Harvard Data Centric Machine Learning Group

Harvard-DCML's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

nihalnayak 

authored a paper 8 days ago

Revisiting Generalization Across Difficulty Levels: It's Not So Easy

Paper • 2511.21692 • Published 13 days ago • 15

jgeuter 

updated a model 21 days ago

Harvard-DCML/boomerang-qwen3-2.3B

Text Generation • 3B • Updated 21 days ago • 2.36k • 1

jgeuter 

authored 2 papers about 2 months ago

Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models

Paper • 2307.11224 • Published Jul 20, 2023 • 6

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

Paper • 2510.05064 • Published Oct 6 • 1

s-kangasl 

authored 3 papers about 2 months ago

Can You Label Less by Using Out-of-Domain Data? Active & Transfer Learning with Few-shot Instructions

Paper • 2211.11798 • Published Nov 21, 2022

Fast Forwarding Low-Rank Training

Paper • 2409.04206 • Published Sep 6, 2024

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

Paper • 2510.05064 • Published Oct 6 • 1

nihalnayak 

in Harvard-DCML/boomerang-qwen3-2.3B about 2 months ago

Add missing metadata tags

#1 opened about 2 months ago by

nielsr

nihalnayak 

authored a paper about 2 months ago

Boomerang Distillation Enables Zero-Shot Model Size Interpolation

Paper • 2510.05064 • Published Oct 6 • 1

nihalnayak 

updated a collection about 2 months ago

Boomerang Distillation

Collection

Distilled models from the boomerang distillation paper (https://arxiv.org/abs/2510.05064). • 6 items • Updated Oct 14 • 1

s-kangasl 

updated a collection about 2 months ago

Boomerang Distillation

Collection

Distilled models from the boomerang distillation paper (https://arxiv.org/abs/2510.05064). • 6 items • Updated Oct 14 • 1

nihalnayak 

updated a collection about 2 months ago

Boomerang Distillation

Collection

Distilled models from the boomerang distillation paper (https://arxiv.org/abs/2510.05064). • 6 items • Updated Oct 14 • 1

s-kangasl 

updated a model about 2 months ago

Harvard-DCML/boomerang-llama-3.2-1.9B

2B • Updated Oct 14 • 41

nihalnayak 

authored a paper almost 2 years ago

Learning to Generate Instruction Tuning Datasets for Zero-Shot Task Adaptation

Paper • 2402.18334 • Published Feb 28, 2024 • 12

nihalnayak 

authored 3 papers over 2 years ago

Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

Paper • 2204.03574 • Published Apr 7, 2022

Zero-Shot Learning with Common Sense Knowledge Graphs

Paper • 2006.10713 • Published Jun 18, 2020

Multitask Prompted Training Enables Zero-Shot Task Generalization

Paper • 2110.08207 • Published Oct 15, 2021 • 2