🧑‍🔬 Xiachong Feng

🏛️ Affiliations

🎓Harbin Institute of TechnologyHarbin · China2018–2026 · 35 paperscurrent🎓University of Hong KongPok Fu Lam · China2024–2026 · 28 paperscurrent🔬Peng Cheng LaboratoryShenzhen · China2021–2026 · 21 paperscurrent

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. Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language Models (2024 · 129 citations)
   Open-source large vision-language models (LVLMs) handle natural photos well but often fail on abstract visuals such as scientific plots and geometric diagrams.
2. Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced Optimization (2025 · 11 citations)
   The paper addresses faithfulness hallucination in retrieval-augmented long-form question answering (LFQA), where a model writes paragraph-length answers containing claims that the retrieved documents do not support or that contradict them.
3. Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation Engineering (2026 · 4 citations)
   Large language models and vision-language models reason noticeably worse in non-English languages, especially low-resource ones such as Thai and Swahili.
4. x1: Learning to Think Adaptively Across Languages and Cultures (2026 · 1 citation)
   Most reasoning LLMs think mainly in one dominant language, usually English, even when a question is posed in another language or depends on a specific culture.
5. Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Management (2026)
   LLM agents working on long-horizon tasks need a memory system that turns a stream of incoming text chunks into a compact, usable store.
6. ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language Models (2026)
   Existing memory benchmarks for LLM agents, such as LoCoMo, LongMemEval and MemoryAgentBench, test whether a model can deliberately retrieve stored facts when asked.

All works

7 works of theirs in our library, the most cited first; 6 with a page here, the others link their original until we summarise them.

1. Multimodal ArXiv: A Dataset for Improving Scientific Comprehension of Large Vision-Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Lei Li, Yuqi Wang, Runxin Xu, et al.2024 · 129 citations
2. Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization ↗Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · no summary yetXiachong Feng et al.2021 · 119 citations
3. Improving Contextual Faithfulness of Large Language Models via Retrieval Heads-Induced OptimizationAnnual Meeting of the Association for Computational Linguistics (ACL)Lei Huang, Xiaocheng Feng, Weitao Ma, et al.2025 · 11 citations
4. Unlocking Multilingual Reasoning Capability of LLMs and LVLMs through Representation EngineeringAnnual Meeting of the Association for Computational Linguistics (ACL)Qiming Li, Xiaocheng Feng, Yixuan Ma, et al.2026 · 4 citations
5. x1: Learning to Think Adaptively Across Languages and CulturesFindings of the Association for Computational LinguisticsYangfan Ye, Xiaocheng Feng, Xiachong Feng, et al.2026 · 1 citation
6. Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory ManagementAnnual Meeting of the Association for Computational Linguistics (ACL)Weitao Ma, Xiaocheng Feng, Lei Huang, et al.2026
7. ImplicitMemBench: Measuring Unconscious Behavioral Adaptation in Large Language ModelsAnnual Meeting of the Association for Computational Linguistics (ACL)Chonghan Qin, Xiachong Feng, Weitao Ma, et al.2026

🤝 Co-authors here

12 of 24 co-authors with a page, the most papers together first.

• Xiaocheng Feng ×5
• Weitao Ma ×4
• Bing Qin ×3
• Lei Huang ×3
• Dandan Tu ×2
• Lingpeng Kong ×2
• Yangfan Ye ×2
• Yunfei Lu ×2
• Baoxin Wang
• Dayong Wu
• Guoping Hu
• Jun Xu

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) ×5: ACL 2026 ×3, ACL 2025, ACL 2024
• Findings of the Association for Computational Linguistics: Findings of the Association for Computational Linguistics 2026
• Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

🔗 Cited by

Papers of our library cite their works 153 times (of the 149,439 papers whose bibliographies we read); 33 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/xiachong-feng/