🧑‍🔬 Xianfeng Tang

🏛️ Affiliations

🏢AmazonSeattle · United States2023–2026 · 16 paperscurrent🎓Chengdu College of University of Electronic Science And Technology of ChinaChengdu · China2026 · 1 papercurrent🎓Southwest Jiaotong UniversityChengdu · China2026 · 1 papercurrent🎓University of Electronic Science and Technology of ChinaChengdu · China2026 · 1 papercurrent🎓Harbin Institute of TechnologyHarbin · China2005–2013 · 4 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution 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. A Comprehensive Survey of Small Language Models in the Era of Large Language Models: Techniques, Enhancements, Applications, Collaboration with LLMs, and Trustworthiness (2024 · 159 citations)
   LLMs such as Llama-3.1 405B are costly to run and fine-tune. They usually sit behind cloud APIs, which creates privacy risks, and they respond too slowly for on-device or real-time use. They can also fall short in specialised fields like medicine or law. This survey examines small language models (SLMs) as an…
2. Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphs (2024 · 89 citations)
   LLMs often hallucinate on knowledge-heavy questions. Standard retrieval augmentation treats each document as a separate unit, so it misses knowledge carried by links between texts, such as citations, co-purchases or legal references. Turning whole neighbourhoods into text is also impractical, because subgraphs grow…
3. Retrieval-Augmented Generation with Graphs (GraphRAG) (2025 · 87 citations)
   Conventional retrieval-augmented generation (RAG) stores knowledge as separate text or image chunks and finds them through lexical or embedding similarity.
4. SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models (2025 · 37 citations)
   The authors examine whether the common recipe of supervised fine-tuning followed by reinforcement learning, popularised by DeepSeek-R1, also works for Large Vision-Language Models (LVLMs).
5. ViLBench: A Suite for Vision-Language Process Reward Modeling (2025 · 9 citations)
   Process reward models (PRMs) score every reasoning step rather than only the final answer, which helps pick good solution paths.
6. Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intents (2026 · 2 citations)
   Tool-calling agents used in customer service often meet users whose requests lack key details, shift during the conversation, or break system policy.
7. Graph-Assisted Large Language Models: A Perspective on Mitigating Intrinsic Limitations (2026)
   This survey asks how graph structures can offset three built-in weaknesses of large language models. The first is knowledge: static training leads to outdated facts, errors, and unwanted memorization. The second is reasoning: token-by-token generation produces linear chains that cannot branch or backtrack. The third…

🤝 Co-authors here

12 of 41 co-authors with a page, the most papers together first.

• Fali Wang ×3
• Hui Liu ×3
• Qi He ×3
• Cihang Xie ×2
• Haoqin Tu ×2
• Hardy Chen ×2
• Suhang Wang ×2
• Xianren Zhang ×2
• Zhiwei Zhang ×2
• Bowen Jin
• Chen Luo
• Chulin Xie

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, Findings of the Association for Computational Linguistics 2024
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• ACM Transactions on Intelligent Systems and Technology: ACM Transactions on Intelligent Systems and Technology 2024
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025

🔗 Cited by

Papers of our library cite their works 211 times (of the 149,439 papers whose bibliographies we read); 49 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/xianfeng-tang/