NeurIPS 2024 Workshop SciForDL Submissions

The Master Key Filters Hypothesis: Deep Filters Are General
Zahra Babaiee, Peyman Kiasari, Daniela Rus, Radu Grosu
- Published: 10 Oct 2024, Last Modified: 13 Nov 2024
- SciForDL Poster
- Readers: Everyone
Input Space Mode Connectivity in Deep Neural Networks
Jakub Vrabel, Ori Shem-Ur, Yaron Oz, David Krueger
- Published: 10 Oct 2024, Last Modified: 12 Nov 2024
- SciForDL Oral
- Readers: Everyone
Standard adversarial attacks only fool the final layer
Stanislav Fort
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Specialization-generalization transition in exemplar-based in-context learning
Chase Goddard, Lindsay M. Smith, Vudtiwat Ngampruetikorn, David J. Schwab
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Eliminating Position Bias of Language Models: A Mechanistic Approach
Ziqi Wang, Hanlin Zhang, Xiner Li, Kuan-Hao Huang, Chi Han, Shuiwang Ji, Sham M. Kakade, Hao Peng, Heng Ji
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Model Recycling: Model component reuse to promote in-context learning
Lindsay M. Smith, Chase Goddard, Vudtiwat Ngampruetikorn, David J. Schwab
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Generalization vs Specialization under Concept Shift
Alex Nguyen, David J. Schwab, Vudtiwat Ngampruetikorn
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Denoising for Manifold Extrapolation
Zeyu Yun, Galen Chuang, Derek Dong, Yubei Chen
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Explicit Regularisation, Sharpness and Calibration
Israel Mason-Williams, Fredrik Ekholm, Ferenc Huszár
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Understanding the Transient Nature of In-Context Learning: The Window of Generalization
Core Francisco Park, Ekdeep Singh Lubana, Hidenori Tanaka
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Interpretability as Compression: Reconsidering SAE Explanations of Neural Activations
Kola Ayonrinde, Michael T Pearce, Lee Sharkey
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Illusions as features: the generative side of recognition
Tahereh Toosi, Kenneth D. Miller
- Published: 10 Oct 2024, Last Modified: 13 Nov 2024
- SciForDL Poster
- Readers: Everyone
Knowledge Distillation: The Functional Perspective
Israel Mason-Williams, Gabryel Mason-Williams, Mark Sandler
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
On the Collapse Errors Induced by the Deterministic Sampler for Diffusion Models
Yi Zhang, Difan Zou
- Published: 10 Oct 2024, Last Modified: 25 Nov 2024
- SciForDL Poster
- Readers: Everyone
Characterizing stable regions in the residual stream of LLMs
Jett Janiak, Jacek Karwowski, Chatrik Singh Mangat, Giorgi Giglemiani, Nora Petrova, Stefan Heimersheim
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Are Capsule Networks Texture or Shape Biased?
Riccardo Renzulli, Dominik Vranay, Marco Grangetto
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Exploring model depth and data complexity through the lens of cellular automata
Tianyu He, Darshil Doshi, Aritra Das, Andrey Gromov
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
softmax is not enough (for sharp out-of-distribution)
Petar Veličković, Christos Perivolaropoulos, Federico Barbero, Razvan Pascanu
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Oral
- Readers: Everyone
Transformers can reinforcement learn to approximate Gittins Index
Vladimir Petrov, Nikhil Vyas, Lucas Janson
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
We Need Far Fewer Unique Filters Than We Thought
Zahra Babaiee, Peyman Kiasari, Daniela Rus, Radu Grosu
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Language model scaling laws and zero-sum learning
Andrei Mircea, Ekaterina Lobacheva, Supriyo Chakraborty, Nima Chitsazan, Irina Rish
- Published: 10 Oct 2024, Last Modified: 19 Nov 2024
- SciForDL Poster
- Readers: Everyone
Distributional Scaling Laws for Emergent Capabilities
Rosie Zhao, Naomi Saphra, Sham M. Kakade
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Probing the Decision Boundaries of In-context Learning in Large Language Models Download PDF
Siyan Zhao, Tung Nguyen, Aditya Grover
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
Learnability in the Context of Neural Tangent Kernels
Progyan Das, Dwip Dalal
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone
The Unreasonable Ineffectiveness of the Deeper Layers
Andrey Gromov, Kushal Tirumala, Hassan Shapourian, Paolo Glorioso, Dan Roberts
- Published: 10 Oct 2024, Last Modified: 09 Nov 2024
- SciForDL Poster
- Readers: Everyone