85 citations · 118 across the 15 of their papers we have counts for
15 papers
Coresets Before Score Sets: Evaluation-Unsupervised Prompt Subset Selection for LLM Benchmarks
Jihan Yao, Gantavya Bhatt, Arnav Das +16
We study LLM benchmark coreset selection: selecting a small subset of prompts over multiple benchmarks whose induced model scores and rankings approximate those obtained from the f…
How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
Jeff A. Bilmes, Gantavya Bhatt, Arnav M. Das
Neural scaling laws appraise data through dataset size, while the Vendi Score uses quantum entropy to measure dataset value. We show both that common neural-scaling-law objectives…
COBRA: COmBinatorial Retrieval Augmentation for Few-Shot Adaptation
Arnav M. Das, Gantavya Bhatt, Lilly Kumari +2
Retrieval augmentation, the practice of retrieving additional data from large auxiliary pools, has emerged as an effective technique for enhancing model performance in the low-data…
How Many Images Does It Take? Estimating Imitation Thresholds in Text-to-Image Models
Sahil Verma, Royi Rassin, Arnav Das +6
Text-to-image models are trained using large datasets of image-text pairs collected from the internet. These datasets often include copyrighted and private images. Training models…
Comparing Bad Apples to Good Oranges: Aligning Large Language Models via Joint Preference Optimization
Hritik Bansal, Ashima Suvarna, Gantavya Bhatt +3
A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, ho…
Deep Submodular Peripteral Networks
Gantavya Bhatt, Arnav Das, Jeff Bilmes
Submodular functions, crucial for various applications, often lack practical learning methods for their acquisition. Seemingly unrelated, learning a scaling from oracles offering g…
An Experimental Design Framework for Label-Efficient Supervised Finetuning of Large Language Models
Gantavya Bhatt, Yifang Chen, Arnav M. Das +9
Supervised finetuning (SFT) on instruction datasets has played a crucial role in achieving the remarkable zero-shot generalization capabilities observed in modern large language mo…
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild +6
Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly conce…
LabelBench: A Comprehensive Framework for Benchmarking Adaptive Label-Efficient Learning
Jifan Zhang, Yifang Chen, Gregory Canal +8
Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer learning…
Accelerating Batch Active Learning Using Continual Learning Techniques
Arnav Das, Gantavya Bhatt, Megh Bhalerao +3
A major problem with Active Learning (AL) is high training costs since models are typically retrained from scratch after every query round. We start by demonstrating that standard…
High Resolution Point Clouds from mmWave Radar
Akarsh Prabhakara, Tao Jin, Arnav Das +6
This paper explores a machine learning approach for generating high resolution point clouds from a single-chip mmWave radar. Unlike lidar and vision-based systems, mmWave radar can…
Matryoshka Representation Learning
Aditya Kusupati, Gantavya Bhatt, Aniket Rege +8
Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computa…
Systematic Generalization in Neural Networks-based Multivariate Time Series Forecasting Models
Hritik Bansal, Gantavya Bhatt, Pankaj Malhotra +1
Systematic generalization aims to evaluate reasoning about novel combinations from known components, an intrinsic property of human cognition. In this work, we study systematic gen…
Can RNNs trained on harder subject-verb agreement instances still perform well on easier ones?
Hritik Bansal, Gantavya Bhatt, Sumeet Agarwal
Previous work suggests that RNNs trained on natural language corpora can capture number agreement well for simple sentences but perform less well when sentences contain agreement a…
How much complexity does an RNN architecture need to learn syntax-sensitive dependencies?
Gantavya Bhatt, Hritik Bansal, Rishubh Singh +1
Long short-term memory (LSTM) networks and their variants are capable of encapsulating long-range dependencies, which is evident from their performance on a variety of linguistic t…