YZ
Yulun Zhang
cs.CVeess.IVcs.AIcs.LGcs.CLcs.MMcs.GRcs.NEAlgorithmscs.AR
On Valency
published · living versionsW_fju6e3df·v1 · currentpublished
Task Relevance-Driven Prompt Expansion for Federated Continual Learning
with Jiahua Dong, Wenqi Liang, Yang Cong, Yichen Li +4
1 version
W_abjnt43j·v1published
W_5hykrwxv·v1published
Preprints & journals
247 papers in the corpus · 2018–2026Hihaze: One-Step Diffusion for High-Resolution Real-World Image Dehazing2610.25832v1 · Zheng Chen, Yuchen Huang, Xiaoyang Liu et al.2026 · 0 citationsarXivon Valency
VASC: Value-Aware Sparse Attention with Cross-Layer Memory for Efficient 3D Reconstruction2610.01013v1 · Junyi Wu, Fanqing Kong, Leyang Chen et al.2026 · 0 citationsarXiv
QuantSR+: Pushing the Limit of Quantized Image Super-Resolution Networks.42202201 · Qin, Haotong, Ma, Xudong, Liu, Xianglong et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):12229-12243
Crafting Your Evolving Dreams: Concept-Incremental Versatile Customization.42258692 · Dong, Jiahua, Liang, Wenqi, Li, Hongliu et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):12211-12228
RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning Models2609.39801v1 · Chengzhu Bao, Xianglong Yan, Tianao Zhang et al.2026 · 0 citationsarXiv
Discrete Annotation, Continuous Preference: Rethinking Supervision for Accurate and Generalizable Aesthetic Image Cropping2610.00582v1 · Ziqing Zhang, Xiao Liu, Kai Liu et al.2026 · 0 citationsarXiv
CAST: Reconstruction-Coupled Acceleration of Interactive World Models2609.34144v1 · Leyang Chen, Junyi Wu, Fanqing Kong et al.2026 · 0 citationsarXiv
JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization2609.33601v1 · Kaicheng Yang, Kaisen Yang, Chunyu Liu et al.2026 · 0 citationsarXiv
Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction2609.32353v2 · Junxian Li, Ruixuan Yang, Tianao Zhang et al.2026 · 0 citationsarXiv
SPHQuant: Efficient extreme low bit weight quantization for Vision-Language Models2609.24875v1 · Kewei Zhang, Zheng Chen, Haotong Qin et al.2026 · 0 citationsarXiv
BC-IHV: Conditioning the Color Space for Stable Rectified-Flow Low-Light Enhancement2608.21847v1 · Yi Ai, Zheng Chen, Yuanhao Cai et al.2026 · 0 citationsarXiv
Binarized High-Efficiency RAW Video Restoration and Beyond.42623200 · Zhu, Tianyu, Fu, Ying, Li, Hesong et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model2608.01845v1 · Leyang Chen, Junyi Wu, Shaoqiu Zhang et al.2026 · 0 citationsarXiv
FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling2608.01847v1 · Xianglong Yan, Hong Liu, Chengzhu Bao et al.2026 · 0 citationsarXiv
ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs2608.01979v2 · Zizhong Ding, Junxian Li, Kai Liu et al.2026 · 0 citationsarXiv
TurboClear: One-Step Object-Effect Removal via Region-Calibrated Distribution Matching and Fusion2608.01288v1 · Jiawei Guo, Junxian Li, Yixin Tang et al.2026 · 0 citationsarXiv
FreqForcing: Autoregressive Long Video Generation via Spectral Self-Anchoring2607.27110v2 · Jiatong Li, Leo Liang, Linghe Kong et al.2026 · 0 citationsarXiv
SAB-LVLM: Significance-Aware Binarization for Large Vision-Language Models2607.01876v1 · Qi Lyu, Jiahua Dong, Baichen Liu et al.2026 · 0 citationsarXiv
Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding2606.29845v2 · Zihan Zhou, Libo Zhu, Jue Gong et al.2026 · 0 citationsarXiv
Learning From Each Other: Generalized Federated Incremental Semantic Segmentation.41678480 · Dong, Jiahua, Liang, Wenqi, Cong, Yang et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(6):6929-6947
VDFP: Video Deflickering with Flicker-banding Priors2605.21079v2 · Zhiyi Zhou, Libo Zhu, Zihan Zhou et al.2026 · 0 citationsarXiv
Accelerating Rectified Flow Models via Trajectory-Aware Caching2605.16789v1 · Xiao Liu, Kai Liu, Naiyang Guan et al.2026 · 0 citationsarXiv
GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction2605.15852v2 · Leyang Chen, Junyi Wu, Zhiteng Li et al.2026 · 0 citationsarXiv
PRISM: Prior Rectification and Uncertainty-Aware Structure Modeling for Diffusion-Based Text Image Super-Resolution2605.13027v1 · Zihang Xu, Xiaoyang Liu, Zheng Chen et al.2026 · 0 citationsarXiv
DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution2605.13182v1 · Zheng Chen, Ruofan Yang, Jin Han et al.2026 · 0 citationsarXiv
PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow2605.14045v1 · Wei Dong, Han Zhou, Terry Ji et al.2026 · 0 citationsarXiv
SOAR: Scale Optimization for Accurate Reconstruction in NVFP4 Quantization2605.12245v1 · Chengzhu Bao, Xianglong Yan, Zhiteng Li et al.2026 · 0 citationsarXiv
GTR: Generation-Guided Visual Token Reduction for Separate-Encoder Unified Multimodal Models2605.12309v3 · Junxian Li, Kai Liu, Zizhong Ding et al.2026 · 0 citationsarXiv
PermuQuant: Lowering Per-Group Quantization Error by Reordering Channels for Diffusion Models2605.09503v2 · Yongsen Cheng, Kai Liu, Kaiwen Tao et al.2026 · 0 citationsarXiv
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching2605.09003v2 · Yixin Tang, Jiawei Guo, Junxian Li et al.2026 · 0 citationsarXiv
The First Challenge on Remote Sensing Infrared Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview2604.21312v1 · Kai Liu, Haoyang Yue, Zeli Lin et al.2026 · 0 citationsarXiv
The First Challenge on Mobile Real-World Image Super-Resolution at NTIRE 2026: Benchmark Results and Method Overview2604.17306v1 · Jiatong Li, Zheng Chen, Kai Liu et al.2026 · 0 citationsarXiv
The Fourth Challenge on Image Super-Resolution ($\times$4) at NTIRE 2026: Benchmark Results and Method Overview2604.14558v1 · Zheng Chen, Kai Liu, Jingkai Wang et al.2026 · 0 citationsarXiv
DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration2604.14560v1 · Zheng Chen, Bowen Chai, Rongjun Gao et al.2026 · 0 citationsarXiv
The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results2604.10532v2 · Jingkai Wang, Jue Gong, Zheng Chen et al.2026 · 0 citationsarXiv
Efficient Video Diffusion with Sparse Information Transmission for Video Compression2603.18501v1 · Mingde Zhou, Zheng Chen, Yulun Zhang2026 · 0 citationsarXiv
LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs2603.19217v1 · Keda Tao, Yuhua Zheng, Jia Xu et al.2026 · 0 citationsarXiv
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution2603.06275v2 · Jingkai Wang, Yixin Tang, Jue Gong et al.2026 · 0 citationsarXiv
AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization2602.09883v1 · Shaoqiu Zhang, Zizhong Ding, Kaicheng Yang et al.2026 · 0 citationsarXiv
PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks2602.06663v3 · Junxian Li, Kai Liu, Leyang Chen et al.2026 · 0 citationsarXiv
Fast-SAM3D: 3Dfy Anything in Images but Faster2602.05293v2 · Weilun Feng, Mingqiang Wu, Zhiliang Chen et al.2026 · 0 citationsarXiv
Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light Enhancement2602.04300v1 · Jue Gong, Zihan Zhou, Jingkai Wang et al.2026 · 0 citationsarXiv
LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration2602.04406v1 · Jue Gong, Zihan Zhou, Jingkai Wang et al.2026 · 0 citationsarXiv
BinaryDemoire: Moiré-Aware Binarization for Image Demoiréing2602.03176v1 · Zheng Chen, Zhi Yang, Xiaoyang Liu et al.2026 · 0 citationsarXiv
LSGQuant: Layer-Sensitivity Guided Quantization for One-Step Diffusion Real-World Video Super-Resolution2602.03182v2 · Tianxing Wu, Zheng Chen, Cirou Xu et al.2026 · 0 citationsarXiv
Combined Flicker-banding and Moire Removal for Screen-Captured Images2602.01559v1 · Libo Zhu, Zihan Zhou, Zhiyi Zhou et al.2026 · 0 citationsarXiv
VEQ: Modality-Adaptive Quantization for MoE Vision-Language Models2602.01037v1 · Guangshuo Qin, Zhiteng Li, Zheng Chen et al.2026 · 0 citationsarXiv
Q-DiT4SR: Exploration of Detail-Preserving Diffusion Transformer Quantization for Real-World Image Super-Resolution2602.01273v4 · Xun Zhang, Kaicheng Yang, Hongliang Lu et al.2026 · 0 citationsarXiv
DQuant: Accurate Low-bit Post-Training Weight Quantization for LLMs2602.02546v2 · Xianglong Yan, ChengZhu Bao, Zhiteng Li et al.2026 · 0 citationsarXiv
UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark2512.17196v1 · Kai Liu, Leyang Chen, Wenbo Li et al.2025 · 0 citationsarXiv
Career total: 329 works. 247 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.