16 citations · 27 across the 25 of their papers we have counts for
15 papers · 1 filter
Assign and Add: A Mechanistic Study of Compositional Arithmetic
Brady Exoo, Alberto Bietti, John Sous
Large language models are able to compose skills in order to perform complex tasks, many of which might not have been seen during training. The details of how exactly this composit…
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
Bhavya Vasudeva, Puneesh Deora, Alberto Bietti +2
Transformer-based language models excel at in-context learning (ICL), where they can adapt to new tasks based on contextual examples, without parameter updates. In a specific form…
Representation Learning for Spatiotemporal Physical Systems
Helen Qu, Rudy Morel, Michael McCabe +4
Machine learning approaches to spatiotemporal physical systems have primarily focused on next-frame prediction, with the goal of learning an accurate emulator for the system's evol…
Understanding the Mechanisms of Fast Hyperparameter Transfer
Nikhil Ghosh, Denny Wu, Alberto Bietti
The growing scale of deep learning models has rendered standard hyperparameter (HP) optimization prohibitively expensive. A promising solution is the use of scale-aware hyperparame…
From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers
Ryotaro Kawata, Yujin Song, Alberto Bietti +4
Transformers can implement both generalizable algorithms (e.g., induction heads) and simple positional shortcuts (e.g., memorizing fixed output positions). In this work, we study h…
Physics Steering: Causal Control of Cross-Domain Concepts in a Physics Foundation Model
Rio Alexa Fear, Payel Mukhopadhyay, Michael McCabe +2
Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but als…
Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme
Rudy Morel, Francesco Pio Ramunno, Jeff Shen +18
Conditional diffusion models provide a natural framework for probabilistic prediction of dynamical systems and have been successfully applied to fluid dynamics and weather predicti…
Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
Michael McCabe, Payel Mukhopadhyay, Tanya Marwah +22
Foundation models have transformed machine learning for language and vision, but achieving comparable impact in physical simulation remains a challenge. Data heterogeneity and unst…
Learning Compositional Functions with Transformers from Easy-to-Hard Data
Zixuan Wang, Eshaan Nichani, Alberto Bietti +4
Transformer-based language models have demonstrated impressive capabilities across a range of complex reasoning tasks. Prior theoretical work exploring the expressive power of tran…
BAnG: Bidirectional Anchored Generation for Conditional RNA Design
Roman Klypa, Alberto Bietti, Sergei Grudinin
Designing RNA molecules that interact with specific proteins is a critical challenge in experimental and computational biology. Existing computational approaches require a substant…
In-context denoising with one-layer transformers: connections between attention and associative memory retrieval
Matthew Smart, Alberto Bietti, Anirvan M. Sengupta
We introduce in-context denoising, a task that refines the connection between attention-based architectures and dense associative memory (DAM) networks, also known as modern Hopfie…
Understanding Factual Recall in Transformers via Associative Memories
Eshaan Nichani, Jason D. Lee, Alberto Bietti
Large language models have demonstrated an impressive ability to perform factual recall. Prior work has found that transformers trained on factual recall tasks can store informatio…
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task
Siavash Golkar, Alberto Bietti, Mariel Pettee +12
Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications. This paper int…
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
Frederik Kunstner, Robin Yadav, Alan Milligan +2
Adam has been shown to outperform gradient descent on large language models by a larger margin than on other tasks, but it is unclear why. We show that a key factor in this perform…
Multiple Physics Pretraining for Physical Surrogate Models
Michael McCabe, Bruno Régaldo-Saint Blancard, Liam Holden Parker +11
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers. I…