Sameer Khurana

activity

20152025

most citedWhisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers

61 citations · 199 across the 16 of their papers we have counts for

collaborators

Showing 2025Show all

2 papers · 1 filter

cs.LG2025

Aligning Multimodal Representations through an Information Bottleneck

Antonio Almudévar, José Miguel Hernández-Lobato, Sameer Khurana +2

Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn a…

cs.CL2025

LF $^{2}$ AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models

Santiago Cuervo, Adel Moumen, Yanis Labrak +5

Text-pretrained language models (LMs) encode rich world knowledge, but adapting them to process and generate perceptual modalities such as audio and images while effectively levera…

Aligning Multimodal Representations through an Information Bottleneck

LF2AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models

LF $^{2}$ AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models