A total of 26 papers from A*STAR have been accepted at the International Conference on Learning Representations (ICLR) 2025, a premier venue for deep learning research with 11,672 submissions this year and an acceptance rate of 32.08%. ICLR this year will be taking place on 24-28 April 2025 at Singapore EXPO.

Of the 26 papers, 4 have been selected as spotlight papers and 1 was selected for oral presentation.

We extend our sincere congratulations to all researchers whose work has been accepted at ICLR 2025!

Visit ICLR 2025 from 24–28 April at Singapore EXPO to engage with our researchers.

Or join us at Singapore AI Research Week (23-30 Apr 2025) held in conjunction with ICLR 2025 to learn the latest about our developments in AI for Online Trust and Safety, Drug Discovery, Manufacturing, and Multi-Modal LLMs. Find out more about AI Research Week 2025 at the event page here.

A*STAR’s accepted papers at ICLR 2025:

1. Easing Training Process of Rectified Flow Models Via Lengthening Inter-Path Distance (Spotlight Paper)
   Shifeng Xu, Yanzhu Liu, Adams Kong
2. Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space (Spotlight Paper)
   Zhiliang Chen, Xinyuan Niu^, Chuan-Sheng Foo, Bryan Kian Hsiang Low
3. Multimodality Helps Few-Shot 3D Point Cloud Semantic Segmentation (Spotlight Paper – Oral Session)
   Zhaochong An, Guolei Sun, Yun Liu, Runjia Li, Min Wu, Ming-Ming Cheng, Ender Konukoglu and Serge Belongie
4. Preference Optimization for Reasoning with Pseudo Feedback  (Spotlight Paper)                                                 Fangkai Jiao^, Geyang Guo, Xingxing Zhang, Nancy F. Chen, Shafiq Joty, Furu Wei
5. Direct Distributional Optimization for Provable Alignment of Diffusion Models  (Poster)
   Ryotaro Kawata, Kazusato Oko, Atsushi Nitanda, Taiji Suzuki
6. Beyond-Expert Performance with Limited Demonstrations: Efficient Imitation Learning with Double Exploration (Poster)
   Heyang Zhao, Xingrui Yu, David Mark Bossens, Ivor Tsang, Quanquan Gu
7. Confidence Elicitation: A New Attack Vector for Large Language Models (Poster)
   Brian Formento, Chuan-Sheng Foo, See-Kiong Ng
8. Evidential Learning-based Certainty Estimation for Robust Dense Feature Matching (Poster)
   Lile Cai, Chuan-Sheng Foo, Xun Xu, ZAIWANG GU, Jun Cheng, Xulei Yang
9. Robust-PIFu: Robust Pixel-aligned Implicit Function for 3D Human Digitalization from a Single Image (Poster)
   Kennard Chan, Fayao Liu, Guosheng Lin, Chuan-Sheng Foo, Weisi Lin
10. Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator (Poster)
    Xin Zhang, Jiawei Du, Ping Liu, Joey Tianyi Zhou
11. Training-Free Dataset Pruning for Instance Segmentation (Poster)
    Yalun Dai^, Lingao Xiao^, Ivor Tsang, Yang He
12. VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking (Poster)
    Runyi Hu, Jie Zhang, Yiming Li, Jiwei Li, Qing Guo, Han Qiu, Tianwei Zhang
13. Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation (Poster)
    Kim Yong Tan, Yueming Lyu, Ivor Tsang, Yew-Soon Ong
14. Sharpness-Aware Black-Box Optimization (Poster)
    Feiyang Ye, Yueming Lyu, Xuehao Wang, Masashi Sugiyama, Yu Zhang, Ivor Tsang
15. Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer (Poster)
    Yanjun Zhao, Sizhe Dang, Haishan Ye, Guang Dai, Yi Qian, Ivor Tsang
16. ProAdvPrompter: A Two-Stage Journey to Effective Adversarial Prompting for LLMs (Poster)
    Hao Di, Tong He, Haishan Ye, Yinghui Huang, Xiangyu Chang, Guang Dai, Ivor Tsang
17. Trajectory-LLM: A Language-based Data Generator for Trajectory Prediction in Autonomous Driving (Poster)
    Kairui Yang, Zihao Guo, Gengjie Lin, Haotian Dong, Zhao Huang, Yipeng Wu, Die Zuo, Jibin Peng, Ziyuan Zhong, Xin WANG, Qing Guo, Xiaosong Jia, Junchi Yan, Di Lin
18. Generative Adversarial Ranking Nets (Journal Track)
    Yinghua YAO, Yuangang PAN, Jing LI, Ivor W. TSANG, Xin YAO
19. Mentored Learning: Improving Generalization and Convergence of Student Learner (ICLR Journal Track) (Journal Track)
    Xiaofeng Cao, Yaming Guo, Heng Tao Shen, Ivor W. Tsang, James T. Kwok
20. On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning (Poster)
    Yongyi Su^, Yushu Li^, Nanqing Liu^, Kui Jia, Xulei Yang, Chuan-Sheng Foo, Xun Xu
21. Text-to-Image Rectified Flow as Plug-and-Play Priors (Poster)
    Xiaofeng Yang, Chen Cheng^, Xulei Yang, Fayao Liu, Guosheng Lin
22. Evidential Learning-based Certainty Estimation for Robust Dense Feature Matching (Poster)
    Lile Cai, Chuan-Sheng Foo, Xun Xu, ZAIWANG GU, Jun Cheng, Xulei Yang
23. Vision and Language Synergy for Rehearsal Free Continual Learning (Poster)
    Muhammad Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy, Lin Liu, H Habibullah, Ryszard Kowalczyk
24. Federated Residual Low-Rank Adaption of Large Language Models (Poster)
    Yunlu Yan, Chun-Mei Feng, Wangmeng Zuo, Lei Zhu, Rick Siow Mong Goh, Yong Liu
25. On the Importance of Language-driven Representation Learning for Heterogeneous Federated Learning (Poster)
    Yunlu Yan, Chun-Mei Feng, Wangmeng Zuo, Salman Khan, Lei Zhu, Yong Liu
26. Differentiable Rule Induction from Raw Sequence Inputs (Poster)
    Kun Gao, Katsumi Inoue, Yongzhi Cao, Hanpin Wang, Feng Yang

^A*STAR Scholar