ISCL算法团队介绍

软硬协同高性能AI算法团队简介

南京大学智能感知与通信实验室——软硬协同高性能AI算法团队，由实验室硕、博研究生组成，致力于探索AI端侧部署和优化，在人工智能国际会议与期刊上发表高质量工作，与国内外知名大学（北京大学、清华大学、香港理工大学、香港科技大学、UC Berkeley、UCLA、University of Arizona、UC Irvine、UCSD等）、研究机构（上海人工智能实验室）和企业（大疆、阿里巴巴、美团、Panasonic、BMW）合作，为学生提供优质的科研平台、计算资源和深造机会。

招募中，加入我们！

加入我们的团队，在工作中相互成就！

欢迎大二、大三同学提前与我们建立合作，相互了解，简历投递至以下邮箱，并注明算法团队：

团队负责人：刘一茳 liuyijiang at smail.nju.edu.cn ，

并抄送杜力 or 杜源老师 {ldu, yuandu} at nju.edu.cn

News

2025-11-11，1篇论文被 AAAI 2026 接收为 Oral（Top5%）！MoASE：自动驾驶混合专家

2025-11-11, 2篇论文被 AAAI 2026 接收！MoLe-VLA：具身混合专家、MoASE：自动驾驶混合专家

2025-4-29，1篇论文被 IJCAI 2025 接收！FBQuant：大模型量化

2025-4-16，第一期：ISCL算法团队（暑期）科研训练面向本科生开放报名（点击查看详情）

2025-4-13, 1篇论文被 TMC 接收！RepCaM++：神经视频传输

2024-12-28，1篇论文被 TCSVT 接收！BEVUDA++：3D目标检测

2024-12-12, 1篇论文被 AAAI 2025 接收！PAT：大模型剪训一体

2024-8-4，1篇论文被 IEEE TMC 接收！

2024-7-18, 1篇论文被 ACM MM 2024 接收！

2024-2-27, 2篇论文被 CVPR 2024 接收！【端云协同】【提示工程】

2024-1-30, 2篇论文被 ICRA 2024 接收！

2023-8-10, 2篇论文被 ICCV 2023 接收！Q-Diffusion: 量化扩散模型(收录MIT课程)

2023-3-23，1篇论文被 CVPR 2023 接收！NoisyQuant：Transformer 量化

发表论文

2025年

(CCF-A, AAAI 2026) Rongyu Zhang, Menghang Dong, Yuan Zhang, Liang Heng, Xiaowei Chi, Gaole Dai, Li Du, Yuan Du, Shanghang Zhang, MoLe-VLA: Dynamic Layer-skipping Vision Language Action Model via Mixture-of-Layers for Efficient Robot Manipulation

(CCF-A, AAAI 2026, ORAL) Rongyu Zhang, Aosong Cheng, Yulin Luo, Gaole Dai, Huanrui Yang, Jiaming Liu, Ran Xu, Li Du, Yuan Du, Yanbing Jiang, Shanghang Zhang, Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation

(CCF-A， IJCAI 2025) Yijiang Liu, Hengyu Fang, Liulu He, Rongyu Zhang, Yichuan Bai, Yuan Du, Li Du. FBQuant: FeedBack Quantization for Large Language Models.

(CCF-A，TMC 2025) Rongyu Zhang, et al. RepCaM++: Exploring Transparent Visual Prompt With Inference-Time Re-Parameterization for Neural Video Delivery

(CAS-Q1，TCSVT 2025) Rongyu Zhang, et al. BEVUDA++: Geometric-aware Unsupervised Domain Adaptation for Multi-View 3D Object Detection

(CCF-A, AAAI 2025) Liu, Yijiang, et al. PAT: Pruning-Aware Tuning for Large Language Models.

2024年

(CCF-A, TMC 2024) Zhang, Rongyu, et al. Multi-level Personalized Federated Learning on Heterogeneous and Long-Tailed Data

(CCF-A, MM 2024) Zhang, Rongyu, et al. Vecaf: vision-language collaborative active finetuning with training objective awareness

(CCF-A, CVPR 2024) Liu, Yijiang, et al. PromptCoT: Align Prompt Distribution via Adapted Chain-of-Thought

(CCF-A, CVPR 2024) Liu, Yijiang, et al. Cloud-Device Collaborative Learning for Multimodal Large Language Models

(CCF-B, ICRA 2024) Li, Jianing, et al. Unsupervised Spike Depth Estimation via Cross-modality Cross-domain Knowledge Transfer

(CCF-B, ICRA 2024) Zhang, Rongyu, et al. Multi-geometric Space Alignments for Domain Adaptive Multi-view 3D Object Detection

(CCF-A, AAAI 2024) Zhang, Rongyu, et al. Efficient Deweather Mixture-of-Experts with Uncertainty-Aware Feature-wise Linear Modulation

2023年

(T-IV 2023) Li, Jianing, et al. BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for Multi-View BEV 3D Object Detection. IEEE Transactions on Intelligent Vehicles (T-IV).

(CCF-A, ICCV 2023) Li, Xiuyu, Yijiang Liu, Long Lian, Huanrui Yang, Zhen Dong, Daniel Kang, Shanghang Zhang, and Kurt Keutzer. Q-diffusion: Quantizing diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 17535-17545. 2023.

(CCF-A, CVPR 2023) Liu, Yijiang, Huanrui Yang, Zhen Dong, Kurt Keutzer, Li Du, and Shanghang Zhang. NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 20321-20330. 2023.

(CCF-A, ICCV 2023) Zhang, Yifan, Zhen Dong, Huanrui Yang, Ming Lu, Cheng-Ching Tseng, Yuan Du, Kurt Keutzer, Li Du, and Shanghang Zhang. QD-BEV: Quantization-aware View-guided Distillation for Multi-view 3D Object Detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 3825-3835. 2023.

(CCF-A, DAC 2023) Xiao, Lirui, Huanrui Yang, Zhen Dong, Kurt Keutzer, Li Du, and Shanghang Zhang. Csq: Growing mixed-precision quantization scheme with bi-level continuous sparsification. In 2023 60th ACM/IEEE Design Automation Conference (DAC), pp. 1-6. IEEE, 2023.

团队负责人

刘一茳

博士	博士	博士	硕士	硕士

李嘉宁 2021级	张融宇 2023级	彭志玉 2024级	方恒宇 2024级	郑沈理 2024级

硕士	保研	保研	保研	保研	保研

李东霖 2025级	徐晓锐 2026级	钱许振 2026级	范睿智 2026级	高力 2026级	郑涵俊 2026级

保研

齐子豪 2026级