PJ
Peng-Tao Jiang
cs.CVcs.AIeess.IVcs.LGcs.IRcs.MMcs.SDeess.AS
On Valency
published · living versionsW_9qudptzx·v1 · currentpublished
FutureWorld: A Plug-and-Play Causal Next-State Predictor for Interactive Video World Exploration
with Guangyuan Li, Kelu Yao, Shuolin Xu, Xinlei Yu +4
1 version
Preprints & journals
56 papers in the corpus · 2018–2026SDMatte++: Grafting High-Resolution Diffusion Models for Interactive Matting.42853740 · Huang, Longfei, Shi, Linxiao, Li, Bo et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation2609.38748v3 · Hanmo Chen, Chengcheng Liu, Tianxiao Chen et al.2026 · 0 citationsarXiv
MotionJEPA: Preventing Temporal Feature Collapse by Capturing Visual Changes in Latent Space2609.23881v1 · Markus Karmann, Shile Li, Christian Interno et al.2026 · 0 citationsarXiv
EditaLive! Unified Character Video Editing for Live Streaming2608.27123v1 · Zhiyuan Li, Chi-Man Pun, Peng-Tao Jiang et al.2026 · 0 citationsarXiv
VIPER: Visual In-Context Physics Reasoning for Physically Plausible Video Generation2607.23472v1 · Tianxiao Chen, Hanmo Chen, Huajin Chen et al.2026 · 0 citationsarXiv
MagicMakeup: A Region-Controllable Diffusion Transformer for High-Fidelity Makeup-Transfer2607.20924v1 · Ziyi Wang, Siming Zheng, Yang Yang et al.2026 · 0 citationsarXiv
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation2606.30849v1 · Juncheng Ma, Yuxuan Du, Yanan Sun et al.2026 · 0 citationsarXiv
SPOT-E: Test-Time Entropy Shaping with Visual Spotlights for Frozen VLMs2606.20244v2 · Bo Yin, Xiaobin Hu, Chengming Xu et al.2026 · 0 citationsarXiv
Towards Photorealistic and Efficient Bokeh Rendering via Diffusion Framework2605.07429v2 · Linxiao Shi, Siming Zheng, Zerong Wang et al.2026 · 0 citationsarXiv
TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation2604.19473v1 · Hongyu Zhang, Yufan Deng, Zilin Pan et al.2026 · 0 citationsarXiv
SmartPhotoCrafter: Unified Reasoning, Generation and Optimization for Automatic Photographic Image Editing2604.19587v1 · Ying Zeng, Miaosen Luo, Guangyuan Li et al.2026 · 0 citationsarXiv
Anchor Forcing: Anchor Memory and Tri-Region RoPE for Interactive Streaming Video Diffusion2603.13405v1 · Yang Yang, Tianyi Zhang, Wei Huang et al.2026 · 0 citationsarXiv
MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems2603.09909v2 · Yunhang Qian, Xiaobin Hu, Jiaquan Yu et al.2026 · 0 citationsarXiv
CFG: Control Classifier-Free Guidance via Score Discrepancy Analysis2603.08155v3 · Jiayang Gao, Tianyi Zheng, Jiayang Zou et al.2026 · 0 citationsarXiv
FlowConsist: Make Your Flow Consistent with Real Trajectory2602.06346v1 · Tianyi Zhang, Chengcheng Liu, Jinwei Chen et al.2026 · 0 citationsarXiv
Trust but Verify: Adaptive Conditioning for Reference-Based Diffusion Super-Resolution via Implicit Reference Correlation Modeling2602.01864v1 · Yuan Wang, Yuhao Wan, Siming Zheng et al.2026 · 0 citationsarXiv
Bidirectional Beta-Tuned Diffusion Model.40875427 · Zheng, Tianyi, Zou, Jiayang, Jiang, Peng-Tao et al.2025 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(1):359-373
CameraMaster: Unified Camera Semantic-Parameter Control for Photography Retouching2511.21024v1 · Qirui Yang, Yang Yang, Ying Zeng et al.2025 · 0 citationsarXiv
MagicWorld: Towards Long-Horizon Stability for Interactive Video World Exploration2511.18886v2 · Guangyuan Li, Bo Li, Jinwei Chen et al.2025 · 0 citationsarXiv
VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models2511.11007v2 · Xinlei Yu, Chengming Xu, Guibin Zhang et al.2025 · 0 citationsarXiv
AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models2510.05715v1 · Shihao Zhu, Bohan Cao, Ziheng Ouyang et al.2025 · 0 citationsarXiv
Realism Control One-step Diffusion for Real-World Image Super-Resolution2509.10122v2 · Zongliang Wu, Siming Zheng, Peng-Tao Jiang et al.2025 · 1 citationarXiv
RED: Robust Event-Guided Motion Deblurring with Modality-Specific Disentanglement2509.05554v3 · Yihong Leng, Siming Zheng, Jinwei Chen et al.2025 · 0 citationsarXiv
A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models2508.01548v1 · Quan-Sheng Zeng, Yunheng Li, Qilong Wang et al.2025 · 2 citationsarXiv
SDMatte: Grafting Diffusion Models for Interactive Matting2508.00443v2 · Longfei Huang, Yu Liang, Hao Zhang et al.2025 · 1 citationarXiv
Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment2506.05384v2 · Zhuoxuan Cai, Jian Zhang, Xinbin Yuan et al.2025 · 0 citationsarXiv
Photography Perspective Composition: Towards Aesthetic Perspective Recommendation2505.20655v5 · Lujian Yao, Siming Zheng, Xinbin Yuan et al.2025 · 0 citationsarXiv
MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on2505.21325v3 · Guangyuan Li, Siming Zheng, Hao Zhang et al.2025 · 0 citationsarXiv
Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model2505.21593v3 · Yang Yang, Siming Zheng, Qirui Yang et al.2025 · 0 citationsarXiv
Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning2505.12370v2 · Xinbin Yuan, Jian Zhang, Kaixin Li et al.2025 · 1 citationarXiv
DSDNet: Raw Domain Demoiréing via Dual Color-Space Synergy2504.15756v2 · Qirui Yang, Fangpu Zhang, Yeying Jin et al.2025 · 3 citationsarXiv
A Temporal Modeling Framework for Video Pre-Training on Video Instance Segmentation2503.17672v1 · Qing Zhong, Peng-Tao Jiang, Wen Wang et al.2025 · 1 citationarXiv
M2N2V2: Multi-Modal Unsupervised and Training-free Interactive Segmentation2503.16254v1 · Markus Karmann, Peng-Tao Jiang, Bo Li et al.2025 · 0 citationsarXiv
DepthMaster: Taming Diffusion Models for Monocular Depth Estimation2501.02576v2 · Ziyang Song, Zerong Wang, Bo Li et al.2025 · 8 citationsarXiv
Learning Differential Pyramid Representation for Tone Mapping2412.01463v2 · Qirui Yang, Yinbo Li, Yihao Liu et al.2024 · 0 citationsarXiv
Learning Adaptive Lighting via Channel-Aware Guidance2412.01493v2 · Qirui Yang, Peng-Tao Jiang, Hao Zhang et al.2024 · 0 citationsarXiv
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation2410.21708v1 · Ruihao Xia, Yu Liang, Peng-Tao Jiang et al.2024 · 1 citationarXiv
ControlSR: Taming Diffusion Models for Consistent Real-World Image Super Resolution2410.14279v2 · Yuhao Wan, Peng-Tao Jiang, Qibin Hou et al.2024 · 0 citationsarXiv
Improving Consistency in Diffusion Models for Image Super-Resolution2410.13807v2 · Junhao Gu, Peng-Tao Jiang, Hao Zhang et al.2024 · 0 citationsarXiv
High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity2410.10105v3 · Qian Yu, Peng-Tao Jiang, Hao Zhang et al.2024 · 0 citationsarXiv
Towards Natural Image Matting in the Wild via Real-Scenario Prior2410.06593v1 · Ruihao Xia, Yu Liang, Peng-Tao Jiang et al.2024 · 0 citationsarXiv
Scalable Visual State Space Model with Fractal Scanning2405.14480v2 · Lv Tang, HaoKe Xiao, Peng-Tao Jiang et al.2024 · 5 citationsarXiv
Multi-Task Dense Prediction via Mixture of Low-Rank Experts2403.17749v2 · Yuqi Yang, Peng-Tao Jiang, Qibin Hou et al.2024 · 54 citationsarXiv
Empowering Segmentation Ability to Multi-modal Large Language Models2403.14141v1 · Yuqi Yang, Peng-Tao Jiang, Jing Wang et al.2024 · 2 citationsarXiv
Decoupling Degradation and Content Processing for Adverse Weather Image Restoration2312.05006v1 · Xi Wang, Xueyang Fu, Peng-Tao Jiang et al.2023 · 3 citationsarXiv
Revisiting Single Image Reflection Removal In the Wild2311.17320v1 · Yurui Zhu, Xueyang Fu, Peng-Tao Jiang et al.2023 · 35 citationsarXiv
Chain of Visual Perception: Harnessing Multimodal Large Language Models for Zero-shot Camouflaged Object Detection2311.11273v2 · Lv Tang, Peng-Tao Jiang, Zhihao Shen et al.2023 · 34 citationsarXiv
Towards Training-free Open-world Segmentation via Image Prompt Foundation Models2310.10912v3 · Lv Tang, Peng-Tao Jiang, Hao-Ke Xiao et al.2023 · 36 citationsarXiv
Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation2305.01275v1 · Peng-Tao Jiang, Yuqi Yang2023 · 19 citationsarXiv
Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections2304.08706v1 · Jiaxiong Qiu, Peng-Tao Jiang, Yifan Zhu et al.2023 · 25 citationsarXiv
Career total: 73 works. 56 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.