Anand Raghunathan

2 papers · 2020–2023 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (10) 🐣 Hot Topic Early Bird

Venues

EMNLP (1) ICLR (1)

Top co-authors

Amrit Nagarajan (1) Sanchari Sen (1) Balaraman Ravindran (1)

Research topics

Deep Learning (2) Machine Learning (2) Natural Language Processing (1) Application Areas (1) Learning Types · Deep Learning (1) Learning Types · Machine Learning (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Resources & Methods (1) Techniques (1)

Keywords

model quantization (1) adversarial robustness (1) ensemble learning (1) adversarial attack (1) language model (1) token pruning (1) language model fine-tuning (1) efficient fine-tuning (1) model efficiency (1) batch sampling (1) quantized neural network (1) mixed precision (1) overfitting prevention (1) model regularization (1) token dropping (1) efficiency optimization (1) sequence padding (1) padding token (1) bucket sampling (1) padding-free training (1)

Papers

TokenDrop + BucketSampler: Towards Efficient Padding-free Fine-tuning of Language Models EMNLP 2023 EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial Attacks ICLR 2020