Xin Jin

MFmamba: A Multi-function Network for Panchromatic Image Resolution Restoration Based on State-Space Model AAAI 2026 Video Echoed in Music: Semantic, Temporal, and Rhythmic Alignment for Video-to-Music Generation AAAI 2026 Hierarchical Dual-Domain Fusion with Frequency-Guided Spatial Modeling for Pan-Sharpening AAAI 2026 Temporal Inconsistency Guidance for Super-resolution Video Quality Assessment AAAI 2026 Electron Density-enhanced Molecular Geometry Learning IJCAI 2025 Dis²Booth: Learning Image Distribution with Disentangled Features for Text-to-Image Diffusion Models AAAI 2025 DiffRetouch: Using Diffusion to Retouch on the Shoulder of Experts AAAI 2025 RLLTE: Long-Term Evolution Project of Reinforcement Learning AAAI 2025 Taming LLMs with Gradient Grouping ACL 2025 Multi-Layer Visual Feature Fusion in Multimodal LLMs: Methods, Analysis, and Best Practices CVPR 2025 Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning CVPR 2025 Classic Video Denoising in a Machine Learning World: Robust, Fast, and Controllable CVPR 2025 UniScene: Unified Occupancy-centric Driving Scene Generation CVPR 2025 UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection CVPR 2025 Towards RAW Object Detection in Diverse Conditions CVPR 2025 Multimodal Language Models See Better When They Look Shallower EMNLP 2025 GeoFormer: Geometry Point Encoder for 3D Object Detection with Graph-based Transformer ICCV 2025 ULTHO: Ultra-Lightweight yet Efficient Hyperparameter Optimization in Deep Reinforcement Learning ICCV 2025 Disentangled World Models: Learning to Transfer Semantic Knowledge from Distracting Videos for Reinforcement Learning ICCV 2025 Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactions ICCV 2025 DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution ICCV 2025 Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation ICCV 2025 Open-World Reinforcement Learning over Long Short-Term Imagination ICLR 2025 GCTAM: Global and Contextual Truncated Affinity Combined Maximization Model For Unsupervised Graph Anomaly Detection IJCAI 2025 MeshTest: End-to-End Testing for Service Mesh Traffic Management NSDI 2025 Optimizing RLHF Training for Large Language Models with Stage Fusion NSDI 2025 StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization ICML 2024 Bridging Stereo Geometry and BEV Representation with Reliable Mutual Interaction for Semantic Scene Completion IJCAI 2024 Paintings and Drawings Aesthetics Assessment with Rich Attributes for Various Artistic Categories IJCAI 2024 Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning NIPS 2024 MegaScale: Scaling Large Language Model Training to More Than 10,000 GPUs NSDI 2024 Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis NIPS 2024 In Pursuit of Causal Label Correlations for Multi-label Image Recognition NIPS 2024 Jolteon: Unleashing the Promise of Serverless for Serverless Workflows NSDI 2024 Fast Vector Query Processing for Large Datasets Beyond GPU Memory with Reordered Pipelining NSDI 2024 Multi-Prompts Learning with Cross-Modal Alignment for Attribute-Based Person Re-identification AAAI 2024 Hierarchical Temporal Context Learning for Camera-based Semantic Scene Completion ECCV 2024 HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects ECCV 2024 Language-Image Pre-training with Long Captions ECCV 2024 Closed-Loop Unsupervised Representation Disentanglement with $\\beta$-VAE Distillation and Diffusion Probabilistic Feedback ECCV 2024 Rate-Distortion-Cognition Controllable Versatile Neural Image Compression ECCV 2024 SUMix: Mixup with Semantic and Uncertain Information ECCV 2024 One at a Time: Progressive Multi-Step Volumetric Probability Learning for Reliable 3D Scene Perception AAAI 2024 SwiftPillars: High-Efficiency Pillar Encoder for Lidar-Based 3D Detection AAAI 2024 DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving OSDI 2024 Burstable Cloud Block Storage with Data Processing Units OSDI 2024 dLoRA: Dynamically Orchestrating Requests and Adapters for LoRA LLM Serving OSDI 2024 Adversarial AutoMixup ICLR 2024 Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation NIPS 2024 Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models NIPS 2024 APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments NIPS 2024 Diff-BGM: A Diffusion Model for Video Background Music Generation CVPR 2024 ReGenNet: Towards Human Action-Reaction Synthesis CVPR 2024 Inter-X: Towards Versatile Human-Human Interaction Analysis CVPR 2024 Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition CVPR 2023 NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation ICCV 2023 Task Residual for Tuning Vision-Language Models CVPR 2023 DNF: Decouple and Feedback Network for Seeing in the Dark CVPR 2023 Semantically Structured Image Compression via Irregular Group-Based Decoupling ICCV 2023 AlpaServe: Statistical Multiplexing with Model Parallelism for Deep Learning Serving OSDI 2023 TeamShakespeare at SemEval-2023 Task 6: Understand Legal Documents with Contextualized Large Language Models SEMEVAL 2023 Enhancing Language Model with Unit Test Techniques for Efficient Regular Expression Generation EMNLP 2023 TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce EMNLP 2023 Enhanced Bi-Directional Motion Estimation for Video Frame Interpolation WACV 2023 Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning ICML 2023 TeamShakespeare at SemEval-2023 Task 6: Understand Legal Documents with Contextualized Large Language Models ACL 2023 Underwater Ranker: Learn Which Is Better and How to Be Better AAAI 2023 Fast, Approximate Vector Queries on Very Large Unstructured Datasets NSDI 2023 Transparent GPU Sharing in Container Clouds for Deep Learning Workloads NSDI 2023 Lighting Every Darkness in Two Pairs: A Calibration-Free Pipeline for RAW Denoising ICCV 2023 Learning Distortion Invariant Representation for Image Restoration From a Causality Perspective CVPR 2023 A Unified Pyramid Recurrent Network for Video Frame Interpolation CVPR 2023 Generalized Lightness Adaptation with Channel Selective Normalization ICCV 2023 ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation ICCV 2023 Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification CVPR 2022 Attribute Group Editing for Reliable Few-Shot Image Generation CVPR 2022 Reusing the Task-Specific Classifier as a Discriminator: Discriminator-Free Adversarial Domain Adaptation CVPR 2022 Learning with Recoverable Forgetting ECCV 2022 Image Coding for Machines with Omnipotent Feature Learning ECCV 2022 Deliberated Domain Bridging for Domain Adaptive Semantic Segmentation NIPS 2022 NetVRM: Virtual Register Memory for Programmable Networks NSDI 2022 Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency AAAI 2022 Cloth-Changing Person Re-Identification From a Single Image With Gait Prediction and Regularization CVPR 2022 Re-Energizing Domain Discriminator With Sample Relabeling for Adversarial Domain Adaptation ICCV 2021 Learning Omni-Frequency Region-adaptive Representations for Real Image Super-Resolution AAAI 2021 Ship Compute or Ship Data? Why Not Both? NSDI 2021 Twenty Years After: Hierarchical Core-Stateless Fair Queueing NSDI 2021 Dense Interaction Learning for Video-Based Person Re-Identification ICCV 2021 Region Normalization for Image Inpainting AAAI 2020 Exploring Categorical Regularization for Domain Adaptive Object Detection CVPR 2020 Relation-Aware Global Attention for Person Re-Identification CVPR 2020 Learning Disentangled Feature Representation for Hybrid-distorted Image Restoration ECCV 2020 Hierarchical Context Embedding for Region-based Object Detection ECCV 2020 Global Distance-distributions Separation for Unsupervised Person Re-identification ECCV 2020 PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications OSDI 2020 Pegasus: Tolerating Skewed Workloads in Distributed Storage with In-Network Coherence Directories OSDI 2020 Style Normalization and Restitution for Generalizable Person Re-Identification CVPR 2020 RackSched: A Microsecond-Scale Scheduler for Rack-Scale Computers OSDI 2020 On Efficient Constructions of Checkpoints ICML 2020 Look One and More: Distilling Hybrid Order Relational Knowledge for Cross-Resolution Image Recognition AAAI 2020 Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification AAAI 2020 Semantics-Aligned Representation Learning for Person Re-Identification AAAI 2020 NetChain: Scale-Free Sub-RTT Coordination NSDI 2018 ASAP: Fast, Approximate Graph Pattern Mining at Scale OSDI 2018 CoVisor: A Compositional Hypervisor for Software-Defined Networks NSDI 2015