activity
20242026
collaborators

5 papers

cs.LG2026

How Architecture and Training Affect TPC Representations Across Experiments

Tyler Wheeler, Michelle P. Kuchera, Raghuram Ramanujan +11

Deep-learning efforts have increasingly shifted toward foundation model approaches. In experimental physics, this allows models and learned representations to be reused beyond the…

cs.LG2026

Forward versus Backward: Comparing Reasoning Objectives in Direct Preference Optimization

Murtaza Nikzad, Raghuram Ramanujan

Large language models exhibit impressive reasoning capabilities yet frequently generate plausible but incorrect solutions, a phenomenon commonly termed hallucination. This paper in…

cs.LG2025

Sparse Methods for Vector Embeddings of TPC Data

Tyler Wheeler, Michelle P. Kuchera, Raghuram Ramanujan +7

Time Projection Chambers (TPCs) are versatile detectors that reconstruct charged-particle tracks in an ionizing medium, enabling sensitive measurements across a wide range of nucle…

cs.CV2025

Unpaired Translation of Point Clouds for Modeling Detector Response

Mingyang Li, Michelle Kuchera, Raghuram Ramanujan +3

Modeling detector response is a key challenge in time projection chambers. We cast this problem as an unpaired point cloud translation task, between data collected from simulations…

physics.comp-ph2024

Implicit Quantile Networks For Emulation in Jet Physics

B. Kronheim, A. Al Kadhim, M. P. Kuchera +2

The ability to model and sample from conditional densities is important in many physics applications. Implicit quantile networks (IQN) have been successfully applied to this task i…