Search Results for author: Aditya Kusupati

Found 23 papers, 14 papers with code

MatMamba: A Matryoshka State Space Model

1 code implementation9 Oct 2024 Abhinav Shukla, Sai Vemprala, Aditya Kusupati, Ashish Kapoor

In this work, we present MatMamba: a state space model which combines Matryoshka-style learning with Mamba2, by modifying the block to contain nested dimensions to enable joint training and adaptive inference.

Representation Learning State Space Models

ActionAtlas: A VideoQA Benchmark for Domain-specialized Action Recognition

no code implementations8 Oct 2024 Mohammadreza Salehi, Jae Sung Park, Tanush Yadav, Aditya Kusupati, Ranjay Krishna, Yejin Choi, Hannaneh Hajishirzi, Ali Farhadi

To evaluate the effectiveness of multimodal foundation models in helping us recognize such actions, we present ActionAtlas v1. 0, a multiple-choice video question answering benchmark featuring short videos across various sports.

Action Recognition Multiple-choice +2

Mixture of Nested Experts: Adaptive Processing of Visual Tokens

no code implementations29 Jul 2024 Gagan Jain, Nidhi Hegde, Aditya Kusupati, Arsha Nagrani, Shyamal Buch, Prateek Jain, Anurag Arnab, Sujoy Paul

We present Mixture of Nested Experts (MoNE), which utilizes a nested structure for experts, wherein individual experts fall on an increasing compute-accuracy curve.

Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass

1 code implementation28 May 2024 Ethan Shen, Alan Fan, Sarah M. Pratt, Jae Sung Park, Matthew Wallingford, Sham M. Kakade, Ari Holtzman, Ranjay Krishna, Ali Farhadi, Aditya Kusupati

We achieve this by feeding a superposition of the most recent token embeddings from the $k$ drafts as input to the next decoding step of the language model.

Code Completion Language Modelling

Are "Hierarchical" Visual Representations Hierarchical?

1 code implementation9 Nov 2023 Ethan Shen, Ali Farhadi, Aditya Kusupati

In this work, we set out to investigate if hierarchical visual representations truly capture the human perceived hierarchy better than standard learned representations.

SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks

no code implementations18 Oct 2023 Mohammadreza Salehi, Sachin Mehta, Aditya Kusupati, Ali Farhadi, Hannaneh Hajishirzi

We introduce SHARCS for adaptive inference that takes into account the hardness of input samples.

EHI: End-to-end Learning of Hierarchical Index for Efficient Dense Retrieval

no code implementations13 Oct 2023 Ramnath Kumar, Anshul Mittal, Nilesh Gupta, Aditya Kusupati, Inderjit Dhillon, Prateek Jain

To facilitate the effective learning of this discrete structure, EHI introduces dense path embeddings that encodes the path traversed by queries and documents within the tree.

Contrastive Learning Retrieval

MatFormer: Nested Transformer for Elastic Inference

2 code implementations11 Oct 2023 Devvrit, Sneha Kudugunta, Aditya Kusupati, Tim Dettmers, KaiFeng Chen, Inderjit Dhillon, Yulia Tsvetkov, Hannaneh Hajishirzi, Sham Kakade, Ali Farhadi, Prateek Jain

Furthermore, we observe that smaller encoders extracted from a universal MatFormer-based ViT (MatViT) encoder preserve the metric-space structure for adaptive large-scale retrieval.

Decoder Language Modelling

Neural Priming for Sample-Efficient Adaptation

1 code implementation NeurIPS 2023 Matthew Wallingford, Vivek Ramanujan, Alex Fang, Aditya Kusupati, Roozbeh Mottaghi, Aniruddha Kembhavi, Ludwig Schmidt, Ali Farhadi

Performing lightweight updates on the recalled data significantly improves accuracy across a variety of distribution shift and transfer learning benchmarks.

Transfer Learning

AdANNS: A Framework for Adaptive Semantic Search

1 code implementation NeurIPS 2023 Aniket Rege, Aditya Kusupati, Sharan Ranjit S, Alan Fan, Qingqing Cao, Sham Kakade, Prateek Jain, Ali Farhadi

Finally, we demonstrate that AdANNS can enable inference-time adaptivity for compute-aware search on ANNS indices built non-adaptively on matryoshka representations.

Natural Questions Quantization +1

Neural Radiance Field Codebooks

1 code implementation10 Jan 2023 Matthew Wallingford, Aditya Kusupati, Alex Fang, Vivek Ramanujan, Aniruddha Kembhavi, Roozbeh Mottaghi, Ali Farhadi

Compositional representations of the world are a promising step towards enabling high-level scene understanding and efficient transfer to downstream tasks.

Object Representation Learning +1

Matryoshka Representation Learning

4 code implementations26 May 2022 Aditya Kusupati, Gantavya Bhatt, Aniket Rege, Matthew Wallingford, Aditya Sinha, Vivek Ramanujan, William Howard-Snyder, KaiFeng Chen, Sham Kakade, Prateek Jain, Ali Farhadi

The flexibility within the learned Matryoshka Representations offer: (a) up to 14x smaller embedding size for ImageNet-1K classification at the same level of accuracy; (b) up to 14x real-world speed-ups for large-scale retrieval on ImageNet-1K and 4K; and (c) up to 2% accuracy improvements for long-tail few-shot classification, all while being as robust as the original representations.

Ranked #25 on Image Classification on ObjectNet (using extra training data)

4k Image Classification +2

Disrupting Model Training with Adversarial Shortcuts

no code implementations ICML Workshop AML 2021 Ivan Evtimov, Ian Covert, Aditya Kusupati, Tadayoshi Kohno

When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes.

BIG-bench Machine Learning Image Classification

FLUID: A Unified Evaluation Framework for Flexible Sequential Data

2 code implementations6 Jul 2020 Matthew Wallingford, Aditya Kusupati, Keivan Alizadeh-Vahid, Aaron Walsman, Aniruddha Kembhavi, Ali Farhadi

To foster research towards the goal of general ML methods, we introduce a new unified evaluation framework - FLUID (Flexible Sequential Data).

Continual Learning Representation Learning +1

Extreme Regression for Dynamic Search Advertising

no code implementations15 Jan 2020 Yashoteja Prabhu, Aditya Kusupati, Nilesh Gupta, Manik Varma

This paper also introduces a (3) new labelwise prediction algorithm in XReg useful for DSA and other recommendation tasks.

regression

One Size Does Not Fit All: Multi-Scale, Cascaded RNNs for Radar Classification

1 code implementation6 Sep 2019 Dhrubojyoti Roy, Sangeeta Srivastava, Aditya Kusupati, Pranshu Jain, Manik Varma, Anish Arora

Edge sensing with micro-power pulse-Doppler radars is an emergent domain in monitoring and surveillance with several smart city applications.

Feature Engineering General Classification

FastGRNN: A Fast, Accurate, Stable and Tiny Kilobyte Sized Gated Recurrent Neural Network

1 code implementation NeurIPS 2018 Aditya Kusupati, Manish Singh, Kush Bhatia, Ashish Kumar, Prateek Jain, Manik Varma

FastRNN addresses these limitations by adding a residual connection that does not constrain the range of the singular values explicitly and has only two extra scalar parameters.

Action Classification Language Modelling +3

Cannot find the paper you are looking for? You can Submit a new open access paper.