Yi Ma

OpenReview

papers

1,730

total citations

papers (29)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

CVPR 2024arXiv

593

citations

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

NEURIPS 2020arXiv

234

citations

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

NEURIPS 2020arXiv

citations

OmniBench: Towards The Future of Universal Omni-Language Models

NEURIPS 2025arXiv

citations

Robust Calibration with Multi-domain Temperature Scaling

NEURIPS 2022arXiv

citations

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

NEURIPS 2020arXiv

citations

Incremental Learning via Rate Reduction

CVPR 2021arXiv

citations

Revisiting Sparse Convolutional Model for Visual Recognition

NEURIPS 2022arXiv

citations

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

NEURIPS 2022arXiv

citations

NeRD: Neural 3D Reflection Symmetry Detector

CVPR 2021arXiv

citations

Estimating Body and Hand Motion in an Ego‑sensed World

CVPR 2025arXiv

citations

RLIF: Interactive Imitation Learning as Reinforcement Learning

ICLR 2024arXiv

citations

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

NEURIPS 2020arXiv

citations

ViP: A Differentially Private Foundation Model for Computer Vision

ICML 2024arXiv

citations

Unsupervised Manifold Linearizing and Clustering

ICCV 2023arXiv

citations

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

ICML 2024arXiv

citations

Canonical Factors for Hybrid Neural Fields

ICCV 2023arXiv

citations

A Global Geometric Analysis of Maximal Coding Rate Reduction

ICML 2024arXiv

citations

Efficient Maximal Coding Rate Reduction by Variational Forms

CVPR 2022arXiv

citations

Differentially Private Representation Learning via Image Captioning

ICML 2024arXiv

citations

Attention-Only Transformers via Unrolled Subspace Denoising

ICML 2025arXiv

citations

EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction

CVPR 2022

citations

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

NEURIPS 2023

citations

EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events

CVPR 2021

citations

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

NEURIPS 2021

citations

Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation

ICML 2024

citations

Yi Ma

papers (29)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

White-Box Transformers via Sparse Rate Reduction

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

OmniBench: Towards The Future of Universal Omni-Language Models

Robust Calibration with Multi-domain Temperature Scaling

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Incremental Learning via Rate Reduction

Revisiting Sparse Convolutional Model for Visual Recognition

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

NeRD: Neural 3D Reflection Symmetry Detector

Estimating Body and Hand Motion in an Ego‑sensed World

RLIF: Interactive Imitation Learning as Reinforcement Learning

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

ViP: A Differentially Private Foundation Model for Computer Vision

Unsupervised Manifold Linearizing and Clustering

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

Canonical Factors for Hybrid Neural Fields

A Global Geometric Analysis of Maximal Coding Rate Reduction

Efficient Maximal Coding Rate Reduction by Variational Forms

Differentially Private Representation Learning via Image Captioning

Attention-Only Transformers via Unrolled Subspace Denoising

EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation

papers (29)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

White-Box Transformers via Sparse Rate Reduction

Learning a Diffusion Model Policy from Rewards via Q-Score Matching

Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities

OmniBench: Towards The Future of Universal Omni-Language Models

Robust Calibration with Multi-domain Temperature Scaling

Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization

Incremental Learning via Rate Reduction

Revisiting Sparse Convolutional Model for Visual Recognition

TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels

NeRD: Neural 3D Reflection Symmetry Detector

Estimating Body and Hand Motion in an Ego‑sensed World

RLIF: Interactive Imitation Learning as Reinforcement Learning

Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization

ViP: A Differentially Private Foundation Model for Computer Vision

Unsupervised Manifold Linearizing and Clustering

Rethinking Decision Transformer via Hierarchical Reinforcement Learning

Canonical Factors for Hybrid Neural Fields

A Global Geometric Analysis of Maximal Coding Rate Reduction

Efficient Maximal Coding Rate Reduction by Variational Forms

Differentially Private Representation Learning via Image Captioning

Attention-Only Transformers via Unrolled Subspace Denoising

EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events

A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems

Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation