I try to keep it up to date; check my Scholar page for the full list.
2024
- 2024
TAB: Transformer Attention Bottlenecks enable User Intervention and Debugging in Vision-Language Models
TL;DR ICCV 2025 arXivPDF - 2024
Logit Scaling for Out-of-Distribution Detection
TL;DR arXivPDF - 2024
Training language models on the knowledge graph: Insights on hallucinations and their detectability
TL;DR COLM 2024 arXivPDF Twitter thread - 2024
Improve mathematical reasoning in language models by automated process supervision
TL;DR arXivPDF Twitter thread - 2024
Long-Span Question-Answering: Automatic Question Generation and QA-System Ranking via Side-by-Side Evaluation
TL;DR arXivPDF - 2024
Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context
TL;DR arXivPDF Twitter thread 1.5 Pro Update
2023
2022
- 2022
Character-Aware Models Improve Visual Text Rendering
TL;DR ACL 2023 arXivPDF Twitter thread - 2022
Extremely Simple Activation Shaping for Out-of-Distribution Detection
TL;DR ICLR 2023 arXivPDF Website Video Code Twitter thread - 2022
What does a platypus look like? Generating customized prompts for zero-shot image classification
TL;DR ICCV 2023 arXivPDF Code Twitter thread - 2022
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
TL;DR TMLR arXivPDF Code Twitter thread - 2022
When less is more: Simplifying inputs aids neural network understanding
TL;DR arXivPDF Twitter thread
2021
- 2021
Natural Adversarial Objects
TL;DR Data Centric AI, NeurIPS 2021 arXivPDF Twitter thread - 2021
Language Models are Few-shot Multilingual Learners
TL;DR EMNLP 2021 MRL Workshop arXivPDF - 2021
Why is Pruning at Initialization Immune to Reinitializing and Shuffling?
TL;DR SNN Workshop 2021 arXivPDF - 2021
When does loss-based prioritization fail?
TL;DR ICML 2021 SubSetML Workshop arXivPDF
2020
2019
- 2019
Plug and Play Language Models: a Simple Approach to Controlled Text Generation
TL;DR ICLR 2020 Blog post Video Code Twitter thread arXiv Demo - 2019
LCA: Loss Change Allocation for Neural Network Training
TL;DR NeurIPS 2019 Blog post Code arXiv - 2019
Deconstructing Lottery Tickets: Zeros, Signs, and the Supermask
TL;DR NeurIPS 2019 Blog post Code arXiv
2018
- 2018
An Atari Model Zoo for Analyzing, Visualizing, and Comparing Deep Reinforcement Learning Agents
TL;DR IJCAI 2019 Blog post Video Code arXiv - 2018
Faster Neural Networks Straight from JPEG
TL;DR NeurIPS 2018 Blog post Code arXiv - 2018
An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution
TL;DR NeurIPS 2018 Blog post Video Code Twitter thread arXiv - 2018
Measuring the Intrinsic Dimension of Objective Landscapes
TL;DR ICLR 2018 Blog post Video Code arXiv
2017
2016
2015
- 2015
Machine learning approaches for elastic localization linkages in high-contrast composite materials
IMMI 2015 PDF - 2015
Pruned search: A machine learning based meta-heuristic approach for constrained continuous optimization
IC3 2015 PDF - 2015
A predictive machine learning approach for microstructure optimization and materials design
nature.com PDF - 2015
A Machine Learning-Based Design Representation Method for Designing Heterogeneous Microstructures
Journal of Mechanical Design PDF - 2015
A scalable hierarchical clustering algorithm using spark
BigDataService 2015 PDF