Yanyong Zhang

On the Entropy Dynamics in Reinforcement Fine-Tuning of Large Language Models

ConsisDrive: Identity-Preserving Driving World Models for Video Generation by Instance Mask

GRACE-MoE: Grouping and Replication with Locality-Aware Routing for Efficient Distributed MoE Inference

Adaptive Sensor Selection for Power Efficient 3D Object Detection on Autonomous Driving

scMoE: single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts

ThinkAfford: Enhancing VLM Reasoning for Affordance Grounding in 3D Scenes

FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens

Modalities Contribute Unequally: Enhancing Medical Multi-modal Learning through Adaptive Modality Token Re-balancing

Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots

$LLaPA$: Harnessing Language Models for Protein Enzyme Function

Regularized Optimal Transport for Single-Cell Temporal Trajectory Analysis

Enhancing single-cell Multi-Modal Multi-Task Learning via Sparse Mixture-of-Experts