Yasaman Bahri
@yasamanbb.bsky.social
Research Scientist @ Google DeepMind. Physics of learning, ML / AI, condensed matter. Prev Ph.D. Physics @ UC Berkeley.
I'll briefly touch on arxiv.org/abs/2502.09863 (with Dhruva, Jamie, and Michael) and then discuss arxiv.org/abs/2505.18651 (with Daniel, Dhruva, and Matthieu).
On the Emergence of Linear Analogies in Word Embeddings
Models such as Word2Vec and GloVe construct word embeddings based on the co-occurrence probability $P(i,j)$ of words $i$ and $j$ in text corpora. The resulting vectors $W_i$ not only group semanticall...
arxiv.org
July 18, 2025 at 5:25 AM
I'll briefly touch on arxiv.org/abs/2502.09863 (with Dhruva, Jamie, and Michael) and then discuss arxiv.org/abs/2505.18651 (with Daniel, Dhruva, and Matthieu).
My talk is "On the emergence of linear structure in word embeddings" & will cover joint works with some fantastic collaborators: Dhruva Karkada, Jamie Simon, Michael DeWeese, Daniel Korchinski, & Matthieu Wyart. I'm excited about this line of work & hope you'll find it interesting!
July 18, 2025 at 5:25 AM
My talk is "On the emergence of linear structure in word embeddings" & will cover joint works with some fantastic collaborators: Dhruva Karkada, Jamie Simon, Michael DeWeese, Daniel Korchinski, & Matthieu Wyart. I'm excited about this line of work & hope you'll find it interesting!