Center for Advanced Intelligence Project

41 papers were accepted at NeurIPS 2024, which is known as a top conference on machine learning.
For more details, please refer to the link below:
[NeurIPS 2024 ]
There were 15,671 full paper submissions to NeurIPS this year, of which the program committee accepted 25.8% for presentation at the conference.

Spotlight

• Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
  Thibault Simonetto (University of Luxembourg)
  Salah Ghamizi (LIST / RIKEN AIP)
  Maxime Cordy (University of Luxembourg)

• Slight Corruption in Pre-training Data Makes Better Diffusion Models
  Hao Chen (Carnegie Mellon University)
  Yujin Han (Tthe University of Hong Kong)
  Diganta Misra (Max-Planck-Institute for Intelligent Systems)
  Xiang Li (Carnegie Mellon University)
  Kai Hu (Carnegie Mellon University)
  Difan Zou (Tthe University of Hong Kong)
  Masashi Sugiyama (RIKEN AIP/The University of Tokyo)
  Jindong Wang (Microsoft Research)
  Bhiksha Raj (Carnegie Mellon University)
• SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
  Jian Song (The University of Tokyo / RIKEN AIP)
  Hongruixuan Chen (The University of Tokyo / RIKEN AIP)
  Weihao Xuan (The University of Tokyo / RIKEN AIP)
  Junshi Xia (RIKEN AIP)
  Naoto Yokoya (The University of Tokyo / RIKEN AIP)

Poster

• A framework for bilevel optimization on Riemannian manifold
  Andi Han (RIKEN AIP)
  Bamdev Mishra (Microsoft India)
  Pratik Jawanpuria (Microsoft India)
  Akiko Takeda (RIKEN AIP / The University of Tokyo)
• A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of Θ(T2/3) and its Application to Best-of-Both-Worlds
  Taira Tsuchiya (The University of Tokyo / RIKEN AIP)
  Shinji Ito (The University of Tokyo / RIKEN AIP)
• Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
  Yivan Zhang (The University of Tokyo)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
  Taira Tsuchiya (The University of Tokyo / RIKEN AIP)
  Shinji Ito (The University of Tokyo / RIKEN AIP)
• Federated Learning from Vision-Language Foundation Models:
  Theoretical Analysis and Method
  Bikang Pan (ShanghaiTech University)
  Wei Huang (RIKEN AIP)
  Ye Shi (ShanghaiTech University)
• Fixed Confidence Best Arm Identification in the Bayesian Setting
  Kyoungseok Jang (Universitá degli Studi di Milano)
  Junpei Komiyama (New York University / RIKEN AIP)
  Kazutoshi Yamazaki (The University of Queensland)
• Generalizable and Animatable Gaussian Head Avatar
  Xuangeng Chu (The University of Tokyo)
  Tatsuya Harada (The University of Tokyo / RIKEN AIP)
• Generalization bound and learning methods for data-driven projections in linear programming
  Shinsaku Sakaue (The University of Tokyo / RIKEN AIP)
  Taihei Oki (Hokkaido University)
• Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
  Andong Wang (RIKEN AIP)
  Yuning Qiu (RIKEN AIP)
  Mingyuan Bai (RIKEN AIP)
  Zhong Jin (China University of Petroleum-Beijing at Karamay)
  Guoxu Zhou (Guangdong University of Technology)
  Qibin Zhao (RIKEN AIP)
• Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
  Hao Chen (Carnegie Mellon University)
  Ankit Shah (Carnegie Mellon University)
  Jindong Wang (Microsoft Research)
  Ran Tao (Carnegie Mellon University)
  Yidong Wang (Peking University)
  Xiang Li (Carnegie Mellon University)
  Xing Xie (Microsoft Research)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Rita Singh (Carnegie Mellon University)
  Bhiksha Raj (Carnegie Mellon University)
• Information-theoretic Generalization Analysis for Expected Calibration Error
  Futoshi Futami* (Osaka University)
  Masahiro Fujisawa* (RIKEN AIP)
  *Equal contribution
• Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
  Zhikang Chen (Tsinghua University)
  Min Zhang (Zhejiang University)
  Sen Cui (Tsinghua University)
  Haoxuan Li (Peking University)
  Gang Niu (RIKEN AIP)
  Mingming Gong (University of Melbourne / MBZUAI)
  Changshui Zhang (Tsinghua University)
  Kun Zhang (MBZUAI / CMU)
• Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
  Kazusato Oko*(The University of Tokyo / RIKEN AIP)
  Denny Wu* (New York University / Flatiron Institute)
  Jason D. Lee* (Princeton University)
  Taiji Suzuki* (The University of Tokyo / RIKEN AIP)
• No-regret M♮-concave function maximization: Stochastic bandit algorithms and NPhardness of adversarial full-information setting
  Taihei Oki (Hokkaido University)
  Shinsaku Sakaue (The University of Tokyo / RIKEN AIP)
• Novel Object Synthesis via Adaptive Text-Image Harmony
  Zeren Xiong (NJUST)
  Ze-dong Zhang (NJUST)
  Zikun Chen (NJUST)
  Shuo Chen (RIKEN AIP)
  Gan Sun (Chinese Academy of Sciences)
  Jian Yang (NJUST)
  Jun Li (NJUST)
• On Mesa-Optimization in Autoregressively Trained Transformers:
  Emergence and Capability
  Chenyu Zheng (Renmin University of China)
  Wei Huang (RIKEN AIP)
  Rongzhen Wang (Renmin University of China)
  Guoqiang Wu (Shandong University)
  Jun Zhu (Tsinghua University)
  Chongxuan Li (Renmin University of China)
• On the Comparison between Multi-modal and Single-modal Contrastive Learning
  Wei Huang (RIKEN AIP)*
  Andi Han (RIKEN AIP)*
  Yongqiang Chen (The Chinese University of Hong Kong)
  Yuan Cao (University of Hong Kong)
  Zhiqiang Xu (MBZUAI)
  Taiji Suzuki (RIKEN AIP / The University of Tokyo)
  *Equal contribution
• On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
  Shinji Ito (The University of Tokyo / RIKEN AIP)
• Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
  Qin-Wen Luo (NUAA)
  Ming-Kun Xie (NUAA/RIKEN AIP)
  Ye-Wen Wang (NUAA)
  Sheng-Jun Huang (NUAA)
• Perplexity-aware Correction for Robust Alignment with Noisy Preferences
  Keyi Kong (Shandong University)
  Xilie Xu (NUS)
  Di Wang (KAUST)
  Jingfeng Zhang (University of Auckland / RIKEN AIP)
  Mohan Kankanhalli (NUS)
• Provable and Efficient Dataset Distillation for Kernel Ridge Regression
  Yilan Chen (UCSD/ RIKEN AIP)
  Wei Huang (RIKEN AIP)
  Tsui-Wei Weng (UCSD)
• Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
  Dake Bu (City University of Hong Kong)
  Wei Huang (RIKEN AIP)
  Andi Han (RIKEN AIP)
  Atsushi Nitanda (A*STAR)
  Taiji Suzuki (RIKEN AIP / The University of Tokyo)
  Qingfu Zhang (City University of Hong Kong)
  Hau-San Wong (City University of Hong Kong)
• Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
  Geng Yu (Shanghai Jiao Tong University)
  Jianing Zhu (Hong Kong Baptist University)
  Jiangchao Yao (Shanghai Jiao Tong University/Shanghai A I Laboratory)
  Bo Han (Hong Kong Baptist University/RIKEN AIP)
• SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
  Andi Han (RIKEN AIP)
  Jiaxiang Li (University of Minnesota)
  Wei Huang (RIKEN AIP)
  Mingyi Hong (University of Minnesota)
  Akiko Takeda (RIKEN AIP / The University of Tokyo)
  Pratik Jawanpuria (Microsoft India)
  Bamdev Mishra (Microsoft India)
• Stepwise Alignment for Constrained Language Model Policy Optimization
  Akifumi Wachi (LY Corporation)
  Thien Q. Tran (LY Corporation)
  Rei Sato (LY Corporation)
  Takumi Tanabe (LY Corporation)
  Youhei Akimoto (University of Tsukuba / RIKEN AIP)
• TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
  Thibault Simonetto (University of Luxembourg)
  Salah Ghamizi (LIST / RIKEN AIP)
  Maxime Cordy (University of Luxembourg)
• Tempered Calculus for ML: Application to Hyperbolic Model Embedding
  Richard Nock (Google Research)
  Ehsan Amid (Google DeepMind)
  Frank Nielsen (Sony CS Labs, Inc.)
  Alexander Soen (RIKEN AIP / The Australian National University)
  Manfred K. Warmuth (Google Research)
• Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
  Zhen-Yu Zhang (RIKEN AIP)
  Zhiyu Xie (Stanford University)
  Huaxiu Yao (University of North Carolina at Chapel Hill)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
• TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
  Huanan LI (Xidian University)
  Juntao Guan (Xidian University)
  Lai Rui (Xidian University)
  Sijun Ma (Xidian University)
  Lin Gu (RIKEN AIP)
  Zhangming Zhu (Xidian University)
• Towards Multi-dimensional Explanation Alignment for Medical Classification
  Lijie Hu (KAUST)
  Songning Lai (Shandong University)
  Wenshuo Chen (Shandong University)
  Hongru Xiao (Tongji University)
  Hongbin Lin (HKUST)
  Lu Yu (KAUST)
  Jingfeng Zhang (University of Auckland / RIKEN AIP)
  Di Wang (KAUST)
• Tradeoffs of Diagonal Fisher Information Matrix Estimators
  Alexander Soen (The Australian National University / RIKEN AIP)
  Ke Sun (CSIRO’s Data61 / The Australian National University)
• Transformers are Minimax Optimal Nonparametric In-Context Learners
  Juno Kim (The University of Tokyo / RIKEN AIP)
  Tai Nakamaki (The University of Tokyo)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
• Transformer Efficiently Learns Low-dimensional Target Functions In-context
  Kazusato Oko* (University of Tokyo / RIKEN AIP)
  Yujin Song* (The University of Tokyo)
  Taiji Suzuki* (University of Tokyo / RIKEN AIP)
  Denny Wu* (New York University / Flatiron Institute)
• Understanding the expressivity and trainability of Fourier Neural Operator
  Takeshi Koshizuka (The University of Tokyo)
  Masahiro Fujisawa (RIKEN AIP)
  Yusuke Tanaka (NTT Communication Science Laboratories)
  Issei Sato (The University of Tokyo)
• Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization Jiarui Jiang (Harbin Institute of Technology, Shenzhen)
  Wei Huang (RIKEN AIP)
  Miao Zhang (Harbin Institute of Technology, Shenzhen)
  Taiji Suzuki (The University of Tokyo / RIKEN AIP)
  Liqiang Nie (Harbin Institute of Technology, Shenzhen)
• What If the Input is Expanded in OOD Detection?
  Boxuan Zhang (Wuhan University)
  Jianing Zhu (Hong Kong Baptist University)
  Zengmao Wang (Wuhan University)
  Tongliang Liu (The University of Sydney)
  Bo Du (Wuhan University)
  Bo Han (Hong Kong Baptist University/RIKEN AIP)
• What Makes Partial-Label Learning Algorithms Effective?
  Jiaqi Lv (Southeast University)
  Yangfan Liu (Southeast University)
  Shiyu Xia (Southeast University)
  Ning Xu (Southeast University)
  Miao Xu (University of Queensland)
  Gang Niu (RIKEN AIP)
  Min-Ling Zhang (Southeast University)
  Masashi Sugiyama (RIKEN AIP / The University of Tokyo)
  Xin Geng (Southeast University)
• Zipfian Whitening
  Sho Yokoi (Tohoku University / RIKEN AIP)
  Han Bao (Kyoto University),
  Hiroto Kurita (Tohoku University)
  Hidetoshi Shimodaira(Kyoto University / RIKEN AIP)

Related Laboratories