Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language Models (2025 · 20 citations)
Popular long-context tests such as needle-in-a-haystack ask a model to find one inserted sentence. Recent LLMs score almost perfectly on them, so these tests no longer separate strong models from weak ones. The authors propose Counting-Stars, a benchmark that measures how well a model gathers many scattered pieces of…
Hunyuan-MT Technical Report (2025 · 17 citations)
Open-source LLM translators still trail proprietary systems, and translation between Mandarin and China's minority languages gets little attention.
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine Translation (2026 · 10 citations)
Most strong LLM-based machine translation (MT) systems depend on costly external supervision, such as human-made reference translations or trained reward models, and this limits how far they can scale.
Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical Study (2025 · 9 citations)
LLM judges are increasingly used to grade other models, but their scores can be unstable and skewed by hidden biases.

All works

6 works of theirs in our library, the most cited first; 4 with a page here, the others link their original until we summarise them.

A Survey of On-Policy Distillation for Large Language Models ↗arXiv:2604.00626 · no summary yetMingyang Song, Mao Zheng2026 · 41 citations
Counting-Stars: A Multi-evidence, Position-aware, and Scalable Benchmark for Evaluating Long-Context Large Language ModelsInternational Conference on Computational Linguistics (COLING)Mingyang Song, Mao Zheng, Xuan Luo2025 · 20 citations
Hunyuan-MT Technical ReportarXiv:2509.05209Mao Zheng, Zheng Li, Bingxin Qu, et al.2025 · 17 citations
SSR-Zero: Simple Self-Rewarding Reinforcement Learning for Machine TranslationFindings of the Association for Computational LinguisticsWenjie Yang, Mao Zheng, Mingyang Song, et al.2026 · 10 citations
Can Many-Shot In-Context Learning Help LLMs as Evaluators? A Preliminary Empirical StudyInternational Conference on Computational Linguistics (COLING)Mingyang Song, Mao Zheng, Xuan Luo2025 · 9 citations
IFMTBench: A Comprehensive Benchmark for Multilingual Translation Instruction Following ↗arXiv:2605.28218 · no summary yetMingrui Sun et al.2026

Co-authors here

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

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

Papers of our library cite their works 97 times (of the 149,439 papers whose bibliographies we read); 18 citing papers with a page here →.

Updated 30 October 2026