NeurIPS 2024 Workshop SciForDL Submissions

Is network fragmentation a useful complexity measure?
Coenraad Mouton, Randle Rabe, Daniël Gerbrand Haasbroek, Marthinus Wilhelmus Theunissen, Hermanus Lambertus Potgieter, Marelie Hattingh Davel
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Ezra Edelman, Nikolaos Tsilivis, Surbhi Goel, Benjamin L. Edelman, eran malach
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Knowledge Distillation for Teaching Symmetry Invariances
Patrick Odagiu, Nicole Nobili, Fabian Dionys Schrag, Yves Bicker, Yuhui Ding
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Comparing Apples and Oranges: is Stitching Similarity a Load of Spheres?
Damian Smith, Antonia Marcu
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Stitching Sparse Autoencoders of Different Sizes
Patrick Leask, Bart Bussmann, Joseph Isaac Bloom, Curt Tigges, Noura Al Moubayed, Neel Nanda
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
BatchTopK Sparse Autoencoders
Bart Bussmann, Patrick Leask, Neel Nanda
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Training Neural Networks for Modularity aids Interpretability
Satvik Golechha, Dylan Cope, Nandi Schoots
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Sometimes I am a Tree: Data Drives Fragile Hierarchical Generalization
Tian Qin, Naomi Saphra, David Alvarez-Melis
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Learned Random Label Predictions as a Neural Network Complexity Metric
Marlon Becker, Benjamin Risse
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Unraveling the Latent Hierarchical Structure of Language and Images via Diffusion Models
Antonio Sclocchi, Noam Itzhak Levi, Alessandro Favero, Matthieu Wyart
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Oral
- Readers: Everyone
Amplified Early Stopping Bias: Overestimated Performance with Deep Learning
Nona Rajabi, Antonio H. Ribeiro, Miguel Vasco, Danica Kragic
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Structure Development in List Sorting Transformers
Einar Urdshals, Jasmina nasufi
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Exploiting Interpretable Capabilities with Concept-Enhanced Diffusion and Prototype Networks
Alba Carballo-Castro, Sonia Laguna, Moritz Vandenhirtz, Julia E Vogt
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Understanding Visual Concepts Across Models
Brandon Trabucco, Max A Gurinas, Kyle Doherty, Russ Salakhutdinov
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Towards Understanding In-Context Learning with Contrastive Demonstrations and Saliency Maps
Fuxiao Liu
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Alice in Wonderland: Simple Tasks Reveal Severe Generalization and Basic Reasoning Deficits in State-Of-the-Art Large Language Models
Marianna Nezhurina, Lucia Cipolina-Kun, Mehdi Cherti, Jenia Jitsev
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Effectiveness of Sparse Autoencoder for understanding and removing gender bias in LLMs
Praveen Hegde
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
A Method on Searching Better Activation Functions
Haoyuan Sun, Zihao Wu, Bo Xia, Pu Chang, Zibin Dong, Yifu Yuan, Yongzhe Chang, Xueqian Wang
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
EmoCAM: Toward Understanding What Drives CNN-based Emotion Recognition
Youssef Doulfoukar, Laurent Mertens, Joost Vennekens
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Revealing the Learning Process in Reinforcement Learning Agents Through Attention-Oriented Metrics
Charlotte Beylier, Simon M. Hofmann, Nico Scherf
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Sparse autoencoders for dense text embeddings reveal hierarchical feature sub-structure
Christine Ye, Charles O'Neill, John F Wu, Kartheik G. Iyer
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Rethinking Knowledge Transfer in Learning Using Privileged Information
Danil Provodin, Bram van den Akker, Christina Katsimerou, Maurits Clemens Kaptein, Mykola Pechenizkiy
- Published: 09 Nov 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Pre-processing and Compression: Understanding Hidden Representation Refinement Across Imaging Domains via Intrinsic Dimension
Nicholas Konz, Maciej A Mazurowski
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone