Abacus.AI - Effortlessly Embed Cutting Edge AI In Your Applications.

Publications

The research team at Abacus.AI makes fundamental contributions to the field of AI/ML that might have an impact in the short or long run and does applied research that has benefits in practice. The areas we have been focusing on include large language models, time-series forecasting, recommender systems, automated machine learning, meta-learning, deep learning for tabular data, deep learning optimization, and fairness/debiasing in deep learning.

The team already has an impressive list of publications in top-tier conferences and workshops in just over four years of its conception.

Preprints

Giraffe: Adventures in Expanding Context Lengths in LLMs

Arka Pal, Deep Karkhanis, Manley Roberts, Samuel Dooley, Arvind Sundararajan, Siddartha Naidu

arXiv Preprint

LiveBench: A Challenging, Contamination-Free LLM Benchmark

Colin White, Samuel Dooley, Manley Roberts, Arka Pal, Ben Feuer, Siddhartha Jain, Ravid Schwartz - Ziv, Neel Jain, Khalid Saifullah, Siddartha Naidu, Chinmay Hegde, Yann LeCun, Tom Goldstein, Willie Neiswanger, Micah Goldblum

Conference and Journal Papers

ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Samuel Dooley, Gurnoor Singh Khurana, Chirag Mohapatra, Siddartha Venkat Naidu, Colin White

NeurIPS 2023

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

Samuel Dooley, Rhea Sukthanker, John P Dickerson, Colin White, Frank Hutter, Micah Goldblum

NeurIPS 2023

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, Vishak Prasad C, Ganesh Ramakrishnan, Micah Goldblum, Colin White

NeurIPS 2023 DBT

A Deep Dive into Dataset Imbalance and Bias in Face Identification

Valeriia Cherepanova, Steven Reich, Samuel Dooley, Hossein Souri, John P Dickerson, Micah Goldblum, Tom Goldstein

AIES 2023

TinyNS: Platform-Aware Neurosymbolic Auto Tiny Machine Learning

Swapnil Sayan Saha, Sandeep Singh Sandha, Mohit Aggarwal, Brian Wang, Liying Han, Julian de Gortari Briseno, and Mani Srivastava

ACM TECS 2023

Inertial Navigation on Extremely Resource-Constrained Platforms: Methods, Opportunities and Challenges

Swapnil Sayan Saha, Yayun Du, Sandeep Singh Sandha, Luis Antonio Garcia, and Mani Srivastava

IEEE/ION PLANS 2023

On the Generalizability and Predictability of Recommender Systems

Duncan McElfresh, Sujay Khandagale, Jonathan Valverde, John Dickerson, Colin White

Workshop at AutoML-Conf 2022

NAS-Bench-Suite-Zero: Accelerating Research on Zero Cost Proxies

Arjun Krishnakumar, Colin White, Arber Zela, Renbo Tu, Mahmoud Safari, Frank Hutter

NeurIPS Datasets Track 2022

A Deeper Look at Zero-Cost Proxies for Lightweight NAS

Colin White, Mikhail Khodak, Renbo Tu, Shital Shah, Sébastien Bubeck, Debadeepta Dey

ICLR 2022 Blog Track

NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy

Yash Mehta, Colin White, Arber Zela, Arjun Krishnakumar, Guri Zabergja, Shakiba Moradian, Mahmoud Safari, Kaicheng Yu, Frank Hutter

ICLR 2022

Synthetic Benchmarks for Scientific Research in Explainable Machine Learning

Yang Liu, Sujay Khandagale, Colin White, Willie Neiswanger

NeurIPS Datasets Track 2021

NAS-Bench-x11 and the Power of Learning Curves

Shen Yan, Colin White, Yash Savani, Frank Hutter

NeurIPS 2021

How Powerful are Performance Predictors in Neural Architecture Search?

Colin White, Arber Zela, Binxin Ru, Yang Liu, Frank Hutter

NeurIPS 2021

An Analysis of Super-Net Heuristics in Weight-Sharing NAS

Kaicheng Yu, René Ranftl, Mathieu Salzmann

TPAMI 2021

Learning by Turning: Neural Architecture Aware Optimisation

Yang Liu, Jeremy Bernstein, Markus Meister, Yisong Yue

ICML 2021

BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search

Colin White, Willie Neiswanger, Yash Savani

AAAI 2021

Exploring the Loss Landscape in Neural Architecture Search

Colin White, Sam Nolen, Yash Savani

UAI 2021

A Study on Encodings for Neural Architecture Search

Colin White, Willie Neiswanger, Sam Nolen, Yash Savani

Selected for spotlight presentation | NeurIPS 2020

Intra-Processing Methods for Debiasing Neural Networks

Yash Savani, Colin White, Naveen Sundar Govindarajulu

NeurIPS 2020

Workshop Papers

A Natural Experiment on LLM Data Contamination in Code Generation

Manley Roberts, Himanshu Thakur, Christine Herlihy, Colin White, Samuel Dooley

NeurIPS Workshop, I Can't Believe It's Not Better: Failure Modes in the Age of Foundation Models, 2023

ForecastPFN: Zero-Shot Low-Resource Forecasting

Gurnoor Khurana, Samuel Dooley, Siddartha Naidu, Colin White

ICLR Workshop on Practical ML for Developing Countries, 2023

Speeding up NAS with Adaptive Subset Selection

Vishak Prasad, Colin White, Paarth Jain, Sibasis Nayak, Rishabh Iyer, Ganesh Ramakrishnan

Workshop at AutoML-Conf 2022

Deep Uncertainty Estimation for Model-based Neural Architecture Search

Colin White, Willie Neiswanger, Yash Savani

NeurIPS Workshop on Bayesian Deep Learning 2019

DECO: Debiasing through Compositional Optimization of Machine Learning Models

Naveen Sundar Govindarajulu and Colin White

NeurIPS Workshop on Robust AI in Financial Services, 2019

Differentiable Functions for Combining First-order Constraints with Deep Learning via Weighted Proof Tracing

Naveen Sundar Govindarajulu and Colin White

NeurIPS Workshop on Knowledge Representation to ML, 2019

Competitions

CVPR 2021 Unseen Data in Neural Architecture Search

Simon Schrodi, Colin White, Ekrem Ozturk, Danny Stoll, Frank Hutter