Tuo Zhao

papers

447

total citations

papers (15)

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

ICLR 2024arXiv

202

citations

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

NEURIPS 2020arXiv

104

citations

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

NEURIPS 2020arXiv

citations

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

NEURIPS 2023arXiv

citations

Module-wise Adaptive Distillation for Multimodality Foundation Models

NEURIPS 2023arXiv

citations

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

NEURIPS 2022arXiv

citations

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

ICML 2024arXiv

citations

Adversarial Training of Reward Models

COLM 2025arXiv

citations

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

NEURIPS 2023arXiv

citations

Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL

NEURIPS 2021

citations

Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process

ICML 2024

citations

Differentiable Top-k with Optimal Transport

NEURIPS 2020

citations

Tuo Zhao

papers (15)

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

Module-wise Adaptive Distillation for Multimodality Foundation Models

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

Adversarial Training of Reward Models

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Deep Reinforcement Learning from Hierarchical Preference Design

A Minimalist Example of Edge-of-Stability and Progressive Sharpening

Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL

Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process

Differentiable Top-k with Optimal Transport

papers (15)

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

Why Do Deep Residual Networks Generalize Better than Deep Feedforward Networks? --- A Neural Tangent Kernel Perspective

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

Module-wise Adaptive Distillation for Multimodality Foundation Models

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO

Adversarial Training of Reward Models

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Deep Reinforcement Learning from Hierarchical Preference Design

A Minimalist Example of Edge-of-Stability and Progressive Sharpening

Pessimism Meets Invariance: Provably Efficient Offline Mean-Field Multi-Agent RL

Beyond Point Prediction: Score Matching-based Pseudolikelihood Estimation of Neural Marked Spatio-Temporal Point Process

Differentiable Top-k with Optimal Transport