WY
Wotao Yin
math.OCcs.LGstat.MLcs.DCcs.NAmath.NAcs.AIcs.CVcs.ITmath.IT
On Valency
published · living versionsW_zr9mr299·v1 · currentpublished
Diagnosing the Reference Gap: What Visual Scaffolds Can and Cannot Fix in Multimodal Reasoning
with Guizhen Chen, Weiwen Xu, Anh Tuan Luu, Hou Pong Chan
1 version
Preprints & journals
146 papers in the corpus · 2005–2026Training Numerical Intelligence via Auto-Diagnosis and Skill Discovery2610.03872v1 · Peter Chen, Wotao Yin2026 · 0 citationsarXiv
ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents2609.23735v3 · ScholarSeed AI Team: Caoqinwei Gong, Xue Jiang, Wei Luo et al.2026 · 0 citationsarXiv
A Zeroth-Order Paradigm for LLM Preference Alignment2609.19144v1 · Peter Chen, Xi Chen, Wotao Yin et al.2026 · 0 citationsarXiv
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators2606.30704v1 · Gan Luo, Zihan Qin, Bin Dong et al.2026 · 0 citationsarXiv
Restarted Reflected Halpern Acceleration for Augmented Primal-Dual Methods2606.16552v1 · Benqi Liu, Ju Cao, Wotao Yin et al.2026 · 0 citationsarXiv
Deeply Learned Robust Matrix Completion for Large-Scale Low-Rank Data Recovery.41610359 · Cai, HanQin, Kundu, Chandra, Liu, Jialin et al.2026 · 1 citationIEEE transactions on pattern analysis and machine intelligence. 2026;48(6):6541-6556
Automating Reformulation for Parallel ADMM2603.19417v1 · Kaizhao Sun, Baihao Wu, Kun Yuan et al.2026 · 0 citationsarXiv
DeepVision-103K: A Visually Diverse, Broad-Coverage, and Verifiable Mathematical Dataset for Multimodal Reasoning2602.16742v1 · Haoxiang Sun, Lizhen Xu, Bing Zhao et al.2026 · 0 citationsarXiv
ALiA: Adaptive Linearized ADMM2602.15000v1 · Uijeong Jang, Kaizhao Sun, Wotao Yin et al.2026 · 0 citationsarXiv
Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling2510.03638v4 · Jialin Liu, Lisang Ding, Stanley Osher et al.2025 · 0 citationsarXiv
AdapThink: Adaptive Thinking Preferences for Reasoning Language Model2506.18237v1 · Xu Wan, Wei Wang, Wenyue Xu et al.2025 · 0 citationsarXiv
ComPO: Preference Alignment via Comparison Oracles2505.05465v2 · Peter Chen, Xi Chen, Wotao Yin et al.2025 · 0 citationsarXiv
SymAgent: A Neural-Symbolic Self-Learning Agent Framework for Complex Reasoning over Knowledge Graphs2502.03283v2 · Ben Liu, Jihai Zhang, Fangquan Lin et al.2025 · 16 citationsarXiv
SAttention: Improving Long Sequence Attention with Smoothed Skeleton Sketching2408.08567v3 · Xue Wang, Tian Zhou, Jianqing Zhu et al.2024 · 2 citationsarXiv
Solving General Natural-Language-Description Optimization Problems with Large Language Models2407.07924v1 · Jihai Zhang, Wei Wang, Siyan Guo et al.2024 · 16 citationsarXiv
Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs2406.05938v2 · Ziang Chen, Xiaohan Chen, Jialin Liu et al.2024 · 0 citationsarXiv
ODE-based Learning to Optimize2406.02006v1 · Zhonglin Xie, Wotao Yin, Zaiwen Wen2024 · 1 citationarXiv
Block Acceleration Without Momentum: On Optimal Stepsizes of Block Gradient Descent for Least-Squares2405.16020v1 · Liangzu Peng, Wotao Yin2024 · 0 citationsarXiv
Learning to optimize: A tutorial for continuous and mixed-integer optimization2405.15251v1 · Xiaohan Chen, Jialin Liu, Wotao Yin2024 · 12 citationsarXiv
Subsampled Ensemble Can Improve Generalization Tail Exponentially2405.14741v5 · Huajie Qian, Donghao Ying, Henry Lam et al.2024 · 2 citationsarXiv
Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark2402.11592v3 · Yihua Zhang, Pingzhi Li, Junyuan Hong et al.2024 · 11 citationsarXiv
Efficient Algorithms for Sum-of-Minimum Optimization2402.07070v2 · Lisang Ding, Ziang Chen, Xinshang Wang et al.2024 · 0 citationsarXiv
Rethinking the Capacity of Graph Neural Networks for Branching Strategy2402.07099v3 · Ziang Chen, Jialin Liu, Xiaohan Chen et al.2024 · 3 citationsarXiv
MindOpt Adapter for CPLEX Benchmarking Performance Analysis2312.13527v4 · Mou Sun, Tao Li, Wotao Yin2023 · 2 citationsarXiv
DIG-MILP: a Deep Instance Generator for Mixed-Integer Linear Programming with Feasibility Guarantee2310.13261v1 · Haoyu Wang, Jialin Liu, Xiaohan Chen et al.2023 · 2 citationsarXiv
A Human-on-the-Loop Optimization Autoformalism Approach for Sustainability2308.10380v2 · Ming Jin, Bilgehan Sel, Fnu Hardeep et al.2023 · 3 citationsarXiv
MindOpt Tuner: Boost the Performance of Numerical Software by Automatic Parameter Tuning2307.08085v1 · Mengyuan Zhang, Wotao Yin, Mengchang Wang et al.2023 · 1 citationarXiv
DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm2306.00256v1 · Lisang Ding, Kexin Jin, Bicheng Ying et al.2023 · 3 citationsarXiv
Towards Constituting Mathematical Structures for Learning to Optimize2305.18577v1 · Jialin Liu, Xiaohan Chen, Zhangyang Wang et al.2023 · 4 citationsarXiv
Lower Bounds and Accelerated Algorithms in Distributed Stochastic Optimization with Communication Compression2305.07612v2 · Yutong He, Xinmeng Huang, Yiming Chen et al.2023 · 1 citationarXiv
An Improved Analysis of (Variance-Reduced) Policy Gradient and Natural Policy Gradient Methods2211.07937v2 · Yanli Liu, Kaiqing Zhang, Tamer Basar et al.2022 · 34 citationsAdvances in Neural Information Processing Systems 33 (2020): 7624-7636
Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization2211.07096v2 · Quan Xiao, Han Shen, Wotao Yin et al.2022 · 0 citationsarXiv
On Representing Mixed-Integer Linear Programs by Graph Neural Networks2210.10759v2 · Ziang Chen, Jialin Liu, Xinshang Wang et al.2022 · 6 citationsarXiv
On Representing Linear Programs by Graph Neural Networks2209.12288v2 · Ziang Chen, Jialin Liu, Xinshang Wang et al.2022 · 10 citationsarXiv
Lower Bounds and Nearly Optimal Algorithms in Distributed Learning with Communication Compression2206.03665v2 · Xinmeng Huang, Yiming Chen, Wotao Yin et al.2022 · 8 citationsarXiv
From the simplex to the sphere: Faster constrained optimization using the Hadamard parametrization2112.05273v2 · Qiuwei Li, Daniel McKenzie, Wotao Yin2021 · 9 citationsarXiv
A Novel Convergence Analysis for Algorithms of the Adam Family2112.03459v1 · Zhishuai Guo, Yi Xu, Wotao Yin et al.2021 · 11 citationsarXiv
BlueFog: Make Decentralized Algorithms Practical for Optimization and Deep Learning2111.04287v1 · Bicheng Ying, Kun Yuan, Hanbin Hu et al.2021 · 9 citationsarXiv
Hyperparameter Tuning is All You Need for LISTA2110.15900v1 · Xiaohan Chen, Jialin Liu, Zhangyang Wang et al.2021 · 15 citationsarXiv
Exponential Graph is Provably Efficient for Decentralized Deep Training2110.13363v1 · Bicheng Ying, Kun Yuan, Yiming Chen et al.2021 · 31 citationsarXiv
Learned Robust PCA: A Scalable Deep Unfolding Approach for High-Dimensional Outlier Detection2110.05649v1 · HanQin Cai, Jialin Liu, Wotao Yin2021 · 25 citationsAdvances in Neural Information Processing Systems 34 (2021): 16977-16989
Curvature-Aware Derivative-Free Optimization2109.13391v2 · Bumsu Kim, HanQin Cai, Daniel McKenzie et al.2021 · 5 citationsJournal of Scientific Computing, 103(43): 1-28, 2025
Tighter Analysis of Alternating Stochastic Gradient Method for Stochastic Nested Problems2106.13781v1 · Tianyi Chen, Yuejiao Sun, Wotao Yin2021 · 7 citationsarXiv
Operator Splitting for Learning to Predict Equilibria in Convex Games2106.00906v4 · Daniel McKenzie, Howard Heaton, Qiuwei Li et al.2021 · 3 citationsarXiv
Accelerating Gossip SGD with Periodic Global Averaging2105.09080v1 · Yiming Chen, Kun Yuan, Yingya Zhang et al.2021 · 24 citationsarXiv
Unified Convergence Analysis for Adaptive Optimization with Moving Average Estimator2104.14840v7 · Zhishuai Guo, Yi Xu, Wotao Yin et al.2021 · 4 citationsarXiv
Feasibility-based Fixed Point Networks2104.14090v1 · Howard Heaton, Samy Wu Fung, Aviv Gibali et al.2021 · 22 citationsarXiv
Improved Analysis and Rates for Variance Reduction under Without-replacement Sampling Orders2104.12112v2 · Xinmeng Huang, Kun Yuan, Xianghui Mao et al.2021 · 1 citationarXiv
DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training2104.11981v1 · Kun Yuan, Yiming Chen, Xinmeng Huang et al.2021 · 29 citationsarXiv
JFB: Jacobian-Free Backpropagation for Implicit Networks2103.12803v4 · Samy Wu Fung, Howard Heaton, Qiuwei Li et al.2021 · 52 citationsarXiv
Career total: at least 341 works. 146 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.