1. Zinan Zeng, Zhenyu Ding, Bo Zhang, Mingyang Wan, Caigui Jiang, Ning Ding, SVPO: A LLM Reinforcement Learning Method Based on Stepwise Value Estimation, ICASSP 2026. (CCF-B)
2. Yiming Liang, Ning Ding, Meiqin Liu, Shanling Dong, Mingyang Wan, Reward-based Efficient Demonstration Selection for In-context Learning, ICASSP 2026. (CCF-B)
3. Ziyang Zhang, Yuechen Lin, Xuanxuan An, Mingyang Wan, Caigui Jiang, Ning Ding, Attn-Defense: Attention-Guided Detection, Location and Removal for Indirect Prompt Injection, ICASSP 2026. (CCF-B)
4. Zhenyu Ding, Yuhao Wang, Tengyue Xiao, Haoying Wang, Caigui Jiang, Ning Ding, W2S-AlignTree: Weak-to-Strong Inference-Time Alignment for Large Language Models via Monte Carlo Tree Search, AAAI Conference on Artificial Intelligence (AAAI) 2026. (CCF-A, Oral, 1059/23680, Top 4.5%)
5. Hongyuan Min, Ning Ding, Mingyang Wan, Guojun Ma, Caigui Jiang, AGCNet: Improving Inertial Odometry via IMU Accelerometer and Gyroscope Online Compensation, IROS2025. (CCF-C)
6. Houyi Li, Wenzhen Zheng, Qiufeng Wang, Zhenyu Ding, Haoying Wang, Zili Wang, Shijie Xuyang, Ning Ding, Shuigeng Zhou, Xiangyu Zhang, Daxin Jiang, Farseer: A Refined Scaling Law in Large Language Models, Annual Conference on Neural Information Processing Systems (NeurIPS) 2025. (CCF-A, Spotlight, 688/21575, Top 3.2%)
7. Dai Yusheng, Hang Chen, Jun Du, Xiaofei Ding, Ning Ding, Feijun Jiang, and Chin-Hui Lee. 2023. "Improving audio-visual speech recognition by lip-subword correlation based visual pre-training and cross-modal fusion encoder." In 2023 IEEE International Conference on Multimedia and Expo (ICME), 2627–32. (CCF-B)
8. Jianlong Wu, Haozhe Yang, Tian Gan, Ning Ding, Feijun Jiang, Liqiang Nie, CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning. Conference on Computer Vision and Pattern Recognition (CVPR) 2023, pp.15762-15772, Jun. 2023. (CCF-A)
9. Haozhe Yang, Xianqiang Gao, Jianlong Wu, Tian Gan, Ning Ding, Feijun Jiang and Liqiang Nie, Self-adaptive Context and Modal-interaction Modeling For Multi-modal Emotion Recognition. Association for Computational Linguistics (ACL) 2023, pp. 6267–6281, Jul. 2023(CCF-A)
10. Zorila, C., Li, M., Hayakawa, D., Liu, M., Ding, N., Doddipatla, R. (2020) Toshiba’s Speech Recognition System for the CHiME 2020 Challenge, International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.62-66, May. 2020 (CCF-B)
11. H. Fujimura, N. Ding, D. Hayakawa, and T. Kagoshima, “Simultaneous Flexible Keyword Detection and Text-dependent Speaker Recognition for Low-resource Devices”, International Conference on Pattern Recognition Applications and Methods (ICPRAM),pp.297-307, Valletta, Malta, Feb. 2020.
12. K. Fujimoto, N. Ding, and N. Hamada, “Multiple Sources' Direction Finding by using Reliable Component on Phase Difference Manifold and Kernel Density Estimator”, ICASSP 2012, pp.2601-2604, Kyoto, Japan, Mar. 2012. (CCF-B)
13. N. Ding and N. Hamada, “DOA estimation in underdetermined stereophonic mixture by kernel density estimator,” ISPACS 2011, pp.1-5, Chiangmai, Thailand, Dec. 2011.
14. N. Ding and N. Hamada, “Speaker localization and speech separation using phase difference versus frequency distribution,” EUSIPCO 2011, pp.250-253, Barcelona, Spain, Aug. 2011.