← Authors

Tuo Zhao

108 papers · 2012–2025 · 12 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (12) 🌍 Conference Polyglot (12) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (30) 🧭 Keyword Pioneer πŸƒ Academic Marathon (13) 🌈 Renaissance Researcher (6) πŸŒ‰ Interdisciplinary Bridge 🏠 Conference Loyalist (28) 🌟 Keyword Trendsetter Combo (4) 🀝 Dynamic Duo (32) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (10) πŸ† Keyword Champion (2) 🌱 Topic Pioneer πŸ—ƒοΈ Keyword Collector (99) πŸš€ Conference Pioneer πŸ”₯ Unstoppable (14) ⚑ Prolific Year (17) ❓ The Questioner (3) πŸ“ˆ Trend Setter πŸ’Ž Century Club (108)

Conferences

NIPS (28) ICML (20) ICLR (13) EMNLP (11) JMLR (10) AISTATS (8) ACL (7) NAACL (4) IJCNLP (2) INTERSPEECH (2) UAI (2) L4DC (1)

Top co-authors

Haoming Jiang (32) Minshuo Chen (24) Simiao Zuo (18) Chen Liang (16) Han Liu (16) Pengcheng He (15) Weizhu Chen (14) Xingguo Li (10) Qingru Zhang (10) Chao Zhang (9)

Research topics

Statistics (2) Robotics (1) Optimization & Theory (1)

Keywords

nonconvex optimization (10) gradient descent (8) model compression (7) sample complexity (6) stochastic optimization (6) function approximation (5) representation learning (5) neural network (5) pre-trained language model (5) sparse learning (5) convex optimization (4) non-convex optimization (4) adversarial regularization (4) weak supervision (3) neural network optimization (3) neural machine translation (3) named entity recognition (3) dimensionality reduction (3) policy gradient (3) manifold learning (3)

Papers

DORM: Preference Data Weights Optimization for Reward Modeling in LLM Alignment EMNLP 2025
Deep Reinforcement Learning from Hierarchical Preference Design ICML 2025
Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data ICML 2025
RoseRAG: Robust Retrieval-augmented Generation with Small-scale LLMs via Margin-aware Preference Optimization ACL 2025
Good regularity creates large learning rate implicit biases: edge of stability, balancing, and catapult JMLR 2025
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks NIPS 2024
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks NIPS 2024
Deep Nonparametric Estimation of Operators between Infinite Dimensional Spaces JMLR 2024
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs ICLR 2024
Data Diversity Matters for Robust Instruction Tuning EMNLP 2024
To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO ICML 2024
Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process ICML 2024
Robust Reinforcement Learning from Corrupted Human Feedback NIPS 2024
Sample Complexity of Neural Policy Mirror Descent for Policy Optimization on Low-Dimensional Manifolds JMLR 2024
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback NIPS 2024
LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models ICLR 2024
RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning EMNLP 2024
BlendFilter: Advancing Retrieval-Augmented Large Language Models via Query Generation Blending and Knowledge Filtering EMNLP 2024
Efficient Long-Range Transformers: You Need to Attend More, but Not Necessarily at Every Layer EMNLP 2023
Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks ICLR 2023
Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning ICLR 2023
HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers ICLR 2023
Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data ICML 2023
Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms NIPS 2023
Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms NIPS 2023
Module-wise Adaptive Distillation for Multimodality Foundation Models NIPS 2023
SMURF-THP: Score Matching-based UnceRtainty quantiFication for Transformer Hawkes Process ICML 2023
LoSparse: Structured Compression of Large Language Models based on Low-Rank and Sparse Approximation ICML 2023
Context-Aware Query Rewriting for Improving Users’ Search Experience on E-commerce Websites ACL 2023
Less is More: Task-aware Layer-wise Distillation for Language Model Compression ICML 2023
Effective Minkowski Dimension of Deep Nonparametric Regression: Function Approximation and Statistical Theories ICML 2023
Reinforcement Learning for Adaptive Mesh Refinement AISTATS 2023
Pivotal Estimation of Linear Discriminant Analysis in High Dimensions JMLR 2023
Machine Learning Force Fields with Data Cost Aware Training ICML 2023
HadSkip: Homotopic and Adaptive Layer Skipping of Pre-trained Language Models for Efficient Inference EMNLP 2023
Taming Sparsely Activated Transformer with Stochastic Experts ICLR 2022
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer Models ICLR 2022
Adversarially Regularized Policy Learning Guided by Trajectory Optimization L4DC 2022
Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect ICLR 2022
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance ICML 2022
On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds NIPS 2022
Benefits of Overparameterized Convolutional Residual Networks: Function Approximation under Smoothness Constraint ICML 2022
CERES: Pretraining of Graph-Conditioned Transformer for Semi-Structured Session Data NAACL 2022
MoEBERT: from BERT to Mixture-of-Experts via Importance-Guided Adaptation NAACL 2022
Self-Training with Differentiable Teacher NAACL 2022
Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably AISTATS 2022
CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing ACL 2022
Steering vector correction in MVDR beamformer for speech enhancement INTERSPEECH 2022
Frequency-aware SGD for Efficient Embedding Learning with Provable Benefits ICLR 2022
Besov Function Approximation and Binary Classification on Low-Dimensional Manifolds Using Convolutional Residual Networks ICML 2021
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization IJCNLP 2021
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data IJCNLP 2021
Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL NIPS 2021
Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data ACL 2021
Super Tickets in Pre-Trained Language Models: From Model Compression to Improving Generalization ACL 2021
Fine-Tuning Pre-trained Language Model with Weak Supervision: A Contrastive-Regularized Self-Training Approach NAACL 2021
Learning to Defend by Learning to Attack AISTATS 2021
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization AISTATS 2021
Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach EMNLP 2021
Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach EMNLP 2021
Token-wise Curriculum Learning for Neural Machine Translation EMNLP 2021
ARCH: Efficient Adversarial Regularized Training with Caching EMNLP 2021
A Hypergradient Approach to Robust Regression without Correspondence ICLR 2021
How Important is the Train-Validation Split in Meta-Learning? ICML 2021
On Computation and Generalization of Generative Adversarial Imitation Learning ICLR 2020
Calibrated Language Model Fine-Tuning for In- and Out-of-Distribution Data EMNLP 2020
On Generalization Bounds of a Family of Recurrent Neural Networks AISTATS 2020
SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization ACL 2020
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing ACL 2020
Towards Understanding Hierarchical Learning: Benefits of Neural Representations NIPS 2020
Differentiable Top-k with Optimal Transport NIPS 2020
Deep Reinforcement Learning with Robust and Smooth Policy ICML 2020
Transformer Hawkes Process ICML 2020
Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective NIPS 2020
Implicit Bias of Gradient Descent based Adversarial Training on Separable Data ICLR 2020
Online Factorization and Partition of Complex Networks by Random Walk UAI 2019
Meta Learning with Relational Information for Short Sequences NIPS 2019
Towards Understanding the Importance of Shortcut Connections in Residual Networks NIPS 2019
Efficient Approximation of Deep ReLU Networks for Functions on Low Dimensional Manifolds NIPS 2019
On Constrained Nonconvex Stochastic Optimization: A Case Study for Generalized Eigenvalue Decomposition AISTATS 2019
On Computation and Generalization of Generative Adversarial Networks under Spectrum Control ICLR 2019
On Scalable and Efficient Computation of Large Scale Optimal Transport ICML 2019
Toward Understanding the Importance of Noise in Training Neural Networks ICML 2019
Picasso: A Sparse Learning Library for High Dimensional Data Analysis in R and Python JMLR 2019
On Fast Convergence of Proximal Algorithms for SQRT-Lasso Optimization: Don’t Worry About its Nonsmooth Loss Function UAI 2019
Provable Gaussian Embedding with One Observation NIPS 2018
Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization NIPS 2018
Dimensionality Reduction for Stationary Time Series via Stochastic Nonconvex Optimization NIPS 2018
The Physical Systems Behind Optimization Algorithms NIPS 2018
On Faster Convergence of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization JMLR 2018
Parametric Simplex Method for Sparse Learning NIPS 2017
Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability ICML 2017
On Quadratic Convergence of DC Proximal Newton Algorithm in Nonconvex Sparse Learning NIPS 2017
Deep Hyperspherical Learning NIPS 2017
The Opensesame NIST 2016 Speaker Recognition Evaluation System INTERSPEECH 2017
An Improved Convergence Analysis of Cyclic Block Coordinate Descent-type Methods for Strongly Convex Minimization AISTATS 2016
NESTT: A Nonconvex Primal-Dual Splitting Method for Distributed and Stochastic Optimization NIPS 2016
Stochastic Variance Reduced Optimization for Nonconvex Sparse Learning ICML 2016
The flare Package for High Dimensional Linear Regression and Precision Matrix Estimation in R JMLR 2015
A Nonconvex Optimization Framework for Low Rank Matrix Estimation NIPS 2015
Calibrated Multivariate Regression with Application to Neural Semantic Basis Discovery JMLR 2015
Multivariate Regression with Calibration NIPS 2014
Accelerated Mini-batch Randomized Block Coordinate Descent Method NIPS 2014
Sparse Inverse Covariance Estimation with Calibration NIPS 2013
CODA: High Dimensional Copula Discriminant Analysis JMLR 2013
The huge Package for High-dimensional Undirected Graph Estimation in R JMLR 2012
Sparse Additive Machine AISTATS 2012
Smooth-projected Neighborhood Pursuit for High-dimensional Nonparanormal Graph Estimation NIPS 2012