◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Junjie Wang

11 papers hereh-index 224 citations13 works total

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

author position
  • middle author10
  • last author1

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

fields
  • cs.CL4
  • cs.CV2
  • cs.AI1
  • cs.GR1
  • cs.IR1
  • cs.MA1
same name
  • Junjie Wang — 15 papers, h 6
  • Junjie Wang — 9 papers, h 16
  • Junjie Wang — 7 papers, h 5
  • Junjie Wang — 6 papers, h 2
  • Junjie Wang — 5 papers, h 1
  • Junjie Wang — 5 papers, h 2

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

works on
cross-platform generalization 1expert routing 1kinematics clustering 1mixture of experts 1robot manipulation 1vision-language agents 1

From the 1 of 11 linked papers with an AI index.

collaborators
Showing cs.CLShow all

4 papers · 1 filter

cs.CL2026

Simple-OPD: Demystifying Warm-up for On-policy Distillation

Tao Liu, Taiqiang Wu, Mao Zheng +5

On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage b…

cs.CL2026

Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning

Xuewei Yang, Jiachen Yu, Jie Wu +3

Reinforcement learning from verifiable rewards improves the reasoning ability of large language models, but often suffers from entropy collapse, in which increasingly concentrated…

cs.CL2026

Think-with-Rubrics: From External Evaluator to Internal Reasoning Guidance

Jiachen Yu, Zhihao Xu, Junjie Wang +1

Rubrics have been extensively utilized for evaluating unverifiable, open-ended tasks, with recent research incorporating them into reward systems for reinforcement learning. Howeve…

cs.CL2026

ProFit: Leveraging High-Value Signals in SFT via Probability-Guided Token Selection

Tao Liu, Taiqiang Wu, Runming Yang +3

Supervised fine-tuning (SFT) is a fundamental post-training strategy to align Large Language Models (LLMs) with human intent. However, traditional SFT often ignores the one-to-many…

◍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.