◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Junxian Li

22 papers hereh-index 9366 citations33 works total

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

author position
  • first author3
  • middle author16

Across the 19 of 22 papers where every author was matched, so the position is known.

fields
  • cs.CV11
  • cs.AI4
  • cs.CL2
  • cs.CR2
  • cs.HC1
  • cs.LG1
Homepage
same name
  • Junxian Li — 3 papers, h 6
  • Junxian Li — 2 papers, h 1
  • Junxian Li — 1 paper, h 0
  • Junxian Li — 1 paper, h 4
  • Junxian Li — 1 paper, h 1

Either other researchers who publish under this name, or the same person where the external sources have not merged their records.

identity via Semantic Scholar / OpenAlex

most citedSpeak-to-Structure: Evaluating LLMs in Open-domain Natural Language-Driven Molecule Generation

2 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

4 papers · 1 filter

cs.AI2026

I^´-mem: Efficient Online Memory for Large Language Models

Jingdi Lei, Di Zhang, Junxian Li +7

Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and…

cs.AI2026

Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs

Junxian Li, Xinyue Xu, Sai Ma +2

Multimodal Large Language Models (MLLMs) frequently suffer from unfaithfulness, generating reasoning chains that drift from visual evidence or contradict final predictions. We prop…

cs.AI2025

AI for Service: Proactive Assistance with AI Glasses

Zichen Wen, Yiyu Wang, Chenfei Liao +10

In an era where AI is evolving from a passive tool into an active and adaptive companion, we introduce AI for Service (AI4Service), a new paradigm that enables proactive and real-t…

cs.AI2025

Control-R: Towards controllable test-time scaling

Di Zhang, Weida Wang, Junxian Li +10

This paper target in addressing the challenges of underthinking and overthinking in long chain-of-thought (CoT) reasoning for Large Reasoning Models (LRMs) by introducing Reasoning…

◍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.