📝 Publications

• Notes:（*）indicates the equal contributions and（†）indicates the corresponding author.

🎙 Foundation Models

上海人工智能实验室主任周伯文: 通专融合是实现AGI的战略路径之一

• Arxiv Position Paper Towards Building Specialized Generalist AI with System 1 and System 2 Fusion, Kaiyan Zhang*, Biqing Qi*, Bowen Zhou.

• NeurIPS 2024 Robustness Theory Exploring Adversarial Robustness of Deep State Space Models, Biqing Qi, Yiang Luo, Junqi Gao, Pengfei Li, Kai Tian, Zhiyuan Ma, Bowen Zhou.
• SPL 2024 Robustness Theory Enhancing Adversarial Transferability via Information Bottleneck Constraints, Biqing Qi, Junqi Gao, Jianxing Liu, Ligang Wu, Bowen Zhou Code.
• NeurIPS 2023 Robustness Theory Perturbation towards easy samples improves targeted adversarial transferability Junqi Gao*, Biqing Qi*, Yao Li, Zhichang Guo, Da Li, Yuming Xing, Dazhi Zhang.
• TNNLS 2023 Robustness Theory Improving robustness of intent detection under adversarial attacks: A geometric constraint perspective Biqing Qi, Bowen Zhou, Weinan Zhang, Jianxing Liu, Ligang Wu.
• NAACL 2024 Hallucination Detection On Large Language Models’ Hallucination with Regard to Known Facts, Che jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou.
• Arxiv Robustness Theory Watermarking Investigating Deep Watermark Security: An Adversarial Transferability Perspective, Biqing Qi, Junqi Gao, Yiang Luo, Jianxing Liu, Ligang Wu, Bowen Zhou.
• ACM MM 2024 Watermarking Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking, Zhiyuan Ma, Guoli Jia, Biqing Qi, Bowen Zhou.

世界人工智能大会报道: Interactive Continual Learning框架是实现通专融合的路径之一

Interactive Continual Learning

CVPR 2024 Continual Learning Cognition-Inspired Interactive continual learning: Fast and slow thinking, Biqing Qi, Xinquan Chen, Junqi Gao, Dong Li, Jianxing Liu, Ligang Wu, Bowen Zhou,

• This work was the first to propose the concept of interactive continual learning.
• Instantiated through the Cognitive Complementarity Theory (System1 and System2).
• An advanced continual learning framework with the novel structured key-value pairs memory unit.
• A potential framework to develop Specialized Generalist AI.

• TCSVT 2025 Continual Learning Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning, Biqing Qi, Junqi Gao, Xingquan Chen, Dong Li, Jianxing Liu, Ligang Wu, Bowen Zhou.
• NeurIPS 2025 Countinual Learning An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning, Dong Li, Aijia Zhang, Junqi Gao, Biqing Qi†.
• NAACL 2024 Reasoning PaD: Program-aided Distillation Can Teach Small Models Reasoning Better than Chain-of-thought Fine-tuning, Xuekai Zhu, Biqing Qi, Kaiyan Zhang, Xinwei Long, Zhouhan Lin, Bowen Zhou.
• Arxiv Reasoning Reinforcement Learning TTRL: Test-time reinforcement learning, Yuxin Zuo, Kaiyan Zhang, Shang Qu, Li Sheng, Xuekai Zhu, Biqing Qi, Youbang Sun, Ganqu Cui, Ning Ding, Bowen Zhou.
• Arxiv Reasoning Evolution of Thought: Diverse and High-Quality Reasoning via Multi-Objective Optimization, Junqi Gao, Zhouyi Qian, Yiang Luo, Kaiyan Zhang, Biqing Qi†, Jianxing Liu.
• ACL 2025 Alignment (Oral) Intuitive Fine-Tuning: Towards Unifying SFT and RLHF into a Single Process, Eermo Hua, Biqing Qi†, Kaiyan Zhang, Yue Yu, Ning Ding, Xintai Lv, Kai Tian, Bowen Zhou.
• Arxiv Alignment Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing, Biqing Qi, Pengfei Li, Fangyuan Li, Junqi Gao, Kaiyan Zhang, Bowen Zhou.
• ACL 2024 (Findings) Model Architecture SMR: State Memory Replay for Long Sequence Modeling, Biqing Qi, Junqi Gao, Kaiyan Zhang, Dong Li, Jianxing Liu, Ligang Wu, Bowen Zhou.
• Arxiv Model Architecture S4++: Elevating Long Sequence Modeling with State Memory Reply, Biqing Qi, Junqi Gao, Dong Li, Kaiyan Zhang, Jianxing Liu, Ligang Wu, Bowen Zhou.
• EMNLP 2024 (Findings) Model Architecture On the token distance modeling ability of higher RoPE attention dimension, Xiangyu Hong, Che Jiang, Biqing Qi†, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou.
• Arxiv Model Architecture SR-CIS: Self-Reflective Incremental System with Decoupled Memory and Reasoning, Biqing Qi, Junqi Gao, Xinquan Chen, Dong Li, Weinan Zhang, Bowen Zhou.
• NeurIPS 2024 Model Architecture Neural Residual Diffusion Models for Deep Scalable Vision Generation，Zhiyuan Ma, Liangliang Zhao, Biqing Qi, Bowen Zhou.
• ICML 2025 Position Embedding Fourier Position Embedding: Enhancing Attention’s Periodic Extension for Length Generalization, Ermo Hua, Che Jiang, Xingtai Lv, Kaiyan Zhang, Ning Ding, Youbang Sun, Biqing Qi†, Yuchen Fan, Xue Kai Zhu, Bowen Zhou.
• ACM MM 2025 Sturctured Memory T-GRAG: Temporal Graph Retrieval Augmented Generation, Dong Li, Yichen Niu, Ying Ai, Xiang Zou, Biqing Qi†, Jianxing Liu.
• AAAI 2025 Optimizer (Oral) Fast and Slow Gradient Approximation for Binary Neural Network Optimization, Xinquan Chen, Junqi Gao, Biqing Qi†, Dong Li, Yiang Luo, Fangyuan Li, Pengfei Li.

🌱 Multi-Agents Systems

• CVPR 2025 Model Merging (Highlight) Less is More: Efficient Model Merging with Binary Task Switch, Biqing Qi, Fangyuan Li, Zhen Wang, Junqi Gao, Dong Li, Peng Ye, Bowen Zhou.
• Arxiv Model Merging Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform, Chenyu Huang, Peng Ye, Xiaohui Wang, Shenghe Zheng, Biqing Qi, Lei Bai, Wanli Ouyang, Tao Chen.
• Arxiv Model Merging Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration, Junqi Gao, Zhichang Guo, Dazhi Zhang, Dong Li, Runze Liu, Pengfei Li, Kai Tian, Biqing Qi†.
• Arxiv Test Time Scaling Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling, Runze Liu, Junqi Gao, Jian Zhao, Kaiyan Zhang, Xiu Li, Biqing Qi†, Wanli Ouyang and Bowen Zhou.
• ICLR 2025 Test Time Scaling OpenPRM: Building Open-domain Process-based Reward Models with Preference Trees, Kaiyan Zhang, Jiayuan Zhang, Haoxin Li, Xuekai Zhu, Ermo Hua, Xingtai Lv, Ning Ding, Biqing Qi, Bowen Zhou.
• Arxiv Test Time Scaling GenPRM: Scaling Test-Time Compute of Process Reward Models via Generative Reasoning, Jian Zhao, Runze Liu, Kaiyan Zhang, Zhimu Zhou, Junqi Gao, Dong Li, Jiafei Lyu, Zhouyi Qian, Biqing Qi†, Xiu Li, Bowen Zhou.
• ACL 2025 Test Time Scaling Graph Counselor: Adaptive Graph Exploration via Multi-Agent Synergy to Enhance LLM Reasoning, Junqi Gao, Xiang Zou, Ying Ai, Dong Li, Yichen Niu, Biqing Qi†, Jianxing Liu.
• ACL 2024 Model Collaboration CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following, Kaiyan Zhang, Jianyu Wang, Ermo Hua, Biqing Qi, Ning Ding, Bowen Zhou.
• EMNLP 2023 Model Collaboration CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model, Kaiyan Zhang, Ning Ding, Biqing Qi, Xuekai Zhu, Xingwei Long, Bowen Zhou.
• Arxiv Model Collaboration Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding, Kaiyan Zhang, Jianyu Wang, Ning Ding, Biqing Qi, Eermo Hua, Xingtai Lv, Bowen Zhou.

👄 Applications

• COLM 2024 Scientific Discovery Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation, Biqing Qi, Kaiyan Zhang, Kai Tian, Haoxiang Li, Zhang-Ren Chen, Sihang Zeng, Ermo Hua, Hu Jinfang, Bowen Zhou.
• Instruct Following@NeurIPS 2023 Scientific Discovery Large Language Models are Zero Shot Hypothesis Proposers, Biqing Qi, Kaiyan Zhang, Haoxiang Li, Kai Tian, Sihang Zeng, Zhang-Ren Chen, Jin-Fang Hu, Bowen Zhou.
• NeurIPS 2024 D&B Track Scientific Discovery (Spotlight) UltraMedical: Building Specialized Generalists in Biomedicine, Kaiyan Zhang, Sihang Zeng, Eermo Hua, Ning Ding, Zhang-Ren Chen, Zhiyuan Ma, Hhaoxiang Li, Ganqu Cui, Biqing Qi, Xuekai Zhu, Bowen Zhou, .
• ACL 2025 Scientific Discovery Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System, Haoyang Su, Renqi Chen, SHIXIANG TANG, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong.
• Arxiv Scientific Discovery SpectrumWorld: Artificial Intelligence Foundation for Spectroscopy, Zhuo Yang, Jiaqing Xie, Shuaike Shen, Daolang Wang, Yeyun Chen, Ben Gao, Shuzhou Sun, Biqing Qi, Dongzhan Zhou, Lei Bai, Linjiang Chen, Shufei Zhang, Jun Jiang, Tianfan Fu, Yuqiang Li.
• EMNLP 2024 Embodied Agents MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making, Dayuan Fu*, Biqing Qi†, Yihuai Gao, Che Jiang, Guanting Dong, Bowen Zhou.
• EMNLP 2025 Scientific Discovery ReviewRL: Towards Automated Scientific Review with RL, Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi†, Bowen Zhou.
• Arxiv GUI Agents Scientific Discovery Scienceboard: Evaluating multimodal autonomous agents in realistic scientific workflows Qiushi Sun, Zhoumianze Liu, Chang Ma, Zichen Ding, Fangzhi Xu, Zhangyue Yin, Haiteng Zhao, Zhenyu Wu, Kanzhi Cheng, Zhaoyang Liu, Jianing Wang, Qintong Li, Xiangru Tang, Tianbao Xie, Xiachong Feng, Xiang Li, Ben Kao, Wenhai Wang, Biqing Qi, Lingpeng Kong, Zhiyong Wu.
• Arxiv GUI Agents OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?, Xuetian Chen, Yinghao Chen, Xinfeng Yuan, Zhuo Peng, Lu Chen, Yuekeng Li, Zhoujia Zhang, Yingqian Huang, Leyan Huang, Jiaqing Liang, Tianbao Xie, Zhiyong Wu, Qiushi Sun, Biqing Qi†, Bowen Zhou.
• AAAI 2025 Visual Question Answering Retrieval-Augmented Visual Question Answering via Built-in Autoregressive Search Engines, Xinwei Long, Zhiyuan Ma, Ermo Hua, Kaiyan Zhang, Biqing Qi, Bowen Zhou.