Yi Xin

UniMedVL: Unifying Medical Multimodal Understanding and Generation through Observation-Knowledge-Analysis

Lightning Video: Building Compact Diffusion Transformers for High-Fidelity On-Device Video Generation

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

AutoCode4Math: Learning Autonomous Code Integration for Math LLMs

$\text{D}_{2}\text{O}$: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Customize Your Visual Autoregressive Recipe with Set Autoregressive Modeling

Exploring the Design Space of Autoregressive Models for Efficient and Scalable Image Generation