Yi Ma

Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric Reasoning CVPR 2026 Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing AAAI 2026 CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling CVPR 2026 Pointer-CAD: Unifying B-Rep and Command Sequences via Pointer-based Edges & Faces Selection CVPR 2026 Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs AAAI 2026 Attention-Only Transformers via Unrolled Subspace Denoising ICML 2025 Estimating Body and Hand Motion in an Ego-sensed World CVPR 2025 SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training ICML 2025 Simplifying DINO via Coding Rate Regularization ICML 2025 Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction ICLR 2025 A Global Geometric Analysis of Maximal Coding Rate Reduction ICML 2024 CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making NeurIPS 2024 Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation NeurIPS 2024 Differentially Private Representation Learning via Image Captioning ICML 2024 ENOTO: Improving Offline-to-Online Reinforcement Learning with Q-Ensembles IJCAI 2024 Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs CVPR 2024 Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning NeurIPS 2024 How Do Neural Spoofing Countermeasures Detect Partially Spoofed Audio? Interspeech 2024 Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models ICLR 2024 Insight: A Multi-Modal Diagnostic Pipeline using LLMs for Ocular Surface Disease Diagnosis MICCAI 2024 Iteratively Refined Behavior Regularization for Offline Reinforcement Learning NeurIPS 2024 Learning a Diffusion Model Policy from Rewards via Q-Score Matching ICML 2024 Lessons from Learning to Spin “Pens” CoRL 2024 Masked Completion via Structured Diffusion with White-Box Transformers ICLR 2024 Representation Learning via Manifold Flattening and Reconstruction JMLR 2024 Rethinking Decision Transformer via Hierarchical Reinforcement Learning ICML 2024 RLIF: Interactive Imitation Learning as Reinforcement Learning ICLR 2024 Scaling White-Box Transformers for Vision NeurIPS 2024 Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback ICLR 2024 Unlock the Cognitive Generalization of Deep Reinforcement Learning via Granular Ball Representation ICML 2024 Unlock the Intermittent Control Ability of Model Free Reinforcement Learning NeurIPS 2024 ViP: A Differentially Private Foundation Model for Computer Vision ICML 2024 White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? JMLR 2024 Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning NeurIPS 2023 Canonical Factors for Hybrid Neural Fields ICCV 2023 General In-hand Object Rotation with Vision and Touch CoRL 2023 Incremental Learning of Structured Memory via Closed-Loop Transcription ICLR 2023 Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform ICLR 2023 Reining Generalization in Offline Reinforcement Learning via Representation Distinction NeurIPS 2023 SplitNet: A Reinforcement Learning Based Sequence Splitting Method for the MinMax Multiple Travelling Salesman Problem AAAI 2023 Understanding the Complexity Gains of Single-Task RL with a Curriculum ICML 2023 Unsupervised Manifold Linearizing and Clustering ICCV 2023 White-Box Transformers via Sparse Rate Reduction NeurIPS 2023 Efficient Maximal Coding Rate Reduction by Variational Forms CVPR 2022 EvUnroll: Neuromorphic Events Based Rolling Shutter Image Correction CVPR 2022 In-Hand Object Rotation via Rapid Motor Adaptation CoRL 2022 Learning To Reconstruct 3D Non-Cuboid Room Layout From a Single RGB Image WACV 2022 On the Convergence of Stochastic Extragradient for Bilinear Games using Restarted Iteration Averaging AISTATS 2022 PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations IJCAI 2022 Predicting Out-of-Distribution Error with the Projection Norm ICML 2022 ReduNet: A White-box Deep Network from the Principle of Maximizing Rate Reduction JMLR 2022 Revisiting Sparse Convolutional Model for Visual Recognition NeurIPS 2022 Robust Calibration with Multi-domain Temperature Scaling NeurIPS 2022 TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels NeurIPS 2022 A Hierarchical Reinforcement Learning Based Optimization Framework for Large-scale Dynamic Pickup and Delivery Problems NeurIPS 2021 EventZoom: Learning To Denoise and Super Resolve Neuromorphic Events CVPR 2021 Incremental Learning via Rate Reduction CVPR 2021 Learning Long-term Visual Dynamics with Region Proposal Interaction Networks ICLR 2021 NeRD: Neural 3D Reflection Symmetry Detector CVPR 2021 Complete Dictionary Learning via L4-Norm Maximization over the Orthogonal Group JMLR 2020 Deep Isometric Learning for Visual Recognition ICML 2020 Dynamic Knapsack Optimization Towards Efficient Multi-Channel Sequential Advertising ICML 2020 KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge IJCAI 2020 Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction NeurIPS 2020 Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising IJCAI 2020 LungRN+NL: An Improved Adventitious Lung Sound Classification Using Non-Local Block ResNet Neural Network with Mixup Data Augmentation Interspeech 2020 Optimistic Dual Extrapolation for Coherent Non-monotone Variational Inequalities NeurIPS 2020 Rethinking Bias-Variance Trade-off for Generalization of Neural Networks ICML 2020 Robust Recovery via Implicit Bias of Discrepant Learning Rates for Double Over-parameterization NeurIPS 2020 Understanding l4-based Dictionary Learning: Interpretation, Stability, and Robustness ICLR 2020 Variance Reduction via Accelerated Dual Averaging for Finite-Sum Optimization NeurIPS 2020 End-to-End Wireframe Parsing ICCV 2019 Learning to Reconstruct 3D Manhattan Wireframes From a Single Image ICCV 2019 NeurVPS: Neural Vanishing Point Scanning via Conic Convolution NeurIPS 2019 Fine-grained Video Categorization with Redundancy Reduction Attention ECCV 2018 Learning to Parse Wireframes in Images of Man-Made Environments CVPR 2018 PizzaPal: Conversational Pizza Ordering using a High-Density Conversational AI Platform EMNLP 2018 Structured Attentions for Visual Question Answering ICCV 2017 Single-Image Crowd Counting via Multi-Column Convolutional Neural Network CVPR 2016 Generalized Tensor Total Variation Minimization for Visual Data Recovery CVPR 2015 Low-Rank Tensor Approximation With Laplacian Scale Mixture Modeling for Multiframe Image Denoising ICCV 2015 Partial Occlusion Handling for Visual Tracking via Robust Part Matching CVPR 2014 Robust Separation of Reflection from Multiple Images CVPR 2014 Learning by Associating Ambiguously Labeled Images CVPR 2013 Plane-Based Content Preserving Warps for Video Stabilization CVPR 2013 Simultaneous Rectification and Alignment via Robust Recovery of Low-rank Tensors NeurIPS 2013 Single-Sample Face Recognition with Image Corruption and Misalignment via Sparse Illumination Transfer CVPR 2013 User Goal Change Model for Spoken Dialog State Tracking NAACL 2013 Video Editing with Temporal, Spatial and Appearance Consistency CVPR 2013 Ranking-based readability assessment for early primary children’s literature NAACL 2012 Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices via Convex Optimization NeurIPS 2009 Classification via Minimum Incremental Coding Length (MICL) NeurIPS 2007