Siddarth Asokan — accepted AI-conference papers

2025

MOGIC: Metadata-infused Oracle Guidance for Improved Extreme Classification

Suchith Chidananda Prabhu, Bhavyajeet Singh, Anshul Mittal, Siddarth Asokan, Shikhar Mohan, Deepak Saini +8

ICML 2025poster

Retrieval-augmented classification and generation models benefit from *early-stage fusion* of high-quality text-based metadata, often called memory, but face high latency and noise sensitivity. In extreme classification (XC), where low latency is crucial, existing methods use *late-stage fusion* for…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2024

Momentum-Imbued Langevin Dynamics (MILD) for Faster Sampling

Nishanth Shetty, Manikanta Bandla, Nishit Neema, Siddarth Asokan, Chandra Sekhar Seelamantula

ICASSP 2024accepted

Score-based generative models have emerged as the state-of-the-art in generative modeling. In this paper, we introduce a novel sampling scheme that can be combined with pre-trained score-based diffusion models to speed up sampling by a factor of two to five in terms of the number of function evaluat…

Cited by 0 Source ↗Scholar ↗

2024

Variational Analysis of Adversarial Regularization for Solving Inverse Problems

Abhishek Shreekant Bhandiwad, Abijith Jagannath Kamath, Siddarth Asokan, Chandra Sekhar Seelamantula

ICASSP 2024accepted

Inverse problems form the backbone of modern signal/image processing and computational imaging, where signal reconstruction from corrupted measurements follows an optimization problem. The objective function is the sum of a data-fidelity term and a regularization functional that enforces desired pro…

Cited by 0 Source ↗Scholar ↗

2023

A Game of Snakes and Gans

Siddarth Asokan, Fatwir Sheikh Mohammed, Chandra Sekhar Seelamantula

ICASSP 2023accepted

Generative adversarial networks (GANs) comprise generator and discriminator networks trained adversarially to learn the underlying distribution of a dataset. Recently, we have shown that the optimal GAN discriminator can be obtained in closed-form as the solution to the Poisson partial differential…

Cited by 0 Source ↗Scholar ↗

2023

Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training

Siddarth Asokan, Chandra Sekhar Seelamantula

CVPR 2023poster

Training Generative adversarial networks (GANs) stably is a challenging task. The generator in GANs transform noise vectors, typically Gaussian distributed, into realistic data such as images. In this paper, we propose a novel approach for training GANs with images as inputs, but without enforcing a…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗

2020

Teaching a GAN What Not to Learn

Siddarth Asokan, Chandra Seelamantula

NeurIPS 2020poster

Generative adversarial networks (GANs) were originally envisioned as unsupervised generative models that learn to follow a target distribution. Variants such as conditional GANs, auxiliary-classifier GANs (ACGANs) project GANs on to supervised and semi-supervised learning frameworks by providing lab…

Cited by 23 Source ↗PDF ↗code ↗Scholar ↗