Wei Shen

Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model AAAI 2026 Efficient Segmentation with Multimodal Large Language Model via Token Routing AAAI 2026 WorldGrow: Generating Infinite 3D World AAAI 2026 Dereflection Any Image with Diffusion Priors and Diversified Data AAAI 2026 A Novel Retrieve-Read-Group Paradigm for Open Knowledge Base Canonicalization AAAI 2026 Few-step Flow for 3D Generation via Marginal-Data Transport Distillation AAAI 2026 Unveiling the Unknown: Open-Set Entity Typing via Two-Stage Generation ACL 2026 CP-CLIP: Customized Parameter Generation for Open-vocabulary Semantic Segmentation AAAI 2026 FATE: Feature-Adapted Parameter Tuning for Vision-Language Models AAAI 2025 Label-Free Backdoor Attacks in Vertical Federated Learning AAAI 2025 A Triple-View Framework for Fine-Grained Emotion Classification with Clustering-Guided Contrastive Learning ACL 2025 LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models ACL 2025 Mitigating Posterior Salience Attenuation in Long-Context LLMs with Positional Contrastive Decoding ACL 2025 EndoDAV: Depth Any Video in Endoscopy with Spatiotemporal Accuracy MICCAI 2025 Policy Filtration for RLHF to Mitigate Noise in Reward Models ICML 2025 On the Training Convergence of Transformers for In-Context Classification of Gaussian Mixtures ICML 2025 AdaptiveStep: Automatically Dividing Reasoning Step through Model Confidence ICML 2025 Tackling View-Dependent Semantics in 3D Language Gaussian Splatting ICML 2025 Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning ICLR 2025 Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-tuning ICLR 2025 Learning LLM-as-a-Judge for Preference Alignment ICLR 2025 RMB: Comprehensively benchmarking reward models in LLM alignment ICLR 2025 A Token-level Text Image Foundation Model for Document Understanding ICCV 2025 Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations ICCV 2025 Learning from LLM Agents: In-Context Generative Models for Text Casing in E-Commerce Ads EMNLP 2025 Joint Enhancement of Relational Reasoning for Long-Context LLMs EMNLP 2025 OpenRLHF: A Ray-based Easy-to-use, Scalable and High-performance RLHF Framework EMNLP 2025 Domain Generalization in CLIP via Learning with Diverse Text Prompts CVPR 2025 Marten: Visual Question Answering with Mask Generation for Multi-modal Document Understanding CVPR 2025 Understanding Fine-tuning CLIP for Open-vocabulary Semantic Segmentation in Hyperbolic Space CVPR 2025 Star with Bilinear Mapping CVPR 2025 Parameter-efficient Fine-tuning in Hyperspherical Space for Open-vocabulary Semantic Segmentation CVPR 2025 Segment Any 3D Gaussians AAAI 2025 UniProcessor: A Text-induced Unified Low-level Image Processor ECCV 2024 Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation NIPS 2024 ViTree: Single-Path Neural Tree for Step-Wise Interpretable Fine-Grained Visual Categorization AAAI 2024 SAM-PARSER: Fine-Tuning SAM Efficiently by Parameter Space Reconstruction AAAI 2024 Partial Label Learning with a Partner AAAI 2024 LoRAMoE: Alleviating World Knowledge Forgetting in Large Language Models via MoE-Style Plugin ACL 2024 Stochastic Smoothed Gradient Descent Ascent for Federated Minimax Optimization AISTATS 2024 Parameter Efficient Fine-tuning via Cross Block Orchestration for Segment Anything Model CVPR 2024 PosFormer: Recognizing Complex Handwritten Mathematical Expression with Position Forest Transformer ECCV 2024 Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation ECCV 2024 Bridging Synthetic and Real Worlds for Pre-training Scene Text Detectors ECCV 2024 Reward Modeling Requires Automatic Adjustment Based on Data Quality EMNLP 2024 Leveraging Web-Crawled Data for High-Quality Fine-Tuning EMNLP 2024 Improving Generalization of Alignment with Human Preferences through Group Invariant Learning ICLR 2024 Linear Alignment: A Closed-form Solution for Aligning Human Preferences without Tuning and Feedback ICML 2024 Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning ICML 2024 EndoGSLAM: Real-Time Dense Reconstruction and Tracking in Endoscopic Surgeries using Gaussian Splatting MICCAI 2024 Missing as Masking: Arbitrary Cross-modal Feature Reconstruction for Incomplete Multimodal Brain Tumor Segmentation MICCAI 2024 Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation CVPR 2023 MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery CVPR 2023 Intriguing Findings of Frequency Selection for Image Deblurring AAAI 2023 CL-QR: Cross-Lingual Enhanced Query Reformulation for Multi-lingual Conversational AI Agents EMNLP 2023 Self-Supervised Implicit Glyph Attention for Text Recognition CVPR 2023 Low-Resource Personal Attribute Prediction from Conversations AAAI 2023 Improving Contextual Query Rewrite for Conversational AI Agents through User-preference Feedback Learning EMNLP 2023 NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds CVPR 2023 Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback EMNLP 2023 RePreM: Representation Pre-training with Masked Model for Reinforcement Learning AAAI 2023 Segment Anything in 3D with NeRFs NIPS 2023 Self-Supervised Character-to-Character Distillation for Text Recognition ICCV 2023 Agglomerative Transformer for Human-Object Interaction Detection ICCV 2023 USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation ICCV 2023 Video-based Human-Object Interaction Detection from Tubelet Tokens NIPS 2022 Unsupervised Domain Adaptation through Shape Modeling for Medical Image Segmentation MIDL 2022 Enhancing Self-Attention with Knowledge-Assisted Attention Maps NAACL 2022 CP2: Copy-Paste Contrastive Pretraining for Semantic Segmentation ECCV 2022 End-to-End Human-Gaze-Target Detection With Transformers CVPR 2022 ContrastMask: Contrastive Learning To Segment Every Thing CVPR 2022 Image BERT Pre-training with Online Tokenizer ICLR 2022 BézierPalm: A Free Lunch for Palmprint Recognition ECCV 2022 Iwin: Human-Object Interaction Detection via Transformer with Irregular Windows ECCV 2022 Community Question Answering Entity Linking via Leveraging Auxiliary Data IJCAI 2022 Shape-Texture Debiased Neural Network Training ICLR 2021 CO2: Consistent Contrast for Unsupervised Visual Representation Learning ICLR 2021 Looking Here or There? Gaze Following in 360-Degree Images ICCV 2021 Glance-and-Gaze Vision Transformer NIPS 2021 Dual Attention Guided Gaze Target Detection in the Wild CVPR 2021 Deeply Shape-Guided Cascade for Instance Segmentation CVPR 2021 Deep Distance Transform for Tubular Structure Segmentation in CT Scans CVPR 2020 Robust Face Detection via Learning Small Faces on Hard Images WACV 2020 Resisting Large Data Variations via Introspective Transformation Network WACV 2020 Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation ECCV 2020 Gradually Updated Neural Networks for Large-Scale Image Recognition ICML 2018 Few-Shot Image Recognition by Predicting Parameters From Activations CVPR 2018 Single-Shot Object Detection With Enriched Semantics CVPR 2018 Deep Regression Forests for Age Estimation CVPR 2018 Hi-Fi: Hierarchical Feature Integration for Skeleton Detection IJCAI 2018 Deep Co-Training for Semi-Supervised Image Recognition ECCV 2018 Label Distribution Learning Forests NIPS 2017 Learning Residual Images for Face Attribute Manipulation CVPR 2017 Multi-Stage Multi-Recursive-Input Fully Convolutional Networks for Neuronal Boundary Detection ICCV 2017 ScaleNet: Guiding Object Proposal Generation in Supermarkets and Beyond ICCV 2017 Object Skeleton Extraction in Natural Images by Fusing Scale-Associated Deep Side Outputs CVPR 2016 Multi-Oriented Text Detection With Fully Convolutional Networks CVPR 2016 DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection CVPR 2015 Symmetry-Based Text Line Detection in Natural Scenes CVPR 2015 Improving Traffic Prediction with Tweet Semantics IJCAI 2013