WEIZHONG ZHANG

Sampling Complexity of TD and PPO in RKHS

Large Language Model Compression with Global Rank and Sparsity Optimization

Efficient Fine-Tuning of Quantized Models via Adaptive Rank and Bitwidth

Efficient Representativeness-Aware Coreset Selection

Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning

Compress Large Language Models via Collaboration Between Learning and Matrix Approximation

Towards Robust Influence Functions with Flat Validation Minima

Computational Budget Should Be Considered in Data Selection

Computation and Memory-Efficient Model Compression with Gradient Reweighting

Efficient Fine-Tuning of Quantized LLMs via Three-Stage Optimization

Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient

Out-of-Distribution Detection using Neural Activation Prior