collaborators

8 papers

cs.CL2026

Esoteric Language Models: A Family of Any-Order Diffusion LLMs

Subham Sekhar Sahoo, Zhihan Yang, Yash Akhauri +7

Diffusion-based language models offer a compelling alternative to autoregressive (AR) models by enabling parallel and controllable generation. Within this family, Masked Diffusion…

cs.LG2026

Scaling Beyond Masked Diffusion Language Models

Subham Sekhar Sahoo, Jean-Marie Lemercier, Zhihan Yang +4

Diffusion language models are a promising alternative to autoregressive models due to their potential for faster generation. Among discrete diffusion approaches, Masked diffusion c…

cs.LG2026

Remasking Discrete Diffusion Models with Inference-Time Scaling

Guanghan Wang, Yair Schiff, Subham Sekhar Sahoo +1

Part of the success of diffusion models stems from their ability to perform iterative refinement, i.e., repeatedly correcting outputs during generation. However, modern masked disc…

cs.LG2025

The Diffusion Duality

Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan +3

Uniform-state discrete diffusion models hold the promise of fast text generation due to their inherent ability to self-correct. However, they are typically outperformed by autoregr…

eess.AS2025

Discrete Diffusion for Generative Modeling of Text-Aligned Speech Tokens

Pin-Jui Ku, He Huang, Jean-Marie Lemercier +3

This paper introduces a discrete diffusion model (DDM) framework for text-aligned speech tokenization and reconstruction. By replacing the auto-regressive speech decoder with a dis…

cs.LG2025

Simple Guidance Mechanisms for Discrete Diffusion Models

Yair Schiff, Subham Sekhar Sahoo, Hao Phung +7

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms. However, controllable diffusion on discrete data face…