Renjing Xu

Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning

Representation Convergence: Mutual Distillation is Secretly a Form of Regularization

FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation

Cross-Species Protein Interaction Prediction by Hierarchical Contrastive Pretraining

Spiking Neural Networks Need High-Frequency Information

Simple Policy Optimization

Optimal Brain Apoptosis

Recursive Cleaning for Large-scale Protein Data via Multimodal Learning

The Meta-Representation Hypothesis

A Dual-Agent Adversarial Framework for Generalizable Reinforcement Learning

MAD: Multi-Alignment MEG-to-Text Decoding

Simple Policy Optimization

Typography Leads Semantic Diversifying: Amplifying Adversarial Transferability across Multimodal Large Language Models

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream

Enhancing Discontinuous Radiance Fields with Continuous representation