◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Joe Logan

2 papers hereh-index 236 citations4 works total

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

author position
  • sole author2

Across the 2 of 2 papers where every author was matched, so the position is known.

fields
  • cs.AI2

identity via Semantic Scholar / OpenAlex

works on
computational efficiency 1depth recurrence 1fixed point convergence 1token-level analysis 1transformers 1

From the 1 of 2 linked papers with an AI index.

collaborators

2 papers

cs.AI2026

Per-Token Fixed-Point Convergence in Depth-Recurrent Transformers

Joe Logan

The paper investigates how depth‑recurrent transformers reach a per‑token fixed point during repeated application of a weight‑tied core, showing that most tokens converge quickly w…

cs.AI2026

Continuum Memory Architectures for Long-Horizon LLM Agents

Joe Logan

Retrieval-augmented generation (RAG) has become the default strategy for providing large language model (LLM) agents with contextual knowledge. Yet RAG treats memory as a stateless…

◍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.