🧑‍🔬 Ping Wang

🏛️ Affiliations

🎓Peking UniversityBeijing · China2003–2026 · 172 papersEmployment · Professorcurrent🎓Wuhan UniversityWuhan · China1998–2026 · 2 paperscurrent🎓Nanyang Technological UniversitySingapore · Singapore2008–2017 · 15 papers🏛️Chinese Academy of SciencesBeijing · China2010–2025 · 12 papers🎓Kun Shan UniversityTainan City · Taiwan2008–2024 · 10 papers🎓Tongji UniversityShanghai · China2009–2022 · 10 papers🎓York UniversityToronto · Canada2018–2025 · 7 papers🎓St. Francis Xavier UniversityAntigonish · Canada2004–2020 · 7 papers🎓Chongqing University of Posts and TelecommunicationsChongqing · China2012–2025 · 6 papers🎓Shandong University of Science and TechnologyQingdao · China2010–2025 · 6 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 115 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.

📅 Works by year

2020s

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. K-BERT: Enabling Language Representation with Knowledge Graph (2019 · 1,019 citations)
   BERT-style encoders trained on open-domain text know little about specialised fields such as medicine, law or finance, and pre-training a domain model from scratch is expensive.
2. SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers (2025 · 9 citations)
   Long-context inference with LLMs is limited by the GPU memory consumed by the KV cache. Earlier token eviction, merging and quantization methods compress deep layers well, but shallow layers resist them. In a preliminary analysis of LLaMA2-7B-chat on 2WikiMQA, the authors found two patterns. Deep layers concentrate…
3. Faster MoE LLM Inference for Extremely Large Models (2026 · 8 citations)
   Fine-grained Mixture-of-Experts models such as DeepSeek-V3 route each token through many small experts. Their inference cost therefore depends heavily on how many experts are activated, yet these models usually apply the same Top-k to every token. The authors study training-free expert skipping at inference time…
4. The Dark Side of Function Calling: Pathways to Jailbreaking Large Language Models (2025 · 8 citations)
   Most jailbreaking research looks at the chat interface of LLMs. This paper asks whether function calling, where a model fills in arguments for user-defined tools, opens a separate route around safety alignment. The authors design a "jailbreak function" attack. A fictional tool called WriteNovel is defined with a…
5. RACER: Retrieval-Augmented Contextual Rapid Speculative Decoding (2026 · 1 citation)
   Large language models decode one token at a time, which makes inference slow. Speculative decoding speeds this up by drafting several tokens and checking them in parallel with the target model. Training-free variants have two weaknesses. Retrieval-based drafters fail when the context contains no exact match.…

🤝 Co-authors here

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

• Zuchao Li ×3
• Hai Zhao ×2
• Lefei Zhang ×2
• Baoyuan Qi
• Haotang Deng
• Liu Guoming
• Peng Zhou
• Qi Ju
• Shi Luohe
• Weijie Liu
• Zhe Zhao
• Zhiruo Wang

Venues

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

• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2025
• International Conference on Computational Linguistics (COLING): COLING 2025
• Proceedings of the AAAI Conference on Artificial Intelligence: Proceedings of the AAAI Conference on Artificial Intelligence 2019

🔗 Cited by

Papers of our library cite their works 233 times (of the 149,439 papers whose bibliographies we read); 23 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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