The Diffusion Duality

1 code implementation • 12 Jun 2025 • Subham Sekhar Sahoo, Justin Deschenaux, Aaron Gokaslan, Guanghan Wang, Justin Chiu, Volodymyr Kuleshov

Models trained with curriculum learning surpass autoregressive models in zero-shot perplexity on 3 of 7 benchmarks.

Text Generation

Remasking Discrete Diffusion Models with Inference-Time Scaling

1 code implementation • 1 Mar 2025 • Guanghan Wang, Yair Schiff, Subham Sekhar Sahoo, Volodymyr Kuleshov

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

Simple Guidance Mechanisms for Discrete Diffusion Models

1 code implementation • 13 Dec 2024 • Yair Schiff, Subham Sekhar Sahoo, Hao Phung, Guanghan Wang, Sam Boshar, Hugo Dalla-torre, Bernardo P. de Almeida, Alexander Rush, Thomas Pierrot, Volodymyr Kuleshov

Diffusion models for continuous data gained widespread adoption owing to their high quality generation and control mechanisms.

Image Generation

Language-Assisted 3D Feature Learning for Semantic Scene Understanding

1 code implementation • 25 Nov 2022 • Junbo Zhang, Guofan Fan, Guanghan Wang, Zhengyuan Su, Kaisheng Ma, Li Yi

To guide 3D feature learning toward important geometric attributes and scene context, we explore the help of textual scene descriptions.

Descriptive Instance Segmentation +5

On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples

no code implementations • 3 Aug 2021 • Adelin Travers, Lorna Licollari, Guanghan Wang, Varun Chandrasekaran, Adam Dziedzic, David Lie, Nicolas Papernot

In the white-box setting, we instantiate this class with a joint, multi-stage optimization attack.

BIG-bench Machine Learning