activity
20242026
collaborators

14 papers

cs.LG2026

Program Synthesis for Simulation-Based Inference: Joint Model Selection and Parameter Estimation

Siddharth Mishra-Sharma

Neural simulation-based inference enables parameter estimation for complex models, but typically requires the user to specify a simulator encoding a fixed model structure. We prese…

hep-ph2026

A Scientific Human-Agent Reproduction Pipeline

Joschka Birk, Gregor Kasieczka, Siddharth Mishra-Sharma +3

Reproducing scientific analyses is essential for preserving knowledge, building extensible codebases, and deepening researcher understanding - yet the effort often outweighs its ac…

astro-ph.IM2026

Deep Learning for Astrophysics: An Open Textbook from the NASA Cosmic Origins AI/ML Science and Technology Interest Group

Yuan-Sen Ting, Digvijay Wadekar, Phill Cargile +21

Recent community assessments identify education as a principal barrier to adopting modern machine learning in astronomy. We present Deep Learning for Astrophysics, a freely availab…

astro-ph.HE2026

High-dimensional inference for the -ray sky with differentiable programming

Siddharth Mishra-Sharma, Tracy R. Slatyer, Yitian Sun +1

We motivate the use of differentiable probabilistic programming techniques in order to account for the large model-space inherent to astrophysical -ray analyses. Targeting the…

stat.ML2026

DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking

Matt L. Wiemann, Lindsay M. Smith, Peter Melchior +4

Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of established science. We introduce Disc…

cs.LG2026

Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction

Darius A. Faroughy, Sofia Palacios Schweitzer, Ian Pang +2

Autonomous language-model agents are increasingly evaluated on long-horizon tool-use tasks, but existing benchmarks rarely capture the complexity and nuance of real scientific work…