arXiv:2602.16568v2 Announce Type: replace-cross Abstract: Sparse recovery is among the most well-studied problems in learning theory and high-dimensional statistics. In this work, we investigate the statistical…
arXiv:2501.07761v2 Announce Type: replace-cross Abstract: Increasingly, recommender systems are tasked with improving users' long-term satisfaction. In this context, we study a content exploration task, which we…
arXiv:2603.12120v2 Announce Type: replace-cross Abstract: We introduce CRAFT hand, a tendon-driven anthropomorphic hand with hybrid hard-soft compliance for contact-rich manipulation. The design is based on a…
arXiv:2606.24391v1 Announce Type: cross Abstract: We introduce Age of LLM, a turn-based 1v1 benchmark in which two LLMs face off on a 13x7 grid to destroy…
arXiv:2606.24589v1 Announce Type: cross Abstract: Scaling adversarial evaluation of large language models requires both a method for generating hard inputs and a reliable way to confirm…
arXiv:2606.23742v1 Announce Type: new Abstract: Physical neural networks promise low-power machine learning by computing directly with analogue device physics, but most architectures force nonlinear device responses…
arXiv:2606.18610v2 Announce Type: replace-cross Abstract: Evaluating generalist robot manipulation policies in the real world is expensive, slow, and difficult to scale. Action-conditioned video world models offer…
arXiv:2606.07558v2 Announce Type: replace Abstract: Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at scale. This work…
arXiv:2401.14483v4 Announce Type: replace-cross Abstract: In the current practices of machine learning, the evaluation of forecasts has become a cornerstone of scientific progress. A multitude of…
arXiv:2410.14843v4 Announce Type: replace Abstract: Vanilla variational inference finds an optimal approximation to the Bayesian posterior distribution, but even the exact Bayesian posterior is often not…
In healthcare settings where patients use LLMs as a medical assistant, LLM performance differs between evaluation and deployment. (a) Bean et al. (2025) find a 61…
What components are needed for building learning algorithms that leverage the structure and properties of graphs?
Understanding the building blocks and design choices of graph neural networks.
After five years, Distill will be taking a break.
Reprogramming Neural CA to exhibit novel behaviour, using adversarial attacks.
Weights in the final layer of common visual models appear as horizontal bands. We investigate how and why.
When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings.
We report the existence of multimodal neurons in artificial neural networks, similar to those found in the human brain.
Neural Cellular Automata learn to generate textures, exhibiting surprising properties.
We present techniques for visualizing, contextualizing, and understanding neural network weights.
Reverse engineering the curve detection algorithm from InceptionV1 and reimplementing it from scratch.
A family of early-vision neurons reacting to directional transitions from high to low spatial frequency.
Neural networks naturally learn many transformed copies of the same feature, connected by symmetric weights.
With diverse environments, we can analyze, diagnose and edit deep reinforcement learning models using attribution.