Li Yuan

SERE: Similarity-based Expert Re-routing for Efficient Batch Decoding in MoE Models

EA3D: Event-Augmented 3D Diffusion for Generalizable Novel View Synthesis

Towards Autonomous Experimentation: BioProBench, a Corpus and Benchmark for Biological Protocol Comprehension

Task-Aware Mechanism: Hybrid MoE Vision Tower Towards Holistic Video Understanding

FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation

Unified Multimodal Model as Auto-Encoder

Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection

MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

MoH: Multi-Head Attention as Mixture-of-Head Attention

PiCO: Peer Review in LLMs based on Consistency Optimization

MoH: Multi-Head Attention as Mixture-of-Head Attention

Mora: Enabling Generalist Video Generation via A Multi-Agent Framework

Deep-ComAIR: A Framework for Predicting TCR-pMHC Binding through Complex Structural Analysis