Elamur Research⌕
☰
home / authors / Boxin Wang

Boxin Wang

Boxin Wang has 4 papers in our library, in 2023–2026, most of them on Language models & pretraining, Bias, fairness & safety, Vision & language; often with Zihan Liu, Bryan Catanzaro, Chejian Xu.

4 papers in our library · 2023–2026

OpenAlex · ORCID · h-index 32 · 152 works · 3,052 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 316 times in our library · 4 more in our library without a page yet · ⭐ Paper Stars ranking: #4802

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

🎓Jilin UniversityChangchun · China2015–2026 · 64 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2020–2026 · 16 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2019–2026 · 15 paperscurrent🔬Institute of PhysicsBeijing · China2023–2026 · 4 paperscurrent🤝National Center for Nanoscience and TechnologyBeijing · China2018–2024 · 32 papers🎓University of Illinois Urbana-ChampaignUrbana · United States2019–2024 · 15 papers🎓Northeast Electric Power UniversityJilin · China2023–2025 · 2 papers🎓Hebei North UniversityZhangjiakou · China2023 · 2 papers🎓Hebei University of EngineeringHandan · China2023 · 2 papers🎓University of Wisconsin SystemMadison · United States2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 15 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 · 4 worksArtificial Intelligence · 4 worksSocial Sciences · 1 workArts and Humanities · 3 worksSafety Research · 1 workSociology and Political Science · 1 workLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 2 works

🧭 Topics 4Research subjects and languages the work is about.Language models & pretraining · 4 worksBias, fairness & safety · 1 workVision & language · 1 workEfficient models & compression · 1 work

 Works by year

2020s

20262 papers20241 paper20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models (2023 · 259 citations)
    Practitioners increasingly propose GPT models for high-stakes domains such as healthcare and finance, yet little systematic evidence exists on how reliable these models are.
  2. NVLM: Open Frontier-Class Multimodal LLMs (2024 · 44 citations)
    Open multimodal LLMs usually trail proprietary systems such as GPT-4o. Their architectures are rarely compared under equal conditions, and they typically lose text-only skill after vision-language training. NVIDIA's NVLM 1.0 addresses all three issues with three variants trained on one shared, carefully curated data…
  3. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation (2026 · 16 citations)
    Post-training a single LLM across many reasoning and agentic domains is hard. Mixing diverse RL environments can destabilize training, and gains in one area often erode others. Nemotron-Cascade 2 extends NVIDIA's earlier Cascade RL approach, which trains domain by domain in sequence, to address this. The base model…
  4. From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models (2026 · 5 citations)
    Open LLMs struggle to reason over very long inputs. Existing context-extension efforts often lack transparent data recipes, require expensive training, or lose quality on ordinary short tasks. The authors present a two-stage recipe that takes Llama-3.1-8B-Instruct from its native 128K window to 1M, 2M, and 4M tokens.

All works

8 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

  1. DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT ModelsConference on Neural Information Processing Systems (NeurIPS)Boxin Wang, Weixin Chen, Hengzhi Pei, et al.2023 · 259 citations
  2. Efficient task-specific data valuation for nearest neighbor algorithms ↗Proceedings of the VLDB Endowment · no summary yetRuoxi Jia et al.2019 · 176 citations
  3. Reinforcement-Learning Based Portfolio Management with Augmented Asset Movement Prediction States ↗Proceedings of the AAAI Conference on Artificial Intelligence · no summary yetYunan Ye et al.2020 · 169 citations
  4. Realization of 2D metals at the ångström thickness limit ↗Nature · no summary yetJiaojiao Zhao et al.2025 · 97 citations
  5. T3: Tree-Autoencoder Constrained Adversarial Text Generation for Targeted Attack ↗Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · no summary yetBoxin Wang et al.2020 · 82 citations
  6. NVLM: Open Frontier-Class Multimodal LLMsarXiv:2409.11402Wenliang Dai, Nayeon Lee, Boxin Wang, et al.2024 · 44 citations
  7. Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy DistillationarXiv:2603.19220Zhuolin Yang, Zihan Liu, Yang Chen, et al.2026 · 16 citations
  8. From 128K to 4M: Efficient Training of Ultra-Long Context Large Language ModelsFindings of the Association for Computational LinguisticsChejian Xu, Wei Ping, Peng Xu, et al.2026 · 5 citations

 Co-authors here

12 of 22 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 316 times (of the 149,439 papers whose bibliographies we read); 61 citing papers with a page here →.

Updated

↑ back to top

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