← Search

Long Chan

2 accepted papers

2025

LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation

ICLR 2025poster

We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models ($s$-MLLM) distilling knowledge from large-scale MLLM ($l$-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structu…

2025

PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation

CVPR 2025poster

Finetuning-free personalized image generation can synthesize customized images without test-time finetuning, attracting wide research interest owing to its high efficiency. Current finetuning-free methods simply adopt a single training stage with a simple image reconstruction task, and they typicall…