---
title: "Yang Liu — papers of 2025 — 11 papers, the most cited first"
description: "Yang Liu — papers of 2025: 11 papers on Elamur Research, the most cited first — what each work is about in our own words."
canonical: "https://research.elamur.ai/free/en/authors/yang-liu/year/2025/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/yang-liu/year/2025/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / [Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/) / 2025

# Yang Liu — papers of 2025 — 11 papers, the most cited first

11 papers · [all years of Yang Liu](https://md.research.elamur.ai/free/en/authors/yang-liu/#years)

- [Inference-Time Scaling for Generalist Reward Modeling arXiv:2504.02495](https://md.research.elamur.ai/free/en/papers/liu-2025-inference-time-scaling-generalist/) — Zijun Liu, Peiyi Wang, Runxin Xu, et al. · 2025 · 65 citations
- [Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy arXiv:2507.01352](https://md.research.elamur.ai/free/en/papers/liu-2025-skywork-reward-v2-scaling/) — Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, et al. · 2025 · 48 citations

**[Vision-Language Models Can Self-Improve Reasoning via Reflection](https://md.research.elamur.ai/free/en/papers/cheng-2025-vision-language-models-can-self/) [Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)](https://md.research.elamur.ai/free/en/venues/naacl/)**Kanzhi Cheng, Li YanTao, Fangzhi Xu, et al.*2025 · 35 citations*

- [InftyThink: Breaking the Length Limits of Long-Context Reasoning in Large Language Models arXiv:2503.06692](https://md.research.elamur.ai/free/en/papers/yan-2025-inftythink-breaking-length-limits-long/) — Yuchen Yan, Yongliang Shen, Yang Liu, et al. · 2025 · 29 citations

**[FinanceReasoning: Benchmarking Financial Numerical Reasoning More Credible, Comprehensive and Challenging](https://md.research.elamur.ai/free/en/papers/tang-2025-financereasoning-benchmarking-financial-numerical-reasoning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zichen Tang, Haihong E, Ziyan Ma, et al.*2025 · 13 citations*

**[Scaffolding Coordinates to Promote Vision-Language Coordination in Large Multi-Modal Models](https://md.research.elamur.ai/free/en/papers/lei-2025-scaffolding-coordinates-promote-vision-language/) [International Conference on Computational Linguistics (COLING)](https://md.research.elamur.ai/free/en/venues/coling/)**Xuanyu Lei, Zonghan Yang, Xinrui Chen, et al.*2025 · 11 citations*

- [Skywork R1V2: Multimodal Hybrid Reinforcement Learning for Reasoning arXiv:2504.16656](https://md.research.elamur.ai/free/en/papers/wang-2025-skywork-r1v2-multimodal-hybrid/) — Peiyu Wang, Yichen Wei, Yi Peng, et al. · 2025 · 10 citations

**[LogicPro: Improving Complex Logical Reasoning via Program-Guided Learning](https://md.research.elamur.ai/free/en/papers/jiang-2025-logicpro-improving-complex-logical-reasoning/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Jin Jiang, Yuchen Yan, Yang Liu, et al.*2025 · 8 citations*

**[G2: Guided Generation for Enhanced Output Diversity in LLMs](https://md.research.elamur.ai/free/en/papers/ruan-2025-g2-guided-generation-enhanced-output/) [Conference on Empirical Methods in Natural Language Processing (EMNLP)](https://md.research.elamur.ai/free/en/venues/emnlp/)**Zhiwen Ruan, Yixia Li, Yefeng Liu, et al.*2025 · 6 citations*

- [Skywork-R1V3 Technical Report arXiv:2507.06167](https://md.research.elamur.ai/free/en/papers/shen-2025-skywork-r1v3-technical-report/) — Wei Shen, Jiangbo Pei, Yi Peng, et al. · 2025 · 6 citations
- [Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs arXiv:2506.19290](https://md.research.elamur.ai/free/en/papers/zeng-2025-skywork-swe-unveiling-data/) — Liang Zeng, Yongcong Li, Yuzhen Xiao, et al. · 2025 · 3 citations