122 citations · 146 across the 6 of their papers we have counts for
7 papers
DACA-GRPO: Denoising-Aware Credit Assignment for Reinforcement Learning in Diffusion Language Models
Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade +4
Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps as equally important and rely…
The Design Space of Tri-Modal Masked Diffusion Models
Louis Bethune, Victor Turrisi, Bruno Kacper Mlodozeniec +21
Discrete diffusion models have emerged as strong alternatives to autoregressive language models, with recent work initializing and fine-tuning a base unimodal model for bimodal gen…
Attention when you need
Lokesh Boominathan, Grayson Matthew, Yizhou Chen +2
Paying attention improves performance, but attention is metabolically costly, so how should a resource-efficient agent allocate it? We study optimal allocation strategies using a n…
Phase transitions in when feedback is useful
Lokesh Boominathan, Xaq Pitkow
Sensory observations about the world are invariably ambiguous. Inference about the world's latent variables is thus an important computation for the brain. However, computational c…
Phase retrieval for Fourier Ptychography under varying amount of measurements
Lokesh Boominathan, Mayug Maniparambil, Honey Gupta +2
Fourier Ptychography is a recently proposed imaging technique that yields high-resolution images by computationally transcending the diffraction blur of an optical system. At the c…
Compensating for Large In-Plane Rotations in Natural Images
Lokesh Boominathan, Suraj Srinivas, R. Venkatesh Babu
Rotation invariance has been studied in the computer vision community primarily in the context of small in-plane rotations. This is usually achieved by building invariant image fea…
CrowdNet: A Deep Convolutional Network for Dense Crowd Counting
Lokesh Boominathan, Srinivas S S Kruthiventi, R. Venkatesh Babu
Our work proposes a novel deep learning framework for estimating crowd density from static images of highly dense crowds. We use a combination of deep and shallow, fully convolutio…