Zhaozhuo Xu

papers

757

total citations

papers (12)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

ICML 2024arXiv

368

citations

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

NEURIPS 2023arXiv

331

citations

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures

NEURIPS 2021arXiv

citations

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

NEURIPS 2023arXiv

citations

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler

NEURIPS 2021

citations

Knowledge Graphs Can be Learned with Just Intersection Features

ICML 2024

citations

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

NEURIPS 2023

citations

Locality Sensitive Teaching

NEURIPS 2021

citations

Zhaozhuo Xu

papers (12)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

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

TVE: Learning Meta-attribution for Transferable Vision Explainer

Soft Prompt Recovers Compressed LLMs, Transferably

GNNs Also Deserve Editing, and They Need It More Than Once

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler

Knowledge Graphs Can be Learned with Just Intersection Features

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

Locality Sensitive Teaching

papers (12)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Breaking the Linear Iteration Cost Barrier for Some Well-known Conditional Gradient Methods Using MaxIP Data-structures

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

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

TVE: Learning Meta-attribution for Transferable Vision Explainer

Soft Prompt Recovers Compressed LLMs, Transferably

GNNs Also Deserve Editing, and They Need It More Than Once

Raw Nav-merge Seismic Data to Subsurface Properties with MLP based Multi-Modal Information Unscrambler

Knowledge Graphs Can be Learned with Just Intersection Features

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

Locality Sensitive Teaching