Lin Song

From Prediction to Perfection: Introducing Refinement to Autoregressive Image Generation

Unbiased Token Pruning for Efficient Large Multimodal Models

Unified Single Transformer for Multimodal Video Understanding and Generation

LoRA-Gen: Specializing Large Language Model via Online LoRA Generation

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

HaploVL: A Single-Transformer Baseline for Multi-Modal Understanding

LoRA-Gen: Specializing Language Model via Online LoRA Generation

SEED-X: Multimodal Models in Real World

GPT4LoRA: Optimizing LoRA Combination via MLLM Self-Reflection