Zhaozhuo Xu

To Compress or Not? Pushing the Frontier of Lossless GenAI Model Weights Compression with Exponent Concentration

Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning

Mitigating Non-IID Drift in Zeroth-Order Federated LLM Fine-Tuning with Transferable Sparsity

Get the GIST of Graphs with Intersection Signature

VTBench: Evaluating Visual Tokenizer for Autoregressive Image Generation

HyperRAG: Query-Centric Retrieval Augmented Generation with Hyperbolic Structuring

Towards Fast LLM Fine-tuning through Zeroth-Order Optimization with Projected Gradient-Aligned Perturbations

Sketch to Adapt: Fine-Tunable Sketches for Efficient LLM Adaptation

Zeroth-Order Fine-Tuning of LLMs with Transferable Static Sparsity

Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate

Retrieval Augmented Zero-Shot Enzyme Generation for Specified Substrate

Large Language Models based Graph Convolution for Text-Attributed Networks

Replicate and Quantize: A Plug-and-Play Strategy for Load Balancing in Sparse Mixture-of-Experts LLMs

Graph Transformers Get the GIST: Graph Invariant Structural Trait for Refined Graph Encoding

SpaLLM: Unified Compressive Adaptation of Large Language Models with Sketching

Weighted Diversified Sampling for Efficient Data-Driven Single-Cell Gene-Gene Interaction Discovery