--- title: "Xiao Luo — author profile and papers — Elamur Research" description: "Xiao Luo, University of Wisconsin–Madison: 11 papers on Elamur Research (2023–2026), h-index 30 — affiliations, topics, co-authors and…" canonical: "https://research.elamur.ai/free/en/authors/xiao-luo/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/xiao-luo/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Xiao Luo # Xiao Luo Xiao Luo has 11 papers in our library, in 2023–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Vision & language](https://md.research.elamur.ai/free/en/topics/multimodal/); often with [Junyu Luo](https://md.research.elamur.ai/free/en/authors/junyu-luo/), [Bohan Wu](https://md.research.elamur.ai/free/en/authors/bohan-wu/), [Ming Zhang](https://md.research.elamur.ai/free/en/authors/ming-zhang/). 11 papers in our library · 2023–2026 [OpenAlex](https://openalex.org/A5100426938) · [ORCID](https://orcid.org/0000-0002-7987-3714) · [Wikidata](https://www.wikidata.org/wiki/Q130853964) · [**h-index 30**](https://openalex.org/authors/A5100426938) · [271 works](https://openalex.org/works?filter=author.id:A5100426938) · [3,228 citations](https://openalex.org/works?filter=author.id:A5100426938&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 11 works in our library](https://md.research.elamur.ai/free/en/authors/xiao-luo/#papers) · [🔗 Cited 116 times in our library](https://md.research.elamur.ai/free/en/authors/xiao-luo/cited-by/) · [⭐ Paper Stars ranking: #7143](https://md.research.elamur.ai/free/en/paper-stars/page/72/#star-7143) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Xiao+Luo) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Xiao+Luo) · [dblp](https://dblp.org/search?q=Xiao+Luo) · [ACL Anthology](https://aclanthology.org/search/?q=Xiao+Luo) ## Affiliations [🎓**University of Wisconsin–Madison** Madison · United States 2025–2026 · 60 papersEmployment · Assistant Professor*current*](https://md.research.elamur.ai/free/en/universities/university-of-wisconsin-madison/) · [🎓**University of California, Los Angeles** Los Angeles · United States 2022–2026 · 107 papers](https://md.research.elamur.ai/free/en/universities/university-of-california-los-angeles/) · [🎓**Peking University** Beijing · China 2019–2025 · 35 papers](https://md.research.elamur.ai/free/en/universities/peking-university/) · [🏢**Alibaba Group** Hangzhou · China 2020–2021 · 11 papers](https://md.research.elamur.ai/free/en/companies/alibaba-group/) · [🏢**Alibaba DAMO Academy** Hangzhou · China 2020–2021 · 10 papers](https://md.research.elamur.ai/free/en/companies/alibaba-damo-academy/) · [🎓**Nankai University** Tianjin · China 2026 · 3 papers](https://md.research.elamur.ai/free/en/universities/nankai-university/) · [🎓**Toyota Technological Institute at Chicago** Chicago · United States 2022–2024 · 3 papers](https://md.research.elamur.ai/free/en/universities/toyota-technological-institute-at-chicago/) · [🔬**Shanghai Artificial Intelligence Laboratory** Shanghai · China 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/labs/shanghai-artificial-intelligence-laboratory/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 5 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 7 The field of science this work belongs to (OpenAlex fields).[Computer Science · 11 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Artificial Intelligence · 11 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Arts and Humanities · 8 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 8 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Computer Vision and Pattern Recognition · 4 works](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · [Information Systems · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/information-systems/) · [Computational Theory and Mathematics · 1 work](https://md.research.elamur.ai/free/en/shelves/computer-science/computational-theory-and-mathematics/) 🧭 Topics 6 Research subjects and languages the work is about.[Language models & pretraining · 8 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Reasoning · 3 works](https://md.research.elamur.ai/free/en/topics/reasoning/) · [Vision & language · 2 works](https://md.research.elamur.ai/free/en/topics/multimodal/) · [Evaluation & benchmarks · 1 work](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Information retrieval & search · 1 work](https://md.research.elamur.ai/free/en/topics/information-retrieval/) · [Efficient models & compression · 1 work](https://md.research.elamur.ai/free/en/topics/efficient-models/) ## Works by year ### 2020s [**2026** 6 papers](https://md.research.elamur.ai/free/en/authors/xiao-luo/year/2026/) · [**2025** 4 papers](https://md.research.elamur.ai/free/en/authors/xiao-luo/year/2025/) · [**2023** 1 paper](https://md.research.elamur.ai/free/en/authors/xiao-luo/year/2023/) ## Papers The most cited first (OpenAlex and our library). 1. **[Large Language Model Agent: A Survey on Methodology, Applications and Challenges](https://md.research.elamur.ai/free/en/papers/luo-2025-large-language-model-agent-survey/)** *(2025 · 62 citations)* Work on LLM-based agents has grown quickly but remains scattered. Existing reviews tend to cover one slice, such as games, deployment settings, multimodality or security, or they give broad overviews without a method-level breakdown. Luo et al. address this with a survey built around how agents are engineered. Its… 2. **[TransNormerLLM: A Faster and Better Large Language Model with Improved TransNormer](https://md.research.elamur.ai/free/en/papers/qin-2023-transnormerllm-faster-better-large/)** *(2023 · 33 citations)* Linear attention promises to remove the quadratic cost of softmax attention. In practice, earlier linear-attention models have trailed Transformers in language-modeling quality and rarely ran faster on real hardware. The authors close this gap with TransNormerLLM, a redesigned version of their TransNormer… 3. **[FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://md.research.elamur.ai/free/en/papers/luo-2025-finmme-benchmark-dataset-financial-multi/)** *(2025 · 19 citations)* FinMME addresses the lack of specialised benchmarks for testing multimodal large language models (MLLMs) on financial material, where charts are data-dense and interpretation requires expert knowledge. 4. **[Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMs](https://md.research.elamur.ai/free/en/papers/li-2025-towards-agentic-rag-deep-reasoning/)** *(2025 · 17 citations)* Large language models face two linked weaknesses. Their stored knowledge is fixed and can be wrong, and they struggle with problems that need several reasoning steps. Retrieval-Augmented Generation (RAG) addresses the first, and reasoning techniques such as Chain-of-Thought address the second. This survey argues that… 5. **[A Survey on Efficient Large Language Model Training: From Data-centric Perspectives](https://md.research.elamur.ai/free/en/papers/luo-2025-survey-efficient-large-language-model/)** *(2025 · 14 citations)* Post-training is the stage where LLMs acquire instruction following, alignment, reasoning and domain skills. 6. **[Context-attended Adversarial Reinforcement Learning for Robust Multi-step Retrieval Augmented Generation](https://md.research.elamur.ai/free/en/papers/ren-2026-context-attended-adversarial-reinforcement-learning/)** *(2026 · 1 citation)* Multi-step RAG systems retrieve evidence over several rounds. The resulting long contexts gather irrelevant noise and can also contain deliberately planted misinformation. Earlier defenses such as fine-tuning on fixed noisy data, verifier agents, or self-reflective reasoning were mostly tested with a single retrieval… 7. **[Easy Samples Are All You Need: Self-Evolving LLMs via Data-Efficient Reinforcement Learning](https://md.research.elamur.ai/free/en/papers/yu-2026-easy-samples-are-all-you/)** *(2026 · 1 citation)* Reinforcement learning for LLM reasoning usually depends either on expensive human-verified answers or on label-free rewards such as majority voting and entropy. 8. **[DANCE: Diversity-attended Dynamic Caching with Asymmetric Quantization for Test-time Adaptation of Vision-Language Models](https://md.research.elamur.ai/free/en/papers/zou-2026-dance-diversity-attended-dynamic-caching/)** *(2026)* The paper addresses test-time adaptation (TTA) of vision-language models such as CLIP, where only unlabeled test data arrive as a stream. 9. **[FLAIR: Steering LLM Mathematical Problem Solving based on A Fuzzy-Logic-AssIsted Reasoner](https://md.research.elamur.ai/free/en/papers/wu-2026-flair-steering-llm-mathematical-problem/)** *(2026)* LLMs solving math word problems usually follow one fixed reasoning style or a hard-coded pipeline. This ignores the fact that one solution attempt can contain several flaws at once, each with different severity. FLAIR (Fuzzy-Logic-AssIsted Reasoner) addresses this by treating the diagnosis of a partial solution as a… 10. **[GALA: Geometric Data Selection with Strategic Prospecting for Large Language Model Self-training](https://md.research.elamur.ai/free/en/papers/xie-2026-gala-geometric-data-selection-strategic/)** *(2026)* Self-training lets an LLM improve by learning from its own solutions. The standard rejection-sampling loop samples many reasoning paths and keeps those that reach the gold answer. This has three weaknesses: it spends compute on near-duplicate solutions, it tends to collapse onto a few dominant solving patterns, and… 11. **[InstructDiff: Domain-Adaptive Data Selection via Contrastive Entropy for Efficient LLM Fine-Tuning](https://md.research.elamur.ai/free/en/papers/su-2026-instructdiff-domain-adaptive-data-selection/)** *(2026)* Fine-tuning LLMs on entire instruction datasets is expensive and yields diminishing returns. Existing data-selection techniques also tend to work only in the domain they were designed for: methods tuned for general instruction-following transfer poorly to reasoning, and vice versa. InstructDiff addresses this with a… ## Co-authors here 12 of 47 co-authors with a page, the most papers together first. - [Junyu Luo](https://md.research.elamur.ai/free/en/authors/junyu-luo/) ×4 - [Bohan Wu](https://md.research.elamur.ai/free/en/authors/bohan-wu/) ×2 - [Ming Zhang](https://md.research.elamur.ai/free/en/authors/ming-zhang/) ×2 - [Wei Ju](https://md.research.elamur.ai/free/en/authors/wei-ju/) ×2 - [Weizhi Zhang](https://md.research.elamur.ai/free/en/authors/weizhi-zhang/) ×2 - [Yusheng Zhao](https://md.research.elamur.ai/free/en/authors/yusheng-zhao/) ×2 - [Zhiping Xiao](https://md.research.elamur.ai/free/en/authors/zhiping-xiao/) ×2 - [Ziyue Qiao](https://md.research.elamur.ai/free/en/authors/ziyue-qiao/) ×2 - [Bo Zhang](https://md.research.elamur.ai/free/en/authors/bo-zhang/) - [Chengzhong Liu](https://md.research.elamur.ai/free/en/authors/chengzhong-liu/) - [Chong Chen](https://md.research.elamur.ai/free/en/authors/chong-chen/) - [Chunkit Chan](https://md.research.elamur.ai/free/en/authors/chunkit-chan/) ## 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)](https://md.research.elamur.ai/free/en/venues/acl/) ×5: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×2, [ACL 2025](https://md.research.elamur.ai/free/en/venues/acl/2025/) ×2 - [Findings of the Association for Computational Linguistics](https://md.research.elamur.ai/free/en/venues/findings/) ×4: [Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/) ×4 ## Cited by Papers of our library cite their works 116 times (of the 149,439 papers whose bibliographies we read); [44 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/xiao-luo/cited-by/). Updated 2 November 2026