3 15 9

Yu Zhao

yuzhaouoe

https://yuzhaouoe.github.io/

AI & ML interests

NLP/ML

Recent Activity

updated a model 29 days ago

yuzhaouoe/Llama2-7b-SAE

authored a paper about 1 month ago

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

View all activity

Organizations

yuzhaouoe's activity

upvoted a paper about 1 month ago

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression

Paper • 2503.02812 • Published Mar 4 • 9

upvoted a collection about 1 month ago

Q-Filters

Collection

Pre-computed Q-Filters for efficient KV cache compression. • 15 items • Updated Mar 3 • 6

upvoted a paper about 1 month ago

Competitive Programming with Large Reasoning Models

Paper • 2502.06807 • Published Feb 3 • 69

upvoted 3 papers 5 months ago

DeCoRe: Decoding by Contrasting Retrieval Heads to Mitigate Hallucinations

Paper • 2410.18860 • Published Oct 24, 2024 • 11

Analysing the Residual Stream of Language Models Under Knowledge Conflicts

Paper • 2410.16090 • Published Oct 21, 2024 • 7

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering

Paper • 2410.15999 • Published Oct 21, 2024 • 20

upvoted a paper 6 months ago

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Paper • 2408.05147 • Published Aug 9, 2024 • 39

upvoted an article 8 months ago

Article

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

Aug 21, 2024

• 33

upvoted a collection 9 months ago

🔍 Interpretability & Analysis of LMs

Collection

Outstanding research in LM interpretability and evaluation, summarized • 105 items • Updated 23 days ago • 97

upvoted an article 9 months ago

Article

Introducing RWKV — An RNN with the advantages of a transformer

May 15, 2023

• 20

upvoted 3 papers 10 months ago

Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation

Paper • 2406.13663 • Published Jun 19, 2024 • 7

A Simple and Effective L_2 Norm-Based Strategy for KV Cache Compression

Paper • 2406.11430 • Published Jun 17, 2024 • 24

Are We Done with MMLU?

Paper • 2406.04127 • Published Jun 6, 2024 • 39

upvoted an article 12 months ago

Article

The Hallucinations Leaderboard, an Open Effort to Measure Hallucinations in Large Language Models

Jan 29, 2024

• 26