GZ
Guangtao Zhai
cs.CVeess.IVcs.MMcs.AIcs.LGcs.CLcs.SDArtificial Intelligencecs.RODeep learning
On Valency
published · living versionsW_6x58tpa2·v1 · currentpublished
KV Cache Quantization for Diffusion Language Models
with Yan Tai, Yunan Ding, Guangzhao Li, Siqi Luo +3
1 version
W_zsxva6bf·v1published
Preprints & journals
397 papers in the corpus · 2010–2026LG-Bench: A Graph-Structured Evaluation Benchmark for Life Sciences2610.26787v1 · Lu Sun, Xiangyi Zhang, Xiangyang Zhu et al.2026 · 0 citationsarXivon Valency
Trapped in Your Story: Evaluating Narrative-Induced Sycophancy in Large Language Models2610.23525v1 · Runtai Yang, Dandan Zhu, Kaiwei Zhang et al.2026 · 0 citationsarXiv
EmoGenie: Benchmarking and Evaluating Expressed and Evoked Emotion in T2I Generation with MLLMs2610.18455v1 · Zixuan Xing, Lancheng Gao, Shengyan Li et al.2026 · 0 citationsarXiv
DexBioLab: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories2610.13643v4 · Xuanye Wu, Yue Shi, Yongcan Yang et al.2026 · 0 citationsarXiv
From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMs2610.10066v1 · Zijian Chen, Zhengyu Chen, Bohan Liang et al.2026 · 0 citationsarXiv
Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection2610.06394v1 · Zhaolin Cai, Huiyu Duan, Liu Yang et al.2026 · 0 citationsarXiv
Q-SiT: Teaching LMMs for Image Quality Scoring and Interpreting.42785264 · Zhang, Zicheng, Wu, Haoning, Jia, Ziheng et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
MCIQA-2K: A Multi-Dimensional Dataset and No-Reference Quality Assessment Benchmark for Colorized Images2609.14495v1 · Yunkai Zhuang, Qihang Yan, Zicheng Zhang et al.2026 · 0 citationsarXiv
Hierarchical Mesh Representation Learning With Spectral Dictionary Embedding.42081425 · Gao, Zhongpai, Yan, Junchi, Luan, Tianyu et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(9):10889-10905
SciMIF: Understanding Multimodal Instruction Following in Scientific Domains2608.25973v1 · Ye Shen, Yuting Zheng, Dun Pei et al.2026 · 0 citationsarXiv
AT-ADD: A Benchmark and Challenge for Robust and All-Type Audio Deepfake Detection2608.23437v2 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
PCQA-R1: Advancing Generalized 3D Point Cloud Quality Assessment with Reinforcement Learning2608.18627v1 · Kangning Ye, Yunhao Li, Sijing Wu et al.2026 · 0 citationsarXiv
CamWorldQA: Perceptual Quality Assessment of Camera-Controlled World Video Generation2608.18710v1 · Yunhe Li, Likun Wu, Sijing Wu et al.2026 · 0 citationsarXiv
FMReward: Aligning and Evaluating Audio-Driven 3D Facial Animation with Human Preferences.42611681 · Wu, Sijing, Li, Yunhao, Gao, Zhilin et al.2026 · 0 citationsIEEE transactions on visualization and computer graphics. 2026;PP
AT-ADD: All-Type Audio Deepfake Detection Challenge Summary2608.14249v1 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
H2R-Bench: Benchmarking Human-to-Robot Manipulation Video Generation in World Models2608.13049v1 · Dingyi Rong, Yue Shi, Chaofan Ma et al.2026 · 0 citationsarXiv
LLaVA-Assessor: Building the Foundation LMM For Visual Quality Assessment2609.26205v1 · Ziheng Jia, Zicheng Zhang, Jiaying Qian et al.2026 · 0 citationsarXiv
ELBench: A Multi-Dimensional Benchmark for Education-Facing Large Language Models2608.09548v2 · Yilin Jiang, Xiaorong Zhu, Fei Tan et al.2026 · 0 citationsarXiv
3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment2608.03279v1 · Yuke Xing, Jiarui Wang, William Gordon et al.2026 · 0 citationsarXiv
MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing2608.02059v1 · Zitong Xu, Huiyu Duan, Xinyun Zhang et al.2026 · 0 citationsarXiv
Variational Bayesian Personalized Ranking.41805520 · Liu, Bin, Liu, Xiaohong, Luo, Qin et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(8):8936-8952
Media Meets Communication in 6G: Fundamentals, Key Technologies, and Applications2608.05184v1 · Bingyan Xie, Longyu Zhou, Zihan Chen et al.2026 · 0 citationsarXiv
Rarity-Aware Discrete Diffusion with Spatially Consistent Decoding for Photo-Realistic Image Super-Resolution2607.17612v2 · Ao Li, Yapeng Du, Yi Xin et al.2026 · 0 citationsarXiv
Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model2607.16742v1 · Sijing Wu, Yunhao Li, Huiyu Duan et al.2026 · 0 citationsarXiv
CompressedVQA-AEV: Full-Reference and No-Reference Quality Assessment Models for Asymmetric Encoded Videos2607.04606v1 · Wei Sun, Xingwei Liu, Dandan Zhu et al.2026 · 0 citationsarXiv
ICME 2026 Grand Challenge on Cross-Scenario Defect Detection and Fine-Grained Severity Grading for High-Precision Manufacturing2607.04675v1 · Wei Sun, Weixia Zhang, Linhan Cao et al.2026 · 0 citationsarXiv
From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation2607.04691v1 · Baixuan Zhao, Xinyu Zhang, Huayu Zheng et al.2026 · 0 citationsarXiv
DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble2607.00416v1 · Wei Sun, Weixia Zhang, Hongjian Zhan et al.2026 · 0 citationsarXiv
Beyond Single Character: Evaluating MLLMs for Sentence-Level Oracle Bone Inscription Understanding2606.31169v1 · Ziqi Li, Zijian Chen, Tingzhu Chen et al.2026 · 0 citationsarXiv
LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning2606.29752v1 · Wei Sun, Yanwei Jiang, Dandan Zhu et al.2026 · 0 citationsarXiv
LatentRevise: Learning from Zero-Hit Reasoning2606.29938v1 · Yiqiu Guo, Xueting Han, Qi Jia et al.2026 · 0 citationsarXiv
In-context Region-based Drag: Drag Any Region to Any Shape2606.25907v1 · Jiacheng Sui, Tianyu Hao, Bingjie Gao et al.2026 · 0 citationsarXiv
Robo2Process: Benchmarking and Learning Process-Aware Understanding in Vision-Language Robotic Manipulation2606.13040v4 · Dayu Xia, Yue Shi, Yao Mu et al.2026 · 0 citationsarXiv
Towards Characterizing Scientific Image Utility and Upgradability2606.03401v2 · WenZhe Li, Qihang Yan, Liang Chen et al.2026 · 0 citationsarXiv
LL-Bench: Rethinking Low-Level Vision Evaluation in the Era of Large-Scale Generative Models2606.02535v1 · Lu Liu, Huiyu Duan, Chenxin Zhu et al.2026 · 0 citationsarXiv
DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation2605.25876v1 · Jiaying Qian, Ziheng Jia, Qian Zhang et al.2026 · 0 citationsarXiv
Efficient One-Step Diffusion Restoration Model with Compact Token Compression and Linear Attention2605.23451v2 · Bingtian Qiao, Yue Shi, Yingjie Zhou et al.2026 · 0 citationsarXiv
Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models2605.16842v1 · Siqi Luo, Jianghan Shen, Yi Xin et al.2026 · 0 citationsarXiv
GeoR-Bench: Evaluating Geoscience Visual Reasoning2605.11541v1 · Yushuo Zheng, Zicheng Zhang, Huiyu Duan et al.2026 · 0 citationsarXiv
EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement2605.07457v1 · Zitong Xu, Huiyu Duan, Yifei Nie et al.2026 · 0 citationsarXiv
ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning2605.07477v1 · Honghua Chen, Zitong Xu, Huiyu Duan et al.2026 · 0 citationsarXiv
DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models2605.06170v1 · Juntong Wang, Jiarui Wang, Huiyu Duan et al.2026 · 0 citationsarXiv
LoViF 2026 The First Challenge on Holistic Quality Assessment for 4D World Model (PhyScore)2605.05187v1 · Wei Luo, Yiting Lu, Xin Li et al.2026 · 0 citationsarXiv
The New Frontier of Quality Evaluation for Visual Sensors: A Survey of Large Multimodal Model-Based Methods.42076638 · Ge, Qihang, Min, Xiongkuo, Wu, Sijing et al.2026 · 0 citationsSensors (Basel, Switzerland). 2026;26(8)
MirrorBench: Evaluating Self-centric Intelligence in MLLMs by Introducing a Mirror2604.14785v2 · Shengyu Guo, Tongrui Ye, Jianbo Zhang et al.2026 · 0 citationsarXiv
DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment2604.12813v2 · Xinyue Li, Shubo Xu, Zhichao Zhang et al.2026 · 0 citationsarXiv
AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan2604.08184v1 · Yuankun Xie, Haonan Cheng, Jiayi Zhou et al.2026 · 0 citationsarXiv
Market-Bench: Benchmarking Large Language Models on Economic and Trade Competition2604.05523v2 · Yushuo Zheng, Huiyu Duan, Zicheng Zhang et al.2026 · 0 citationsarXiv
ITIScore: An Image-to-Text-to-Image Rating Framework for the Image Captioning Ability of MLLMs2604.03765v2 · Zitong Xu, Huiyu Duan, Shengyao Qin et al.2026 · 0 citationsarXiv
Developing Evolving Adaptability in Biological Intelligence: A Novel Biologically-Inspired Continual Learning Model for Video Saliency Prediction.41385441 · Zhu, Dandan, Zhang, Kaiwei, Zhu, Kun et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(4):4257-4274
Career total: 981 works. 397 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.