Mert Yuksekgonul
@mertyuksekgonul
(he/him) Computer Science PhD Candidate @Stanford @StanfordAILab
ID: 175309364
https://cs.stanford.edu/~merty 06-08-2010 07:11:25
2,2K Tweet
4,4K Followers
721 Following
*TextGrad: Automatic “Differentiation” via Text* by Mert Yuksekgonul Federico Bianchi Sheng Liu Zhi Huang James Zou PyTorch syntax for optimizing graphs of LLM calls, where "gradients" and "optimization" are computed by additional LLM instances. arxiv.org/abs/2406.07496
🔥#TextGrad is now multi-modal! TextGrad boosts GPT-4o's visual reasoning ability: 📊MathVista score 63.8➡️66.1 w/ TextGrad 🧬Reduces ScienceQA error rate by 20%. Best reported 0-shot score Tutorial: colab.research.google.com/github/zou-gro… Great work Pan Lu Mert Yuksekgonul + team! Works
Work co-supervised with Hidenori Tanaka, led by Udith Haputhanthri, has now been accepted to ICML Mechanistic Interpretability workshop. TLDR: High-dimensional bifurcations underly skill acquisition in task-trained RNNs Link: openreview.net/forum?id=njmXd… A tweetprint🧵
A while ago I wrote a thread about #TextGrad, which is an alternative prompt optimization method, based on "natural language gradients". Cool! Since we are still waiting for Andrej Karpathy's video reimplementing this from scratch... I thought I had to make my own... So here is the