◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Hugo Koubbi

4 papers hereh-index 462 citations4 works total

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

author position
  • first author2
  • middle author2

Across the 4 of 4 papers where every author was matched, so the position is known.

fields
  • cs.LG3
  • math.PR1

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators

4 papers

cs.LG2026

Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics

Hugo Koubbi, Louis Hernandez, Matthieu Boussard

Low-Rank Adaptation (LoRA) is the dominant parameter-efficient fine-tuning method due to its favorable compute-performance trade-off, yet it suffers from catastrophic forgetting. W…

math.PR2026

Homogenized Transformers

Hugo Koubbi, Borjan Geshkovski, Philippe Rigollet

We study a random model of deep multi-head self-attention in which the weights are resampled independently across layers and heads, as at initialization of training. Viewing depth…

cs.LG2025

Learning single-index models via harmonic decomposition

Nirmit Joshi, Hugo Koubbi, Theodor Misiakiewicz +1

We study the problem of learning single-index models, where the label y∈R depends on the input x∈Rd only through an unknown one-dimensio…

cs.LG2024

Dynamic metastability in the self-attention model

Borjan Geshkovski, Hugo Koubbi, Yury Polyanskiy +1

We consider the self-attention model - an interacting particle system on the unit sphere, which serves as a toy model for Transformers, the deep neural network architecture behind…

◍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.