101 citations · 383 across the 24 of their papers we have counts for
24 papers
Matryoshka Quantization
Pranav Nair, Puranjay Datta, Jeff Dean +2
Quantizing model weights is critical for reducing the communication and inference costs of large models. However, quantizing models -- especially to low precisions like int4 or int…
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Gagan Jain, Nidhi Hegde, Aditya Kusupati +5
The visual medium (images and videos) naturally contains a large amount of information redundancy, thereby providing a great opportunity for leveraging efficiency in processing. Wh…
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Ethan Shen, Alan Fan, Sarah M. Pratt +7
Many applications today provide users with multiple auto-complete drafts as they type, including GitHub's code completion, Gmail's smart compose, and Apple's messaging auto-suggest…
Gecko: Versatile Text Embeddings Distilled from Large Language Models
Jinhyuk Lee, Zhuyun Dai, Xiaoqi Ren +17
We present Gecko, a compact and versatile text embedding model. Gecko achieves strong retrieval performance by leveraging a key idea: distilling knowledge from large language model…
Are "Hierarchical" Visual Representations Hierarchical?
Ethan Shen, Ali Farhadi, Aditya Kusupati
Learned visual representations often capture large amounts of semantic information for accurate downstream applications. Human understanding of the world is fundamentally grounded…
SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks
Mohammadreza Salehi, Sachin Mehta, Aditya Kusupati +2
We introduce SHARCS for adaptive inference that takes into account the hardness of input samples. SHARCS can train a router on any transformer network, enabling the model to direct…
EHI: End-to-end Learning of Hierarchical Index for Efficient Dense Retrieval
Ramnath Kumar, Anshul Mittal, Nilesh Gupta +3
Dense embedding-based retrieval is widely used for semantic search and ranking. However, conventional two-stage approaches, involving contrastive embedding learning followed by app…
MatFormer: Nested Transformer for Elastic Inference
Devvrit, Sneha Kudugunta, Aditya Kusupati +8
Foundation models are applied in a broad spectrum of settings with different inference constraints, from massive multi-accelerator clusters to resource-constrained standalone mobil…
MADLAD-400: A Multilingual And Document-Level Large Audited Dataset
Sneha Kudugunta, Isaac Caswell, Biao Zhang +8
We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-a…
Objaverse-XL: A Universe of 10M+ 3D Objects
Matt Deitke, Ruoshi Liu, Matthew Wallingford +14
Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks hav…
Neural Priming for Sample-Efficient Adaptation
Matthew Wallingford, Vivek Ramanujan, Alex Fang +5
We propose Neural Priming, a technique for adapting large pretrained models to distribution shifts and downstream tasks given few or no labeled examples. Presented with class names…
AdANNS: A Framework for Adaptive Semantic Search
Aniket Rege, Aditya Kusupati, Sharan Ranjit S +5
Web-scale search systems learn an encoder to embed a given query which is then hooked into an approximate nearest neighbor search (ANNS) pipeline to retrieve similar data points. T…
Neural Radiance Field Codebooks
Matthew Wallingford, Aditya Kusupati, Alex Fang +4
Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks. Learning such representa…
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…
ProtoSound: A Personalized and Scalable Sound Recognition System for Deaf and Hard-of-Hearing Users
Dhruv Jain, Khoa Huynh Anh Nguyen, Steven Goodman +7
Recent advances have enabled automatic sound recognition systems for deaf and hard of hearing (DHH) users on mobile devices. However, these tools use pre-trained, generic sound rec…
MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound
Rowan Zellers, Jiasen Lu, Ximing Lu +7
As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- t…
Disrupting Model Training with Adversarial Shortcuts
Ivan Evtimov, Ian Covert, Aditya Kusupati +1
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes. Successful model training may be preventabl…
LLC: Accurate, Multi-purpose Learnt Low-dimensional Binary Codes
Aditya Kusupati, Matthew Wallingford, Vivek Ramanujan +6
Learning binary representations of instances and classes is a classical problem with several high potential applications. In modern settings, the compression of high-dimensional ne…
FLUID: A Unified Evaluation Framework for Flexible Sequential Data
Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid +3
Modern ML methods excel when training data is IID, large-scale, and well labeled. Learning in less ideal conditions remains an open challenge. The sub-fields of few-shot, continual…
RNNPool: Efficient Non-linear Pooling for RAM Constrained Inference
Oindrila Saha, Aditya Kusupati, Harsha Vardhan Simhadri +2
Standard Convolutional Neural Networks (CNNs) designed for computer vision tasks tend to have large intermediate activation maps. These require large working memory and are thus un…
Soft Threshold Weight Reparameterization for Learnable Sparsity
Aditya Kusupati, Vivek Ramanujan, Raghav Somani +4
Sparsity in Deep Neural Networks (DNNs) is studied extensively with the focus of maximizing prediction accuracy given an overall parameter budget. Existing methods rely on uniform…
Extreme Regression for Dynamic Search Advertising
Yashoteja Prabhu, Aditya Kusupati, Nilesh Gupta +1
This paper introduces a new learning paradigm called eXtreme Regression (XR) whose objective is to accurately predict the numerical degrees of relevance of an extremely large numbe…
One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification
Dhrubojyoti Roy, Sangeeta Srivastava, Aditya Kusupati +3
Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications. Existing solutions for the clutter ver…
FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network
Aditya Kusupati, Manish Singh, Kush Bhatia +3
This paper develops the FastRNN and FastGRNN algorithms to address the twin RNN limitations of inaccurate training and inefficient prediction. Previous approaches have improved acc…