ICLR 2023 Workshop ME-FoMo Submissions

Accelerating Neural Self-Improvement via Bootstrapping
Kazuki Irie, Jürgen Schmidhuber
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Poster
- Readers: Everyone
Mini-Batch Optimization of Contrastive Loss
Kartik Sreenivasan, Keon Lee, Jeong-Gwan Lee, Anna Lee, Jaewoong Cho, Jy-yong Sohn, Dimitris Papailiopoulos, Kangwook Lee
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Poster
- Readers: Everyone
On the Role of Attention in Prompt-tuning
Samet Oymak, Ankit Singh Rawat, Mahdi Soltanolkotabi, Christos Thrampoulidis
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
LOOPED TRANSFORMERS AS PROGRAMMABLE COMPUTERS
Angeliki Giannou, Shashank Rajput, Jy-yong Sohn, Kangwook Lee, Jason D. Lee, Dimitris Papailiopoulos
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Diffusion Models are Minimax Optimal Distribution Estimators
Kazusato Oko, Shunta Akiyama, Taiji Suzuki
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Spotlight
- Readers: Everyone
The Effects of Pretraining Task Diversity on In-Context Learning of Ridge Regression
Allan Raventos, Mansheej Paul, Feng Chen, Surya Ganguli
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Conservative Prediction via Transductive Confidence Minimization
Caroline Choi, Fahim Tajwar, Yoonho Lee, Huaxiu Yao, Ananya Kumar, Chelsea Finn
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Controlled assessment of CLIP-style language-aligned vision models in prediction of brain & behavioral data
Colin Conwell, Jacob S. Prince, Christopher J Hamblin, George A. Alvarez
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
The Independent Compositional Subspace Hypothesis for the Structure of CLIP's Last Layer
Max Wolff, Wieland Brendel, Stuart Wolff
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Exploring Demonstration Ensembling for In-context Learning
Muhammad Khalifa, Lajanugen Logeswaran, Moontae Lee, Honglak Lee, Lu Wang
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Spotlight
- Readers: Everyone
A Tale of Two Circuits: Grokking as Competition of Sparse and Dense Subnetworks
William Merrill, Nikolaos Tsilivis, Aman Shukla
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
A Comprehensive Benchmark of Human-Like Relational Reasoning for Text-to-Image Foundation Models
Colin Conwell, Tomer Ullman
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Objectives Matter: Understanding the Impact of Self-Supervised Objectives on Vision Transformer Representations
Shashank Shekhar, Florian Bordes, Pascal Vincent, Ari S. Morcos
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Spotlight
- Readers: Everyone
Robustness of edited neural networks
Davis Brown, Charles Godfrey, Cody Nizinski, Jonathan Tu, Henry Kvinge
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Poster
- Readers: Everyone
Exploring the Representation Manifolds of Stable Diffusion Through the Lens of Intrinsic Dimension
Henry Kvinge, Davis Brown, Charles Godfrey
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Towards Understanding Chain-of-Thought Prompting: An Empirical Study of What Matters
Boshi Wang, Sewon Min, Xiang Deng, Jiaming Shen, You Wu, Luke Zettlemoyer, Huan Sun
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Poster
- Readers: Everyone
SemDeDup: Data-efficient learning at web-scale through semantic deduplication
Amro Kamal Mohamed Abbas, Kushal Tirumala, Daniel Simig, Surya Ganguli, Ari S. Morcos
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Effective Data Augmentation With Diffusion Models
Brandon Trabucco, Kyle Doherty, Max Gurinas, Ruslan Salakhutdinov
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Spotlight
- Readers: Everyone
Text-to-Image Diffusion Models are Zero-Shot Classifiers
Kevin Clark, Priyank Jaini
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Spotlight
- Readers: Everyone
Simple Hardware-Efficient Long Convolutions for Sequence Modeling
Daniel Y Fu, Elliot L Epstein, Eric Nguyen, Armin W Thomas, Michael Zhang, Tri Dao, Atri Rudra, Christopher Re
- Published: 04 Mar 2023, Last Modified: 14 Apr 2024
- ME-FoMo 2023 Poster
- Readers: Everyone
Understanding HTML with Large Language Models
Izzeddin Gur, Ofir Nachum, Yingjie Miao, Mustafa Safdari, Austin V Huang, Aakanksha Chowdhery, Sharan Narang, Noah Fiedel, Aleksandra Faust
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Instruction-Finetuned Foundation Models for Multimodal Web Navigation
Hiroki Furuta, Ofir Nachum, Kuang-Huei Lee, Yutaka Matsuo, Shixiang Shane Gu, Izzeddin Gur
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Out-of-context Meta-learning in Large Language Models
Dmitrii Krasheninnikov, Egor Krasheninnikov, David Krueger
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
What Happens to the Source Domain in Transfer Learning?
Amal Alnouri, Bilal Alsallakh
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone
Modality-Aware Adaptation of Contrastive Language-Image Models
Alexander Long, Thalaiyasingam Ajanthan, Anton van den Hengel
- Published: 04 Mar 2023, Last Modified: 16 May 2023
- ME-FoMo 2023 Poster
- Readers: Everyone