Raghav Mehta — accepted AI-conference papers

2026

Factored Classifier-Free Guidance

Tian Xia, Fabio De Sousa Ribeiro, Rajat Rasal, Avinash Kori, Raghav Mehta, Ben Glocker

ICML 2026poster

Counterfactual generation aims to simulate realistic hypothetical outcomes under causal interventions. Diffusion models have emerged as a powerful tool for this task, combining DDIM inversion with conditional generation and classifier-free guidance (CFG). In this work, we identify a key limitation o…

Cited by 0 Source ↗Scholar ↗

2025

Flow Stochastic Segmentation Networks

Fabio De Sousa Ribeiro, Omar Todd, Charles Jones, Avinash Kori, Raghav Mehta, Ben Glocker

ICCV 2025poster

We propose the Flow Stochastic Segmentation Network (Flow-SSN), a generative model for probabilistic segmentation featuring discrete-time autoregressive and modern continuous-time flow parameterisations. We prove fundamental limitations of the low-rank parameterisation of previous methods and show t…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗