| Do NOT Think That Much for 2+ 3=? On the Overthinking of Long Reasoning Models X Chen, J Xu, T Liang, Z He, J Pang, D Yu, L Song, Q Liu, M Zhou, ... Forty-second International Conference on Machine Learning, 0 | 367* | |
| Thoughts are all over the place: On the underthinking of o1-like llms Y Wang, Q Liu, J Xu, T Liang, X Chen, Z He, L Song, D Yu, J Li, Z Zhang, ... arXiv preprint arXiv:2501.18585, 2025 | 130* | 2025 |
| Deepmath-103k: A large-scale, challenging, decontaminated, and verifiable mathematical dataset for advancing reasoning Z He, T Liang, J Xu, Q Liu, X Chen, Y Wang, L Song, D Yu, Z Liang, ... arXiv preprint arXiv:2504.11456, 2025 | 111* | 2025 |
| La-hcn: label-based attention for hierarchical multi-label text classification neural network X Zhang, J Xu, C Soh, L Chen Expert Systems with Applications 187, 115922, 2022 | 73 | 2022 |
| Refuse whenever you feel unsafe: Improving safety in llms via decoupled refusal training Y Yuan, W Jiao, W Wang, J Huang, J Xu, T Liang, P He, Z Tu Proceedings of the 63rd Annual Meeting of the Association for Computational …, 2025 | 50* | 2025 |
| Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability Z Lin, T Liang, J Xu, Q Lin, X Wang, R Luo, C Shi, S Li, Y Yang, Z Tu arXiv preprint arXiv:2411.19943, 2024 | 40 | 2024 |
| SimCSE++: Improving contrastive learning for sentence embeddings from two perspectives J Xu, W Shao, L Chen, L Liu arXiv preprint arXiv:2305.13192, 2023 | 34 | 2023 |
| The first few tokens are all you need: An efficient and effective unsupervised prefix fine-tuning method for reasoning models K Ji, J Xu, T Liang, Q Liu, Z He, X Chen, X Liu, Z Wang, J Chen, B Wang, ... arXiv preprint arXiv:2503.02875, 2025 | 21 | 2025 |
| On synthetic data for back translation J Xu, Y Ruan, W Bi, G Huang, S Shi, L Chen, L Liu Proceedings of the 2022 Conference of the north american chapter of the …, 2022 | 15 | 2022 |
| Findings of the WMT 2024 shared task on discourse-level literary translation L Wang, S Liu, C Lyu, W Jiao, X Wang, J Xu, Z Tu, Y Gu, W Chen, M Wu, ... arXiv preprint arXiv:2412.11732, 2024 | 14 | 2024 |
| Transagents: Build your translation company with language agents M Wu, J Xu, L Wang Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024 | 12 | 2024 |
| BlendCSE: Blend contrastive learnings for sentence embeddings with rich semantics and transferability J Xu, CS Zhanyi, L Xu, L Chen Expert Systems with Applications 238, 121909, 2024 | 11 | 2024 |
| Dancing with critiques: Enhancing llm reasoning with stepwise natural language self-critique Y Li, J Xu, T Liang, X Chen, Z He, Q Liu, R Wang, Z Zhang, Z Tu, H Mi, ... arXiv preprint arXiv:2503.17363, 2025 | 9 | 2025 |
| Deeptheorem: Advancing llm reasoning for theorem proving through natural language and reinforcement learning Z Zhang, J Xu, Z He, T Liang, Q Liu, Y Li, L Song, Z Liang, Z Zhang, ... arXiv preprint arXiv:2505.23754, 2025 | 8 | 2025 |
| (perhaps) beyond human translation: Harnessing multi-agent collaboration for translating ultra-long literary texts M Wu, J Xu, Y Yuan, G Haffari, L Wang, W Luo, K Zhang arXiv preprint arXiv:2405.11804, 2024 | 8 | 2024 |
| Learn from heterophily: Heterophilous information-enhanced graph neural network Y Zheng, J Xu, L Chen arXiv preprint arXiv:2403.17351, 2024 | 8 | 2024 |
| DistillCSE: Distilled contrastive learning for sentence embeddings J Xu, W Shao, L Chen, L Liu arXiv preprint arXiv:2310.13499, 2023 | 8 | 2023 |
| FanChuan: A Multilingual and Graph-Structured Benchmark For Parody Detection and Analysis Y Zheng, S Li, F Wu, Y Ziyi, L Hongchao, Z Hu, C Xinjun, Z Wang, J Chen, ... arXiv preprint arXiv:2502.16503, 2025 | 7 | 2025 |
| RaSA: Rank-sharing low-rank adaptation Z He, Z Tu, X Wang, X Chen, Z Wang, J Xu, T Liang, W Jiao, Z Zhang, ... arXiv preprint arXiv:2503.12576, 2025 | 5 | 2025 |
| Two experts are all you need for steering thinking: Reinforcing cognitive effort in moe reasoning models without additional training M Wang, X Chen, Y Wang, Z He, J Xu, T Liang, Q Liu, Y Yao, W Wang, ... arXiv preprint arXiv:2505.14681, 2025 | 4 | 2025 |
Zhaopeng TuTech Lead @ Tencent Hunyuan Digital HumanVerified email at tencent.com
