Huaibo Huang

HAD: Hybrid Architecture Distillation for Bridging Large-Transformer Knowledge into Compact Genomic Models

ID-Cloak: Crafting Identity-Specific Cloaks Against Personalized Text-to-Image Generation

PROOF: Perturbation-Robust Noise Finetune via Optimal Transport Information Bottleneck for Highly-Correlated Asset Generation

Boosting RL-based Multimodal Reasoning via Difficulty Prior

GAT-Flow: Predictor-Corrector Flow Matching with Graph Attention Network for Crystalline Materials

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs

Semantic Equitable Clustering: You Only Iterate Once to Cluster Vision Tokens

eRAM-V: From Interaction to Integration in Efficient Multimodal Large Language Models