2 citations · 4 across the 10 of their papers we have counts for
11 papers
Activation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Ryan Solgi, Parsa Madinei, Jiayi Tian +4
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment.…
SharpZO: Hybrid Sharpness-Aware Vision Language Model Prompt Tuning via Forward-Only Passes
Yifan Yang, Zhen Zhang, Rupak Vignesh Swaminathan +3
Fine-tuning vision language models (VLMs) has achieved remarkable performance across various downstream tasks; yet, it requires access to model gradients through backpropagation (B…
Saten: Sparse Augmented Tensor Networks for Post-Training Compression of Large Language Models
Ryan Solgi, Kai Zhen, Rupak Vignesh Swaminathan +4
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…
SIFT-50M: A Large-Scale Multilingual Dataset for Speech Instruction Fine-Tuning
Prabhat Pandey, Rupak Vignesh Swaminathan, K V Vijay Girish +4
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-50…
Wanda++: Pruning Large Language Models via Regional Gradients
Yifan Yang, Kai Zhen, Bhavana Ganesh +11
Large Language Models (LLMs) pruning seeks to remove unimportant weights for inference speedup with minimal accuracy impact. However, existing methods often suffer from accuracy de…
Accelerator-Aware Training for Transducer-Based Speech Recognition
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen +6
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network a…
Leveraging Redundancy in Multiple Audio Signals for Far-Field Speech Recognition
Feng-Ju Chang, Anastasios Alexandridis, Rupak Vignesh Swaminathan +6
To achieve robust far-field automatic speech recognition (ASR), existing techniques typically employ an acoustic front end (AFE) cascaded with a neural transducer (NT) ASR model. T…
Contextual-Utterance Training for Automatic Speech Recognition
Alejandro Gomez-Alanis, Lukas Drude, Andreas Schwarz +2
Recent studies of streaming automatic speech recognition (ASR) recurrent neural network transducer (RNN-T)-based systems have fed the encoder with past contextual information in or…
ConvRNN-T: Convolutional Augmented Recurrent Neural Network Transducers for Streaming Speech Recognition
Martin Radfar, Rohit Barnwal, Rupak Vignesh Swaminathan +4
The recurrent neural network transducer (RNN-T) is a prominent streaming end-to-end (E2E) ASR technology. In RNN-T, the acoustic encoder commonly consists of stacks of LSTMs. Very…
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition
Rupak Vignesh Swaminathan, Brian King, Grant P. Strimel +2
We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs…
Exploiting Large-scale Teacher-Student Training for On-device Acoustic Models
Jing Liu, Rupak Vignesh Swaminathan, Sree Hari Krishnan Parthasarathi +3
We present results from Alexa speech teams on semi-supervised learning (SSL) of acoustic models (AM) with experiments spanning over 3000 hours of GPU time, making our study one of…