Elamur Research⌕
☰
home / authors / Xiangyu Wu

Xiangyu Wu

Xiangyu Wu has 3 papers in our library, in 2026, most of them on Reasoning, Vision & language; often with Guorui Zhou, Hao LU, Jiaqi Tang.

3 papers in our library · 2026

OpenAlex · ORCID · h-index 7 · 31 works · 319 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 25 times in our library · ⭐ Paper Stars ranking: #8571

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🏢KuaishouBeijing · China2026 · 1 papercurrent🎓Nanjing University of Science and TechnologyNanjing · China2026 · 1 papercurrent🎓China Agricultural UniversityBeijing · China2019–2025 · 9 papers🎓Guangdong University of TechnologyGuangzhou · China2018–2023 · 6 papers🎓Guangdong Pharmaceutical UniversityGuangzhou · China2007–2015 · 5 papers🎓South China Normal UniversityGuangzhou · China2017 · 4 papers🎓Hong Kong Polytechnic UniversityHong Kong · China2014–2015 · 3 papers🏛️Ministry of Agriculture and Rural AffairsBeijing · China2022–2023 · 2 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.

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 3 worksComputer Science · 3 worksArtificial Intelligence · 3 worksLanguage and Linguistics · 3 worksInformation Systems · 2 works

🧭 Topics 2Research subjects and languages the work is about.Reasoning · 2 worksVision & language · 1 work

 Works by year

2020s

20263 papers

 Papers

The most cited first (OpenAlex and our library).

  1. Unlocking Exploration in RLVR: Uncertainty-aware Advantage Shaping for Deeper Reasoning (2026 · 15 citations)
    Standard RLVR algorithms such as GRPO give every token in a sampled response the same advantage. They cannot tell pivotal reasoning decisions from routine ones, so the policy settles too early on a few safe trajectories and suffers entropy collapse. The authors, from Kuaishou Technology, propose UCAS…
  2. OneRec-Think: In-Text Reasoning for Generative Recommendation (2026 · 10 citations)
    Generative recommenders such as OneRec decode item identifiers directly. This makes them implicit predictors: they cannot produce explicit, controllable reasoning the way modern LLMs do. OneRec-Think, developed at Kuaishou, addresses this by placing dialogue, textual reasoning and personalized recommendation in a…
  3. LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization (2026 · 3 citations)
    GUI agents built on multimodal LLMs often click or point at the wrong spot. Supervised Fine-Tuning (SFT) handles coordinates poorly. Earlier reinforcement-learning approaches judge location coarsely, using text matching, fixed IoU thresholds, or rigid decision boundaries. UI-TARS-style DPO also needs hand-built…

 Co-authors here

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

Venues

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

 Cited by

Papers of our library cite their works 25 times (of the 149,439 papers whose bibliographies we read); 10 citing papers with a page here →.

Updated

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