Papers
Award Winners
Entropic Award - Most Surprising Negative Result
The Best Deep Ensembles Sacrifice Predictive Diversity Taiga Abe, E. Kelly Buchanan, Geoff Pleiss, John Patrick Cunningham (Poster)
Didactic Award - Most Well Written paper
Much Easier Said Than Done: Falsifying the Causal Relevance of Decoding Methods Lucas Hayne, Abhijit Suresh, Hunar Jain, Rahul Kumar Mohan Kumar, R. McKell Carter
Best Poster
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations Yongyi Yang, Jacob Steinhardt, Wie Hu (Poster)
Accepted Papers
How many trained neural networks are needed for influence estimation in modern deep learning? Sasha Doubov, Tianshi Cao, David Acuna, Sanja Fidler (Poster)
Analysing the Relations of Misclassified Inputs Between Models Hadar Shavit (Poster)
When Does Re-initialization Work? Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jorg Bornschein, Claudia Clopath, Yee Whye Teh, Razvan Pascanu (spotlight video) (Poster)
On the performance of Direct Loss Minimization for Bayesian Neural Networks Yadi Wei, Roni Khardon (Poster)
Are you using test log-likelihood correctly? Sameer Deshpande, Soumya Ghosh, Tin D. Nguyen, Tamara Broderick (Poster)
Exploring the Sharpened Cosine Similarity Skyler Wu, Fred Lu, Edward Raff, James Holt (Poster)
DARTFormer: Finding The Best Type Of Attention Jason Ross Brown, Yiren Zhao, Ilia Shumailov, Robert D. Mullins (Poster)
Adversarial Attacks are a Surprisingly Strong Baseline for Poisoning Few-Shot Meta-Learners Elre Talea Oldewage, John F Bronskill, Richard E Turner (Poster)
When Are Graph Neural Networks Better Than Structure-Agnostic Methods? Diana Gomes, Frederik Ruelens, Kyriakos Efthymiadis, Ann Nowe, Peter Vrancx (Poster)
An Empirical Study on Clustering Pretrained Embeddings: Is Deep Strictly Better? Tyler R. Scott, Ting Liu, Michael Curtis Mozer, Andrew Gallagher (Poster)
Denoising Deep Generative Models Gabriel Loaiza-Ganem, Brendan Leigh Ross, Luhuan Wu, John Patrick Cunningham, Jesse C Cresswell, Anthony L. Caterini (Poster)
Paradigmatic Revolutions in Computer Vision Andreas Kriegler (Poster)
Model Stitching: Looking For Functional Similarity Between Representations Adriano Hernandez, Rumen Dangovski, Peter Y. Lu (Poster)
On the Maximum Hessian Eigenvalue and Generalization Simran Kaur, Jeremy Cohen, Zachary Chase Lipton (Poster)
Are Neurons Actually Collapsed? On the Fine-Grained Structure in Neural Representations Yongyi Yang, Jacob Steinhardt, Wie Hu (Poster)
Continuous Soft Pseudo-Labeling in ASR Tatiana Likhomanenko, Ronan Collobert, Navdeep Jaitly, Samy Bengio (Poster)
An Empirical Analysis of the Advantages of Finite v.s. Infinite Width Bayesian Neural Networks Jiayu Yao, Yaniv Yacoby, Beau Coker, Weiwei Pan, Finale Doshi-Velez (Poster)
Lessons from Developing Multimodal Models with Code and Developer Interactions Nicholas Botzer, Sameera Horawalavithana, Tim Weninger, Svitlana Volkova (Poster)
On The Diversity of ASR Hypotheses In Spoken Language Understanding Surya Kant Sahu, Swaraj Dalmia (Poster)
Volume-based Performance not Guaranteed by Promising Patch-based Results in Medical Imaging Abhishek Moturu, Sayali Joshi, Andrea S. Doria, Anna Goldenberg (Poster)
Models with Conditional Computation Learn Suboptimal Solutions Muqeeth Mohammed, Haokun Liu, Colin Raffel (Poster)
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts Yoonho Lee, Annie S Chen, Fahim Tajwar, Ananya Kumar, Huaxiu Yao, Percy Liang, Chelsea Finn (Poster)
Can We Forecast And Detect Earthquakes From Heterogeneous Multivariate Time Series Data? Asadullah Hill Galib, Luke Cullen, Andrew William Smith, Debvrat Varshney, Edward Brown, Peter Chi, Xiangning Chu, Filip Svoboda (Poster)
The Best Deep Ensembles Sacrifice Predictive Diversity Taiga Abe, E. Kelly Buchanan, Geoff Pleiss, John Patrick Cunningham (Poster)
The Effect of Data Dimensionality on Neural Network Prunability Zachary Ankner, Alex Renda, Gintare Karolina Dziugaite, Jonathan Frankle, Tian Jin (Poster)
Pitfalls of conditional computation for multi-modal learning Ivaxi Sheth, Mohammad Havaei, Samira Ebrahimi Kahou (Poster)
Spread Love Not Hate: Undermining the Importance of Hateful Pre-training for Hate Speech Detection Omkar Bhushan Gokhale, Aditya Kane, Shantanu Patankar, Tanmay Chavan, Raviraj Bhuminand Joshi (Poster)
Dynamic Statistical Learning with Engineered Features Outperforms Deep Neural Networks for Smart Building Cooling Load Predictions Yiren Liu, S. Joe Qin, Xiangyu Zhao, Yixiao HUANG, Shenglong Yao, Guo Han (Poster)
Scaling Laws Beyond Backpropagation Matthew Filipovich, Alessandro Cappelli, Daniel Hesslow, Julien Launay (Poster)
Exploring the Long-Term Generalization of Counting Behavior in RNNs Nadine El-Naggar, Pranava Madhyastha, Tillman Weyde (Poster)
On the Sparsity of Image Super-resolution Network Chenyu Dong, Hailong Ma, Jinjin Gu, Ruofan Zhang, Jieming Li, Chun Yuan (Poster)
Spike-and-Slab Probabilistic Backpropagation: When Smarter Approximations Make No Difference Evan Ott, Sinead Williamson (Poster)
Evaluating Robust Perceptual Losses for Image Reconstruction Tobias Uelwer, Felix Michels, Oliver De Candido
Much Easier Said Than Done: Falsifying the Causal Relevance of Decoding Methods Lucas Hayne, Abhijit Suresh, Hunar Jain, Rahul Kumar Mohan Kumar, R. McKell Carter
Lempel-Ziv Networks Rebecca Saul, Mohammad Mahmudul Alam, John Hurwitz, Edward Raff, Tim Oates, James Holt
On Equivalences between Weight and Function-Space Langevin Dynamics Ziyu Wang, Yuhao Zhou, Ruqi Zhang, Jun Zhu
The curse of (non)convexity: The case of an Optimization-Inspired Data Pruning algorithm Fadhel Ayed, Soufiane Hayou
Identifying the Context Shift between Test Benchmarks and Production Data Matthew Groh
Certified defences hurt generalization Piersilvio De Bartolomeis, Jacob Clarysse, Fanny Yang, Amartya Sanyal
The (Un)Scalability of Heuristic Approximators for NP-Hard Search Problems Sumedh Pendurkar, Taoan Huang, Sven Koenig, Guni Sharon