◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Lukas Helff

11 papers hereh-index 5114 citations13 works total

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

author position
  • first author4
  • middle author4

Across the 8 of 11 papers where every author was matched, so the position is known.

fields
  • cs.AI6
  • cs.CV2
  • cs.LG2
  • cs.CL1

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2026

ActivationReasoning: Logical Reasoning in Latent Activation Spaces

Lukas Helff, Ruben Härle, Wolfgang Stammer +6

Large language models (LLMs) excel at generating fluent text, but their internal reasoning remains opaque and difficult to control. Sparse autoencoders (SAEs) make hidden activatio…

cs.LG2026

LLMs Gaming Verifiers: RLVR can Lead to Reward Hacking

Lukas Helff, Quentin Delfosse, David Steinmann +6

As reinforcement Learning with Verifiable Rewards (RLVR) has become the dominant paradigm for scaling reasoning capabilities in LLMs, a new failure mode emerges: LLMs gaming verifi…

◍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.