Tao Sun
47 papers · 2006–2026 · 13 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 15 separate collaboration groups - the largest holds only 34% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Tao Sun?
6 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Dongsheng Li, Bao Wang, Wotao Yin
16 papers
· 2017–2025
· NeurIPS, ICML, IJCAI
Hide ▲
Investigating the Role of Weight Decay in Enhancing Nonconvex SGD
CVPR 2025
Targeted Low-rank Refinement: Enhancing Sparse Language Models with Precision
ICML 2025
Exploring the Inefficiency of Heavy Ball as Momentum Parameter Approaches 1
IJCAI 2024
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
NeurIPS 2024
Momentum Ensures Convergence of SIGNSGD under Weaker Assumptions
ICML 2023
Stability-Based Generalization Analysis of the Asynchronous Decentralized SGD
AAAI 2023
Adaptive Random Walk Gradient Descent for Decentralized Optimization
ICML 2022
Finite-Time Analysis of Adaptive Temporal Difference Learning with Deep Neural Networks
NeurIPS 2022
Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast
IJCAI 2022
Stability and Generalization of Decentralized Stochastic Gradient Descent
AAAI 2021
General Proximal Incremental Aggregated Gradient Algorithms: Better and Novel Results under General Scheme
NeurIPS 2019
Heavy-ball Algorithms Always Escape Saddle Points
IJCAI 2019
Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms
AAAI 2019
LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning
NeurIPS 2018
On Markov Chain Gradient Descent
NeurIPS 2018
Asynchronous Coordinate Descent under More Realistic Assumptions
NeurIPS 2017
9 papers whose co-authors appear nowhere else under this name
APT: Affine Prototype-Timestamp for Time Series Forecasting Under Distribution Shift
AAAI 2026
Context-Preserving Dermoscopic Editing: Mask-Guided Lesion-Aware Diffusion for Attribute Modification
WACV 2026
LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
COLING 2025
Revisiting Gradient Normalization and Clipping for Nonconvex SGD under Heavy-Tailed Noise: Necessity, Sufficiency, and Acceleration
JMLR 2025
WoMAP: World Models For Embodied Open-Vocabulary Object Localization
CoRL 2025
Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
ICLR 2024
Stability and Generalization for Stochastic Recursive Momentum-based Algorithms for (Strongly-)Convex One to K-Level Stochastic Optimizations
ICML 2024
Leveraging Crowdsourced GPS Data for Road Extraction From Aerial Imagery
CVPR 2019
Consistency of Multiclass Empirical Risk Minimization Methods Based on Convex Loss
JMLR 2006