Center for Advanced Intelligence Project

25 papers were accepted at ICLR 2025, a major conference on machine learning.
For more details, please refer to the link below.
https://iclr.cc/

[Acceptance rate]
The number of valid submissions was close to 11,500 submissions, with the overall acceptance rate of 32.08%.

[Accepted papers]

• A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches
  Hiroyuki Deguchi (NAIST)
  Go Kamoda (Tohoku University)
  Yusuke Matsushita (Kyoto University)
  Chihiro Taguchi (University of Notre Dame)
  Kohei Suenaga (Kyoto University)
  Masaki Waga (Kyoto University)
  Sho Yokoi (NINJAL / Tohoku University / RIKEN AIP)
• Connecting Federated ADMM to Bayes
  Siddharth Swaroop (Harvard University)
  Mohammad Emtiyaz Khan (RIKEN AIP)
  Finale Doshi-Velez (Harvard University)
• Difference-of-submodular Bregman Divergence
  Masanari Kimura (The University of Melbourne)
  Takahio Kawashima (ZOZO Research)
  Tasuku Soma (ISM / SOKENDAI / RIKENAIP)
  Hideitsu Hino (ISM/RIKEN AIP)
• Diffusing to the Top: Boost Graph Neural Networks with Minimal Hyperparameter Tuning.
  Lequan Lin (USYD)
  Dai Shi (USYD)
  Andi Han (RIKEN AIP)
  Zhiyong Wang (USYD)
  Junbin Gao (USYD).
• Direct Distributional Optimization for Provable Alignment of Diffusion Models
  Ryotaro Kawata (The University of Tokyo / RIKEN AIP)
  Kazusato Oko (UC Berkeley / RIKEN AIP)
  Atsushi Nitanda (A*STAR)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization
  Taishi Nakamura (Institute of Science Tokyo)
  Takuya Akiba (Sakana AI)
  Kazuki Fujii (Institute of Science Tokyo)
  Yusuke Oda (NII LLMC)
  Rio Yokota (Institute of Science Tokyo / NII LLMC)
  Jun Suzuki (Tohoku University / RIKEN AIP / NII LLMC)
• Flow matching achieves almost minimax optimal convergence
  Kenji Fukumizu (The Institute of Statistical Mathematics / Preferred Networks)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Noboru Isobe (The University of Tokyo)
  Kazusato Oko (UC Berkeley / RIKEN AIP)
  Masanori Koyama (Preferred Networks)
• Improved Approximation Algorithms for k-Submodular Maximization via
  Multilinear Extension
  Huanjian Zhou (The University of Tokyo / RIKEN AIP)
  Lingxiao Huang (Nanjing University)
  Baoxiang Wang (Chinese University of Hong Kong, Shenzhen)
• Improving Convergence Guarantees of Random Subspace Second-order Algorithm for Nonconvex Optimization
  Rei Higuchi (University of Tokyo)
  Pierre-Louis Poirion (RIKEN AIP)
  Akiko Takeda (University of Tokyo / RIKEN AIP)
• Learning View-invariant World Models for Visual Robotic Manipulation
  Jing-Cheng Pang (Nanjing University)
  Nan Tang (Nanjing University)
  Kaiyuan Li (Nanjing University)
  Yuting Tang (University of Tokyo / RIKEN AIP)
  Xin-Qiang Cai (RIKEN AIP)
  Zhen-Yu Zhang (RIKEN AIP)
  Gang Niu (RIKEN AIP / Southeast University)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Yang Yu (Nanjing University)
• On the feature learning in diffusion models
  Andi Han (RIKEN AIP)
  Wei Huang (RIKEN AIP)
  Yuan Cao (The University of Hong Kong)
  Difan Zou (The University of Hong Kong)
• On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
  Bingrui Li (Tsinghua University)
  Wei Huang (RIKEN AIP)
  Andi Han (RIKEN AIP)
  Zhangpeng Zhou (Shanghai Jiao Tong University)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Jun Zhu (Tsinghua University)
  Jianfei Chen (Tsinghua University)
• Optimality and Adaptivity of Deep Neural Features for Instrumental
  Variable Regression
  Juno Kim (The University of Tokyo / RIKEN AIP)
  Dimitri Meunier (University College London)
  Arthur Gretton (University College London)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Zhu Li (University College London)
• PLENCH: Realistic Evaluation of Deep Partial-Label Learning Algorithms
  Wei Wang (The University of Tokyo / RIKEN AIP)
  Dong-Dong Wu (Mohamed bin Zayed University of Artificial Intelligence)
  Jindong Wang (William & Mary)
  Gang Niu (RIKEN AIP / Southeast University)
  Min-Ling Zhang (Southeast University)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Sharpness-Aware Black-Box Optimization
  Feiyang Ye (University of Technology Sydney / RIKEN AIP) **
  Yueming Lyu (A*STAR)
  Xuehao Wang (Southern University of Science and Technology)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Yu Zhang (Southern University of Science and Technology)
  Ivor Tsang (A*STAR)
• Sketch2Diagram: Generating Vector Diagrams from Hand-Drawn Sketches
  Itsumi Saito (Tohoku University / RIKEN AIP)
  Haruto Yoshida (Tohoku University)
  Keisuke Sakaguchi (Tohoku University / RIKEN AIP)
• State Space Models are Provably Comparable to Transformers in Dynamic
  Token Selection
  Naoki Nishikawa (The University of Tokyo / RIKEN AIP)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• TAID: Temporally Adaptive Interpolated Distillation for Efficient Knowledge Transfer in Language Models
  Makoto Shing (Sakana AI)
  Kou Misaki (Sakana AI)
  Han Bao (Kyoto University)
  Sho Yokoi (NINJAL / Tohoku University / RIKEN AIP)
  Takuya Akiba (Sakana AI)
• T2V2: A Unified Non-Autoregressive Model for Speech Recognition and Synthesis via
  Multitask Learning
  Nabarun Goswami (The University of Tokyo)
  Hanqin Wang (The University of Tokyo)
  Tatsuya Harada (The University of Tokyo/RIKEN AIP)
• The Adaptive Complexity of Log-Concave Sampling
  Huanjian Zhou (The University of Tokyo / RIKEN AIP)
  Baoxiang Wang (Chinese University of Hong Kong, Shenzhen)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Towards Effective Evaluations and Comparison for LLM Unlearning Methods
  Qizhou Wang (Hong Kong Baptist University / RIKEN AIP)*
  Bo Han (Hong Kong Baptist University/RIKEN AIP)
  Puning Yang (Hong Kong Baptist University)
  Jianing Zhu (Hong Kong Baptist University)
  Tongliang Liu (The University of Sydney / RIKEN AIP / Mohamed bin Zayed University of Artificial Intelligence)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Towards Out-of-Modal Generalization without Instance-level Modal Correspondence
  Zhuo Huang (University of Sydney)
  Gang Niu (RIKEN AIP / Southeast University)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Tongliang Liu (The University of Sydney / RIKEN AIP / Mohamed bin Zayed
  University of Artificial Intelligence)
• Transformers Provably Solve Parity Efficiently with Chain of Thought
  Juno Kim (The University of Tokyo / RIKEN AIP)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Weighted Point Cloud Embedding for Multimodal Contrastive Learning
  Toward Optimal Similarity Metric
  Toshimitsu Uesaka (Sony AI)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Yuhta Takida (Sony AI)
  Chieh-Hsin Lai (Sony AI)
  Naoki Murata (Sony AI)
  Yuki Mitsufuji (Sony AI / Sony Group Corporation)
• When Graph Neural Networks Meet Dynamic Mode Decomposition.
  Dai Shi (USYD)
  Lequan Lin (USYD)
  Andi Han (RIKEN AIP)
  Zhiyong Wang (USYD)
  Yi Guo (Western Sydney University)
  Junbin Gao (USYD).

*Intern at RIKEN AIP
**Trainee at RIKEN AIP

Related Laboratories