can generate images and interpret them, but their two capabilities are usually optimized with separate supervision. We introduce Bidirectional Self-Refine…
Search-to-World: Evaluation of 3D World Delivery from User Request through Web Search
Zixiao Gu, Yabo Chen, Xunzhi Xiang +5
Agentic systems can interpret user requests, search the live web, and use external tools, but their ability to transform retrieved web content into a usable 3D world has not been s…
TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image
Xin Zhang, Yabo Chen, Zixuan Duan +4
Interactive visual world models must distinguish observation from physical intervention. Camera motion reveals new surfaces, whereas intervention changes object motion, contact, an…
RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing
Bojia Zi, Xiaoyan Yang, Yu Zhou +7
Recent advances in video editing have been largely driven by large-scale instruction-based datasets. However, existing datasets still suffer from two critical limitations. First, t…
Sample-Adaptive Latent Rewards for Uncertainty-Guided Diffusion Post-Training
Rui Li, Yuanzhi Liang, Ke Hao +4
Latent reward models can supervise visual diffusion models without decoding intermediate states into pixel space. This makes alignment with human preferences more efficient. Howeve…
CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling
Yuyang Huang, Yabo Chen, Wenrui Dai +6
Cinematic video generation is challenging for text-to-video diffusion models due to concurrent requirements on multi-shot generation, fine-grained controllability over characters a…
MMOE: Modernizing Diffusion Transformers with Efficient Expert Design
Yanhao Jia, Jiepeng Wang, Haibin Huang +3
Modern large language models scale successfully by pairing capacity growth with efficiency, keeping per-token and deployment costs under control as capacity grows. AIGC Foundation…
ShotPlan: Cinematic Video Generation with Learnable Planning Token
Su Guo, Guangce Liu, Haosen Yang +7
Current video generation models achieve impressive results in single-shot generation, yet remain limited in cinematic video generation, where coherent narratives and effective mult…
Generative Transmission: Rethinking Computation, Bandwidth, and Memory in Communication
Xiangyu Chen, Jixiang Luo, Yuankai Fan +3
Under the AI Flow framework, communication is shifting from transmitting fidelity-oriented information flows toward delivering task-oriented and perception-oriented token flows acr…
From World Action Models to Embodied Brains: A Roadmap for Open-World Physical Intelligence
Yuanzhi Liang, Xufeng Zhan, Haibin Huang +2
Artificial general intelligence ultimately requires agents that can reason and act in the physical world. Action models, vision-language-action policies, and world models have adva…
Style-CCL: Content-Preserving Style Transfer via Curriculum Continual Learning
Shiwen Zhang, Haoyuan Wang, Xianghao Zang +3
Content-Preserving Style transfer, given content and style references, remains challenging for Diffusion Transformers (DiTs) due to entangled content and style features. With a rev…
Directing the World: Fast Autoregressive Video Generation with Compositional Human-Camera Control
Haoyuan Wang, Yabo Chen, Haibin Huang +2
Building interactive world models requires generating realistic videos while maintaining controllable dynamics over long horizons. Autoregressive video generation offers a scalable…
TeleStyle V2: Beyond Content-Preserving Style Transfer with Self-Distillation and Distribution-Matching-Distillation
Shiwen Zhang, Yifan Xu, Haibin Huang +2
Given a content reference and a style reference, content-preserving style transfer requires the model to generate stylized outputs with content and style consistency. We introduced…
VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modeling
Xunzhi Xiang, Zixuan Duan, Yabo Chen +8
Large-scale video diffusion models often fail to preserve 3D structure over time, causing geometric drift and implausible motion under viewpoint changes. Existing methods usually e…
SwiftVR: Real-Time One-Step Generative Video Restoration
Jiaqi Yan, Xiangyu Chen, Xinlin Zhong +5
Real-time video restoration (VR) for live streams requires high-resolution outputs under strict per-frame latency constraints. Existing one-step diffusion-based VR models remain di…
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Ruoyu Wang, Jialun Liu, Huayang Huang +5
Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic fail…
Full-4D: Generating Full-Scope 4D Scenes from a Single-View Video
Tingxi Chen, Ke Hao, Yabo Chen +6
Generating 4D scenes from a single-view video is inherently ill-posed: a single viewpoint lacks the information needed to recover a complete, dynamic scene with full coverage. Exis…
PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction
Xin Zhang, Yabo Chen, Yijie Fang +5
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provi…
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
Rui Li, Ke Hao, Yuanzhi Liang +4
Reinforcement learning, particularly Group Relative Policy Optimization (GRPO), has emerged as an effective framework for post-training visual generative models with human preferen…
Reward-Aware Trajectory Shaping for Few-step Visual Generation
Rui Li, Bingyu Li, Yuanzhi Liang +3
Achieving high-fidelity generation in extremely few sampling steps has long been a central goal of generative modeling. Existing approaches largely rely on distillation-based frame…