Profiles2020-2026ORCID 0000-0002-4798-230X
Bin Chen
Harbin Institute of Technology, Shenzhen
33Papers
3Last author
40Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers33
- PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and AlignmentAuthor 6 of 8ICLR 2026 · 3 citations
- Bypassing Copyright Protection in Diffusion-based Customization via Two-Stage Latent Feature OptimizationAuthor 9 of 9KDD 2026 · 2 citations
- Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature FilteringAuthor 5 of 9KDD 2026 · 2 citations
- Rectified Decoupled Dataset Distillation: A Closer Look for Fair and Comprehensive EvaluationAuthor 5 of 6ICLR 2026 · 2 citations
- GaussTrap: Stealthy Backdoor Attacks on 3D Gaussian Splatting for Targeted Scene MisperceptionAuthor 7 of 8KDD 2026 · 1 citation
- Towards Efficient Low-rate Image Compression with Frequency-aware Diffusion Prior RefinementAuthor 4 of 4AAAI 2026 · 1 citation
- SDiD:Shared diffusion prior for efficient distributed stereo image compressionAuthor 6 of 7ICML 2026
- When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language ModelsAuthor 7 of 8ACL 2026
- Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMsAuthor 5 of 8NeurIPS 2025 · 25 citations
- Efficient Self-Supervised Video Hashing with Selective State SpacesAuthor 6 of 8AAAI 2025 · 7 citations
- MoSEs: Uncertainty-Aware AI-Generated Text Detection via Mixture of Stylistics Experts with Conditional ThresholdsAuthor 4 of 7EMNLP 2025 · 4 citations
- Cassic: Towards Content-Adaptive State-Space Models for Learned Image CompressionAuthor 4 of 9ICCV 2025 · 2 citations
- 3D-LMVIC: Learning-based Multi-View Image Compression with 3D Gaussian Geometric PriorsAuthor 2 of 7ICML 2025
- An Exploration with Entropy Constrained 3D Gaussians for 2D Video CompressionAuthor 2 of 5ICLR 2025
- AutoSSVH: Exploring Automated Frame Sampling for Efficient Self-Supervised Video HashingAuthor 7 of 7CVPR 2025
- Embracing Collaboration Over Competition: Condensing Multiple Prompts for Visual In-Context LearningAuthor 6 of 10CVPR 2025
- Going Beyond Feature Similarity: Effective Dataset distillation based on Class-aware Conditional Mutual InformationAuthor 2 of 6ICLR 2025
- Hierarchical Features Matter: A Deep Exploration of Progressive Parameterization Method for Dataset DistillationAuthor 3 of 7CVPR 2025
- Stealthy Shield Defense: A Conditional Mutual Information-Based Approach against Black-Box Model Inversion AttacksAuthor 5 of 6ICLR 2025
- Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text DetectorsAuthor 6 of 9EMNLP 2025
- Vision-Language Pre-training with Object Contrastive Learning for 3D Scene UnderstandingAuthor 4 of 6AAAI 2024 · 42 citations
- GMMFormer: Gaussian-Mixture-Model Based Transformer for Efficient Partially Relevant Video RetrievalAuthor 3 of 5AAAI 2024 · 32 citations
- COSMIC: Compress Satellite Image Efficiently via Diffusion CompensationAuthor 5 of 7NeurIPS 2024 · 4 citations
- GIFD: A Generative Gradient Inversion Method with Feature Domain OptimizationAuthor 2 of 5ICCV 2023 · 62 citations
- Contrastive Masked Autoencoders for Self-Supervised Video HashingAuthor 3 of 5AAAI 2023 · 29 citations
- FSR: A General Frequency-Oriented Framework to Accelerate Image Super-resolution NetworksAuthor 4 of 6AAAI 2023 · 18 citations
- Learned Distributed Image Compression with Multi-Scale Patch Matching in Feature DomainAuthor 2 of 7AAAI 2023 · 11 citations
- One-stage Low-resolution Text Recognition with High-resolution Knowledge TransferAuthor 5 of 7ACM MM 2023 · 5 citations
- Learning Transferable Spatiotemporal Representations from Natural Script KnowledgeAuthor 4 of 7CVPR 2023
- Contrastive Quantization with Code Memory for Unsupervised Image RetrievalAuthor 3 of 5AAAI 2022 · 56 citations
Showing the 30 most recent indexed papers.
