5 citations · 8 across the 19 of their papers we have counts for
20 papers
WAM-Sim0.1: World Anchored Memory Meets Online RL for Consistent and Realistic Driving Simulation
Jiahao Cui, Jiaye Li, Wenhao Zhang +7
Autoregressive driving world models systematically suffer from structural drift, identity drift, and quality decay over long rollout horizons due to transient conditioning signals…
Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation
Tianyi Zeng, Junchao Liao, Yujie Wei +9
Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Profession…
WAM-Diff2: Hierarchical AR-to-Diffusion Distillation for Highly Efficient Autonomous Driving VLA
Zhihao Zhu, Hanlin Shang, Mingwang Xu +6
Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is severely constrained by high comp…
GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling
Yixuan Lai, Tianjia Shao, Weijia Dou +2
Generating visually consistent multi-shot videos remains an open challenge. As videos span more shots, inconsistencies can accumulate across shots, causing entities that reappear a…
SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
Weijia Dou, Hui Li, Jiahao Cui +3
Streaming video generation models typically rely on temporal-centric memory, organizing historical context as latent queues, compressed context tokens, or unclustered token sets. T…
ML-CLIPSim: Multi-Layer CLIP Similarity for Machine-Oriented Image Quality
Feng Ding, Haisheng Fu, Jie Liang +3
We study full-reference image quality assessment from a machine-centric perspective, where images are evaluated by how well they preserve information for downstream models. We form…
Hallo-Live: Real-Time Streaming Joint Audio-Video Avatar Generation with Asynchronous Dual-Stream and Human-Centric Preference Distillation
Chunyu Li, Jiaye Li, Ruiqiao Mei +4
Real-time text-driven joint audio-video avatar generation requires jointly synthesizing portrait video and speech with high fidelity and precise synchronization, yet existing audio…
Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence
Junchao Liao, Zhenghao Zhang, Xiangyu Meng +5
Audio-video (AV) generation has recently made strong progress in perceptual quality and multimodal coherence, yet generating content with plausible motion-sound relations remains c…
Prompt Reinjection: Alleviating Prompt Forgetting in Multimodal Diffusion Transformers for Text-to-Image Generation
Yuxuan Yao, Yuxuan Chen, Hui Li +6
Multimodal Diffusion Transformers (MMDiTs) for text-to-image generation maintain separate text and image branches, with bidirectional information flow between text tokens and visua…
WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
Yifang Xu, Jiahao Cui, Feipeng Cai +8
We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressiv…
WAM-Diff: A Masked Diffusion VLA Framework with MoE and Online Reinforcement Learning for Autonomous Driving
Mingwang Xu, Jiahao Cui, Feipeng Cai +8
End-to-end autonomous driving systems based on vision-language-action (VLA) models integrate multimodal sensor inputs and language instructions to generate planning and control sig…
MixFlow Training: Alleviating Exposure Bias with Slowed Interpolation Mixture
Hui Li, Fu-Yun Wang, Haoyuan Xia +4
This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one tra…
Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
Jiaye Li, Baoyou Chen, Hui Li +3
Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation revea…
DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration
Yan Chen, Hanlin Shang, Ce Liu +6
Video face restoration faces a critical challenge in maintaining temporal consistency while recovering fine facial details from degraded inputs. This paper presents a novel approac…
Pyramidal Patchification Flow for Visual Generation
Hui Li, Baoyou Chen, Liwei Zhang +3
Diffusion transformers (DiTs) adopt Patchify, mapping patch representations to token representations through linear projections, to adjust the number of tokens input to DiT blocks…
Hallo4: High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization
Jiahao Cui, Yan Chen, Mingwang Xu +7
Generating highly dynamic and photorealistic portrait animations driven by audio and skeletal motion remains challenging due to the need for precise lip synchronization, natural fa…
OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation
Hui Li, Mingwang Xu, Yun Zhan +8
Recent advancements in visual generation technologies have markedly increased the scale and availability of video datasets, which are crucial for training effective video generatio…
Hallo3: Highly Dynamic and Realistic Portrait Image Animation with Video Diffusion Transformer
Jiahao Cui, Hui Li, Yun Zhan +7
Existing methodologies for animating portrait images face significant challenges, particularly in handling non-frontal perspectives, rendering dynamic objects around the portrait,…
Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation
Jiahao Cui, Hui Li, Yao Yao +6
Recent advances in latent diffusion-based generative models for portrait image animation, such as Hallo, have achieved impressive results in short-duration video synthesis. In this…
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
Mingwang Xu, Hui Li, Qingkun Su +6
The field of portrait image animation, driven by speech audio input, has experienced significant advancements in the generation of realistic and dynamic portraits. This research de…