Long Chen

Assistant Professor@The Hong Kong University of Science and Technology·中国香港·OpenReview

研究方向

Vision Generation · Multimodal Large Language Models · Scene Understanding · Zero/Few-Shot Learning · Visual-Lanaguage Tasks · Multimodal Understanding

Long Chen

GIR-Bench: Versatile Benchmark for Generating Images with Reasoning

Agreement with the Ensemble for Zero-Shot Vision-Language Model Selection

Exploring Cross-Modal Flows for Few-Shot Learning

FlowCycle: Pursuing Cycle-Consistent Flows for Text-based Editing

AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization

DPA-SGG: Dual Prompt Learning with Pseudo-Visual Augmentation for Open-Vocabulary Scene Graph Generation

Segmentation as a Plug-and-Play Capability for Frozen Multimodal LLMs

Empowering Small VLMs to Think with Dynamic Memorization and Exploration

Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Models

CoMo: Compositional Motion Customization for Text-to-Video Generation

Learning Hierarchical Hyperbolic Embeddings for Compositional Zero-Shot Learning

Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Multi-Resolution Decomposable Diffusion Model for Non-Stationary Time Series Anomaly Detection

Noise Matters: Optimizing Matching Noise for Diffusion Classifiers

DisPose: Disentangling Pose Guidance for Controllable Human Image Animation

Event-Customized Image Generation

CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editing

Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection

Event-Customized Image Generation

Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing

Improving Diffusion-based Data Augmentation with Inversion Circle Interpolation

R3HF: Reward Redistribution for Enhancing Reinforcement Learning from Human Feedback