Hi! I’m Peng Fu (付鹏)，an Associate Professor at the Institute of Information Engineering (IIE), Chinese Academy of Sciences (CAS). I earned my Ph.D degree from the University of Chinese Academy of Sciences (UCAS) in 2018, under the supervision of Prof. Weiping Wang. I have also been fortunate to engage in academic collaborations with Prof. Zheng Lin from the Institute of Information Engineering (IIE), CAS.

My current research interests primarily cover large language models, efficient learning for large models, controllable text generation, sentiment analysis, machine reading comprehension, and general text generation.

Email:fupeng[at]iie[dot]ac[dot]cn

Recent News

• 2026.02：One paper is accepted by CVPR 2026.

Publications

2026

• Yuchen Feng, Zhenyu Zhang, Naibin Gu, Yilong Chen, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang: Blink: Dynamic Visual Token Resolution for Enhanced Multimodal Understanding. CVPR 2026 : 3511-3521

2025

• Jiaxuan Zhao, Naibin Gu, Yuchen Feng, Xiyu Liu, Peng Fu, Zheng Lin, Weiping Wang: CBP-Tuning: Efficient Local Customization for Black-box Large Language Models. EMNLP 2025 : 19617-19630
• Peize Li, Qingyi Si, Peng Fu, Zheng Lin, Yan Wang: Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering. AAAI 2025: 4851-4859
• Naibin Gu, Peng Fu, Xiyu Liu, Ke Ma, Zheng Lin, Weiping Wang: Adapt Once, Thrive with Updates: Transferable Parameter-Efficient Fine-Tuning on Evolving Base Models. SAC Highlights. ACL 2025: 14765-14783
• Naibin Gu, Zhenyu Zhang, Xiyu Liu, Peng Fu, Zheng Lin, Shuohuan Wang, Yu Sun, Hua Wu, Weiping Wang, Haifeng Wang: BeamLoRA: Beam-Constraint Low-Rank Adaptation. ACL 2025: 11871-11883
• Yuchen Feng, Bowen Shen, Naibin Gu, Jiaxuan Zhao, Peng Fu, Zheng Lin, Weiping Wang: DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts. ACL 2025: 19375-19394

2024

• Naibin Gu, Peng Fu, Xiyu Liu, Bowen Shen, Zheng Lin, Weiping Wang: Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning. ACL (Findings) 2024: 7528-7541
• Peize Li, Qingyi Si, Peng Fu, Zheng Lin, Yan Wang: Object Attribute Matters in Visual Question Answering. AAAI 2024: 18545-18553
• Yan Wang, Peize Li, Qingyi Si, Hanwen Zhang, Wenyu Zang, Zheng Lin, Peng Fu: Cross-modality Multiple Relations Learning for Knowledge-based Visual Question Answering. ACM Trans. Multim. Comput. Commun. Appl. 20(3): 63:1-63:22 (2024)
• Hanwen Zhang, Qingyi Si, Peng Fu, Zheng Lin, Weiping Wang: Are Large Language Models Table-based Fact-Checkers?. CSCWD 2024: 3086-3091

2023

• Naibin Gu, Peng Fu, Xiyu Liu, Zhengxiao Liu, Zheng Lin, Weiping Wang: A Gradient Control Method for Backdoor Attacks on Parameter-Efficient Tuning. ACL, 2023
• Jiangnan Li, Mo Yu, Fandong Meng, Zheng Lin, Peng Fu, Weiping Wang, Jie Zhou: Question-Interlocutor Scope Realized Graph Modeling over Key Utterances for Dialogue Reading Comprehension. ACL, 2023
• Qingyi Si, Yuanxin Liu, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang: Compressing and Debiasing Vision-Language Pre-Trained Models for Visual Question Answering. EMNLP 2023: 513-529
• Zhe Wen, Qingyi Si, Zheng Lin, Huan Liu, Peng Fu, Weiping Wang: Schema Item Matters in Knowledge Base Question Answering. IJCNN 2023: 1-8

2022

• Rui Liu, Zheng Lin, Huishan Ji, Jiangnan Li, Peng Fu, Weiping Wang: Target Really Matters: Target-aware Contrastive Learning and Consistency Regularization for Few-shot Stance Detection. COLING, 2022
• Qingyi Si, Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou: Towards Robust Visual Question Answering: Making the Most of Biased Samples via Contrastive Learning. EMNLP (Findings), 2022
• Qingyi Si, Fandong Meng, Mingyu Zheng, Zheng Lin, Yuanxin Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou: Language Prior Is Not the Only Shortcut: A Benchmark for Shortcut Learning in VQA. EMNLP (Findings), 2022
• Yuanxin Liu, Fandong Meng, Zheng Lin, Jiangnan Li, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou: A Win-win Deal: Towards Sparse and Robust Pre-trained Language Models. NeurIPS, 2022
• Yutong Tan, Zheng Lin, Peng Fu, Mingyu Zheng, Lanrui Wang, Yanan Cao, Weiping Wang: Detach and Attach: Stylized Image Captioning without Paired Stylized Dataset. ACM’MM, 2022
• Jiangnan Li, Fandong Meng, Zheng Lin, Rui Liu, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou: Neutral Utterances are Also Causes: Enhancing Conversational Causal Emotion Entailment with Social Commonsense Knowledge. IJCAI, 2022
• Yuanxin Liu, Fandong Meng, Zheng Lin, Peng Fu, Yanan Cao, Weiping Wang, Jie Zhou: Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training. NAACL, 2022
• Huishan Ji, Zheng Lin, Peng Fu, Weiping Wang: Cross-Target Stance Detection Via Refined Meta-Learning. ICASSP 2022: 7822-7826
• Rui Liu, Zheng Lin, Peng Fu, Yuanxin Liu, Weiping Wang: Connecting Targets via Latent Topics And Contrastive Learning: A Unified Framework For Robust Zero-Shot and Few-Shot Stance Detection. ICASSP 2022: 7812-7816
• Jingzi Gu, Dayan Wu, Peng Fu, Bo Li, Weiping Wang: Deep Piecewise Hashing for Efficient Hamming Space Retrieval. ICASSP 2022: 3199-3203

2021

• Jiangnan Li, Zheng Lin, Peng Fu, Weiping Wang: Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge. EMNLP (Findings) 2021: 1204-1214
• Jiangnan Li, Hongliang Pan, Zheng Lin, Peng Fu, Weiping Wang: Sarcasm Detection with Commonsense Knowledge. IEEE/ACM TASLP, VOL.29, 2021: 3192-3201
• Qingyi Si, Zheng Lin, Mingyu Zheng, Peng Fu, Weiping Wang: Check It Again: Progressive Visual Question Answering via Visual Entailment. ACL/IJCNLP (1) 2021: 4101-4110
• Qingyi Si, Yuanxin Liu, Peng Fu, Zheng Lin, Jiangnan Li, Weiping Wang: Learning Class-Transductive Intent Representations for Zero-shot Intent Detection. IJCAI 2021: 3922-3928
• Miaojin Li, Peng Fu, Zheng Lin, Weiping Wang, Wenyu Zang: Exemplar Guided Latent Pre-trained Dialogue Generation. ICCS (2) 2021: 118-132

2020

• Hongliang Pan, Zheng Lin, Peng Fu, Yatao Qi, Weiping Wang: Modeling Intra and Inter-modality Incongruity for Multi-Modal Sarcasm Detection. EMNLP (Findings) 2020: 1383-1392. [code]
• Hongliang Pan, Zheng Lin, Peng Fu, Weiping Wang: Modeling the Incongruity Between Sentence Snippets for Sarcasm Detection. ECAI 2020: 2132-2139
• Rui Liu, Zheng Lin, Peng Fu, Weiping Wang: Reinforced Keyphrase Generation with BERT-based Sentence Scorer. ISPA/BDCloud/SocialCom/SustainCom 2020: 1-8
• Miaojin Li, Peng Fu, Zheng Lin, Weiping Wang: Parallel Variational Autoencoders for Multiple Responses Generation. ISPA/BDCloud/SocialCom/SustainCom 2020: 128-136

2019 and before

• Yue Geng, Zheng Lin, Peng Fu, Weiping Wang: Rumor Detection on Social Media: A Multi-view Model Using Self-attention Mechanism. ICCS (1) 2019: 339-352
• Ran Li, Zheng Lin, Peng Fu, Weiping Wang, Gang Shi: EmoMix: Building an Emotion Lexicon for Compound Emotion Analysis. ICCS (1) 2019: 353-368
• Ran Li, Qingyi Si, Peng Fu, Zheng Lin, Weiping Wang, Gang Shi: A Multi-channel Neural Network for Imbalanced Emotion Recognition. ICTAI 2019: 353-360
• Peng Fu, Zheng Lin, Fengcheng Yuan, Weiping Wang, Dan Meng: Learning Sentiment-Specific Word Embedding via Global Sentiment Representation. AAAI 2018: 4808-4815
• Peng Fu, Zheng Lin, Hailun Lin, Fengcheng Yuan, Weiping Wang, Dan Meng: Quantifying the Effect of Sentiment on Topic Evolution in Chinese Microblog. APWeb (1) 2016: 531-542

Education

• Sep. 2014 - Jun. 2018, Ph.D. in Computer Application, University of Chinese Academy of Sciences
• Sep. 2007 - Aug. 2014, Bachelor and Master in Computer Science, School of Computer Science and Technology, Xidian University