ICLR

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression

Lijia Zhou, James B. Simon, Gal Vardi, Nathan Srebro

Comments This is the ICLR CR version

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

Shangbin Feng, Weijia Shi, Yuyang Bai, Vidhisha Balachandran, Tianxing He, Yulia Tsvetkov

Comments ICLR 2024, oral

RAmBLA: A Framework for Evaluating the Reliability of LLMs as Assistants in the Biomedical Domain

William James Bolton, Rafael Poyiadzi, Edward R. Morrell, Gabriela van Bergen Gonzalez Bueno, Lea Goetz

Comments Published at ICLR 2024 Workshop on Reliable and Responsible Foundation Models

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

Sihyun Yu, Weili Nie, De-An Huang, Boyi Li, Jinwoo Shin, Anima Anandkumar

Comments ICLR 2024. Project page: https://sihyun.me/CMD

DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

Xiangxin Zhou, Xiwei Cheng, Yuwei Yang, Yu Bao, Liang Wang, Quanquan Gu

Comments Accepted to ICLR 2024

Efficient Subgraph GNNs by Learning Effective Selection Policies

Beatrice Bevilacqua, Moshe Eliasof, Eli Meirom, Bruno Ribeiro, Haggai Maron

Comments ICLR 2024 Camera Ready; 27 pages, 3 figures

TD-MPC2: Scalable, Robust World Models for Continuous Control

Nicklas Hansen, Hao Su, Xiaolong Wang

Comments ICLR 2024. Explore videos, models, data, code, and more at https://tdmpc2.com

TiC-CLIP: Continual Training of CLIP Models

Saurabh Garg, Mehrdad Farajtabar, Hadi Pouransari, Raviteja Vemulapalli, Sachin Mehta, Oncel Tuzel, Vaishaal Shankar, Fartash Faghri

Comments ICLR 2024

Self-supervised Representation Learning From Random Data Projectors

Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu, George Stein, Xiao Shi Huang, Xiaochen Zhang, Maksims Volkovs

Comments Published as a conference paper of ICLR 2024. https://openreview.net/pdf?id=EpYnZpDpsQ

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Xiaogeng Liu, Nan Xu, Muhao Chen, Chaowei Xiao

Comments Published as a conference paper at ICLR 2024. Code is available at https://github.com/SheltonLiu-N/AutoDAN

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel

Paul Hagemann, Johannes Hertrich, Fabian Altekrüger, Robert Beinert, Jannis Chemseddine, Gabriele Steidl

Comments Published as a conference paper at ICLR 2024

ED-NeRF: Efficient Text-Guided Editing of 3D Scene with Latent Space NeRF

Jangho Park, Gihyun Kwon, Jong Chul Ye

Comments ICLR 2024; Project Page: https://jhq1234.github.io/ed-nerf.github.io/

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

Samuel Pegg, Kai Li, Xiaolin Hu

Comments Accepted by The Twelfth International Conference on Learning Representations (ICLR) 2024, see https://openreview.net/forum?id=PEuDO2EiDr

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

Yang Yang, Wenhai Wang, Zhe Chen, Jifeng Dai, Liang Zheng

Comments ICLR 2024 spotlight

Towards Principled Representation Learning from Videos for Reinforcement Learning

Dipendra Misra, Akanksha Saran, Tengyang Xie, Alex Lamb, John Langford

Comments ICLR 2024 Spotlight Conference Paper

BadEdit: Backdooring large language models by model editing

Yanzhou Li, Tianlin Li, Kangjie Chen, Jian Zhang, Shangqing Liu, Wenhan Wang, Tianwei Zhang, Yang Liu

Comments ICLR 2024

A Unified and General Framework for Continual Learning

Zhenyi Wang, Yan Li, Li Shen, Heng Huang

Comments ICLR 2024

NetInfoF Framework: Measuring and Exploiting Network Usable Information

Meng-Chieh Lee, Haiyang Yu, Jian Zhang, Vassilis N. Ioannidis, Xiang Song, Soji Adeshina, Da Zheng, Christos Faloutsos

Comments Accepted to ICLR 2024 (Spotlight)

Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials

Ivan Grega, Ilyes Batatia, Gábor Csányi, Sri Karlapati, Vikram S. Deshpande

Comments International Conference on Learning Representations 2024

Interpretable Meta-Learning of Physical Systems

Matthieu Blanke, Marc Lelarge

Journal ref The Twelfth International Conference on Learning Representations, ICLR 2024

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, Bo Zhao

Comments Code released at (https://github.com/BAAI-DCAI/Training-Data-Synthesis)

Journal ref ICLR 2024

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

Shreyas Havaldar, Navodita Sharma, Shubhi Sareen, Karthikeyan Shanmugam, Aravindan Raghuveer

Comments Published as a conference paper at The Twelfth International Conference on Learning Representations (ICLR 2024) & Oral Presentation at Regulatable ML @ NeurIPS 2023

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, Lijuan Wang

Comments 40 pages, 32 figures, ICLR 2024

Topological data analysis on noisy quantum computers

Ismail Yunus Akhalwaya, Shashanka Ubaru, Kenneth L. Clarkson, Mark S. Squillante, Vishnu Jejjala, Yang-Hui He, Kugendran Naidoo, Vasileios Kalantzis, Lior Horesh

Comments This paper is a follow up to arXiv:2108.02811 with improved theoretical results and other additional results. This new version presents an improved runtime for the algorithm, and fixes an issue present in the previous version

Journal ref In the Proceedings of The Twelfth International Conference on Learning Representations (ICLR 2024)

AffineQuant: Affine Transformation Quantization for Large Language Models

Yuexiao Ma, Huixia Li, Xiawu Zheng, Feng Ling, Xuefeng Xiao, Rui Wang, Shilei Wen, Fei Chao, Rongrong Ji

Comments ICLR 2024

Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram

Yeongyeon Na, Minje Park, Yunwon Tae, Sunghoon Joo

Comments ICLR 2024. The first three authors contribute equally

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

Grzegorz Rypeść, Sebastian Cygert, Valeriya Khan, Tomasz Trzciński, Bartosz Zieliński, Bartłomiej Twardowski

Comments Accepted for ICLR 2024 (main track), code is available at: https://github.com/grypesc/SEED

Differentiable Euler Characteristic Transforms for Shape Classification

Ernst Roell, Bastian Rieck

Comments Accepted at ICLR 2024 (https://openreview.net/forum?id=MO632iPq3I)

Do Generated Data Always Help Contrastive Learning?

Yifei Wang, Jizhe Zhang, Yisen Wang

Comments 19 pages. Accepted by ICLR 2024

Improving LoRA in Privacy-preserving Federated Learning

Youbang Sun, Zitao Li, Yaliang Li, Bolin Ding

Comments published at ICLR 2024, full paper 17 pages