← Search

Susmit Agrawal

8 accepted papers

2026

ALPHA: Action-Based Learning for Pluralistic Human Alignment in Large Language Models

AAAI 2026technical

Large language models are widely used, but aligning them with societal values remains challenging. Current approaches often rely on human annotations, which are hard to scale, or synthetic data produced by models that may themselves be misaligned, making it difficult to capture genuine public opinio

Cited by 0SourcePDFScholar
2025

Analyzing Memorization in Large Language Models through the Lens of Model Attribution

NAACL 2025long

Large Language Models (LLMs) are prevalent in modern applications but often memorize training data, leading to privacy breaches and copyright issues. Existing research has mainly focused on post-hoc analyses—such as extracting memorized content or developing memorization metrics—without exploring th…

2025

Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks

NeurIPS 2025poster

Organisms constantly pivot between tasks such as evading predators, foraging, traversing rugged terrain, and socializing, often within milliseconds. Remarkably, they preserve knowledge of once-learned environments sans catastrophic forgetting, a phenomenon neuroscientists hypothesize, is due to a si…

Cited by 0SourceScholar
2025

Walking the Web of Concept-Class Relationships in Incrementally Trained Interpretable Models

AAAI 2025technical

Concept-based methods have emerged as a promising direction to develop interpretable neural networks in standard supervised settings. However, most works that study them in incremental settings assume either a static concept set across all experiences or assume that each experience relies on a disti…

2022

Hierarchical Semantic Regularization of Latent Spaces in StyleGANs

ECCV 2022poster

"Progress in GANs has enabled the generation of high-resolution photorealistic images of astonishing quality. StyleGANs allow for compelling attribute modification on such images via mathematical operations on the latent style vectors in the W/W+ space that effectively modulate the rich hierarchical…

Cited by 10SourcePDFScholar
2021

Labeled From Unlabeled: Exploiting Unlabeled Data for Few-Shot Deep HDR Deghosting

CVPR 2021poster

High Dynamic Range (HDR) deghosting is an indispensable tool in capturing wide dynamic range scenes without ghosting artifacts. Recently, convolutional neural networks (CNNs) have shown tremendous success in HDR deghosting. However, CNN-based HDR deghosting methods require collecting large datasets…

Cited by 37PDFScholar
2020

Towards Practical and Efficient High-Resolution HDR Deghosting with CNN

ECCV 2020poster

Generating High Dynamic Range (HDR) image in the presence of camera and object motion is a tedious task. If uncorrected, these motions will manifest as ghosting artifacts in the fused HDR image. On one end of the spectrum, there exist methods that generate high-quality results that are computational…

Cited by 75SourcePDFScholar