◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Junjun He

8 papers hereh-index 239 citations8 works total

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

author position
  • middle author2
  • last author3

Across the 5 of 8 papers where every author was matched, so the position is known.

fields
  • cs.CV4
  • cs.AI3
  • physics.flu-dyn1
same name
  • Junjun He — 19 papers, h 5
  • Junjun He — 12 papers, h 13
  • Junjun He — 9 papers, h 3
  • Junjun He — 5 papers, h 5
  • Junjun He — 5 papers, h 3
  • Junjun He — 4 papers, h 3

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
agentic retrieval 1dynamic knowledge graphs 1graph-based reasoning 1markov decision process 1multimodal reinforcement learning 1multimodal VQA 1policy alignment 1retrieval-augmented generation 1reward shaping 1visual grounding 1visual intervention 1

From the 2 of 8 linked papers with an AI index.

collaborators
Showing cs.AIShow all

3 papers · 1 filter

cs.AI2026

A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions

Jianghan Shen, Siqi Luo, Yue Li +9

Policy gradient algorithms for language models optimize the same objective J(I^¸)=E∗I¨„∼p∗I^¸(I¨„)[R(I¨„)], which has exactly two factors: the trajectory probability…

cs.AI2026

Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models

Siqi Luo, Jianghan Shen, Yi Xin +9

Diffusion Multi-Modal Large Language Models (dMLLMs) are powerful for image generation, but optimizing them through reinforcement learning (RL) remains a major challenge. One prima…

cs.AI2026

CuSearch: Curriculum Rollout Sampling via Search Depth for Agentic RAG

Jianghan Shen, Siqi Luo, Xinyu Cheng +6

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a promising paradigm for training agentic retrieval-augmented generation (RAG) systems from outcome-only superv…

◍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.