activity
20242026
collaborators

8 papers

cs.AI2026

Guaranteed Optimal Compositional Explanations for Neurons

Biagio La Rosa, Leilani H. Gilpin

Compositional explanations are a family of methods that aim to describe the spatial alignment between neurons' receptive field activations and concepts through logical rules, typic…

cs.CV2025

Open Vocabulary Compositional Explanations for Neuron Alignment

Biagio La Rosa, Leilani H. Gilpin

Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding ho…

cs.AI2025

Follow My Lead: Logical Fallacy Classification with Knowledge-Augmented LLMs

Olivia Peiyu Wang, Tashvi Bansal, Ryan Bai +2

Large Language Models (LLMs) suffer from critical reasoning gaps, including a tendency to hallucinate and poor accuracy in classifying logical fallacies. This limitation stems from…

cs.LG2025

Explore the Loss space with Hill-ADAM

Meenakshi Manikandan, Leilani Gilpin

This paper introduces Hill-ADAM. Hill-ADAM is an optimizer with its focus towards escaping local minima in prescribed loss landscapes to find the global minimum. Hill-ADAM escapes…

cs.CV2025

VFSI: Validity First Spatial Intelligence for Constraint-Guided Traffic Diffusion

Kargi Chauhan, Leilani H. Gilpin

Modern diffusion models generate realistic traffic simulations but systematically violate physical constraints. In a large-scale evaluation of SceneDiffuser++, a state-of-the-art t…

cs.RO2025

Slug Mobile: Test-Bench for RL Testing

Jonathan Wellington Morris, Vishrut Shah, Alex Besanceney +2

Sim-to real gap in Reinforcement Learning is when a model trained in a simulator does not translate to the real world. This is a problem for Autonomous Vehicles (AVs) as vehicle dy…