Papers by Nilesh Jain

4 papers
EFTNAS: Searching for Efficient Language Models in First-Order Weight-Reordered Super-Networks (2024.lrec-main)

Copied to clipboard

Challenge: Depending on the size of transformer-based models, they can be restricted from deployment in resource-constrained environments.
Approach: They propose to combine neural architecture search and network pruning techniques to generate and train weight-sharing super-networks that contain efficient transformer-based models.
Outcome: The proposed model achieves high-performing, high-performance subnetworks on the general language understanding evaluation and the Stanford Question Answering Dataset.
LoNAS: Elastic Low-Rank Adapters for Efficient Large Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) reach hundreds of billions of parameters and require resources for training and inference stages.
Approach: They propose a low-rank adapter to reduce the number of trainable parameters in a model and reduce memory requirements.
Outcome: The proposed approach reduces memory and compute requirements while preserving performance.
Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models (2025.naacl-long)

Copied to clipboard

Challenge: Large pre-trained models have achieved outstanding results in sequence modeling . alternative architectures, such as Selective Structured State Space Models (SSMs), have been proposed to address these inefficiencies.
Approach: They propose to reduce the size and computational overhead of large pre-trained models by removing selected components at different granularities.
Outcome: The proposed models achieve a speedup of up to 1.4x during inference while maintaining accuracy.
SQFT: Low-cost Model Adaptation in Low-precision Sparse Foundation Models (2024.findings-emnlp)

Copied to clipboard

Challenge: Large pre-trained models are often adapted to a desired domain or task through a fine-tuning stage.
Approach: They propose an end-to-end solution for sparse parameter-efficient fine-tuning of large pre-trained models.
Outcome: The proposed approach can be used to combine sparse weights with low-rank adapters without losing sparsity and accuracy.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations