2 papers
cs.LG2026
Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures
Jaineet Shah
When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (eval…
cs.CV2024
Enhancing Diffusion Models for High-Quality Image Generation
Jaineet Shah, Michael Gromis, Rickston Pinto
This report presents the comprehensive implementation, evaluation, and optimization of Denoising Diffusion Probabilistic Models (DDPMs) and Denoising Diffusion Implicit Models (DDI…