AIConfPaper
← Search

Rupak Vignesh Swaminathan

5 accepted papers

2025

SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning

Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish, Arunasish Sen, Jian. Xie, Grant Strimel +1
ACL 2025long

We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50M is built from publicly available speech corpora, which collectively contain 14K hours of speech, and leverages LLMs al…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models

Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan, Nathan Susanj, Athanasios Mouchtaris, Siegfried Kunzmann +1
EMNLP 2025

The efficient implementation of large language models (LLMs) is crucial for deployment on resource-constrained devices. Low-rank tensor compression techniques, such as tensor-train (TT) networks, have been widely studied for over-parameterized neural networks. However, their applications to compress

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes

Yifan Yang, Zhen Zhang, Rupak Vignesh Swaminathan, Jing Liu, Nathan Susanj, Zheng Zhang
NeurIPS 2025poster

Fine-tuning vision language models (VLMs) has achieved remarkable performance across various downstream tasks; yet, it requires access to model gradients through backpropagation (BP), making them unsuitable for memory-constrained, inference-only edge devices. To address this limitation, previous wo…

Cited by 0Source ↗code ↗Scholar ↗
2025

Wanda++: Pruning Large Language Models via Regional Gradients

Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus Müller +8
ACL 2025finding

Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy degradation without full-model sparsity-aware fine-tuning. This paper presents Wanda++, a novel pruning framework that out…

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Max-Margin Transducer Loss: Improving Sequence-Discriminative Training Using a Large-Margin Learning Strategy

Rupak Vignesh Swaminathan, Grant P. Strimel, Ariya Rastrow, Sri Harish Mallidi, Kai Zhen, Hieu Duy Nguyen +2
ICASSP 2024accepted

In this work, we propose a novel sequence-discriminative training criterion for automatic speech recognition (ASR) based on the Conformer Transducer. Inspired by the large-margin classifier framework, we separate the "good" and the "bad" hypotheses in an N-best list produced from a pre-trained trans…

Cited by 0Source ↗Scholar ↗