Search Results for author:
Found 20 papers, 6 papers with code
Symmetry-Aware Generative Modeling through Learned Canonicalization
Generative modeling of symmetric densities has a range of applications in AI for science, from drug discovery to physics simulations.
Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale
Rapid advancements in GPU computational power has outpaced memory capacity and bandwidth growth, creating bottlenecks in Large Language Model (LLM) inference.
Learning Disentangled Representation in Object-Centric Models for Visual Dynamics Prediction via Transformers
Recent work has shown that object-centric representations can greatly help improve the accuracy of learning dynamics while also bringing interpretability.
Improved Canonicalization for Model Agnostic Equivariance
This work introduces a novel approach to achieving architecture-agnostic equivariance in deep learning, particularly addressing the limitations of traditional layerwise equivariant architectures and the inefficiencies of the existing architecture-agnostic methods.
HumMUSS: Human Motion Understanding using State Space Models
Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition.
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
We approach this problem from the lens of Koopman theory, where the nonlinear dynamics of the environment can be linearized in a high-dimensional latent space.
Image Manipulation via Multi-Hop Instructions -- A New Dataset and Weakly-Supervised Neuro-Symbolic Approach
We are interested in image manipulation via natural language text -- a task that is useful for multiple AI applications but requires complex reasoning over multi-modal spaces.
Equivariance with Learned Canonicalization Functions
Symmetry-based neural networks often constrain the architecture in order to achieve invariance or equivariance to a group of transformations.
Transformation Coding: Simple Objectives for Equivariant Representations
We present a simple non-generative approach to deep representation learning that seeks equivariant deep embedding through simple objectives.
Investigating Power laws in Deep Representation Learning
Access to task relevant labels at scale is often scarce or expensive, motivating the need to learn from unlabelled datasets with self-supervised learning (SSL).
EqR: Equivariant Representations for Data-Efficient Reinforcement Learning
We study different notions of equivariance as an inductive bias in Reinforcement Learning (RL) and propose new mechanisms for recovering representations that are equivariant to both an agent’s action, and symmetry transformations of the state-action pairs.
ScRAE: Deterministic Regularized Autoencoders with Flexible Priors for Clustering Single-cell Gene Expression Data
The basic idea in RAEs is to learn a non-linear mapping from the high-dimensional data space to a low-dimensional latent space and vice-versa, simultaneously imposing a distributional prior on the latent space, which brings in a regularization effect.
Mini-batch graphs for robust image classification
Current deep learning models for classification tasks in computer vision are trained using mini-batches.
RespVAD: Voice Activity Detection via Video-Extracted Respiration Patterns
The Respiration Pattern is first extracted from the video focusing on the abdominal-thoracic region of a speaker using an optical flow based method.
Group Equivariant Deep Reinforcement Learning
In Reinforcement Learning (RL), Convolutional Neural Networks(CNNs) have been successfully applied as function approximators in Deep Q-Learning algorithms, which seek to learn action-value functions and policies in various environments.
To Regularize or Not To Regularize? The Bias Variance Trade-off in Regularized AEs
Specifically, we consider the class of RAEs with deterministic Encoder-Decoder pairs, Wasserstein Auto-Encoders (WAE), and show that having a fixed prior distribution, \textit{a priori}, oblivious to the dimensionality of the `true' latent space, will lead to the infeasibility of the optimization problem considered.
C-MI-GAN : Estimation of Conditional Mutual Information using MinMax formulation
Estimation of information theoretic quantities such as mutual information and its conditional variant has drawn interest in recent times owing to their multifaceted applications.
MaskAAE: Latent space optimization for Adversarial Auto-Encoders
The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse.
Revisiting CycleGAN for semi-supervised segmentation
In this work, we study the problem of training deep networks for semantic image segmentation using only a fraction of annotated images, which may significantly reduce human annotation efforts.
Few-shot 3D Multi-modal Medical Image Segmentation using Generative Adversarial Learning
In addition, our work presents a comprehensive analysis of different GAN architectures for semi-supervised segmentation, showing recent techniques like feature matching to yield a higher performance than conventional adversarial training approaches.
