ICLR 2024 Conference Submissions

How to fix a broken confidence estimator: Evaluating post-hoc methods for selective classification with deep neural networks
Luís Felipe Prates Cattelan, Danilo Silva
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
Oren Mangoubi, Nisheeth K. Vishnoi
- Published: 16 Jan 2024, Last Modified: 12 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
On Robustness-Accuracy Characterization of Large Language Models using Synthetic Datasets
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Yung-Sung Chuang, Luca Daniel
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Counterfactual Fairness on Graphs: Augmentations, Hidden Confounders, and Identifiability
Hongyi Ling, Zhimeng Jiang, Na Zou, Shuiwang Ji
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
An Invariant Information Geometric Method for High-dimensional Online Optimization
Zhengfei Zhang, Yunyue Wei, Yanan Sui
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models
Zeyu Zhou, Ruqi Bai, Sean Kulinski, Murat Kocaoglu, David I. Inouye
- Published: 16 Jan 2024, Last Modified: 21 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Detecting Language Model Attacks With Perplexity
Gabriel Alon, Michael J Kamfonas
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Grokking as the transition from lazy to rich training dynamics
Tanishq Kumar, Blake Bordelon, Samuel J. Gershman, Cengiz Pehlevan
- Published: 16 Jan 2024, Last Modified: 05 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Frequency-Aware Masked Autoencoders for Multimodal Pretraining on Biosignals
Ran Liu, Ellen L. Zippi, Hadi Pouransari, Christopher Michael Sandino, Jingping Nie, Hanlin Goh, Erdrin Azemi, Ali Moin
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
SynBench: Evaluating Pretrained Representations for Image Classification using Synthetic Data
Ching-Yun Ko, Pin-Yu Chen, Payel Das, Jeet Mohapatra, Luca Daniel
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Are training trajectories of deep single-spike and deep ReLU network equivalent?
Ana Stanojevic, Stanisław Woźniak, Guillaume Bellec, Giovanni Cherubini, Angeliki Pantazi, Wulfram Gerstner
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Performance Bounds for Active Binary Testing with Information Maximization
Aditya Chattopadhyay, Benjamin David Haeffele, Rene Vidal, Donald Geman
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
RINGER: Conformer Ensemble Generation of Macrocyclic Peptides with Sequence-Conditioned Internal Coordinate Diffusion
Colin A Grambow, Hayley Weir, Nathaniel Lee Diamant, Tommaso Biancalani, Gabriele Scalia, Kangway V. Chuang
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
Mirco Mutti, Riccardo De Santi, Marcello Restelli, Alexander Marx, Giorgia Ramponi
- Published: 16 Jan 2024, Last Modified: 16 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Language Model Cascades: Token-Level Uncertainty And Beyond
Neha Gupta, Harikrishna Narasimhan, Wittawat Jitkrittum, Ankit Singh Rawat, Aditya Krishna Menon, Sanjiv Kumar
- Published: 16 Jan 2024, Last Modified: 12 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
The Marginal Value of Momentum for Small Learning Rate SGD
Runzhe Wang, Sadhika Malladi, Tianhao Wang, Kaifeng Lyu, Zhiyuan Li
- Published: 16 Jan 2024, Last Modified: 16 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Towards Principled Representation Learning from Videos for Reinforcement Learning
Dipendra Misra, Akanksha Saran, Tengyang Xie, Alex Lamb, John Langford
- Published: 16 Jan 2024, Last Modified: 16 Apr 2024
- ICLR 2024 spotlight
- Readers: Everyone
GIST: Generating Image-Specific Text for Fine-grained Object Representations
Kathleen M. Lewis, Emily Mu, Adrian V Dalca, John Guttag
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
A Fast and Effective Alternative to Graph Transformers
Kaan Sancak, Zhigang Hua, Jin Fang, Yan Xie, Bo Long, Andrey Malevich, Muhammed Fatih Balin, Umit Catalyurek
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Revitalizing Channel-dimension Fourier Transform for Image Enhancement
Jie Huang, Man Zhou, Dong Li, Bing Li, Chun-Le Guo, Chongyi Li
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance
Hannah Lawrence, Mitchell Tong Harris
- Published: 16 Jan 2024, Last Modified: 15 Mar 2024
- ICLR 2024 poster
- Readers: Everyone
Mixture of Weak and Strong Experts on Graphs
Hanqing Zeng, Hanjia Lyu, Diyi Hu, Yinglong Xia, Jiebo Luo
- Published: 16 Jan 2024, Last Modified: 15 Apr 2024
- ICLR 2024 poster
- Readers: Everyone
Explicit Foundation Model Optimization with Self-Attentive Feed-Forward Neural Units
Jake Ryland Williams, Haoran Zhao
- 22 Sept 2023 (modified: 25 Mar 2024)
- ICLR 2024 Conference Withdrawn Submission
- Readers: Everyone
Meta-Learning Strategies through Value Maximization in Neural Networks
Rodrigo Antonio Carrasco-Davis, Javier Alejandro Masís Obando, Andrew M Saxe
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone
Pylic: Leveraging Source Code for Planning in Structured Environments
Leonardo Hernandez Cano, Nathan Hunt, Sara Magliacane, Armando Solar-Lezama
- 22 Sept 2023 (modified: 11 Feb 2024)
- Submitted to ICLR 2024
- Readers: Everyone