🧑‍🔬 Chenxu Yang

🏛️ Affiliations

🎓Qinghai Normal UniversityXining · China2022–2026 · 23 paperscurrent🏛️Chinese Academy of SciencesBeijing · China2022–2026 · 17 paperscurrent🔬Institute of Information EngineeringBeijing · China2022–2026 · 17 paperscurrent🎓University of Chinese Academy of SciencesBeijing · China2022–2026 · 10 paperscurrent🎓Tianjin Chengjian UniversityTianjin · China2024–2026 · 8 paperscurrent🎓Hunan UniversityChangsha · China2023–2025 · 3 papers🎓University of Electronic Science and Technology of ChinaChengdu · China2022–2023 · 2 papers🎓Zhengzhou UniversityZhengzhou · China2022–2023 · 2 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 9 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

📄 Papers

The most cited first (OpenAlex and our library).

1. Dynamic Early Exit in Reasoning Models (2025 · 74 citations)
   Large reasoning models such as DeepSeek-R1 and GPT-O1 often produce very long chains of thought (CoT). This "overthinking" adds latency and compute cost, and it can also turn a correct line of reasoning into a wrong one. In pilot runs, the authors forced models to answer at different points in their reasoning. Many…
2. Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense Inference (2025 · 9 citations)
   LLM-based chatbots often fall short on empathy and emotional support in multi-turn conversations, even when they are given commonsense knowledge.
3. VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization (2026)
   During LLM inference, the KV cache grows with context length and takes up a large share of GPU memory. Vector quantization (VQ) can shrink it flexibly across bit-widths, but at very low bit-widths accuracy drops sharply. The authors trace this to outliers in the key cache, which sit far from the learned centroids and…

All works

4 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

1. Dynamic Early Exit in Reasoning ModelsarXiv:2504.15895Chenxu Yang, Qingyi Si, Yongjie Duan, et al.2025 · 74 citations
2. Self-Distilled RLVR ↗arXiv:2604.03128 · no summary yetChenxu Yang et al.2026 · 37 citations
3. Sibyl: Empowering Empathetic Dialogue Generation in Large Language Models via Sensible and Visionary Commonsense InferenceInternational Conference on Computational Linguistics (COLING)Lanrui Wang, Jiangnan Li, Chenxu Yang, et al.2025 · 9 citations
4. VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector QuantizationAnnual Meeting of the Association for Computational Linguistics (ACL)Dingyu Yao, Chenxu Yang, Zhengyang Tong, et al.2026

🤝 Co-authors here

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

• Weiping Wang ×3
• Zheng Lin ×3
• Chenyu Zhu
• Huan Liu
• Jian Luan
• Jiangnan Li
• Jingang Wang
• Qingyi Si
• Wei Liu
• Yanan Cao

Venues

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

• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• International Conference on Computational Linguistics (COLING): COLING 2025

🔗 Cited by

Papers of our library cite their works 118 times (of the 149,439 papers whose bibliographies we read); 36 citing papers with a page here →.

Updated 2 November 2026

↑ back to top

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