NeurIPS 2023 Workshop UniReps Submissions

Understanding Learning Dynamics of Neural Representations via Feature Visualization at Scale
Chandana Kuntala, Carlos R Ponce, Deepak Kumar Sharma, Binxu Wang
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Linearly Structured World Representations in Maze-Solving Transformers
Michael Ivanitskiy, Alexander F Spies, Tilman Räuker, Guillaume Corlouer, Christopher Mathwin, Lucia Quirke, Can Rager, Rusheb Shah, Dan Valentine, Cecilia Diniz Behn, Katsumi Inoue, Samy Wu Fung
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Evaluation of Representational Similarity Scores Across Human Visual Cortex
Francisco Acosta, Colin Conwell, Sophia Sanborn, David A. Klindt, Nina Miolane
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
What Mechanisms Does Knowledge Distillation Distill?
Cindy Wu, Ekdeep Singh Lubana, Bruno Kacper Mlodozeniec, Robert Kirk, David Krueger
- Published: 02 Nov 2023, Last Modified: 04 Dec 2023
- UniReps Poster
- Readers: Everyone
A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry
Tim Z. Xiao, Weiyang Liu, Robert Bamler
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Disentangling Linear Mode Connectivity
Gül Sena Altıntaş, Gregor Bachmann, Lorenzo Noci, Thomas Hofmann
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Role Taxonomy of Units in Deep Neural Networks
Yang Zhao, Hao Zhang, Xiuyuan Hu
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks
Samyak Jain, Robert Kirk, Ekdeep Singh Lubana, Robert P. Dick, Hidenori Tanaka, Tim Rocktäschel, Edward Grefenstette, David Krueger
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Mixture of Multimodal Interaction Experts
Haofei Yu, Paul Pu Liang, Ruslan Salakhutdinov, Louis-Philippe Morency
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Randomly Weighted Neuromodulation in Neural Networks Facilitates Learning of Manifolds Common Across Tasks
Jinyung Hong, Theodore P. Pavlic
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Oral
- Readers: Everyone
Sufficient conditions for offline reactivation in recurrent neural networks
Nanda H Krishna, Colin Bredenberg, Daniel Levenstein, Blake Aaron Richards, Guillaume Lajoie
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Understanding Mode Connectivity via Parameter Space Symmetry
Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
A sparse null code emerges in deep neural networks
Brian S Robinson, Nathan Drenkow, Colin Conwell, Michael Bonner
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Oral
- Readers: Everyone
Duality of Bures and Shape Distances with Implications for Comparing Neural Representations
Sarah E Harvey, Brett W. Larsen, Alex H Williams
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Oral
- Readers: Everyone
Predictive variational autoencoder for learning robust representations of time-series data
Julia Huiming Wang, Dexter Tsin, Tatiana A Engel
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Ecological data and objectives align deep neural network representations with humans
Akash Nagaraj, Alekh Karkada Ashok, Drew Linsley, Francis E Lewis, Peisen Zhou, Thomas Serre
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Representational constraints underlying similarity between task-optimized neural systems
Tahereh Toosi
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Comparing neural models using their perceptual discriminability predictions
Jingyang Zhou, Chanwoo Chun, Ajay Subramanian, Eero P Simoncelli
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Comparing Representational and Functional Similarity in Small Transformer Language Models
Dan Friedman, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Instruction-tuned LLMs with World Knowledge are More Aligned to the Human Brain
Khai Loong Aw, Syrielle Montariol, Badr AlKhamissi, Martin Schrimpf, Antoine Bosselut
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Supervising Variational Autoencoder Latent Representations with Language
Thomas Lu, Aboli Marathe, Ada Martin
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Multi-timescale reinforcement learning in the brain
Paul Masset, Pablo Tano, HyungGoo Kim, Athar N. Malik, Alexandre Pouget, Naoshige Uchida
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
Estimating shape distances on neural representations with limited samples
Dean A Pospisil, Brett W. Larsen, Sarah E Harvey, Alex H Williams
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
UniCat: Crafting a Stronger Fusion Baseline for Multimodal Re-Identification
Jennifer Crawford, Haoli Yin, Luke McDermott, Daniel Cummings
- Published: 02 Nov 2023, Last Modified: 18 Dec 2023
- UniReps Poster
- Readers: Everyone
DISCOV: A Time Series Representations Disentanglement via Contrastive for Non-Intrusive Load Monitoring (NILM)
Khalid Oublal, Said Ladjal, David Benhaiem, Emmanuel LE BORGNE, François Roueff
- Published: 02 Nov 2023, Last Modified: 16 Apr 2024
- UniReps Poster
- Readers: Everyone