502 citations · 1.4k across the 190 of their papers we have counts for
196 papers
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…
PA-BiCoop: A Primary-Auxiliary Cooperative Framework for General Bimanual Manipulation
Bai Qicheng, Wang Ziru, Ma Teli +3
Bimanual manipulation is essential for advanced robotic systems because it offers higher efficiency and flexibility compared to single-arm configurations. However, existing approac…
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…
Exploring Time Conditioning in Diffusion Generative Models from Disjoint Noisy Data Manifolds
Liuzhuozheng Li, Zhiyuan Zhan, Shuhong Liu +5
Practically, training diffusion models typically requires explicit time conditioning to guide the network through the denoising sampling process. Especially in deterministic method…
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…
ERNIE 5.0 Technical Report
Haifeng Wang, Hua Wu, Tian Wu +432
In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio…
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…