activity
20242026
collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2026

At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization

Praneet Suresh, Jack Stanley, Sonia Joseph +2

Pre-trained transformers have demonstrated remarkable generalization abilities, at times extending beyond the scope of their training data. Yet, real-world deployments often face u…

cs.LG2025

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise

Luca Scimeca, Thomas Jiralerspong, Berton Earnshaw +2

Diffusion Probabilistic Models (DPMs) have achieved strong generative performance, yet their inductive biases remain largely implicit. In this work, we aim to build inductive biase…

cs.LG2025

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers

Praneet Suresh, Jack Stanley, Sonia Joseph +2

As generative AI systems become competent and democratized in science, business, and government, deeper insight into their failure modes now poses an acute need. The occasional vol…

cs.LG2025

Torsional-GFN: a conditional conformation generator for small molecules

Alexandra Volokhova, Léna Néhale Ezzine, Piotr Gaiński +5

Generating stable molecular conformations is crucial in several drug discovery applications, such as estimating the binding affinity of a molecule to a target. Recently, generative…

cs.LG2025

Outsourced diffusion sampling: Efficient posterior inference in latent spaces of generative models

Siddarth Venkatraman, Mohsin Hasan, Minsu Kim +5

Any well-behaved generative model over a variable can be expressed as a deterministic transformation of an exogenous ('outsourced') Gaussian noise variable $\mathbf{z}…

cs.LG2025

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles

Luca Scimeca, Alexander Rubinstein, Damien Teney +2

Spurious correlations in the data, where multiple cues are predictive of the target labels, often lead to a phenomenon known as shortcut learning, where a model relies on erroneous…