Search Results for author:
Found 8 papers, 5 papers with code
Investigating Training Strategies and Model Robustness of Low-Rank Adaptation for Language Modeling in Speech Recognition
The use of low-rank adaptation (LoRA) with frozen pretrained language models (PLMs) has become increasing popular as a mainstream, resource-efficient modeling approach for memory-constrained hardware.
Low-rank Adaptation of Large Language Model Rescoring for Parameter-Efficient Speech Recognition
We propose a neural language modeling system based on low-rank adaptation (LoRA) for speech recognition output rescoring.
Large Language Models of Code Fail at Completing Code with Potential Bugs
We find that the presence of potential bugs significantly degrades the generation performance of the high-performing Code-LLMs.
LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Tasks
LIFT does not make any changes to the model architecture or loss function, and it solely relies on the natural language interface, enabling "no-code machine learning with LMs."
Utilizing Language-Image Pretraining for Efficient and Robust Bilingual Word Alignment
Word translation without parallel corpora has become feasible, rivaling the performance of supervised methods.
Improved Input Reprogramming for GAN Conditioning
Motivated by real-world scenarios with scarce labeled data, we focus on the input reprogramming approach and carefully analyze the existing algorithm.
Coded-InvNet for Resilient Prediction Serving Systems
Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures.
Constrained Deep Learning using Conditional Gradient and Applications in Computer Vision
We provide convergence guarantees and show a suite of immediate benefits that are possible -- from training ResNets with fewer layers but better accuracy simply by substituting in our version of CG to faster training of GANs with 50% fewer epochs in image inpainting applications to provably better generalization guarantees using efficiently implementable forms of recently proposed regularizers.
