Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Complement Submodular Information Measures for Balanced and Robust Data Selection
Rishabh Iyer
Submodular optimization has become a fundamental paradigm for data selection, retrieval, summarization, and representation learning due to its ability to model coverage, diversity,…
cs.LG2026
SMA: Submodular Modality Aligner For Data Efficient Multimodal Learning
Truong Pham, Anay Majee, Rishabh Iyer
Despite the recent success of Multimodal Foundation Models (FMs), their reliance on massive paired datasets limits their applicability in low-data and rare-scenario settings where…
cs.LG2024
SCoRe: Submodular Combinatorial Representation Learning
Anay Majee, Suraj Kothawade, Krishnateja Killamsetty +1
In this paper we introduce the SCoRe (Submodular Combinatorial Representation Learning) framework, a novel approach in representation learning that addresses inter-class bias and i…