xszheng2020

PhD Candidate

Pinned Repositories

Agent-Smith
[ICML 2024] Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
Language:Python90 7 413
Cheating-LLM-Benchmarks
[SafeGenAi @ NeurIPS 2024] Cheating Automatic LLM Benchmarks: Null Models Achieve High Win Rates
Language:Jupyter Notebook600
D-TRAK
Intriguing Properties of Data Attribution on Diffusion Models (ICLR 2024)
Language:Jupyter Notebook23 5 03
I-FSJ
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses (NeurIPS 2024)
Language:Python46 4 07
regmix
🧬 RegMix: Data Mixture as Regression for Language Model Pre-training
Language:Jupyter Notebook88 5 104
Classical-LOO
Leave One Out
Language:Jupyter Notebook1 1 00
LLM-TRAK
Language:Jupyter Notebook5 1 00
memorization
An Empirical Study of Memorization in NLP (ACL 2022)
Language:Jupyter Notebook13 1 20
xszheng2020
1 1 00
xszheng2020.github.io
Language:HTML1 1 00

xszheng2020/memorization
An Empirical Study of Memorization in NLP (ACL 2022)
Language:Jupyter Notebook13 1 20
xszheng2020/LLM-TRAK
Language:Jupyter Notebook5 1 00
xszheng2020/Classical-LOO
Leave One Out
Language:Jupyter Notebook1 1 00
xszheng2020/xszheng2020
1 1 00
xszheng2020/xszheng2020.github.io
Language:HTML1 1 00
xszheng2020/fast-influence-functions
Language:Python0 0 00
xszheng2020/heldout-influence-estimation
Language:Python0 0 00
xszheng2020/readme-best-practices
Best practices for writing a README for your open source project
0 0 00
xszheng2020/responsibleNLPresearch
templates and other documents regarding responsible NLP research
Language:TeX0 0 00
xszheng2020/stable-diffusion-analytic-dpm
Language:Python0 0 00
xszheng2020/alpaca_eval
An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.
Language:Jupyter Notebook