◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Vincent-Pierre Berges

12 papers hereh-index 122.3k citations19 works total

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

author position
  • first author2
  • middle author9

Across the 11 of 12 papers where every author was matched, so the position is known.

fields
  • cs.CL4
  • cs.CV3
  • cs.LG2
  • cs.AI1
  • cs.HC1
  • cs.RO1

identity via Semantic Scholar / OpenAlex

activity
20182025
most citedOffline Visual Representation Learning for Embodied Navigation

24 citations · 42 across the 10 of their papers we have counts for

collaborators
Showing cs.CLShow all

3 papers · 1 filter

cs.CL2025

Continual Learning via Sparse Memory Finetuning

Jessy Lin, Luke Zettlemoyer, Gargi Ghosh +4

Modern language models are powerful, but typically static after deployment. A major obstacle to building models that continually learn over time is catastrophic forgetting, where u…

cs.CL2025

Learning Facts at Scale with Active Reading

Jessy Lin, Vincent-Pierre Berges, Xilun Chen +3

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on…

cs.CL2024★ 1 cited

Memory Layers at Scale

Vincent-Pierre Berges, Barlas Oğuz, Daniel Haziza +3

Memory layers use a trainable key-value lookup mechanism to add extra parameters to a model without increasing FLOPs. Conceptually, sparsely activated memory layers complement comp…

◍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.