Chen Zhu

papers

1,472

total citations

papers (12)

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

NEURIPS 2020arXiv

540

citations

Long-Short Transformer: Efficient Transformers for Language and Vision

NEURIPS 2021arXiv

163

citations

On the Exploitability of Instruction Tuning

NEURIPS 2023arXiv

134

citations

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

NEURIPS 2025arXiv

117

citations

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

NEURIPS 2021arXiv

citations

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

NEURIPS 2021arXiv

citations

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

NEURIPS 2022arXiv

citations

VMBench: A Benchmark for Perception-Aligned Video Motion Generation

ICCV 2025arXiv

citations

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

ICCV 2025arXiv

citations

Chen Zhu

papers (12)

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Long-Short Transformer: Efficient Transformers for Language and Vision

On the Exploitability of Instruction Tuning

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Learning From Noisy Anchors for One-Stage Object Detection

Robust Optimization As Data Augmentation for Large-Scale Graphs

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

VMBench: A Benchmark for Perception-Aligned Video Motion Generation

EA-Vit: Efficient Adaptation for Elastic Vision Transformer

papers (12)

Large-Scale Adversarial Training for Vision-and-Language Representation Learning

Long-Short Transformer: Efficient Transformers for Language and Vision

On the Exploitability of Instruction Tuning

AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

ODIN: Disentangled Reward Mitigates Hacking in RLHF

Learning From Noisy Anchors for One-Stage Object Detection

Robust Optimization As Data Augmentation for Large-Scale Graphs

GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training

VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization

Pre-Train Your Loss: Easy Bayesian Transfer Learning with Informative Priors

VMBench: A Benchmark for Perception-Aligned Video Motion Generation

EA-Vit: Efficient Adaptation for Elastic Vision Transformer