1 citations · 1 across the 5 of their papers we have counts for
6 papers
Composing Flow-Matching Energies with Known Physics: Generation, OOD Detection, and Inversion on PDE Fields
Yixuan Sun, Anirban Samaddar, Sandeep Madireddy
Probabilistic modeling of physical fields benefits from both a data-driven prior and known physical structure such as the governing equations. Energy-based models (EBMs) are a natu…
Chance-constrained Flow Matching for High-Fidelity Constraint-aware Generation
Jinhao Liang, Yixuan Sun, Anirban Samaddar +2
Generative models excel at synthesizing high-fidelity samples from complex data distributions, but they often violate hard constraints arising from physical laws or task specificat…
UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making
Jinhao Duan, James Diffenderfer, Sandeep Madireddy +3
As Large Language Models (LLMs) are integrated into safety-critical applications involving sequential decision-making in the real world, it is essential to know when to trust LLM d…
Efficient Flow Matching using Latent Variables
Anirban Samaddar, Yixuan Sun, Viktor Nilsson +1
Flow matching models have shown great potential in image generation tasks among probabilistic generative models. However, most flow matching models in the literature do not explici…
Question Rephrasing for Quantifying Uncertainty in Large Language Models: Applications in Molecular Chemistry Tasks
Zizhang Chen, Pengyu Hong, Sandeep Madireddy
Uncertainty quantification enables users to assess the reliability of responses generated by large language models (LLMs). We present a novel Question Rephrasing technique to evalu…
Surrogate Neural Networks to Estimate Parametric Sensitivity of Ocean Models
Yixuan Sun, Elizabeth Cucuzzella, Steven Brus +5
Modeling is crucial to understanding the effect of greenhouse gases, warming, and ice sheet melting on the ocean. At the same time, ocean processes affect phenomena such as hurrica…