ICLR 2024 Workshop Re-Align Submissions

Is my "red" your "red"?: Unsupervised alignment of qualia structures via optimal transport
Genji Kawakita, Ariel Mikhael Zeleznikow-Johnston, Ken Takeda, Naotsugu Tsuchiya, Masafumi Oizumi
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Removing High Frequency Information Improves DNN Behavioral Alignment
Max Wolff, Evgenia Rusak, Wieland Brendel
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Less is More: Discovering Concise Network Explanations
Neehar Kondapaneni, Markus Marks, Oisin Mac Aodha, Pietro Perona
- Published: 02 Mar 2024, Last Modified: 24 Jun 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Learning and Aligning Structured Random Feature Networks
Vivian White, Muawiz Sajjad Chaudhary, Guy Wolf, Guillaume Lajoie, Kameron Decker Harris
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
The role of shared labels and experiences in representational alignment
Kushin Mukherjee, Siddharth Suresh, Xizheng Yu, Gary Lupyan
- Published: 02 Mar 2024, Last Modified: 09 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Disentangling Recurrent Neural Dynamics with Stochastic Representational Geometry
David Lipshutz, Amin Nejatbakhsh, Alex H Williams
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align ContributedTalk
- Readers: Everyone
Comparing supervised learning dynamics: Deep neural networks match human data efficiency but show a generalisation lag
Lukas S. Huber, Fred W. Mast, Felix A. Wichmann
- Published: 02 Mar 2024, Last Modified: 12 Jul 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
What Causes Polysemanticity? An Alternative Origin Story of Mixed Selectivity from Incidental Causes
Victor Lecomte, Kushal Thaman, Rylan Schaeffer, Naomi Bashkansky, Trevor Chow, Sanmi Koyejo
- Published: 02 Mar 2024, Last Modified: 02 Mar 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Comparing Abstraction in Humans and Large Language Models Using Multimodal Serial Reproduction
Sreejan Kumar, Raja Marjieh, Byron Zhang, Declan Iain Campbell, Michael Y. Hu, Umang Bhatt, Brenden Lake, Thomas L. Griffiths
- Published: 02 Mar 2024, Last Modified: 02 Mar 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Measuring Human-CLIP Alignment at Different Abstraction Levels
Pablo Hernández-Cámara, Jorge Vila-Tomás, Jesus Malo, Valero Laparra
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Symbolic Variables in Distributed Networks that Count
Satchel Grant, Zhengxuan Wu, James Lloyd McClelland, Noah Goodman
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Inter-animal transforms as a guide to model-brain comparison
Imran Thobani, Javier Sagastuy-Brena, Aran Nayebi, Rosa Cao, Daniel LK Yamins
- Published: 02 Mar 2024, Last Modified: 10 May 2024
- ICLR 2024 Workshop Re-Align ContributedTalk
- Readers: Everyone
The benefits of Incorporating Shape Priors in Contrastive Learning
Junru Zhao, Tianqin Li, Tai Sing Lee
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Humans diverge from language models when predicting spoken language
Thomas L. Botch, Emily S Finn
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
ReAlnet: Achieving More Human Brain-Like Vision via Human Neural Representational Alignment
Zitong Lu, Yile Wang, Julie Golomb
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Modality-Agnostic fMRI Decoding of Vision and Language
Mitja Nikolaus, Milad Mozafari, Nicholas Asher, Leila Reddy, Rufin VanRullen
- Published: 02 Mar 2024, Last Modified: 30 Mar 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
An Analysis of Human Alignment of Latent Diffusion Models
Lorenz Linhardt, Marco Morik, Sidney Bender, Naima Elosegui Borras
- Published: 02 Mar 2024, Last Modified: 30 Mar 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Learning to Abstract Visuomotor Mappings using Meta-Reinforcement Learning
Carlos A. Velazquez-Vargas, Isaac Ray Christian, Jordan Taylor, Sreejan Kumar
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Unveiling the Dynamics of Transfer Learning Representations
Thomas Goerttler, Klaus Obermayer
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Texture bias in primate ventral visual cortex
Akshay Vivek Jagadeesh, Margaret Livingstone
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Lessons learned in the study of representational alignment in physical reasoning
Felix Jedidja Binder, Rahul Mysore Venkatesh, Daniel LK Yamins, Judith E Fan
- Published: 02 Mar 2024, Last Modified: 07 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Can Generative Multimodal Models Count to Ten?
Sunayana Rane, Alexander Ku, Jason Michael Baldridge, Ian Tenney, Thomas L. Griffiths, Been Kim
- Published: 02 Mar 2024, Last Modified: 06 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Measuring Mechanistic Interpretability at Scale Without Humans
Roland S. Zimmermann, David A. Klindt, Wieland Brendel
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Towards neural foundation models for vision: Aligning EEG, MEG and fMRI representations to perform decoding, encoding and modality conversion
Matteo Ferrante, Tommaso Boccato, Nicola Toschi
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone
Simplicity in Complexity
Surabhi S Nath, Kevin Shen, Aenne Annelie Brielmann, Peter Dayan
- Published: 02 Mar 2024, Last Modified: 05 May 2024
- ICLR 2024 Workshop Re-Align Poster
- Readers: Everyone