About Me

Apr. 2025 You’re welcome to join our 4th Workshop on Computer Vision in the Wild (CVinW) at @CVPR 2025!
Apr. 2025 We release MMInference, accelerating pre-filling for long-context VLMs!
Feb. 2025 We release Magma, a foundation model for multimodal AI agents!
Jan. 2025 SeCom and SCBench are accepted at ICLR 2025!
Sep. 2024 MInference is accepted at NeurIPS 2024 as a spotlight!
Sep. 2024 I’m serving as an Area Chair for COLING 25!
Jun. 2024 MInference and LLM Position Bias paper are accepted to ES-FoMo II @ ICML24 and LCFM @ ICML24, respectively.
May. 2024 LLMLingua Series has been integrated as a custom tool in Prompt Flow, AutoGen, LangChain and LlamaIndex.
May. 2024 LongLLMLingua and LLMLingua-2 are accepted to ACL-2024 in main track and findings!
Mar. 2024 We release LLMLingua-2, an efficient option for task-agnostic prompt compression with good performance and generalizability across different scenarios, boasting a 3x-6x speed improvement over LLMLingua!
Oct. 2023 We release LongLLMLingua, aiming to accelerate and enhance LLM inference in long-context scenarios via question-aware prompt compression and content reorganization!
Oct. 2023 We release LLMLingua, a coarse-to-fine prompt compression method based on perplexity from a small language model such as LLaMA-7B!

• Preprint 2026 Orchard: An Open-source Agentic Modeling Framework
  Baolin Peng*, Wenlin Yao*, Qianhui Wu*, Hao Cheng*, Xiao Yu, Rui Yang, Tao Ge, Alessandrio Sordoni, Xingdi Yuan, Yelong Shen, Pengcheng He, Tong Zhang, Zhou Yu, Jianfeng Gao
• Preprint 2026 WebXSkill: Skill Learning for Autonomous Web Agents
  Zhaoyang Wang, Qianhui Wu, Xuchao Zhang, Chaoyun Zhang, Wenlin Yao, Fazle Elahi Faisal, Baolin Peng, Si Qin, Suman Nath, Qingwei Lin, Chetan Bansal, Dongmei Zhang, Saravan Rajmohan, Jianfeng Gao, Huaxiu Yao
• Preprint 2026 GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
  Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang, Hao Cheng, Huaxiu Yao, Baoling Peng, Huan Zhang, Jianfeng Gao, Tong Zhang
• Preprint 2025 Multimodal Reinforcement Learning with Agentic Verifier for AI Agents
  Reuben Tan, Baolin Peng, Zhengyuan Yang, Hao Cheng, Oier Mees, Theodore Zhao, Andrea Tupini, Isar Meijier, Qianhui Wu, Yuncong Yang, Lars Liden, Yu Gu, Sheng Zhang, Xiaodong Liu, Lijuan Wang, Marc Pollefeys, Yong Jae Lee, Jianfeng Gao
• ACL-2026 Adapting Web Agents with Synthetic Supervision
  Zhaoyang Wang, Yiming Liang, Xuchao Zhang, Qianhui Wu, Siwei Han, Anson Bastos, Rujia Wang, Chetan Bansal, Baolin Peng, Jianfeng Gao, Saravan Rajmohan, Huaxiu Yao
• ICLR-2026 Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
  Xiao Yu, Baolin Peng, Michel Galley, Hao Cheng, Qianhui Wu, Janardhan Kulkarni, Suman Nath, Zhou Yu, Jianfeng Gao
• NeurIPS-2025 GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
  Qianhui Wu*, Kanzhi Cheng*, Rui Yang*, Chaoyun Zhang, Jianwei Yang, Huiqiang Jiang, Jian Mu, Baolin Peng, Bo Qiao, Reuben Tan, Si Qin, Lars Liden, Qingwei Lin, Huan Zhang, Tong Zhang, Jianbing Zhang, Dongmei Zhang, Jianfeng Gao.
• CVPR-2025 Magma: A Foundation Model for Multimodal AI Agents
  Jianwei Yang*, Reuben Tan*, Qianhui Wu*, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Jianfeng Gao.
• ICLR-2025 SeCom: On Memory Construction and Retrieval for Personalized Conversational Agents
  Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Xufang Luo, Hao Cheng, Dongsheng Li, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Jianfeng Gao.

• ICML-2025 MMInference: Accelerating Pre-filling for Long-Context Visual Language Models via Modality-Aware Permutation Sparse Attention
  Yucheng Li, Huiqiang Jiang, Chengruidong Zhang, Qianhui Wu, Xufang Luo, Surin Ahn, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu.
• ICLR-2025 SharedContextBench: How Lossy are Long-context Methods in KV Cache Reuse
  Yucheng Li, Huiqiang Jiang, Qianhui Wu, Xufang Luo, Surin Ahn, Chengruidong Zhang, Amir H. Abdi, Dongsheng Li, Jianfeng Gao, Yuqing Yang, Lili Qiu.
• NeurIPS-2024 MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
  Huiqiang Jiang*, Yucheng Li*, Chengruidong Zhang*, Qianhui Wu, Xufang Luo, Surin Ahn, Zhenhua Han, Amir H. Abdi, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu.
• ACL-2024 Findings LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
  Zhuoshi Pan, Qianhui Wu, Huiqiang Jiang, Menglin Xia, Xufang Luo, Jue Zhang, Qingwei Lin, Victor Rühle, Yuqing Yang, Chin-Yew Lin, H. Vicky Zhao, Lili Qiu, Dongmei Zhang.
• ACL-2024 LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
  Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu.
• EMNLP-2023 LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models
  Huiqiang Jiang, Qianhui Wu, Chin-Yew Lin, Yuqing Yang, Lili Qiu.
• ACL-2023 Multi-Level Knowledge Distillation for Out-of-Distribution Detection in Text
  Qianhui Wu, Huiqiang Jiang, Haonan Yin, Börje Karlsson, Chin-Yew Lin.

• ACL-2023 CoLaDa: A Collaborative Label Denoising Framework for Cross-lingual Named Entity Recognition
  Tingting Ma, Qianhui Wu, Huiqiang Jiang, Börje Karlsson, Tiejun Zhao, Chin-Yew Lin.
• ACL-2022 Findings Decomposed Meta-Learning for Few-Shot Named Entity Recognition
  Tingting Ma*, Huiqiang Jiang*, Qianhui Wu*, Tiejun Zhao, Chin-Yew Lin.
• NAACL-2022 On the Effectiveness of Sentence Encoding for Intent Detection Meta-Learning
  Tingting Ma, Qianhui Wu, Zhiwei Yu, Tiejun Zhao, Chin-Yew Lin.
• IJCAI-2020 UniTrans: Unifying Model Transfer and Data Transfer for Cross-Lingual Named Entity Recognition with Unlabeled Data
  Qianhui Wu, Zijia Lin, Börje Karlsson, Biqing Huang, Jian-Guang Lou.
• ACL-2020 Single-/Multi-Source Cross-Lingual NER via Teacher-Student Learning on Unlabeled Data in Target Language
  Qianhui Wu, Zijia Lin, Börje Karlsson, Jian-Guang Lou, Biqing Huang.
• AAAI-2020 Enhanced Meta-Learning for Cross-Lingual Named Entity Recognition with Minimal Resources
  Qianhui Wu, Zijia Lin, Guoxin Wang, Hui Chen, Börje Karlsson, Biqing Huang, Chin-Yew Lin.
• NTCIR-2019 DeepMRT at the NTCIR-14 FinNum Task: A Hybrid Neural Model for Numeral Type Classification in Financial Tweets
  Qianhui Wu*, Guoxin Wang*, Yuyin Zhu, Haoyan Liu, Börje Karlsson.