Haitao Mi

157 papers A* 25A 1B 6C 1Misc 1Journal 90Unranked 33
YearRankTypeTitle / Venue / Authors
2026 J jnl
DocDancer: Towards Agentic Document-Grounded Information Seeking.
CoRR
Qintong Zhang, Xinjie Lv, Jialong Wu, Baixuan Li, Zhengwei Tao, Guochen Yan, Huanyao Zhang, Bin Wang, Jiahao Xu, Haitao Mi, Wentao Zhang
2026 J jnl
Exploring Information Seeking Agent Consolidation.
CoRR
Guochen Yan, Jialong Wu, Zhengwei Tao, Bo Li, Qintong Zhang, Jiahao Xu, Haitao Mi, Yuejian Fang, Qingni Shen, Wentao Zhang, Zhonghai Wu
2026 J jnl
Free(): Learning to Forget in Malloc-Only Reasoning Models.
CoRR
Yilun Zheng, Dongyang Ma, Tian Liang, Jiahao Xu, Xinting Huang, Lihui Chen, Haitao Mi, Yan Wang
2026 J jnl
Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning.
CoRR
Kishan Panaganti, Zhenwen Liang, Wenhao Yu, Haitao Mi, Dong Yu
2026 J jnl
Inference-Time Scaling of Verification: Self-Evolving Deep Research Agents via Test-Time Rubric-Guided Verification.
CoRR
Yuxuan Wan, Tianqing Fang, Zaitang Li, Yintong Huo, Wenxuan Wang, Haitao Mi, Dong Yu, Michael R. Lyu
2026 J jnl
Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories.
CoRR
Sidi Lu, Zhenwen Liang, Dongyang Ma, Yan Wang, Haitao Mi, Dong Yu
2026 J jnl
RAGShaper: Eliciting Sophisticated Agentic RAG Skills via Automated Data Synthesis.
CoRR
Zhengwei Tao, Bo Li, Jialong Wu, Guochen Yan, Huanyao Zhang, Jiahao Xu, Haitao Mi, Wentao Zhang
2026 J jnl
Save the Good Prefix: Precise Error Penalization via Process-Supervised RL to Enhance LLM Reasoning.
CoRR
Haolin Liu, Dian Yu, Sidi Lu, Yujun Zhou, Rui Liu, Zhenwen Liang, Haitao Mi, Chen-Yu Wei, Dong Yu
2026 J jnl
The Pensieve Paradigm: Stateful Language Models Mastering Their Own Context.
CoRR
Xiaoyuan Liu, Tian Liang, Dongyang Ma, Deyu Zhou, Haitao Mi, Pinjia He, Yan Wang
2026 J jnl
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models.
Trans. Mach. Learn. Res.
Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Hongming Zhang, Zhisong Zhang, Haitao Mi, Dong Yu
2026 J jnl
Verified Critical Step Optimization for LLM Agents.
CoRR
Mukai Li, Qingcheng Zeng, Tianqing Fang, Zhenwen Liang, Linfeng Song, Qi Liu, Haitao Mi, Dong Yu
2026 — conf
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms.
EACL (Volume 2: Short Papers)
Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, Dong Yu
2025 J jnl
CDE: Curiosity-Driven Exploration for Efficient Reinforcement Learning in Large Language Models.
CoRR
Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, Dong Yu
2025 J jnl
CLUE: Non-parametric Verification from Experience via Hidden-State Clustering.
CoRR
Zhenwen Liang, Ruosen Li, Yujun Zhou, Linfeng Song, Dian Yu, Xinya Du, Haitao Mi, Dong Yu
2025 J jnl
Can LLMs Guide Their Own Exploration? Gradient-Guided Reinforcement Learning for LLM Reasoning.
CoRR
Zhenwen Liang, Sidi Lu, Wenhao Yu, Kishan Panaganti, Yujun Zhou, Haitao Mi, Dong Yu
2025 J jnl
Cognitive Kernel-Pro: A Framework for Deep Research Agents and Agent Foundation Models Training.
CoRR
Tianqing Fang, Zhisong Zhang, Xiaoyang Wang, Rui Wang, Can Qin, Yuxuan Wan, Jun-Yu Ma, Ce Zhang, Jiaqi Chen, Xiyun Li, Hongming Zhang, Haitao Mi, Dong Yu
2025 J jnl
Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains.
CoRR
Yi Su, Dian Yu, Linfeng Song, Juntao Li, Haitao Mi, Zhaopeng Tu, Min Zhang, Dong Yu
2025 A* conf
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search.
ICLR
Murong Yue, Wenlin Yao, Haitao Mi, Dian Yu, Ziyu Yao, Dong Yu
2025 J jnl
Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique.
CoRR
Yansi Li, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Qiuzhi Liu, Rui Wang, Zhuosheng Zhang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 J jnl
DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains.
CoRR
Tian Liang, Wenxiang Jiao, Zhiwei He, Jiahao Xu, Haitao Mi, Dong Yu
2025 J jnl
DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning.
CoRR
Zhiwei He, Tian Liang, Jiahao Xu, Qiuzhi Liu, Xingyu Chen, Yue Wang, Linfeng Song, Dian Yu, Zhenwen Liang, Wenxuan Wang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 J jnl
DeepTheorem: Advancing LLM Reasoning for Theorem Proving Through Natural Language and Reinforcement Learning.
CoRR
Ziyin Zhang, Jiahao Xu, Zhiwei He, Tian Liang, Qiuzhi Liu, Yansi Li, Linfeng Song, Zhengwen Liang, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 A* conf
Do NOT Think That Much for 2+3=? On the Overthinking of Long Reasoning Models.
ICML
Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 — conf
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls.
ACL (1)
Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu
2025 J jnl
Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls.
CoRR
Ante Wang, Linfeng Song, Ye Tian, Dian Yu, Haitao Mi, Xiangyu Duan, Zhaopeng Tu, Jinsong Su, Dong Yu
2025 J jnl
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving.
CoRR
Mukai Li, Linfeng Song, Zhenwen Liang, Jiahao Xu, Shansan Gong, Qi Liu, Haitao Mi, Dong Yu
2025 J jnl
Enhancing Web Agents with Explicit Rollback Mechanisms.
CoRR
Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, Dong Yu
2025 B conf
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models.
COLING
Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi, Baolin Peng, Dong Yu
2025 J jnl
Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values.
CoRR
Dian Yu, Yulai Zhao, Kishan Panaganti, Linfeng Song, Haitao Mi, Dong Yu
2025 J jnl
Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation.
CoRR
Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, Dong Yu
2025 J jnl
Explore to Evolve: Scaling Evolved Aggregation Logic via Proactive Online Exploration for Deep Research Agents.
CoRR
Rui Wang, Ce Zhang, Jun-Yu Ma, Jianshu Zhang, Hongru Wang, Yi Chen, Boyang Xue, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu, Kam-Fai Wong
2025 J jnl
Guided Self-Evolving LLMs with Minimal Human Supervision.
CoRR
Wenhao Yu, Zhenwen Liang, Chengsong Huang, Kishan Panaganti, Tianqing Fang, Haitao Mi, Dong Yu
2025 J jnl
Improving LLM General Preference Alignment via Optimistic Online Mirror Descent.
CoRR
Yuheng Zhang, Dian Yu, Tao Ge, Linfeng Song, Zhichen Zeng, Haitao Mi, Nan Jiang, Dong Yu
2025 J jnl
InComeS: Integrating Compression and Selection Mechanisms into LLMs for Efficient Model Editing.
CoRR
Shuaiyi Li, Zhisong Zhang, Yang Deng, Chenlong Deng, Tianqing Fang, Hongming Zhang, Haitao Mi, Dong Yu, Wai Lam
2025 A* conf
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning.
ICLR
Yuheng Zhang, Dian Yu, Baolin Peng, Linfeng Song, Ye Tian, Mingyue Huo, Nan Jiang, Haitao Mi, Dong Yu
2025 A* conf
LiteSearch: Efficient Tree Search with Dynamic Exploration Budget for Math Reasoning.
AAAI
Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Dian Yu, Haitao Mi, Jinsong Su, Dong Yu
2025 — conf
Low-Bit Quantization Favors Undertrained LLMs.
ACL (1)
Xu Ouyang, Tao Ge, Thomas Hartvigsen, Zhisong Zhang, Haitao Mi, Dong Yu
2025 J jnl
MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation.
CoRR
Zhenwen Liang, Linfeng Song, Yang Li, Tao Yang, Feng Zhang, Haitao Mi, Dong Yu
2025 J jnl
MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment.
CoRR
Yucheng Shi, Wenhao Yu, Zaitang Li, Yonglin Wang, Hongming Zhang, Ninghao Liu, Haitao Mi, Dong Yu
2025 J jnl
One Token to Fool LLM-as-a-Judge.
CoRR
Yulai Zhao, Haolin Liu, Dian Yu, S. Y. Kung, Haitao Mi, Dong Yu
2025 J jnl
R-Zero: Self-Evolving Reasoning LLM from Zero Data.
CoRR
Chengsong Huang, Wenhao Yu, Xiaoyang Wang, Hongming Zhang, Zongxia Li, Ruosen Li, Jiaxin Huang, Haitao Mi, Dong Yu
2025 A* conf
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation.
EMNLP
Jun-Yu Ma, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu
2025 J jnl
Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation.
CoRR
Junyu Ma, Tianqing Fang, Zhisong Zhang, Hongming Zhang, Haitao Mi, Dong Yu
2025 J jnl
Self-Rewarding Vision-Language Model via Reasoning Decomposition.
CoRR
Zongxia Li, Wenhao Yu, Chengsong Huang, Rui Liu, Zhenwen Liang, Fuxiao Liu, Jingxi Che, Dian Yu, Jordan L. Boyd-Graber, Haitao Mi, Dong Yu
2025 — conf
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching.
ACL (Findings)
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Yipeng Zhang, Haitao Mi, Helen M. Meng
2025 J jnl
Stable and Efficient Single-Rollout RL for Multimodal Reasoning.
CoRR
Rui Liu, Dian Yu, Lei Ke, Haolin Liu, Yujun Zhou, Zhenwen Liang, Haitao Mi, Pratap Tokekar, Dong Yu
2025 J jnl
The End of Manual Decoding: Towards Truly End-to-End Language Models.
CoRR
Zhichao Wang, Dongyang Ma, Xinting Huang, Deng Cai, Tian Lan, Jiahao Xu, Haitao Mi, Xiaoying Tang, Yan Wang
2025 J jnl
The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models.
CoRR
Ke Ji, Jiahao Xu, Tian Liang, Qiuzhi Liu, Zhiwei He, Xingyu Chen, Xiaoyuan Liu, Zhijie Wang, Junying Chen, Benyou Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 J jnl
Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs.
CoRR
Yue Wang, Qiuzhi Liu, Jiahao Xu, Tian Liang, Xingyu Chen, Zhiwei He, Linfeng Song, Dian Yu, Juntao Li, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 J jnl
Towards Solving More Challenging IMO Problems via Decoupled Reasoning and Proving.
CoRR
Zhenwen Liang, Linfeng Song, Yang Li, Tao Yang, Feng Zhang, Haitao Mi, Dong Yu
2025 J jnl
Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards.
CoRR
Xiaoyuan Liu, Tian Liang, Zhiwei He, Jiahao Xu, Wenxuan Wang, Pinjia He, Zhaopeng Tu, Haitao Mi, Dong Yu
2025 J jnl
Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training.
CoRR
Mengru Wang, Xingyu Chen, Yue Wang, Zhiwei He, Jiahao Xu, Tian Liang, Qiuzhi Liu, Yunzhi Yao, Wenxuan Wang, Ruotian Ma, Haitao Mi, Ningyu Zhang, Zhaopeng Tu, Xiaolong Li, Dong Yu
2025 J jnl
UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression.
CoRR
Chenlong Deng, Zhisong Zhang, Kelong Mao, Shuaiyi Li, Tianqing Fang, Hongming Zhang, Haitao Mi, Dong Yu, Zhicheng Dou
2025 J jnl
VOGUE: Guiding Exploration with Visual Uncertainty Improves Multimodal Reasoning.
CoRR
Rui Liu, Dian Yu, Tong Zheng, Runpeng Dai, Zongxia Li, Wenhao Yu, Zhenwen Liang, Linfeng Song, Haitao Mi, Pratap Tokekar, Dong Yu
2025 J jnl
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models.
CoRR
Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Hongming Zhang, Zhisong Zhang, Yaqi Xie, Katia P. Sycara, Haitao Mi, Dong Yu
2025 — conf
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback.
EMNLP (Findings)
Minda Hu, Tianqing Fang, Jianshu Zhang, Jun-Yu Ma, Zhisong Zhang, Jingyan Zhou, Hongming Zhang, Haitao Mi, Dong Yu, Irwin King
2025 J jnl
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback.
CoRR
Minda Hu, Tianqing Fang, Jianshu Zhang, Junyu Ma, Zhisong Zhang, Jingyan Zhou, Hongming Zhang, Haitao Mi, Dong Yu, Irwin King
2025 A* conf
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model.
EMNLP
Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, Dong Yu
2025 J jnl
WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model.
CoRR
Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, Dong Yu
2024 — conf
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation.
LREC/COLING
Xiangci Li, Linfeng Song, Lifeng Jin, Haitao Mi, Jessica Ouyang, Dong Yu
2024 J jnl
A Knowledge Plug-and-Play Test Bed for Open-domain Dialogue Generation.
CoRR
Xiangci Li, Linfeng Song, Lifeng Jin, Haitao Mi, Jessica Ouyang, Dong Yu
2024 J jnl
Collaborative decoding of critical tokens for boosting factuality of large language models.
CoRR
Lifeng Jin, Baolin Peng, Linfeng Song, Haitao Mi, Ye Tian, Dong Yu
2024 J jnl
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search.
CoRR
Murong Yue, Wenlin Yao, Haitao Mi, Dian Yu, Ziyu Yao, Dong Yu
2024 J jnl
Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs.
CoRR
Xingyu Chen, Jiahao Xu, Tian Liang, Zhiwei He, Jianhui Pang, Dian Yu, Linfeng Song, Qiuzhi Liu, Mengfei Zhou, Zhuosheng Zhang, Rui Wang, Zhaopeng Tu, Haitao Mi, Dong Yu
2024 J jnl
Entropy Guided Extrapolative Decoding to Improve Factuality in Large Language Models.
CoRR
Souvik Das, Lifeng Jin, Linfeng Song, Haitao Mi, Baolin Peng, Dong Yu
2024 J jnl
Fine-Grained Self-Endorsement Improves Factuality and Reasoning.
CoRR
Ante Wang, Linfeng Song, Baolin Peng, Ye Tian, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu
2024 J jnl
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows.
CoRR
Wenlin Yao, Haitao Mi, Dong Yu
2024 J jnl
HUNYUANPROVER: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving.
CoRR
Yang Li, Dong Du, Linfeng Song, Chen Li, Weikang Wang, Tao Yang, Haitao Mi
2024 — conf
Improving LLM Generations via Fine-Grained Self-Endorsement.
ACL (Findings)
Ante Wang, Linfeng Song, Baolin Peng, Lifeng Jin, Ye Tian, Haitao Mi, Jinsong Su, Dong Yu
2024 — conf
Inconsistent dialogue responses and how to recover from them.
EACL (Findings)
Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Dong Yu
2024 J jnl
Inconsistent dialogue responses and how to recover from them.
CoRR
Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Dong Yu
2024 J jnl
Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning.
CoRR
Yuheng Zhang, Dian Yu, Baolin Peng, Linfeng Song, Ye Tian, Mingyue Huo, Nan Jiang, Haitao Mi, Dong Yu
2024 J jnl
LiteSearch: Efficacious Tree Search for LLM.
CoRR
Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Dian Yu, Haitao Mi, Jinsong Su, Dong Yu
2024 J jnl
Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens.
CoRR
Xu Ouyang, Tao Ge, Thomas Hartvigsen, Zhisong Zhang, Haitao Mi, Dong Yu
2024 J jnl
SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models.
CoRR
Dian Yu, Baolin Peng, Ye Tian, Linfeng Song, Haitao Mi, Dong Yu
2024 J jnl
Scaling Synthetic Data Creation with 1,000,000,000 Personas.
CoRR
Xin Chan, Xiaoyang Wang, Dian Yu, Haitao Mi, Dong Yu
2024 — conf
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation.
ACL (1)
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng
2024 J jnl
Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation.
CoRR
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Lifeng Jin, Linfeng Song, Haitao Mi, Helen Meng
2024 — conf
Self-Consistency Boosts Calibration for Math Reasoning.
EMNLP (Findings)
Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu
2024 J jnl
Self-Consistency Boosts Calibration for Math Reasoning.
CoRR
Ante Wang, Linfeng Song, Ye Tian, Baolin Peng, Lifeng Jin, Haitao Mi, Jinsong Su, Dong Yu
2024 J jnl
Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching.
CoRR
Xiaoying Zhang, Baolin Peng, Ye Tian, Jingyan Zhou, Yipeng Zhang, Haitao Mi, Helen Meng
2024 J jnl
Teaching LLMs to Refine with Tools.
CoRR
Dian Yu, Yuheng Zhang, Jiahao Xu, Tian Liang, Linfeng Song, Zhaopeng Tu, Haitao Mi, Dong Yu
2024 A* conf
The Trickle-down Impact of Reward Inconsistency on RLHF.
ICLR
Lingfeng Shen, Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu
2024 A* conf
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing.
NeurIPS
Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Lei Han, Haitao Mi, Dong Yu
2024 J jnl
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing.
CoRR
Ye Tian, Baolin Peng, Linfeng Song, Lifeng Jin, Dian Yu, Haitao Mi, Dong Yu
2024 J jnl
Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning.
CoRR
Xiyao Wang, Linfeng Song, Ye Tian, Dian Yu, Baolin Peng, Haitao Mi, Furong Huang, Dong Yu
2023 — conf
Bi-level Finetuning with Task-dependent Similarity Structure for Low-resource Training.
ACL (Findings)
Sai Ashish Somayajula, Lifeng Jin, Linfeng Song, Haitao Mi, Dong Yu
2023 J jnl
D$^{2}$PSG: Multi-Party Dialogue Discourse Parsing as Sequence Generation.
IEEE ACM Trans. Audio Speech Lang. Process.
Ante Wang, Linfeng Song, Lifeng Jin, Junfeng Yao, Haitao Mi, Chen Lin, Jinsong Su, Dong Yu
2023 J jnl
Discover, Explain, Improve: An Automatic Slice Detection Benchmark for Natural Language Processing.
Trans. Assoc. Comput. Linguistics
Wenyue Hua, Lifeng Jin, Linfeng Song, Haitao Mi, Yongfeng Zhang, Dong Yu
2023 A conf
Friend-training: Learning from Models of Different but Related Tasks.
EACL
Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Xiabing Zhou, Dong Yu
2023 J jnl
Friend-training: Learning from Models of Different but Related Tasks.
CoRR
Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Xiabing Zhou, Dong Yu
2023 A* conf
More Than Spoken Words: Nonverbal Message Extraction and Generation.
EMNLP
Dian Yu, Xiaoyang Wang, Wanshun Chen, Nan Du, Longyue Wang, Haitao Mi, Dong Yu
2023 J jnl
OpenFact: Factuality Enhanced Open Knowledge Extraction.
Trans. Assoc. Comput. Linguistics
Linfeng Song, Ante Wang, Xiaoman Pan, Hongming Zhang, Dian Yu, Lifeng Jin, Haitao Mi, Jinsong Su, Yue Zhang, Dong Yu
2023 — conf
SafeConv: Explaining and Correcting Conversational Unsafe Behavior.
ACL (1)
Mian Zhang, Lifeng Jin, Linfeng Song, Haitao Mi, Wenliang Chen, Dong Yu
2023 J jnl
Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production.
CoRR
Ante Wang, Linfeng Song, Qi Liu, Haitao Mi, Longyue Wang, Zhaopeng Tu, Jinsong Su, Dong Yu
2023 J jnl
Search-engine-augmented dialogue response generation with cheaply supervised query production.
Artif. Intell.
Ante Wang, Linfeng Song, Qi Liu, Haitao Mi, Longyue Wang, Zhaopeng Tu, Jinsong Su, Dong Yu
2023 J jnl
Stabilizing RLHF through Advantage Model and Selective Rehearsal.
CoRR
Baolin Peng, Linfeng Song, Ye Tian, Lifeng Jin, Haitao Mi, Dong Yu
2023 J jnl
The Trickle-down Impact of Reward (In-)consistency on RLHF.
CoRR
Lingfeng Shen, Sihao Chen, Linfeng Song, Lifeng Jin, Baolin Peng, Haitao Mi, Daniel Khashabi, Dong Yu
2022 A* conf
COSSUM: Towards Conversation-Oriented Structured Summarization for Automatic Medical Insurance Assessment.
KDD
Sheng Xu, Xiaojun Wan, Sen Hu, Mengdi Zhou, Teng Xu, Hongbin Wang, Haitao Mi
2022 — conf
Cross-lingual Text-to-SQL Semantic Parsing with Representation Mixup.
EMNLP (Findings)
Peng Shi, Linfeng Song, Lifeng Jin, Haitao Mi, He Bai, Jimmy Lin, Dong Yu
2022 J jnl
Discover, Explanation, Improvement: Automatic Slice Detection Framework for Natural Language Processing.
CoRR
Wenyue Hua, Lifeng Jin, Linfeng Song, Haitao Mi, Yongfeng Zhang, Dong Yu
2022 A* conf
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation.
EMNLP
Xiang Hu, Haitao Mi, Liang Li, Gerard de Melo
2022 J jnl
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation.
CoRR
Xiang Hu, Haitao Mi, Liang Li, Gerard de Melo
2022 A* conf
Learning a Grammar Inducer from Massive Uncurated Instructional Videos.
EMNLP
Songyang Zhang, Linfeng Song, Lifeng Jin, Haitao Mi, Kun Xu, Dong Yu, Jiebo Luo
2022 J jnl
Learning a Grammar Inducer from Massive Uncurated Instructional Videos.
CoRR
Songyang Zhang, Linfeng Song, Lifeng Jin, Haitao Mi, Kun Xu, Dong Yu, Jiebo Luo
2022 J jnl
Towards Generalized Models for Task-oriented Dialogue Modeling on Spoken Conversations.
CoRR
Ruijie Yan, Shuang Peng, Haitao Mi, Liang Jiang, Shihui Yang, Yuchi Zhang, Jiajun Li, Liangrui Peng, Yongliang Wang, Zujie Wen
2021 — conf
A Dialogue-based Information Extraction System for Medical Insurance Assessment.
ACL/IJCNLP (Findings)
Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu
2021 J jnl
A Dialogue-based Information Extraction System for Medical Insurance Assessment.
CoRR
Shuang Peng, Mengdi Zhou, Minghui Yang, Haitao Mi, Shaosheng Cao, Zujie Wen, Teng Xu, Hongbin Wang, Lei Liu
2021 J jnl
DP-FP: Differentially Private Forward Propagation for Large Models.
CoRR
Jian Du, Haitao Mi
2021 A* conf
IIAS: An Intelligent Insurance Assessment System through Online Real-time Conversation Analysis.
IJCAI
Mengdi Zhou, Shuang Peng, Minghui Yang, Nan Li, Hongbin Wang, Li Qiao, Haitao Mi, Zujie Wen, Teng Xu, Lei Liu
2021 — conf
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling.
ACL/IJCNLP (1)
Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo
2021 J jnl
R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling.
CoRR
Xiang Hu, Haitao Mi, Zujie Wen, Yafang Wang, Yi Su, Jing Zheng, Gerard de Melo
2016 J jnl
A Coverage Embedding Model for Neural Machine Translation.
CoRR
Haitao Mi, Baskaran Sankaran, Zhiguo Wang, Abe Ittycheriah
2016 A* conf
Coverage Embedding Models for Neural Machine Translation.
EMNLP
Haitao Mi, Baskaran Sankaran, Zhiguo Wang, Abe Ittycheriah
2016 — conf
Memory chunking analysis of numerical password for Chinese websites.
MILCOM
Rui Xu, Xiaojun Chen, Yingbing Wang, Jinqiao Shi, Haitao Mi
2016 J jnl
Multi-Perspective Context Matching for Machine Comprehension.
CoRR
Zhiguo Wang, Haitao Mi, Wael Hamza, Radu Florian
2016 B conf
Semi-supervised Clustering for Short Text via Deep Representation Learning.
CoNLL
Zhiguo Wang, Haitao Mi, Abraham Ittycheriah
2016 J jnl
Semi-supervised Clustering for Short Text via Deep Representation Learning.
CoRR
Zhiguo Wang, Haitao Mi, Abraham Ittycheriah
2016 — conf
Sense Embedding Learning for Word Sense Induction.
*SEM@ACL
Linfeng Song, Zhiguo Wang, Haitao Mi, Daniel Gildea
2016 J jnl
Sense Embedding Learning for Word Sense Induction.
CoRR
Linfeng Song, Zhiguo Wang, Haitao Mi, Daniel Gildea
2016 B conf
Sentence Similarity Learning by Lexical Decomposition and Composition.
COLING
Zhiguo Wang, Haitao Mi, Abraham Ittycheriah
2016 J jnl
Sentence Similarity Learning by Lexical Decomposition and Composition.
CoRR
Zhiguo Wang, Haitao Mi, Abraham Ittycheriah
2016 A* conf
Supervised Attentions for Neural Machine Translation.
EMNLP
Haitao Mi, Zhiguo Wang, Abe Ittycheriah
2016 J jnl
Supervised Attentions for Neural Machine Translation.
CoRR
Haitao Mi, Zhiguo Wang, Abe Ittycheriah
2016 J jnl
Temporal Attention Model for Neural Machine Translation.
CoRR
Baskaran Sankaran, Haitao Mi, Yaser Al-Onaizan, Abe Ittycheriah
2016 — conf
Vocabulary Manipulation for Neural Machine Translation.
ACL (2)
Haitao Mi, Zhiguo Wang, Abe Ittycheriah
2016 J jnl
Vocabulary Manipulation for Neural Machine Translation.
CoRR
Haitao Mi, Zhiguo Wang, Abe Ittycheriah
2015 — conf
Feature Optimization for Constituent Parsing via Neural Networks.
ACL (1)
Zhiguo Wang, Haitao Mi, Nianwen Xue
2015 — conf
Shift-Reduce Constituency Parsing with Dynamic Programming and POS Tag Lattice.
HLT-NAACL
Haitao Mi, Liang Huang
2014 B conf
A Structured Language Model for Incremental Tree-to-String Translation.
COLING
Heng Yu, Haitao Mi, Liang Huang, Qun Liu
2014 — conf
Hierarchical MT Training using Max-Violation Perceptron.
ACL (2)
Kai Zhao, Liang Huang, Haitao Mi, Abraham Ittycheriah
2013 A* conf
Flexible and Efficient Hypergraph Interactions for Joint Hierarchical and Forest-to-String Decoding.
EMNLP
Martin Cmejrek, Haitao Mi, Bowen Zhou
2013 A* conf
Max-Violation Perceptron and Forced Decoding for Scalable MT Training.
EMNLP
Heng Yu, Liang Huang, Haitao Mi, Kai Zhao
2011 A* conf
A novel dependency-to-string model for statistical machine translation.
EMNLP
Jun Xie, Haitao Mi, Qun Liu
2011 — conf
Bagging-based System Combination for Domain Adaption.
MTSummit
Linfeng Song, Haitao Mi, Yajuan Lü, Qun Liu
2011 Misc conf
Parallelizing a machine translation decoder for multicore computer.
ICNC
Long Chen, Wei Huo, Haitao Mi, Zhaoqing Zhang, Xiaobing Feng, Zhiyuan Li
2011 A* conf
Rule Markov Models for Fast Tree-to-String Translation.
ACL
Ashish Vaswani, Haitao Mi, Liang Huang, David Chiang
2010 — conf
An Efficient Shift-Reduce Decoding Algorithm for Phrased-Based Machine Translation.
COLING (Posters)
Yang Feng, Haitao Mi, Yang Liu, Qun Liu
2010 A* conf
Constituency to Dependency Translation with Forests.
ACL
Haitao Mi, Qun Liu
2010 — conf
Dependency-Based Bracketing Transduction Grammar for Statistical Machine Translation.
COLING (Posters)
Jinsong Su, Yang Liu, Haitao Mi, Hongmei Zhao, Yajuan Lv, Qun Liu
2010 A* conf
Efficient Incremental Decoding for Tree-to-String Translation.
EMNLP
Liang Huang, Haitao Mi
2010 A* conf
Forest-Based Semantic Role Labeling.
AAAI
Hao Xiong, Haitao Mi, Yang Liu, Qun Liu
2010 — conf
Learning Lexicalized Reordering Models from Reordering Graphs.
ACL (2)
Jinsong Su, Yang Liu, Yajuan Lü, Haitao Mi, Qun Liu
2010 — conf
Machine Translation with Lattices and Forests.
COLING (Posters)
Haitao Mi, Liang Huang, Qun Liu
2010 C conf
Statistical Translation Model Based On Source Syntax Structure.
PACLIC
Qun Liu, Yang Liu, Haitao Mi
2010 — conf
The ICT statistical machine translation system for IWSLT 2010.
IWSLT
Hao Xiong, Jun Xie, Hui Yu, Kai Liu, Wei Luo, Haitao Mi, Yang Liu, Yajuan Lü, Qun Liu
2009 — conf
Joint Decoding with Multiple Translation Models.
ACL/IJCNLP
Yang Liu, Haitao Mi, Yang Feng, Qun Liu
2009 A* conf
Lattice-based System Combination for Statistical Machine Translation.
EMNLP
Yang Feng, Yang Liu, Haitao Mi, Qun Liu, Yajuan Lü
2009 — conf
Sub-Sentence Division for Tree-Based Machine Translation.
ACL/IJCNLP (2)
Hao Xiong, Wenwen Xu, Haitao Mi, Yang Liu, Qun Liu
2009 — conf
The ICT statistical machine translation system for the IWSLT 2009.
IWSLT (Evaluation Campaign)
Haitao Mi, Yang Liu, Tian Xia, Xinyan Xiao, Yang Feng, Jun Xie, Hao Xiong, Zhaopeng Tu, Daqi Zheng, Yanjuan Lu, Qun Liu
2009 — conf
The ICT statistical machine translation systems for the IWSLT 2009.
IWSLT
Haitao Mi, Yang Liu, Tian Xia, Xinyan Xiao, Yang Feng, Jun Xie, Hao Xiong, Zhaopeng Tu, Daqi Zheng, Yajuan Lü, Qun Liu
2008 A* conf
Forest-Based Translation.
ACL
Haitao Mi, Liang Huang, Qun Liu
2008 A* conf
Forest-based Translation Rule Extraction.
EMNLP
Haitao Mi, Liang Huang
2008 B conf
Refinements in BTG-based Statistical Machine Translation.
IJCNLP
Deyi Xiong, Min Zhang, AiTi Aw, Haitao Mi, Qun Liu, Shouxun Lin
2008 — conf
The ICT system description for IWSLT 2008.
IWSLT
Yang Liu, Zhongjun He, Haitao Mi, Yun Huang, Yang Feng, Wenbin Jiang, Yajuan Lü, Qun Liu
2008 B conf
Word Lattice Reranking for Chinese Word Segmentation and Part-of-Speech Tagging.
COLING
Wenbin Jiang, Haitao Mi, Qun Liu
2007 — conf
The ICT statistical machine translation systems for IWSLT 2007.
IWSLT
Zhongjun He, Haitao Mi, Yang Liu, Deyi Xiong, Weihua Luo, Yun Huang, Zhixiang Ren, Yajuan Lü, Qun Liu