DT
Dacheng Tao
cs.CVcs.LGcs.AIcs.CLstat.MLAlgorithmscs.CRquant-phmath.OCArtificial Intelligence
On Valency
published · living versionsW_s238b7ub·v1 · currentpublished
AdaGround: Token-Normalized Adaptive Zooming with Verifier-in-the-Loop Refinement for GUI Grounding
with Bingchao Wang, Yongcheng Jing, Chengyu Wang, Jun Huang +2
1 version
W_89re7bev·v1published
W_euauuauq·v1published
W_6wgw3hc9·v1published
W_td3fyhyw·v1published
W_2m4cjw2n·v1published
Preprints & journals
1,296 papers in the corpus · 2006–2026Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability2610.31551v1 · Guodong Zheng, Yan Sun, Peng Wang et al.2026 · 0 citationsarXivon Valency
Generalized CycleGRPO for Fine-Grained Multimodal Understanding and Grounding2610.29552v1 · Xin Zhang, Haochen Wang, Beibei Lin et al.2026 · 0 citationsarXivon Valency
A Sharp Dynamic Haussler Lemma2610.29898v1 · Shihao Shao, Dacheng Tao2026 · 0 citationsarXivon Valency
Disentangled Information Asymmetry in Spatial High-dimensional Data Interpretation.42905594 · He, Xiao, Zhao, Huangxuan, Liao, Minghui et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization2610.14942v1 · Shizhan Cai, Qixin Zhang, Siyuan Ma et al.2026 · 0 citationsarXiv
Rewiring Semantics, Dynamics, and Control: A Simple yet Effective Action-Centric Tri-Stream Transformer2610.11416v1 · Shuang Luo, Yilun Kong, Yunpeng Qing et al.2026 · 0 citationsarXiv
Causal Improvement Graph for Agentic Harness Optimization2610.05039v1 · Junjie Zhang, Shunyu Liu, Haoyu Wang et al.2026 · 0 citationsarXiv
Benchmarking the Robustness of Autonomous Driving to Environmental Illusions: A Lane Perception Perspective.42398000 · Zhang, Tianyuan, Liu, Xianglong, Liu, Aishan et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(10):13370-13388
ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents2609.37311v2 · Haohao Qu, Yongcheng Jing, Chun Hin Chan et al.2026 · 0 citationsarXiv
Q-learning Penalized Transformer for Safe Offline Reinforcement Learning2609.34426v2 · Shengchao Hu, Peng Wang, Jifeng Hu et al.2026 · 0 citationsarXiv
Alignment-Guided Flow Transformer for Efficient Vision-Language-Action Policy Learning2609.34467v2 · Shengchao Hu, Peng Wang, Qiyang Zhou et al.2026 · 0 citationsarXiv
Poisson Exchange Beyond Submodularity: Effective Approximation Algorithms for Offline and Online Subset Selection over Matroids2609.24569v2 · Shi Fu, Youming Qiao, Dacheng Tao et al.2026 · 0 citationsarXiv
World Models for Embodied Intelligence: From Plausible to Controllable to Actionable2609.16697v1 · Nanjie Yao, Hao Wang, Chong Cheng et al.2026 · 0 citationsarXiv
CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration.42743024 · Qiao, Ting, Li, Yiming, Li, Jianbin et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;PP
TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-Tuning LLMs.42785259 · Sun, Yan, Zhang, Qixin, Ding, Liang et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;PP
Sharp Norms from Finite Structure: Graph Matrices and Structured Chaoses2609.14266v1 · Huibo Xu, Shi Fu, Youming Qiao et al.2026 · 0 citationsarXiv
A Sharp Barrier for Consistent Submodular Maximization: Any Improvement over Entails Exponential Queries or Linear Recourse2609.09986v1 · Shi Fu, Qixin Zhang, Dacheng Tao2026 · 0 citationsarXiv
TrojanWorld: Backdooring World-Model Agents via Imagination Steering2609.07051v1 · Wenkai Huang, Siyuan Liang, Gaolei Li et al.2026 · 0 citationsarXiv
Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy Tails2609.03504v1 · Shi Fu, Huibo Xu, Qixin Zhang et al.2026 · 0 citationsarXiv
Synchronization Strings over the Optimal Alphabet2609.04122v2 · Huibo Xu, Shi Fu, Youming Qiao et al.2026 · 0 citationsarXivon Valency
Efficient Communication With Skill Neurons in Decentralized Multi-Agent Reinforcement Learning.42678856 · Lan, Jiahua, Shen, Li, Liu, Ruijun et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;PP
RegimeFormer: A Large Protein Model of Global Perturbation Regimes2608.26586v1 · Siyuan Ma, Yi Chai, Yi Wu et al.2026 · 0 citationsarXivon Valency
CIVA: Critic-Induced Value-Subspace Attacks on Visual World-Model Agents2608.21114v3 · Jiancheng Wang, Mingli Zhu, Tong Zhang et al.2026 · 0 citationsarXiv
Feature Priming in Online Linear Regression: Sparse-Regret Lower Bounds and Tight Coordinatewise Rates2608.17573v2 · Huibo Xu, Shi Fu, Qixin Zhang et al.2026 · 0 citationsarXiv
Human-Centric Intelligence in the Era of Foundation Models: A Survey2608.18184v1 · Yang Chen, Tianqi Wang, Xiaorui Jiang et al.2026 · 0 citationsarXiv
A cross-modal generative model for incomplete and degraded prostate MRI with multicentre clinical validation2608.16233v1 · Siyuan Ma, Liang He, Mengying Zhu et al.2026 · 0 citationsarXiv
ComBodied Agents: a New Paradigm of Human-Centric Agentic AI2608.10915v2 · Qianggang Ding, Xingyao Wang, Rui Feng et al.2026 · 0 citationsarXiv
SafeCA: Safe Cross-Attention Localization and Regulation for Text-to-Video Jailbreak Defense2608.10933v1 · Siyuan Liang, Yupeng Qiu, Junfeng Fang et al.2026 · 0 citationsarXiv
Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models2608.08199v1 · Wenwen He, Wenke Huang, Wei Yang Bryan Lim et al.2026 · 0 citationsarXiv
Beyond Isolation: Unlocking Reinforcement Learning Component Synergy for Sample-Efficient Continuous Control2608.07086v1 · Qi Zhao, Guozheng Ma, Yilun Kong et al.2026 · 0 citationsarXiv
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models2608.06020v1 · Jiale Han, Xiang Li, Jing Qian et al.2026 · 0 citationsarXiv
Learnable yet not simulable: a quantum resource theory of learning models2608.02325v1 · Xinbiao Wang, Yuxuan Du, Dacheng Tao2026 · 0 citationsarXiv
SoK: Intent-Oriented Systematization of Multi-Turn LLM Jailbreaks2608.01117v2 · Siyuan Li, Aodu Wulianghai, Zehao Liu et al.2026 · 0 citationsarXiv
Escaping Confidence Trap: Evolutionary Decoding for Mathematical Reasoning in Diffusion LLMs2608.00605v1 · Zhenhong Sun, Hanqing Zhao, Yatao Bian et al.2026 · 0 citationsarXiv
Stability and Generalization for Distributed SGDA.41875005 · Zhu, Miaoxi, Sun, Yan, Shen, Li et al.2026 · 0 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(8):9197-9209
ACE-Data-0: Human-Centric Ambient Capture as Embodied Data Engine2607.28625v1 · Yukang Cao, Haozhe Xie, Beichen Wen et al.2026 · 0 citationsarXiv
Stochastic Pauli-path simulator for large-scale quantum optimization2607.17804v1 · Kaining Zhang, Xinbiao Wang, Kunsheng Li et al.2026 · 0 citationsarXiv
MobileSAM2: Lightweight Segment Anything for Spatial Intelligence2607.12297v1 · Kai Jiang, Jiaxing Huang, Jingyi Zhang et al.2026 · 0 citationsarXiv
ExToken: Structured Exploration for Efficient Vision-Language-Action Reinforcement Fine-tuning2607.12931v1 · Yilun Kong, Yunpeng Qing, Guozheng Ma et al.2026 · 0 citationsarXiv
Technical Report on the CVPR 2026@AdvML Workshop Challenge2607.11560v1 · Tianyuan Zhang, Zonglei Jing, Jiangfan Liu et al.2026 · 0 citationsarXiv
Cycle-World: Mitigating Error Accumulation in Long-term Video World Models via Reverse-Prediction Cycle Consistency2607.11836v1 · Zihan Su, Teng Hu, Jiangning Zhang et al.2026 · 0 citationsarXiv
Behavioural Signatures of Risk-Sensitive Decision-Making in Large Language Models2607.10251v1 · Xuankun Rong, Wenke Huang, Bo Du et al.2026 · 0 citationsarXiv
Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning2607.07178v1 · Zetian Hu, Shunyu Liu, Junjie Zhang et al.2026 · 0 citationsarXiv
ACE-Brain-0.5: A Unified Embodied Foundational Model for Physical Agentic AI2607.04426v1 · ACE-Brain Team: Ziyang Gong, Haoming Gu, Zehang Luo et al.2026 · 0 citationsarXiv
Aligning Few-Step Diffusion Models With Dense Reward Difference Learning.41729671 · Zhang, Ziyi, Shen, Li, Zhang, Sen et al.2026 · 2 citationsIEEE transactions on pattern analysis and machine intelligence. 2026;48(7):7375-7386
Brightness-Aware Synthetic-to-Real Learning for Nighttime Hazy Image Enhancement.41801787 · Gui, Jie, Cong, Xiaofeng, Zhang, Yu-Xin et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(7):7640-7655
Beyond One-Size-Fits-All: Diagnosis-Driven Online Reinforcement Learning with Offline Priors2606.25527v1 · Guozheng Ma, Lu Li, Zilin Wang et al.2026 · 0 citationsarXiv
Beyond Scalar Scores: Exploring LLM-based Metrics for Clinical Significance Evaluation in Radiology Reports2606.18797v1 · Qingyu Lu, Ruochen Li, Liang Ding et al.2026 · 0 citationsarXiv
Attribution-Guided and Coverage-Maximized Pruning for Structural MoE Compression2606.18304v1 · Yifu Ding, Jiacheng Wang, Ge Yang et al.2026 · 0 citationsarXiv
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI2606.16533v3 · Kairos Team: Fei Wang, Shan You, Qiming Zhang et al.2026 · 0 citationsarXiv
Career total: 2392 works. 1296 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.