activity
20242026
most citedOn the Diversity of Synthetic Data and its Impact on Training Large Language Models

5 citations · 9 across the 51 of their papers we have counts for

collaborators

52 papers

cs.SD2026

Heard but Not Heeded: Paralinguistic Information Encoding and Loss in Audio-Language Models

Bhuvan Koduru, Dareen Safar B Alharthi, Rita Singh +1

Audio language models are designed to understand speech, yet it remains unclear whether they capture how something is said beyond what is said. We present a mechanistic analysis of…

cs.LG2026

Encoder-Decoder Manifold Alignment for Idempotent Generation

Dareen Alharthi, Abdul Waheed, Bhiksha Raj

Recently, several learning paradigms have been introduced to enforce idempotency in generative models. The goal is to ensure that repeated application of a model leaves samples unc…

cs.SD2026

RIVET: Robust Idempotent Voice Attribute Editing

Dareen Alharthi, Bhuvan Koduru, Rita Singh +1

Voice attribute editing models modify characteristics such as age and gender while preserving speaker identity. In large-scale speech datasets, however, attribute annotations are o…

cs.SD2026

Audio Language Model for Deepfake Detection Grounded in Acoustic Chain-of-Thought

Runkun Chen, Yixiong Fang, Pengyu Chang +3

Deepfake speech detection systems are often limited to binary classification tasks and struggle to generate interpretable reasoning or provide context-rich explanations for their d…

cs.LG2026

-DPO: Fairness Direct Preference Optimization Approach to Continual Learning in Large Multimodal Models

Thanh-Dat Truong, Huu-Thien Tran, Jackson Cothren +2

Fairness in Continual Learning for Large Multimodal Models (LMMs) is an emerging yet underexplored challenge, particularly in the presence of imbalanced data distributions that can…

cs.SD2026

What and When to Learn: CURriculum Ranking Loss for Large-Scale Speaker Verification

Massa Baali, Sarthak Bisht, Rita Singh +1

Speaker verification at large scale remains an open challenge as fixed-margin losses treat all samples equally regardless of quality. We hypothesize that mislabeled or degraded sam…