Elamur Research⌕
☰
home / authors / Jun Liu

Jun Liu

Jun Liu has 7 papers in our library, in 2023–2026, most of them on Reasoning, Language models & pretraining, Evaluation & benchmarks; often with Fangzhi Xu, Da Pan, Guosheng Dong.

7 papers in our library · 2023–2026

OpenAlex · ORCID · Wikidata · h-index 57 · 431 works · 18,664 citations OpenAlex, 2026-10-14

📄 7 works in our library · 🔗 Cited 245 times in our library · 15 more in our library without a page yet · ⭐ Paper Stars ranking: #5339

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓Lancaster UniversityLancaster · United Kingdom2024–2026 · 47 papersEmploymentEmployment · Professorcurrent🎓University of LeicesterLeicester · United Kingdom2026 · 1 papercurrent🎓Singapore University of Technology and DesignSingapore · Singapore2019–2025 · 114 papersEmployment🎓Nanyang Technological UniversitySingapore · Singapore1992–2021 · 31 papersEducation · PhD🏢TencentShenzhen · China2022–2025 · 16 papers🏛️Chinese Academy of SciencesBeijing · China2005–2025 · 14 papers🎓Xi'an Jiaotong UniversityXi'an · China2018–2025 · 11 papers🎓Northeastern UniversityShenyang · China2007–2025 · 8 papers🎓Fudan UniversityShanghai · China2013–2024 · 8 papers🎓Zhejiang UniversityHangzhou · China2005–2023 · 7 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 101 more institutions on single bylines are not listed.

 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 8The field of science this work belongs to (OpenAlex fields).Computer Science · 7 worksArts and Humanities · 6 worksArtificial Intelligence · 7 worksLanguage and Linguistics · 6 worksComputer Vision and Pattern Recognition · 4 worksPsychology · 1 workSignal Processing · 1 workExperimental and Cognitive Psychology · 1 work

🧭 Topics 4Research subjects and languages the work is about.Reasoning · 4 worksLanguage models & pretraining · 3 worksEvaluation & benchmarks · 2 worksSpeech & spoken language · 1 work

 Works by year

2020s

20261 paper20255 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond (2023 · 142 citations)
    The paper asks whether current LLMs reason logically or mostly rely on surface patterns and memorized benchmark content.
  2. Baichuan-Omni-1.5 Technical Report (2025 · 28 citations)
    Open-source multimodal LLMs mostly pair vision with text. Voice support usually relies on separate ASR and TTS modules, which add latency. End-to-end omni models such as VITA-1.5 and Mini-Omni2 often lose quality when modalities compete, especially on text-only tasks. Baichuan-Omni-1.5 is a single 7B-scale model that…
  3. PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning (2025 · 25 citations)
    Existing physics benchmarks for large language models (e.g., ScienceQA, SciBench, GPQA) mostly use short solutions of about 3–4 formulas and score only the final answer.
  4. Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction (2025 · 16 citations)
    Cascaded voice assistants chain ASR, an LLM and TTS. This adds latency, compounds errors and discards paralinguistic cues. End-to-end alternatives such as Moshi and GLM-4-Voice tend to lose reasoning ability once speech is added. Baichuan-Audio is a 7B end-to-end audio LLM for real-time bilingual (Chinese/English)…
  5. Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models (2025 · 15 citations)
    Large language models increasingly solve tasks by writing symbolic intermediate forms, such as programs, logic forms, or web actions, which an external environment then executes.
  6. MUR: Momentum Uncertainty guided Reasoning for Large Language Models (2026 · 8 citations)
    Test-time scaling (TTS) makes LLMs reason better but tends to cause overthinking: extra compute goes to every reasoning step, including trivial ones.
  7. Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning (2025 · 8 citations)
    Genius tackles the problem of improving LLM reasoning after pre-training without any external supervision.

All works

22 works of theirs in our library, the most cited first; 7 with a page here, the others link their original until we summarise them.

  1. NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetAmir Shahroudy et al.2016 · 3,166 citations
  2. Global Context-Aware Attention LSTM Networks for 3D Action Recognition ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJun Liu et al.2017 · 685 citations
  3. VERI-Wild: A Large Dataset and a New Method for Vehicle Re-Identification in the Wild ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetYihang Lou et al.2019 · 328 citations
  4. Deep Level Sets for Salient Object Detection ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetPing Hu et al.2017 · 207 citations
  5. A convex formulation for learning shared structures from multiple tasks ↗International Conference on Machine Learning · no summary yetJianhui Chen et al.2009 · 197 citations
  6. DiffPose: Toward More Reliable 3D Pose Estimation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJia Lin Gong et al.2023 · 188 citations
  7. IDM: An Intermediate Domain Module for Domain Adaptive Person Re-ID ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetYongxing Dai et al.2021 · 151 citations
  8. Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and BeyondIEEE Transactions on Knowledge and Data EngineeringFangzhi Xu, Qika Lin, Jiawei Han, et al.2023 · 142 citations
  9. Skeleton Cloud Colorization for Unsupervised 3D Action Representation Learning ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetSiyuan Yang et al.2021 · 116 citations
  10. Not All Pixels Are Matched ↗ACM International Conference on Multimedia (ACM MM) · no summary yetHanzhe Sun et al.2022 · 90 citations
  11. En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetXia Kong et al.2022 · 81 citations
  12. Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models ↗Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume · no summary yetTianxing He et al.2021 · 69 citations
  13. Meta Agent Teaming Active Learning for Pose Estimation ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetJia Gong et al.2022 · 58 citations
  14. Else-Net: Elastic Semantic Network for Continual Action Recognition from Skeleton Data ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetTianjiao Li et al.2021 · 50 citations
  15. Baichuan-Omni-1.5 Technical ReportarXiv:2501.15368Yadong Li, Jun Liu, Tao Zhang, et al.2025 · 28 citations
  16. PhysReason: A Comprehensive Benchmark towards Physics-Based ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Xinyu Zhang, Yuxuan Dong, Yanrui Wu, et al.2025 · 25 citations
  17. Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models ↗arXiv (Cornell University) · no summary yetTianxing He et al.2019 · 19 citations
  18. Baichuan-Audio: A Unified Framework for End-to-End Speech InteractionarXiv:2502.17239Tianpeng Li, Jun Liu, Tao Zhang, et al.2025 · 16 citations
  19. Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Fangzhi Xu, Qiushi Sun, Kanzhi Cheng, et al.2025 · 15 citations
  20. MUR: Momentum Uncertainty guided Reasoning for Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Hang Yan, Fangzhi Xu, Rongman Xu, et al.2026 · 8 citations
  21. Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced ReasoningAnnual Meeting of the Association for Computational Linguistics (ACL)Fangzhi Xu, Hang Yan, Chang Ma, et al.2025 · 8 citations
  22. Training ASR Models By Generation of Contextual Information ↗IEEE International Conference on Acoustics Speech and Signal Processing · no summary yetKritika Singh et al.2020 · 8 citations

 Co-authors here

12 of 33 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

 Cited by

Papers of our library cite their works 245 times (of the 149,439 papers whose bibliographies we read); 48 citing papers with a page here →.

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/jun-liu/