150 citations · 177 across the 13 of their papers we have counts for
13 papers
R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables
Maxwell Horton, Wei Lu, Quan Tran +6
Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmarks do not reflect the challenge…
OpenELM: An Efficient Language Model Family with Open Training and Inference Framework
Sachin Mehta, Mohammad Hossein Sekhavat, Qingqing Cao +8
The reproducibility and transparency of large language models are crucial for advancing open research, ensuring the trustworthiness of results, and enabling investigations into dat…
CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data
Sachin Mehta, Maxwell Horton, Fartash Faghri +5
Contrastive learning has emerged as a transformative method for learning effective visual representations through the alignment of image and text embeddings. However, pairwise simi…
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton +7
Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on ima…
Diffusion Models as Masked Audio-Video Learners
Elvis Nunez, Yanzi Jin, Mohammad Rastegari +2
Over the past several years, the synchronization between audio and visual signals has been leveraged to learn richer audio-visual representations. Aided by the large availability o…
On the Efficacy of Multi-scale Data Samplers for Vision Applications
Elvis Nunez, Thomas Merth, Anish Prabhu +4
Multi-scale resolution training has seen an increased adoption across multiple vision tasks, including classification and detection. Training with smaller resolutions enables faste…
Bytes Are All You Need: Transformers Operating Directly On File Bytes
Maxwell Horton, Sachin Mehta, Ali Farhadi +1
Modern deep learning approaches usually utilize modality-specific processing. For example, the most common deep learning approach to image classification involves decoding image fi…
RangeAugment: Efficient Online Augmentation with Range Learning
Sachin Mehta, Saeid Naderiparizi, Fartash Faghri +5
State-of-the-art automatic augmentation methods (e.g., AutoAugment and RandAugment) for visual recognition tasks diversify training data using a large set of augmentation operation…
SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks
Chien-Yu Lin, Anish Prabhu, Thomas Merth +4
Recent isotropic networks, such as ConvMixer and vision transformers, have found significant success across visual recognition tasks, matching or outperforming non-isotropic convol…
LCS: Learning Compressible Subspaces for Adaptive Network Compression at Inference Time
Elvis Nunez, Maxwell Horton, Anish Prabhu +3
When deploying deep learning models to a device, it is traditionally assumed that available computational resources (compute, memory, and power) remain static. However, real-world…
Learning Neural Network Subspaces
Mitchell Wortsman, Maxwell Horton, Carlos Guestrin +2
Recent observations have advanced our understanding of the neural network optimization landscape, revealing the existence of (1) paths of high accuracy containing diverse solutions…
Layer-Wise Data-Free CNN Compression
Maxwell Horton, Yanzi Jin, Ali Farhadi +1
We present a computationally efficient method for compressing a trained neural network without using real data. We break the problem of data-free network compression into independe…
Label Refinery: Improving ImageNet Classification through Label Progression
Hessam Bagherinezhad, Maxwell Horton, Mohammad Rastegari +1
Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labe…