Research

Publications

• MiroEval: Benchmarking Multimodal Deep Research Agents in Process and Outcome
  F Ye, Y Hu, P Zhu, Y Li, Z Jin, Y Xiao, Y Wang, L Wang, Z Zhang, L Wang, ...
  arXiv preprint arXiv:2603.28407, 2026 • 2026
• Self-Rewarding Sequential Monte Carlo for Masked Diffusion Language Models
  Z Luo, Z Jin, L Wang, L Bing, TB Schön
  arXiv preprint arXiv:2602.01849, 2026 • 2026
• MARS: Enabling Autoregressive Models Multi-Token Generation
  Z Jin, L Wang, Z Luo, A Sun
  arXiv preprint arXiv:2604.07023, 2026 • 2026
• Document Reconstruction Unlocks Scalable Long-Context RLVR
  Y Xiao, L Wang, Y Deng, G Chen, Z Jin, J Kim, X Li, RK Lee, L Bing
  arXiv preprint arXiv:2602.08237, 2026 • 2026
• Sailor2: sailing in south-east Asia with inclusive multilingual LLMs
  L Dou, Q Liu, F Zhou, C Chen, Z Wang, Z Jin, Z Liu, T Zhu, C Du, P Yang, ...
  arXiv preprint arXiv:2502.12982, 2025 • 2025
• As simple as fine-tuning: Llm alignment via bidirectional negative feedback loss
  X Mao, H Xu, FL Li, Z Jin, W Chen, W Zhang, AT Luu
  International Conference on Learning Representations 2025, 30610-30631, 2025 • 2025
• On the Role of Discreteness in Diffusion LLMs
  Z Jin, B Wang, X Lin, L Bing, A Sun
  arXiv preprint arXiv:2512.22630, 2025 • 2025
• Sailor: Open language models for south-east asia
  L Dou, Q Liu, G Zeng, J Guo, J Zhou, X Mao, Z Jin, W Lu, M Lin
  Proceedings of the 2024 Conference on Empirical Methods in Natural Language …, 2024 • 2024
• Self-harmonized chain of thought
  Z Jin, W Lu
  NAACL 2025, 2024 • 2024
• Tab-cot: Zero-shot tabular chain of thought
  J Ziqi, W Lu
  Findings of the Association for Computational Linguistics: ACL 2023, 10259-10277, 2023 • 2023