JL
Jing Lyu
cs.CVcs.AIcs.CLcs.ROcs.DCcs.IRcs.LGcs.SD
On Valency
published · living versionsW_3mgrdh7a·v1 · currentpublished
From Evaluation to Evolution: Benchmarking Image Editing and Evolving Image Models
with Jun He, Canmiao Fu, Ying Zhang, Zhipeng Huang +5
1 version
W_vgx55xdr·v2published
W_w722hxqt·v1published
Preprints & journals
40 papers in the corpus · 2026WeVisOne-VL: Unified Visual Perception from Objects to Pixels2610.31329v2 · Tianming Liang, Junyi Pan, Yuxi Li et al.2026 · 0 citationsarXivon Valency
Wan-Alpha++: Animating a Single RGBA Asset into Controllable Transparent Video Effects2610.26189v1 · Haotian Dong, Xin Wang, Wenjing Wang et al.2026 · 0 citationsarXivon Valency
Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation2610.20794v1 · Sujie Hu, Huaisong Zhang, Pujing Yang et al.2026 · 0 citationsarXiv
SyncReward: Human-Aligned Synchronization Reward for Audio-Visual Generation2610.16338v1 · Kaisi Guan, Ying Ba, Wenjing Wang et al.2026 · 0 citationsarXiv
StageBreaker: Shifting Video RL Post-Training Scheduling from Stages down to Data Dependencies2610.16691v1 · Li Peng, Chenghuan Huang, Ziyang Ma et al.2026 · 0 citationsarXiv
All-in-One Multilingual Scene Text Recognition with Script-aware Mixture-of-Experts2609.24058v1 · Xingsong Ye, Yongkun Du, Jiaxin Zhang et al.2026 · 0 citationsarXiv
WeVisDoc: From Coverage to Capability for Robust End-to-End Document Parsing2609.20423v1 · Hao Yu, Kang Liu, Linnan Zhao et al.2026 · 0 citationsarXiv
WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report2608.24053v1 · Junjie Zhou, Ke Mei, Lei Li et al.2026 · 0 citationsarXiv
Loopy: Seamless Video Loop Generation via Anchored Looping Shift of Positional Embedding2608.23090v1 · Haotian Dong, Wenjing Wang, Chen Li et al.2026 · 0 citationsarXiv
PaDoc: Layout-Grounded Parallel Decoding for Document Parsing2608.06146v1 · Hao Yu, Jiabo Zhan, Kang Liu et al.2026 · 0 citationsarXiv
FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation2607.16190v1 · Hao Liu, Chenghuan Huang, Ye Huang et al.2026 · 0 citationsarXiv
Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing2607.08497v1 · Feng Wang, Canmiao Fu, Zhipeng Huang et al.2026 · 0 citationsarXiv
MMAgent-R: Learning to Rerank and Reject for Agentic mRAG2607.07383v1 · Tao Zhang, Ziqi Zhang, Zongyang Ma et al.2026 · 0 citationsarXiv
Segmentation before Answering: Pixel Grounding for MLLM Visual Reasoning2607.05798v1 · Yake Wei, Yuan Wang, Fengyun Rao et al.2026 · 0 citationsarXiv
Orca: The World is in Your Mind2606.30534v3 · Yihao Wang, Yuheng Ji, Mingyu Cao et al.2026 · 0 citationsarXiv
PortraitGen: Exemplar-Driven GRPO with Dual-Reward Guidance for Photorealistic Portrait Generation2606.26930v1 · Xiaomin Li, Qian Liang, Yinan Li et al.2026 · 0 citationsarXiv
Advancing WordArt-Oriented Scene Text Recognition: Datasets and Methods2606.24484v1 · Xingsong Ye, Yongkun Du, Jiaxin Zhang et al.2026 · 0 citationsarXiv
Chorus II: Cross-Request Sparsity Reuse for Efficient Image-to-Video Generation2606.25040v1 · Hao Liu, Chenghuan Huang, Hao Liu et al.2026 · 0 citationsarXiv
WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization2606.20100v1 · Qian Liang, Xiaomin Li, Ying Zhang et al.2026 · 0 citationsarXiv
MBench: A Comprehensive Benchmark on Memory Capability for Video World Models2606.00793v2 · Shengjun Zhang, Zhang Zhang, Simin Huang et al.2026 · 0 citationsarXiv
REVERSE: Reinforcing Evidence Verification and Search for Agentic Image geo-localization2605.26861v1 · Yong Li, Furong Jia, Dacheng Yin et al.2026 · 0 citationsarXiv
DRM: Diffusion-based Reward Model With Step-wise Guidance2605.25661v2 · Jaxon Zhang, Binxin Yang, Hubery Yin et al.2026 · 0 citationsarXiv
ClueAegis: Heuristic-to-Reasoning Cognitive-skill Learning for Unified Evidence-based Synthetic Image Detection2605.25009v1 · Huangsen Cao, Hongkang Chu, Yuxi Li et al.2026 · 0 citationsarXiv
Stage-adaptive Token Selection for Efficient Omni-modal LLMs2605.20035v2 · Zijie Xin, Jie Yang, Ruixiang Zhao et al.2026 · 0 citationsarXiv
WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens2605.18115v1 · Yiwei Guo, Shaobin Zhuang, Zhipeng Huang et al.2026 · 0 citationsarXiv
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding2605.18577v1 · Ruixiang Zhao, Jie Yang, Zijie Xin et al.2026 · 0 citationsarXiv
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models2605.10903v1 · Wenxuan Song, Han Zhao, Fuhao Li et al.2026 · 0 citationsarXiv
Beyond Chain-of-Thought: Rewrite as a Universal Interface for Generative Multimodal Embeddings2604.22280v4 · Peixi Wu, Ke Mei, Feipeng Ma et al.2026 · 0 citationsarXiv
Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse2604.04451v1 · Hao Liu, Ye Huang, Chenghuan Huang et al.2026 · 0 citationsarXiv
From Understanding to Erasing: Towards Complete and Stable Video Object Removal2604.01693v2 · Dingming Liu, Wenjing Wang, Chen Li et al.2026 · 0 citationsarXiv
Identity as Presence: Towards Appearance and Voice Personalized Joint Audio-Video Generation2603.17889v4 · Qin Chen, Yingjie Chen, Shilun Lin et al.2026 · 0 citationsarXiv
AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agents2603.16496v2 · Shannan Yan, Jingchen Ni, Leqi Zheng et al.2026 · 0 citationsarXiv
NOVA: Sparse Control, Dense Synthesis for Pair-Free Video Editing2603.02802v1 · Tianlin Pan, Jiayi Dai, Chenpu Yuan et al.2026 · 0 citationsarXiv
Learning Cross-View Object Correspondence via Cycle-Consistent Mask Prediction2602.18996v2 · Shannan Yan, Leqi Zheng, Keyu Lv et al.2026 · 0 citationsarXiv
Improving Reconstruction of Representation Autoencoder2602.08620v1 · Siyu Liu, Chujie Qin, Hubery Yin et al.2026 · 0 citationsarXiv
D-ORCA: Dialogue-Centric Optimization for Robust Audio-Visual Captioning2602.07960v1 · Changli Tang, Tianyi Wang, Fengyun Rao et al.2026 · 1 citationarXiv
What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolution2602.06450v2 · Xingsong Ye, Yongkun Du, JiaXin Zhang et al.2026 · 0 citationsarXiv
Reshaping Action Error Distributions for Reliable Vision-Language-Action Models2602.04228v1 · Shuanghao Bai, Dakai Wang, Cheng Chi et al.2026 · 0 citationsarXiv
ObjEmbed: Towards Universal Multimodal Object Embeddings2602.01753v3 · Shenghao Fu, Yukun Su, Fengyun Rao et al.2026 · 0 citationsarXiv
Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Models2602.01166v2 · Shuanghao Bai, Jing Lyu, Wanqi Zhou et al.2026 · 0 citationsarXiv
Career total: 43 works. 40 are in this corpus.
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.