发表论文（部分已发表论文：）
（1） ST-Prune: Training-Free Spatio-Temporal Token Pruning for Vision-Language Models in Autonomous Driving, arxiv, 2026, 第 2 作者（2） ReCALL: Recalibrating Capability Degradation for MLLM-based Composed Image Retrieval, CVPR, 2026, 第 6 作者 通讯作者（3） Rethinking Representativeness and Diversity in Dynamic Data Selection, arxiv, 2026, 第 3 作者（4） R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training, ICML, 2026, 第 9 作者 通讯作者（5） Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration, arxiv, 2026, 第 6 作者（6） PixCLIP: Achieving Fine-grained Visual Language Understanding via Any-granularity Pixel-Text Alignment Learning, ICML, 2026, 第 2 作者 通讯作者（7） PLUME: Latent Reasoning Based Universal Multimodal Embedding, arxiv, 2026, 第 8 作者（8） WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval, CVPR, 2026, 第 6 作者 通讯作者（9） MLLM-CTBench: A Benchmark for Continual Instruction Tuning with Reasoning Process Diagnosis, arxiv, 2026, 第 1 作者（10） PASs-MoE: Mitigating Misaligned Co-drift among Router and Experts via Pathway Activation Subspaces for Continual Learning, ACL, 2026, 第 2 作者 通讯作者（11） TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval, arxiv, 2026, 第 5 作者（12） CLEAR: Unlocking Generative Potential for Degraded Image Understanding in Unified Multimodal Models, arxiv, 2026, 第 7 作者（13） Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing, arxiv, 2026, 第 6 作者（14） UniFGVC: Universal Training-Free Few-Shot Fine-Grained Vision Classification via Attribute-Aware Multimodal Retrieval, arxiv, 2025, 第 4 作者（15） Referring Expression Instance Retrieval and A Strong End-to-End Baseline, ACM MM, 2025, 第 4 作者 通讯作者（16） Steering LVLMs via Sparse Autoencoder for Hallucination Mitigation, arxiv, 2025, 第 5 作者（17） FOCUS:Fine-grained Optimization with Semantic Guided Understanding for Pedestrian Attributes Recognition, ICME, 2025, 第 3 作者 通讯作者（18） PhysVLM: Enabling Visual Language Models to Understand Robotic Physical Reachability, CVPR, 2025, 第 4 作者（19） Semantic-aware Fine-grained Point Augmentation for 3D Multi-modal Object Detection, ICME, 2025, 第 3 作者 通讯作者（20） Cracking the Code of Hallucination in LVLMs with Vision-aware Head Divergence, ACL, 2025, 第 3 作者 通讯作者（21） Continual Instruction Tuning for Large Multimodal Models., Ieee Transactions on Image Processing, 2025, 第 2 作者 通讯作者（22） SEEKR: Selective Attention-Guided Knowledge Retention for Continual Learning of Large Language Models, EMNLP, 2024, 第 2 作者 通讯作者（23） Monocular Lane Detection Based on Deep Learning: A Survey, arxiv, 2024, 第 2 作者（24） AAformer: Auto-aligned transformer for person re-identification, TNNLS, 2023, 第 2 作者 通讯作者（25） Bi-Level Implicit Semantic Data Augmentation for Vehicle Re-Identification, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 第 2 作者 通讯作者（26） Learning Semantics-Consistent Stripes With Self-Refinement for Person Re-Identification, IEEE Trans. Neural Networks Learn. Syst., 2023, 第 2 作者（27） Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2023, 第 2 作者 通讯作者（28） Learning semantics- consistent stripes with self-refinement for person re-identification, IEEE Transactions on neural networks and learning system, 2022, 第 2 作者 通讯作者（29） Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 第 2 作者 通讯作者（30） Learning Semantics-Consistent Stripes With Self-Refinement for Person Re-Identification, IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2022, 第 2 作者 通讯作者（31） Hybrid Modality Metric Learning for Visible-Infrared Person Re-Identification, ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2022, 第 2 作者 通讯作者（32） PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification, ECCV, 2022, 第 2 作者（33） Multi-granularity Mutual Learning Network for Object Re-identification, IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2022, 第 3 作者 通讯作者（34） Unsupervised cycle-consistent person pose transfer, NEUROCOMPUTING, 2021, 第 2 作者 通讯作者（35） Adaptive Variance Based Label Distribution Learning For Facial Age Estimation, ECCV, 2020, 第 3 作者（36） A novel data augmentation scheme for pedestrian detection with attribute preserving GAN, NEUROCOMPUTING, 2020, 第 2 作者 通讯作者（37） Identity-Guided Human Semantic Parsing for Person Re-Identification, ECCV, 2020, 第 2 作者（38） Two-Level Attention Network With Multi-Grain Ranking Loss for Vehicle Re-Identification, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, 第 1 作者（39） Attention couplenet: fully convolutional attention coupling network for object detection, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2019, （40） Cascade Attention Network for Person Re-Identification, 26th IEEE International Conference on Image Processing (ICIP), 2019, 第 1 作者 通讯作者（41） Elite Loss for scene text detection, NEUROCOMPUTING, 2019, 第 3 作者（42） Learning Coarse-to-fine Structured Feature Embedding for Vehicle Re-identification, AAAI, 2018, 第 1 作者（43） Deep Embedding Network For Robust Age Estimation, 2017, 第 2 作者（44） Scale-Adaptive Deconvolutional Regression Network for Pedestrian Detection, Asian Conference on Computer Vision (ACCV), 2016, 第 4 作者（45） Scale-adaptive Deconvolutional Regression Network for Pedestrian Detection, 2016, 第 3 作者（46） Multiple deep features learning for object retrieval in surveillance videos, IETCOMPUTERVISION, 2016, 第 1 作者 通讯作者（47） Multi-View 3D Object Retrieval With Deep Embedding Network, IEEE TRANSACTIONS ON IMAGE PROCESSING, 2016, 第 1 作者（48） Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios, ACM Multimedia, 2015, 第 1 作者（49） Learning Deep Compact Descriptor with Bagging Auto-encoders for Object Retrieval, ICIP, 2015, 第 1 作者（50） Learning Multi-view Deep Features for Small Object Retrieval in Surveillance Scenarios, ACM International Conference on Multimedia, 2015, 第 1 作者 通讯作者
