LW
Limin Wang
cs.CVcs.AIcs.LGcs.ROcs.CLcs.MMcs.IRAlgorithmscs.GRcs.HC
On Valency
published · living versionsW_yzkyv33s·v1 · currentpublished
Preprints & journals
239 papers in the corpus · 2014–2026Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation2610.11756v3 · Jiaming Zhang, Xinyu Wang, Huafeng Shi et al.2026 · 0 citationsarXiv
Phase-aware video generation for physics-grounded dynamics and interactions2610.11791v1 · Jingfeng Ou, Kun Wang, Rui Zhao et al.2026 · 0 citationsarXiv
Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation2609.38886v1 · Yansong Shi, Jiange Yang, Xijie Yang et al.2026 · 0 citationsarXiv
Beyond a single latent space: a dual-latent world model for long-horizon planning2609.37644v1 · Delin Zhao, Zhengrong Yue, Shaobin Zhuang et al.2026 · 0 citationsarXiv
CoViT: Instance-Correspondence Contrastive Learning for Vision Transformer2609.01787v1 · Yisen Wang, Zhirong Wu, Limin Wang2026 · 0 citationsarXiv
SparseBEV: A Fully Sparse Framework for Multi-View 3D Object Detection.41921151 · Chen, Yang, Liu, Haisong, Wang, Limin2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(8):9748-9764
PercepCap: Video Captioner with Structured Spatio-Temporal Perception2607.20389v2 · Yifan Xu, Zihao Wang, Zhixiao Wang et al.2026 · 0 citationsarXiv
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs2607.17423v1 · Yuhan Zhu, Changlian Ma, Xiangyu Zeng et al.2026 · 0 citationsarXiv
VIABench: A Comprehensive Video Benchmark Collected from Blind Individuals for Visual Impairment Assistance2607.14660v1 · Yunfeng Liu, Yuandong Yang, Jiarui Han et al.2026 · 0 citationsarXiv
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding2607.14935v2 · Xinhao Li, Yuhan Zhu, Xiangyu Zeng et al.2026 · 0 citationsarXiv
MIMFlow: Integrating Masked Image Modeling with Normalizing Flows for End-to-End Image Generation2606.26016v3 · Yang Chen, Xiaowei Xu, Shuai Wang et al.2026 · 0 citationsarXiv
UniDDT: Unifying Multimodal Understanding and Generation with Decoupled Diffusion Transformer2606.16255v1 · Shuai Wang, Liang Li, Yang Chen et al.2026 · 0 citationsarXiv
HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers2606.13289v1 · Guozhen Zhang, Xuerui Qiu, Yutao Cui et al.2026 · 0 citationsarXiv
SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection2606.12033v1 · Min Yang, Mi Zhou, Limin Wang2026 · 0 citationsarXiv
InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning2606.12195v1 · Ziang Yan, Sheng Xia, Jiashuo Yu et al.2026 · 0 citationsarXiv
Explainable Forensics of Manipulated Segments in Untrimmed Long Videos2606.02402v1 · Yue Feng, Jingjing Li, Qijia Lu et al.2026 · 0 citationsarXiv
StreamOV: Streaming Omni-Video Understanding via Evidence-Guided Memory and Response Triggering2605.25621v1 · Ming Xie, Zizheng Huang, Xudong Tan et al.2026 · 0 citationsarXiv
USV: Towards Understanding the User-generated Short-form Videos2605.20838v1 · Haoyue Cheng, Su Xu, Liwei Jin et al.2026 · 0 citationsarXiv
S2T-RLHF: Hierarchical Credit Assignment for Stable Preference-Based RLHF2607.18258v1 · Wei Chen, Guanghui Zhu, Yafei Li et al.2026 · 0 citationsarXiv
Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline2603.05484v1 · Guo Chen, Lidong Lu, Yicheng Liu et al.2026 · 0 citationsarXiv
RIVER: A Real-Time Interaction Benchmark for Video LLMs2603.03985v1 · Yansong Shi, Qingsong Zhao, Tianxiang Jiang et al.2026 · 0 citationsarXiv
VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models.41247905 · Huang, Ziqi, Zhang, Fan, Xu, Xiaojie et al.2025 · 13 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;PP
LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization2602.02341v1 · Zhenpeng Huang, Jiaqi Li, Zihan Jia et al.2026 · 0 citationsarXiv
GLAD: Generative Language-Assisted Visual Tracking for Low-Semantic Templates2602.00570v1 · Xingyu Luo, Yidong Cai, Jie Liu et al.2026 · 1 citationarXiv
Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning2601.23224v2 · Xiangyu Zeng, Zhiqiu Zhang, Yuhan Zhu et al.2026 · 0 citationsarXiv
VMonarch: Efficient Video Diffusion Transformers with Structured Attention2601.22275v1 · Cheng Liang, Haoxian Chen, Liang Hou et al.2026 · 0 citationsarXiv
TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs2512.14698v2 · Jun Zhang, Teng Wang, Yuying Ge et al.2025 · 0 citationsarXiv
TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning2512.03963v3 · Tao Wu, Li Yang, Gen Zhan et al.2025 · 0 citationsarXiv
InternVideo-Next: Towards General Video Foundation Models without Video-Text Supervision2512.01342v2 · Chenting Wang, Yuhan Zhu, Yicheng Xu et al.2025 · 0 citationsCVPR2026
Flowing Backwards: Improving Normalizing Flows via Reverse Representation Alignment2511.22345v2 · Yang Chen, Xiaowei Xu, Shuai Wang et al.2025 · 0 citationsarXiv
VKnowU: Evaluating Visual Knowledge Understanding in Multimodal LLMs2511.20272v3 · Tianxiang Jiang, Sheng Xia, Yicheng Xu et al.2025 · 0 citationsarXiv
SteadyDancer: Harmonized and Coherent Human Image Animation with First-Frame Preservation2511.19320v2 · Jiaming Zhang, Shengming Cao, Rui Li et al.2025 · 0 citationsarXiv
Reasoning Guided Embeddings: Leveraging MLLM Reasoning for Improved Multimodal Retrieval2511.16150v1 · Chunxu Liu, Jiyuan Yang, Ruopeng Gao et al.2025 · 0 citationsarXiv
UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions2511.03334v2 · Guozhen Zhang, Zixiang Zhou, Teng Hu et al.2025 · 0 citationsarXiv
CycleACR: Cycle Modeling of Actor-Context Relations for Video Action Detection.40758518 · Chen, Lei, Tong, Zhan, Song, Yibing et al.2025 · 5 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):10588-10603
Deep Equilibrium Object Detection and Segmentation.40758523 · Wang, Shuai, Teng, Yao, Wang, Limin2025 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2025;47(11):10094-10111
VideoTG-R1: Boosting Video Temporal Grounding via Curriculum Reinforcement Learning on Reflected Boundary Annotations2510.23397v1 · Lu Dong, Haiyu Zhang, Han Lin et al.2025 · 1 citationarXiv
MUVR: A Multi-Modal Untrimmed Video Retrieval Benchmark with Multi-Level Visual Correspondence2510.21406v1 · Yue Feng, Jinwei Hu, Qijia Lu et al.2025 · 0 citationsarXiv
SAM 2++: Tracking Anything at Any Granularity2510.18822v4 · Jiaming Zhang, Cheng Liang, Yichun Yang et al.2025 · 0 citationsarXiv
ExpVid: A Benchmark for Experiment Video Understanding & Reasoning2510.11606v1 · Yicheng Xu, Yue Wu, Jiashuo Yu et al.2025 · 0 citationsarXiv
UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation2510.10575v2 · Zhengrong Yue, Haiyu Zhang, Xiangyu Zeng et al.2025 · 0 citationsarXiv
Evolaris: A Roadmap to Self-Evolving Software Intelligence Management2510.04689v1 · Chengwei Liu, Wenbo Guo, Yuxin Zhang et al.2025 · 1 citationarXiv
Arbitrary Generative Video Interpolation2510.00578v3 · Guozhen Zhang, Haiguang Wang, Chunyu Wang et al.2025 · 0 citationsarXiv
MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation2509.26391v1 · Chenhui Zhu, Yilu Wu, Shuai Wang et al.2025 · 1 citationarXiv
FreeRet: MLLMs as Training-Free Retrievers2509.24621v3 · Yuhan Zhu, Xiangyu Zeng, Chenting Wang et al.2025 · 0 citationsarXiv
StreamForest: Efficient Online Video Understanding with Persistent Event Memory2509.24871v1 · Xiangyu Zeng, Kefan Qiu, Qingyu Zhang et al.2025 · 7 citationsarXiv
Learning Goal-Oriented Vision-and-Language Navigation with Self-Improving Demonstrations at Scale2509.24910v2 · Songze Li, Zun Wang, Gengze Zhou et al.2025 · 0 citationsarXiv
VideoChat-R1.5: Visual Test-Time Scaling to Reinforce Multimodal Reasoning by Iterative Perception2509.21100v1 · Ziang Yan, Xinhao Li, Yinan He et al.2025 · 6 citationsarXiv
InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency2508.18265v2 · Weiyun Wang, Zhangwei Gao, Lixin Gu et al.2025 · 6 citationsarXiv
MobileViCLIP: An Efficient Video-Text Model for Mobile Devices2508.07312v1 · Min Yang, Zihan Jia, Zhilin Dai et al.2025 · 0 citationsarXiv
Career total: at least 401 works. 239 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.