Center for Advanced Intelligence Project

34 papers were accepted at ICLR 2026, a major conference on machine learning.

For more details, please refer to the link below.
https://iclr.cc/

• Accessible, Realistic, and Fair Evaluation of Positive-Unlabeled Learning Algorithms
  Wei Wang (RIKEN AIP / University of Tokyo)
  Dong-Dong Wu (University of Tokyo / RIKEN AIP)
  Ming Li (University of Maryland, College Park)
  Jingxiong Zhang (University of Tokyo)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Bayesian Parameter Shift Rules in Variational Quantum Eigensolvers
  Samuele Pedrielli (BIFOLD / TU Berlin)
  Christopher Anders (RIKEN AIP)
  Lena Funcke (University of Bonn, HISKP)
  Karl Jansen (DESY Zeuthen, The Cyprus Institute)
  Kim A. Nicoli (Oldendorff Carriers)
  Shinichi Nakajima (BIFOLD, TU Berlin / RIKEN AIP)
• Bilateral Information-aware Test-time Adaptation for Vision-Language Models
  Jingwei Sun (Hong Kong Baptist University)++
  Jianing Zhu (Hong Kong Baptist University)
  Jiangchao Yao (Shanghai Jiao Tong University)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
• CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Vision-Language Model
  Ruijiang Dong (University of Melbourne)
  Zesheng Ye (University of Melbourne)
  Feng Liu (University of Melbourne / RIKEN AIP)
  Jianzhong Qi (University of Melbourne)
  Lei Feng (Southeast University / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Cross-Embodiment Offline Reinforcement Learning for Heterogeneous Robot Datasets
  Haruki Abe (University of Tokyo / RIKEN AIP)
  Takayuki Osa (RIKEN AIP)
  Yusuke Mukuta (University of Tokyo)
  Tatsuya Harada (University of Tokyo / RIKEN AIP)
• Decoupling the Class Label and the Target Concept in Machine Unlearning
  Jianing Zhu (Hong Kong Baptist University / RIKEN AIP)+
  Bo Han (Hong Kong Baptist University)
  Jiangchao Yao (Shanghai Jiao Tong University)
  Jianliang Xu (Hong Kong Baptist University)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Diffusion Bridge Variational Inference for Deep Gaussian Processes
  Jian Xu (South China University of Technology/ RIKEN AIP) +
  Delu Zeng (South China University of Technology)
  Qibin Zhao (RIKEN AIP)
  John Paisley (Columbia University)
• Dynamical Properties of Dense Associative Memory
  Kazushi Mimura (Hiroshima City University/ RIKEN AIP)
  Jun’ichi Takeuchi (Kyushu University)
  Yuto Sumikawa (University of Tokyo)
  Yoshiyuki Kabashima (University of Tokyo)
  Anthony C. C. Coolen (Radboud University)
• Expert Heads: Robust Evidence Identification for Large Language Models.
  Qi Wu (Soochow University)
  Jianfeng Qu (Renmin University of China)
  Ximing Li (Jilin University / RIKEN AIP)
  Zhixu Li (Renmin University of China)
• Fast Escape, Slow Convergence: Learning Dynamics of Phase Retrieval under Power-Law Data
  Guillaume Braun (RIKEN AIP)
  Bruno Loureiro (Ecole Normale Supérieure)
  Minh Ha Quang (RIKEN AIP)
  Masaaki Imaizumi (University of Tokyo / RIKEN AIP)
• Fast Frank–Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
  Shota Takahashi (University of Tokyo)
  Sebastian Pokutta (ZIB / TU Berlin)
  Akiko Takeda (University of Tokyo / RIKEN AIP)
• Federated ADMM from Bayesian Duality
  Thomas Möllenhoff (RIKEN AIP)
  Siddharth Swaroop (University College London, London)
  Finale Doshi-Velez (Harvard University N / Cambridge, United States)
  Mohammad Emtiyaz Khan (RIKEN AIP)
• HEEGNet: Hyperbolic Embeddings for EEG
  Shanglin Li (ATR / RIKEN AIP)
  Chu Shiwen (NAIST / ATR)
  Okan Koc (RIKEN AIP)
  Yi Ding (Nanyang Technological University)
  Qibin Zhao (RIKEN AIP)
  Motoaki Kawanabe (ATR)
  Ziheng Chen (University of Trento)
• JAPAN: Joint Adaptive Prediction Areas with Normalising-Flows
  Eshant English (Hasso Plattner Institute / University of Tokyo/ RIKEN AIP)
  Christoph Lippert (Hasso Plattner Institute/ Icahn School of Medicine at Mount Sinai)
• Learning from Label Proportions via Proportional Value Classification
  Tianhao Ma (University of Tokyo)
  Wei Wang (RIKEN AIP / University of Tokyo)
  Ximing Li (Jilin University / RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP/ University of Tokyo)
• Learning Semi-Structured Sparsity for LLMs via Shared and Context-Aware Hypernetwork
  Lu Sun (RIKEN AIP)
  Jun Sakuma (RIKEN AIP/Science Tokyo)
• Neuron-Level Analysis of Cultural Understanding in Large Language Models
  Taisei Yamamoto (University of Tokyo / RIKEN AIP)
  Ryoma Kumon (University of Tokyo / RIKEN AIP)
  Danushka Bollegala (University of Liverpool)
  Hitomi Yanaka (University of Tokyo / RIKEN AIP / Tohoku University)
• Noisy-Pair Robust Representation Alignment for Positive-Unlabeled Learning
  Hengwei Zhao (Texas A&M University)
  Zhengzhong Tu (Texas A&M University)
  Zhuo Zheng (Stanford University)
  Wei Wang (RIKEN AIP / University of Tokyo)
  Junjue Wang (University of Tokyo)
  Rusty Feagin (Texas A&M University)
  Wenzhe Jiao (Texas A&M University)
• Practical estimation of the optimal classification error with soft labels and calibration
  Ryota Ushio (University of Tokyo / RIKEN AIP)
  Takashi Ishida (RIKEN AIP / University of Tokyo)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
  Naoki Morihira (Honda R&D Co., Ltd. / University of Tokyo)
  Amal Nahar (Honda R&D Co., Ltd.)
  Kartik Bharadwaj (Honda R&D Co., Ltd.)
  Yasuhiro Kato (University of Tokyo)
  Akinobu Hayashi (Honda R&D Co., Ltd. / University of Tokyo)
  Tatsuya Harada (University of Tokyo / RIKEN AIP)
• Rethinking Consistent Multi-Label Classification Under Inexact Supervision
  Wei Wang (RIKEN AIP/ University of Tokyo)
  Tianhao Ma (University of Tokyo)
  Ming-Kun Xie (RIKEN AIP)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning
  Naoki Shitanda (University of Tokyo / RIKEN AIP )
  Motoki Omura (University of Tokyo)
  Tatsuya Harada (University of Tokyo / RIKEN AIP)
  Takayuki Osa (RIKEN AIP)
• Rewriting Pre-Training Data Boosts LLM Performance in Math and Code
  Kazuki Fujii (Science Tokyo)
  Yukito Tajima (Science Tokyo)
  Sakae Mizuki (Science Tokyo)
  Masaki Kawamura (Science Tokyo)
  Hinari Shimada (Science Tokyo)
  Taihei Shiotani (Science Tokyo)
  Koshiro Saito (Science Tokyo)
  Masanari Oi (Science Tokyo),
  Taishi Nakamura (Science Tokyo)
  Takumi Okamoto (Science Tokyo)
  Shigeki Ishida　(Science Tokyo)
  Kakeru Hattori (Science Tokyo)
  Youmi Ma (Science Tokyo)
  Hiroya Takamura (AIST)
  Rio Yokota (Science Tokyo)
  Jun Sakuma (RIKEN AIP /Science Tokyo)
  Naoaki Okazaki (Science Tokyo)
• Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation
  Shojiro Yamabe (Science Tokyo)
  Kazuto Fukuchi (University of Tsukuba/RIKEN AIP)
  Jun Sakuma (RIKEN AIP/Science Tokyo)
• Scalable Oversight via Partitioned Human Supervision
  Ren Yin (University of Tokyo / RIKEN AIP)
  Takashi Ishida (RIKEN AIP / University of Tokyo)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Smooth Calibration Error: Uniform Convergence and Functional Gradient Analysis
  Futoshi Futami (University of Osaka / RIKEN AIP / University of Tokyo)
  Atsushi Nitanda(A*STAR / Nanyang Technological University)
• Submodular Function Minimization with Dueling Oracle
  Kaien Sho (University of Tokyo)
  Shinji Ito (University of Tokyo / RIKEN AIP)
• Toward Safer Diffusion Language Models: Discovery and Mitigation of Priming Vulnerability
  Shojiro Yamabe (Science Tokyo)
  Jun Sakuma (RIKEN AIP/ Science Tokyo)
• Towards Understanding Valuable Preference Data for Large Language Model Alignment
  Zizhuo Zhang (Hong Kong Baptist University) ++
  Qizhou Wang (RIKEN AIP / Hong Kong Baptist University)
  Shanshan Ye (University of Technology Sydney)
  Jianing Zhu (Hong Kong Baptist University)
  Jiangchao Yao (Shanghai Jiao Tong University)
  Bo Han (Hong Kong Baptist University / RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Transformers as a Measure-Theoretic Associative Memory: A Statistical Perspective
  Ryotaro Kawata (University of Tokyo / RIKEN AIP)
  Taiji Suzuki (University of Tokyo / RIKEN AIP)
• Unlearning Evaluation through Subset Statistical Independence.
  Chenhao Zhang (University of Queensland / University of Melbourne)
  Muxing Li (University of Melbourne)
  Feng Liu (University of Melbourne / RIKEN AIP)
  Weitong Chen (Adelaide University)
  Miao Xu (University of Queensland / RIKEN AIP)
• Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification
  Ming-Kun Xie (RIKEN AIP)
  Zhiqiang Kou (Hong Kong Polytechnic University)
  Zhongnian Li (China University of Mining Technology)
  Gang Niu (RIKEN AIP)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
• Weak-to-Strong Diffusion
  Lichen Bai (Hong Kong University of Science and Technology, Guangzhou)
  Masashi Sugiyama (RIKEN AIP / University of Tokyo)
  Zeke Xie (Hong Kong University of Science and Technology, Guangzhou)
• Why High-rank Neural Networks Generalize?: An Algebraic Framework with RKHSs
  Yuka Hashimoto (NTT Corporation / RIKEN AIP)
  Sho Sonoda (RIKEN AIP)
  Isao Ishikawa (Kyoto University / RIKEN AIP)
  Masahiro Ikeda (University of Osaka / RIKEN AIP)

+Intern at RIKEN AIP
++Trainee at RIKEN AIP (including remote trainees)

Related Laboratories