ICLR

Correcting Biased Centered Kernel Alignment Measures in Biological and Artificial Neural Networks

Alex Murphy, Joel Zylberberg, Alona Fyshe

Comments ICLR 2024 Re-Align Workshop

S$^2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic

Safa Messaoud, Billel Mokeddem, Zhenghai Xue, Linsey Pang, Bo An, Haipeng Chen, Sanjay Chawla

Comments Accepted for publication at ICLR 2024

F$^3$low: Frame-to-Frame Coarse-grained Molecular Dynamics with SE(3) Guided Flow Matching

Shaoning Li, Yusong Wang, Mingyu Li, Jian Zhang, Bin Shao, Nanning Zheng, Jian Tang

Comments Accepted by ICLR 2024 GEM workshop

Evaluating Tool-Augmented Agents in Remote Sensing Platforms

Simranjit Singh, Michael Fore, Dimitrios Stamoulis

Comments ICLR 2024 Machine Learning for Remote Sensing (ML4RS) Workshop

Learning to Embed Time Series Patches Independently

Seunghan Lee, Taeyoung Park, Kibok Lee

Comments ICLR 2024

On the Learnability of Watermarks for Language Models

Chenchen Gu, Xiang Lisa Li, Percy Liang, Tatsunori Hashimoto

Comments Accepted at ICLR 2024

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances

Mikhail Khodak, Edmond Chow, Maria-Florina Balcan, Ameet Talwalkar

Comments ICLR 2024 Spotlight

TExplain: Explaining Learned Visual Features via Pre-trained (Frozen) Language Models

Saeid Asgari Taghanaki, Aliasghar Khani, Ali Saheb Pasand, Amir Khasahmadi, Aditya Sanghi, Karl D. D. Willis, Ali Mahdavi-Amiri

Comments Accepted to ICLR 2024, Reliable and Responsible Foundation Models workshop

On the Reliability of Watermarks for Large Language Models

John Kirchenbauer, Jonas Geiping, Yuxin Wen, Manli Shu, Khalid Saifullah, Kezhi Kong, Kasun Fernando, Aniruddha Saha, Micah Goldblum, Tom Goldstein

Comments 9 pages in the main body. Published at ICLR 2024. Code is available at https://github.com/jwkirchenbauer/lm-watermarking

Time-Varying Propensity Score to Bridge the Gap between the Past and Present

Rasool Fakoor, Jonas Mueller, Zachary C. Lipton, Pratik Chaudhari, Alexander J. Smola

Comments Published at ICLR 2024

Quadratic models for understanding catapult dynamics of neural networks

Libin Zhu, Chaoyue Liu, Adityanarayanan Radhakrishnan, Mikhail Belkin

Comments accepted in ICLR 2024; changed the title

Are Models Biased on Text without Gender-related Language?

Catarina G Belém, Preethi Seshadri, Yasaman Razeghi, Sameer Singh

Comments In International Conference on Learning Representations 2024

Exploring the Robustness of In-Context Learning with Noisy Labels

Chen Cheng, Xinzhi Yu, Haodong Wen, Jingsong Sun, Guanzhang Yue, Yihao Zhang, Zeming Wei

Comments ICLR 2024 Workshop on Reliable and Responsible Foundation Models

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

Mohamed Elsayed, A. Rupam Mahmood

Comments Published in the Proceedings of the 12th International Conference on Learning Representations (ICLR 2024). Code is available at https://github.com/mohmdelsayed/upgd

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

Yu Tian, Min Shi, Yan Luo, Ava Kouhana, Tobias Elze, Mengyu Wang

Comments ICLR 2024; Codes available at https://github.com/Harvard-Ophthalmology-AI-Lab/FairSeg

Eureka: Human-Level Reward Design via Coding Large Language Models

Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, Anima Anandkumar

Comments ICLR 2024. Project website and open-source code: https://eureka-research.github.io/

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

Jonas Belouadi, Anne Lauscher, Steffen Eger

Comments Accepted at ICLR 2024 (poster); Project Page: https://github.com/potamides/AutomaTikZ

Journal ref The Twelfth International Conference on Learning Representations, 2024

Prediction without Preclusion: Recourse Verification with Reachable Sets

Avni Kothari, Bogdan Kulynych, Tsui-Wei Weng, Berk Ustun

Comments ICLR 2024 Spotlight. The first two authors contributed equally

MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation

Min Zhang, Haoxuan Li, Fei Wu, Kun Kuang

Comments ICLR 24

Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference

Haoxuan Li, Chunyuan Zheng, Sihao Ding, Peng Wu, Zhi Geng, Fuli Feng, Xiangnan He

Comments ICLR 24

Debiased Collaborative Filtering with Kernel-Based Causal Balancing

Haoxuan Li, Chunyuan Zheng, Yanghao Xiao, Peng Wu, Zhi Geng, Xu Chen, Peng Cui

Comments ICLR 24 Spotlight

Contrastive Preference Learning: Learning from Human Feedback without RL

Joey Hejna, Rafael Rafailov, Harshit Sikchi, Chelsea Finn, Scott Niekum, W. Bradley Knox, Dorsa Sadigh

Comments ICLR 2024. Code released at https://github.com/jhejna/cpl

NOLA: Compressing LoRA using Linear Combination of Random Basis

Soroush Abbasi Koohpayegani, KL Navaneet, Parsa Nooralinejad, Soheil Kolouri, Hamed Pirsiavash

Comments ICLR 2024. Our code is available here: https://github.com/UCDvision/NOLA

Universal Jailbreak Backdoors from Poisoned Human Feedback

Javier Rando, Florian Tramèr

Comments Accepted as conference paper in ICLR 2024

Annotating Ambiguous Images: General Annotation Strategy for High-Quality Data with Real-World Biomedical Validation

Lars Schmarje, Vasco Grossmann, Claudius Zelenka, Johannes Brünger, Reinhard Koch

Comments Accepted at ICLR 2024, DMLR Workshop

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Divyat Mahajan, Ioannis Mitliagkas, Brady Neal, Vasilis Syrgkanis

Comments Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024. (Spotlight)

Neural-Symbolic Recursive Machine for Systematic Generalization

Qing Li, Yixin Zhu, Yitao Liang, Ying Nian Wu, Song-Chun Zhu, Siyuan Huang

Comments ICLR 2024. Project website: https://liqing-ustc.github.io/NSR/

Cauchy-Schwarz Divergence Information Bottleneck for Regression

Shujian Yu, Xi Yu, Sigurd Løkse, Robert Jenssen, Jose C. Principe

Comments accepted by ICLR-24, project page: \url{https://github.com/SJYuCNEL/Cauchy-Schwarz-Information-Bottleneck}

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

Yassine Abbahaddou, Sofiane Ennadir, Johannes F. Lutzeyer, Michalis Vazirgiannis, Henrik Boström

Comments Accepted at ICLR 2024

Hard ASH: Sparsity and the right optimizer make a continual learner

Santtu Keskinen

Comments ICLR 2024 TinyPaper