120 citations · 152 across the 13 of their papers we have counts for
15 papers
Hierarchical Masked Diffusion Language Models
Parul Gupta, Satwik, Avni Aggarwal +5
Masked diffusion language models have emerged as an alternative to autoregressive models, enabling parallel token generation. However, standard masked diffusion language models use…
Rendering-Aware Reinforcement Learning for Vector Graphics Generation
Juan A. Rodriguez, Haotian Zhang, Abhay Puri +12
Scalable Vector Graphics (SVG) offer a powerful format for representing visual designs as interpretable code. Recent advances in vision-language models (VLMs) have enabled high-qua…
Spectral State Space Model for Rotation-Invariant Visual Representation Learning
Sahar Dastani, Ali Bahri, Moslem Yazdanpanah +8
State Space Models (SSMs) have recently emerged as an alternative to Vision Transformers (ViTs) due to their unique ability of modeling global relationships with linear complexity.…
Symmetry-Aware Generative Modeling through Learned Canonicalization
Kusha Sareen, Daniel Levy, Arnab Kumar Mondal +3
Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations. The existing generative modeling paradigm for…
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
Ayush Kaushal, Tejas Vaidhya, Arnab Kumar Mondal +3
Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Model (LLM) inference. Post-training quantiz…
Improved Canonicalization for Model Agnostic Equivariance
Siba Smarak Panigrahi, Arnab Kumar Mondal
This work introduces a novel approach to achieving architecture-agnostic equivariance in deep learning, particularly addressing the limitations of traditional layerwise equivariant…
HumMUSS: Human Motion Understanding using State Space Models
Arnab Kumar Mondal, Stefano Alletto, Denis Tome
Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition. While state-of-the-art methods pred…
Equivariant Adaptation of Large Pretrained Models
Arnab Kumar Mondal, Siba Smarak Panigrahi, Sékou-Oumar Kaba +2
Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to higher sample efficiency and more accurate a…
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
Arnab Kumar Mondal, Siba Smarak Panigrahi, Sai Rajeswar +2
The accurate modeling of dynamics in interactive environments is critical for successful long-range prediction. Such a capability could advance Reinforcement Learning (RL) and Plan…
Equivariance with Learned Canonicalization Functions
Sékou-Oumar Kaba, Arnab Kumar Mondal, Yan Zhang +2
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations. In this paper, we propose an alternati…
Investigating Power laws in Deep Representation Learning
Arna Ghosh, Arnab Kumar Mondal, Kumar Krishna Agrawal +1
Representation learning that leverages large-scale labelled datasets, is central to recent progress in machine learning. Access to task relevant labels at scale is often scarce or…
Mini-batch graphs for robust image classification
Arnab Kumar Mondal, Vineet Jain, Kaleem Siddiqi
Current deep learning models for classification tasks in computer vision are trained using mini-batches. In the present article, we take advantage of the relationships between samp…
Group Equivariant Deep Reinforcement Learning
Arnab Kumar Mondal, Pratheeksha Nair, Kaleem Siddiqi
In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn acti…
Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
Arnab Kumar Mondal, Jose Dolz, Christian Desrosiers
We address the problem of segmenting 3D multi-modal medical images in scenarios where very few labeled examples are available for training. Leveraging the recent success of adversa…
Retinal Vessel Segmentation under Extreme Low Annotation: A Generative Adversarial Network Approach
Avisek Lahiri, Vineet Jain, Arnab Mondal +1
Contemporary deep learning based medical image segmentation algorithms require hours of annotation labor by domain experts. These data hungry deep models perform sub-optimally in t…