PW
Pengfei Wan
cs.CVcs.AIcs.LGcs.CLcs.SDcs.GRcs.MMcs.ROComputer Graphicscs.HC
On Valency
published · living versionsW_5r9tq5an·v1 · currentpublished
RVG-Bench: A Benchmark for Reasoning-Driven Audio-Visual Temporal Grounding
with Yue Feng, Boshen Xu, Zihao Yue, Xiaokun Liu +3
1 version
W_qgpfjyy6·v2published
W_hm5m379s·v1published
Preprints & journals
207 papers in the corpus · 2014–2026GSHeadRelight: Fast Relightability for 3D Gaussian Head Synthesis2610.30619v1 · Henglei Lv, Bailin Deng, Jianzhu Guo et al.2026 · 0 citationsarXiv
Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video Generation2610.26801v1 · Yingshuang Zou, Xiaoyu Shi, Yawen Luo et al.2026 · 0 citationsarXivon Valency
PixelMoE: Scaling Pixel-Space Diffusion with LLM-Style Mixture-of-Experts2610.18857v1 · Ruixiao Dong, Jianmin Bao, Bozhi Luan et al.2026 · 0 citationsarXiv
PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary2610.16066v1 · Xinlong Chen, Weihong Lin, Yuanxing Zhang et al.2026 · 0 citationsarXiv
EventLens: Event-Structure Reinforcement Learning for Video Understanding2610.16172v1 · Guowen Zhang, Boshen Xu, Zihao Yue et al.2026 · 0 citationsarXiv
WorldAlign: Decoupled 4D Reward for World-Consistent Video Generation2610.12382v1 · Jing He, Kaixin Ding, Xingye Tian et al.2026 · 0 citationsarXiv
ORCA: The Annealed Spectral Conditioning Optimizer for Faster, Better LLM Training2610.06116v1 · Yuanshi Liu, Boyuan Jiang, Liang Hou et al.2026 · 0 citationsarXiv
SubjectAnchor: Subject-Aware Memory-to-Video for Multi-Shot Storytelling2609.34502v1 · Xinyu Wang, Huafeng Shi, Zian Li et al.2026 · 0 citationsarXiv
From Evaluation to Enhancement: Benchmarking and Improving Think-with-Video Reasoning for Video Generative Models2609.11242v1 · Meng Luo, Yicheng Liu, Jiahao Wang et al.2026 · 0 citationsarXiv
FlowCPO: A Unified Divergence View of Preference Alignment for Flow Models2609.09905v1 · Yansen Han, Shengyi Liao, Peng Sun et al.2026 · 0 citationsarXiv
Human-Centric Image Captioning with Subject-Centered Spatial Understanding2609.08300v1 · Bozhou Li, Jiahang Zhang, Yue Ding et al.2026 · 0 citationsarXiv
MVWeaver: A Hierarchical Music Video Generation Agent with a Learned Song-to-Visual Bridge2609.06478v1 · Sifei Li, Minyan Luo, Xu Li et al.2026 · 0 citationsarXiv
Closing the Verification Loop: Self-Check Captioning for Long-Paragraph Detailed Audio Captioning2608.30713v1 · Fengji Ma, Yan Rong, Xu Li et al.2026 · 0 citationsarXiv
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking2608.20011v1 · Yansen Han, Shengyi Liao, Yuanxing Zhang et al.2026 · 0 citationsarXiv
PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives2608.13552v2 · Kaixin Ding, Xi Chen, Minghong Cai et al.2026 · 0 citationsarXiv
SonicWeave: Chunk-Routed Mixture-of-Experts for Unified Audio Scene Generation2608.09571v1 · Yunrui Cai, Xu Li, Yucheng Zhou et al.2026 · 0 citationsarXiv
ContextMaster: Interactive Multi-Shot Video Creation via Fixed-Budget Sparse Context Routing2608.04956v1 · Xu Guo, Zhengxuan Wei, Xinghui Li et al.2026 · 0 citationsarXiv
Motion Beyond Morphology: Bootstrapping Cross-Category Motion Transfer from Abstract Motion Representations2608.01628v2 · Zhixue Fang, Zhimin Zhang, Bi'an Du et al.2026 · 0 citationsarXiv
Temporal Concentration from Rollout Errors: Implicit Preference Optimization for Text-to-Video Diffusion2607.28058v1 · Henglin Liu, Fangyuan Kong, Jing Wang et al.2026 · 0 citationsarXiv
Beacon: Knowing When and How to Perform Agentic Visual Reasoning2607.28595v2 · Qixun Wang, Yang Shi, Letian Cheng et al.2026 · 0 citationsarXiv
Amortized Moment Matching for Visual Generation2607.26860v1 · Wenze Liu, Xintao Wang, Pengfei Wan et al.2026 · 0 citationsarXiv
StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation2607.20174v1 · Zejing Rao, Haoxian Zhang, Xiaoqiang Liu et al.2026 · 0 citationsarXiv
PercepCap: Video Captioner with Structured Spatio-Temporal Perception2607.20389v2 · Yifan Xu, Zihao Wang, Zhixiao Wang et al.2026 · 0 citationsarXiv
ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships2607.14681v1 · Xinyu Liu, Shihao Li, Weihong Lin et al.2026 · 0 citationsarXiv
HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control2607.02075v3 · Yushuo Chen, Xiaoyu Shi, Xiaoshi Wu et al.2026 · 0 citationsarXiv
ExGes: Expressive Human Motion Retrieval and Modulation for Audio-Driven Gesture Synthesis.41921182 · Zhou, Xukun, Li, Fengxin, Chen, Ming et al.2026 · 1 citationIEEE transactions on visualization and computer graphics. 2026;32(7):6305-6318
MultiPaint: A Unified Framework for Multi-Task, Multi-Object, and Multi-Condition Video Inpainting.42127054 · Yang, Shiyuan, Gu, Zheng, Hou, Liang et al.2026 · 0 citationsIEEE transactions on visualization and computer graphics. 2026;32(7):7031-7045
MAVIN: Multi-Shot Audio-Visual Generation with Customized Narrative Control2606.29473v2 · Kaiqi Liu, Yunyao Mao, Ziqi Cai et al.2026 · 0 citationsarXiv
MindFlow: Harmonizing Cognitive Semantics and Acoustic Dynamics for Facial Animation Generation in Dyadic Conversations2606.27779v1 · Hejia Chen, Haoxian Zhang, Xu He et al.2026 · 0 citationsarXiv
Geometry-Instructed Video Editing2606.24225v1 · Chirui Chang, Xiaoyang Lyu, Yi-Hua Huang et al.2026 · 0 citationsarXiv
CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning2606.24636v1 · Xinyu Mao, Yuhui Zeng, Xiaokun Liu et al.2026 · 0 citationsarXiv
CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales2606.21949v1 · Xinlong Chen, Jiafu Tang, Yue Ding et al.2026 · 0 citationsarXiv
UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating2606.21661v1 · Jiehui Huang, Yuechen Zhang, Bin Xia et al.2026 · 0 citationsarXiv
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data2606.13432v1 · Jiwen Liu, Shujuan Li, Zhixue Fang et al.2026 · 0 citationsarXiv
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization2606.07326v1 · Yu Li, Menghan Xia, Gongye Liu et al.2026 · 0 citationsarXiv
Edit-R2: Context-Aware Reinforcement Learning for Multi-Turn Image Editing2606.05950v2 · Yuxiao Ye, Haoran He, Fangyuan Kong et al.2026 · 0 citationsarXiv
Diffusing in the Right Space: A Systematic Study of Latent Diffusability2606.03578v1 · Tianxiong Zhong, Xingye Tian, Xuebo Wang et al.2026 · 0 citationsarXiv
Geometry-Aware Implicit Memory for Video World Models2606.02436v1 · Zhengxuan Wei, Xu Guo, Xinghui Li et al.2026 · 0 citationsarXiv
VLMs are Good Teachers for Video Reasoning via Adaptive Test-Time Optimization2606.02564v3 · Junhao Cheng, Liang Hou, Tianxiong Zhong et al.2026 · 0 citationsarXiv
DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory2605.31336v1 · Zhenhao Yang, Xiaoshi Wu, Zhengyao Lv et al.2026 · 0 citationsarXiv
LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV2605.26244v1 · Tengfei Liu, Yang Shi, Xuanyu Zhu et al.2026 · 0 citationsarXiv
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning2605.22012v1 · Yifan Dai, Zhenhua Wu, Bohan Zeng et al.2026 · 0 citationsarXiv
Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos2605.18984v1 · Yuqi Tang, Yang Shi, Zhuoran Zhang et al.2026 · 0 citationsarXiv
FU-MPC: Frontier- and Uncertainty-Aware Model Predictive Control for Efficient and Accurate UAV Exploration with Motorized LiDAR2605.14920v1 · Jianping Li, Pengfei Wan, Zhongyuan Liu et al.2026 · 0 citationsarXiv
UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation2605.12088v2 · Yiyan Xu, Qiulin Wang, Wenjie Wang et al.2026 · 0 citationsarXiv
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling2605.05922v2 · Yuan Wang, Ouxiang Li, Yulong Xu et al.2026 · 0 citationsarXiv
Omni-o3: Deep Nested Omnimodal Deduction for Deliberative Audio-Visual Reasoning2604.24191v1 · Zhicheng Zhang, Wentao Gu, Weicheng Wang et al.2026 · 0 citationsarXiv
LIVE: Leveraging Image Manipulation Priors for Instruction-based Video Editing2604.17021v1 · Weicheng Wang, Zhicheng Zhang, Zhongqi Zhang et al.2026 · 0 citationsarXiv
Efficient Video Diffusion Models: Advancements and Challenges2604.15911v1 · Shitong Shao, Lichen Bai, Pengfei Wan et al.2026 · 0 citationsarXiv
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models2604.04707v2 · DataFlow Team, Bohan Zeng, Daili Hua et al.2026 · 0 citationsarXiv
Career total: at least 295 works. 207 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.