🧑‍🔬 Xinyu Zhang

🏛️ Affiliations

🏢Zhipu AIBeijing · China2026 · 1 papercurrent🎓Wenzhou UniversityWenzhou · China2024–2025 · 5 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. MIRACL: A Multilingual Retrieval Dataset Covering 18 Diverse Languages (2023 · 149 citations)
   Neural retrieval research has relied mostly on large English collections such as MS MARCO. Resources for other languages tend to be small, machine-translated, synthetic, or designed for QA rather than passage search. MIRACL fills this gap with a monolingual ad hoc retrieval benchmark over Wikipedia in 18 languages…
2. PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning (2025 · 25 citations)
   Existing physics benchmarks for large language models (e.g., ScienceQA, SciBench, GPQA) mostly use short solutions of about 3–4 formulas and score only the final answer.
3. Qwen3-ASR Technical Report (2026 · 23 citations)
   The Qwen Team presents Qwen3-ASR, an open family of speech models built on the large audio-language model approach.
4. Qwen3-TTS Technical Report (2026 · 14 citations)
   Qwen3-TTS is the Qwen team's first text-to-speech family. It aims for synthesis that is multilingual, controllable through natural-language voice descriptions, able to clone a voice from roughly three seconds of audio, and fast enough for streaming. The models use a Qwen3 LM backbone in a dual-track setup: text and…
5. Beyond the Surface: Measuring Self-Preference in LLM Judgments (2025 · 10 citations)
   LLMs used as evaluators often favor their own outputs. Earlier work measured this by comparing the scores a judge gives its own answers with the scores it gives other models' answers. That approach cannot tell bias apart from genuine quality: a strong model may deserve its higher scores. The authors propose the DBG…
6. Glyph: Scaling Context Windows via Visual-Text Compression (2026 · 6 citations)
   Long-context LLMs usually scale by handling more text tokens, which raises compute and memory costs. Glyph takes a different route. Instead of enlarging the token window, it packs more source text into each token: documents are rendered as images and fed to a vision-language model. Built on GLM-4.1V-9B-Base, the…
7. Decoding-Unlearning: Fact Forgetting via Entropy-Guided Inference (2026)
   Large language models memorize copyrighted, private, or hazardous facts. Most unlearning methods remove them by fine-tuning, which is expensive and irreversible and requires forget and retain datasets. Pu et al. propose SEGUE, which forgets at inference time with no training and no change to weights. It has two stages:

🤝 Co-authors here

12 of 38 co-authors with a page, the most papers together first.

• Hongkun Hao ×2
• Pei Zhang ×2
• Xiong Wang ×2
• Zhifang Guo ×2
• Zishan Guo ×2
• Baosong Yang
• Basura Fernando
• Bin Zhang
• Chengyou Jia
• Ehsan Kamalloo
• Hangrui Hu
• Hao Wang

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) ×3: ACL 2026 ×2, ACL 2025
• Conference on Empirical Methods in Natural Language Processing (EMNLP): EMNLP 2025
• Transactions of the Association for Computational Linguistics (TACL): Transactions of the Association for Computational Linguistics (TACL) 2023

🔗 Cited by

Papers of our library cite their works 160 times (of the 149,439 papers whose bibliographies we read); 38 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/xinyu-zhang/