◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

H. Sompolinsky

10 papers hereh-index 8326.3k citations251 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • last author10

Across the 10 of 10 papers where every author was matched, so the position is known.

fields
  • cs.LG6
  • cs.CL2
  • cond-mat.dis-nn1
  • q-bio.NC1

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing 2024Show all

3 papers · 1 filter

cs.LG2024

Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers

Lorenzo Tiberi, Francesca Mignacco, Kazuki Irie +1

Despite the remarkable empirical performance of Transformers, their theoretical understanding remains elusive. Here, we consider a deep multi-head self-attention network, that is c…

cs.LG2024

Diverse capability and scaling of diffusion and auto-regressive models when learning abstract rules

Binxu Wang, Jiaqi Shang, Haim Sompolinsky

Humans excel at discovering regular structures from limited samples and applying inferred rules to novel settings. We investigate whether modern generative models can similarly lea…

cs.LG2024

Coding schemes in neural networks learning classification tasks

Alexander van Meegen, Haim Sompolinsky

Neural networks posses the crucial ability to generate meaningful representations of task-dependent features. Indeed, with appropriate scaling, supervised learning in neural networ…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.