◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Lukas Mauch

4 papers hereh-index 12841 citations38 works total

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

author position
  • middle author4

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

fields
  • cs.LG2
  • cs.CL1
  • cs.CV1

identity via Semantic Scholar / OpenAlex

collaborators

4 papers

cs.CL2026

Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers

Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4

Large Language Models (LLMs) are trained with next-token prediction, implemented in autoregressive Transformers via causal masking for parallelism. This creates a subtle misalignme…

cs.LG2026

Inner Loop Inference for Pretrained Transformers: Unlocking Latent Capabilities Without Training

Jonathan Lys, Vincent Gripon, Bastien Pasdeloup +4

Deep Learning architectures, and in particular Transformers, are conventionally viewed as a composition of layers. These layers are actually often obtained as the sum of two contri…

cs.LG2025

GaLLoP: Gradient-based Sparse Learning on Low-Magnitude Parameters

Anand Choudhary, Yasser Sulaıman, Lukas Mauch +3

Sparse fine-tuning techniques adapt LLMs to downstream tasks by only tuning a sparse subset of model parameters. However, the effectiveness of sparse adaptation depends on optimall…

cs.CV2025

A Novel Benchmark for Few-Shot Semantic Segmentation in the Era of Foundation Models

Reda Bensaid, Vincent Gripon, François Leduc-Primeau +3

Few-shot semantic segmentation (FSS) is a crucial challenge in computer vision, driving extensive research into a diverse range of methods, from advanced meta-learning techniques t…

◍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.