502 citations · 1.4k across the 190 of their papers we have counts for
185 papers · 1 filter
4LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling
Jianhui Zhang, Zuyao Lin, Pengxin Xu +2
For video generation in dynamic world modeling, observed static and dynamic content should be efficiently reused to provide conditions for repeated generation at different times an…
Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams
Weihao Bo, Shan Zhang, Yanpeng Sun +7
Multimodal Large Language Models (MLLMs) have been growing the capability for scientific writing and collaboration. For example, OpenAI Prism is a free workspace for scientific wri…
Unveiling the Secret of AdaLN-Zero in Diffusion Transformer
Jie Zhu, Mingyu Ding, Boqiang Duan +2
Diffusion transformer (DiT), a rapidly emerging architecture for image generation, has gained much attention. However, despite ongoing efforts to improve its performance, the under…
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…
From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting
Zizhao Chen, Ping Wei, Guang Dai +2
Video object removal is a fundamental yet challenging task in video editing. Despite recent progress, existing methods typically fall into two categories. Traditional approaches ba…
From SRA to Self-Flow: Data Augmentation or Self-Supervision?
Dengyang Jiang, Mengmeng Wang, Harry Yang +1
Representation alignment has become an effective way to accelerate diffusion transformer training and improve generation quality. Recent self-alignment methods, such as SRA and Sel…
VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
Ming Dai, Sen Yang, Boqiang Duan +4
Reasoning Video Object Segmentation (RVOS) demands a sophisticated integration of temporal dynamics, spatial details, and linguistic reasoning to achieve precise pixel-level locali…
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, which organizes historical context as raw frames, chunk segments, or unclustered tokens. This organizat…
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…
OptiMVMap: Offline Vectorized Map Construction via Optimal Multi-vehicle Perspectives
Zedong Dan, Zijie Wang, Wei Zhang +6
Offline vectorized maps constitute critical infrastructure for high-precision autonomous driving and mapping services. Existing approaches rely predominantly on single ego-vehicle…
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Keming Wu, Zuhao Yang, Kaichen Zhang +24
Recent visual generation models have made major progress in photorealism, typography, instruction following, and interactive editing, yet they still struggle with spatial reasoning…
Identity-Consistent Video Generation under Large Facial-Angle Variations
Bin Hu, Zipeng Qi, Guoxi Huang +6
Single-view reference-to-video methods often struggle to preserve identity consistency under large facial-angle variations. This limitation naturally motivates the incorporation of…
From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing
Haoyuan Zhang, Keyao Wang, Guosheng Zhang +11
Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classificat…
Rethinking Vector Field Learning for Generative Segmentation
Chaoyang Wang, Yaobo Liang, Boci Peng +3
Taming diffusion models for generative segmentation has attracted increasing attention. While existing approaches primarily focus on architectural tweaks or training heuristics, th…
DISPLAY: Directable Human-Object Interaction Video Generation via Sparse Motion Guidance and Multi-Task Auxiliary
Jiazhi Guan, Quanwei Yang, Luying Huang +7
Human-centric video generation has advanced rapidly, yet existing methods struggle to produce controllable and physically consistent Human-Object Interaction (HOI) videos. Existing…
GenHOI: Towards Object-Consistent Hand-Object Interaction with Temporally Balanced and Spatially Selective Object Injection
Xuan Huang, Mochu Xiang, Zhelun Shen +9
Hand-Object Interaction (HOI) remains a core challenge in digital human video synthesis, where models must generate physically plausible contact and preserve object identity across…
RefAlign: Representation Alignment for Reference-to-Video Generation
Lei Wang, YuXin Song, Ge Wu +5
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applica…
MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model
Jinguang Tong, Jinbo Wu, Kaisiyuan Wang +12
Human-Object Interaction (HOI) video reenactment aims to transfer the interaction dynamics of a source video to a novel target object while preserving realistic hand-object coordin…
RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations
Mochu Xiang, Zhelun Shen, Xuesong Li +7
Human perceive the 3D world through 2D observations from limited viewpoints. While recent feed-forward generalizable 3D reconstruction models excel at recovering 3D structures from…
CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
YuXin Song, Yu Lu, Haoyuan Sun +6
Unified conditional image generation remains difficult because different tasks depend on fundamentally different internal representations. Some require conceptual understanding for…
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…
SRA 2: Variational Autoencoder Self-Representation Alignment for Efficient Diffusion Training
Mengmeng Wang, Dengyang Jiang, Liuzhuozheng Li +6
Denoising-based diffusion transformers, despite their strong generation performance, suffer from inefficient training convergence. Existing methods addressing this issue, such as R…
CoT4Det: A Chain-of-Thought Framework for Perception-Oriented Vision-Language Tasks
Yu Qi, Yumeng Zhang, Chenting Gong +4
Large Vision-Language Models (LVLMs) have demonstrated remarkable success in a broad range of vision-language tasks, such as general visual question answering and optical character…
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…