Search Results for author: Aayush Mishra

Found 9 papers, 4 papers with code

Automatic Machine Learning Framework to Study Morphological Parameters of AGN Host Galaxies within $z < 1.4$ in the Hyper Supreme-Cam Wide Survey

1 code implementation27 Jan 2025 Chuan Tian, C. Megan Urry, Aritra Ghosh, Daisuke Nagai, Tonima T. Ananna, Meredith C. Powell, Connor Auge, Aayush Mishra, David B. Sanders, Nico Cappelluti, Kevin Schawinski

We present a composite machine learning framework to estimate posterior probability distributions of bulge-to-total light ratio, half-light radius, and flux for Active Galactic Nucleus (AGN) host galaxies within $z<1. 4$ and $m<23$ in the Hyper Supreme-Cam Wide survey.

Transfer Learning

Robust Amortized Bayesian Inference with Self-Consistency Losses on Unlabeled Data

no code implementations23 Jan 2025 Aayush Mishra, Daniel Habermann, Marvin Schmitt, Stefan T. Radev, Paul-Christian Bürkner

In this proof-of-concept paper, we propose a semi-supervised approach that enables training not only on (labeled) simulated data generated from the model, but also on unlabeled data originating from any source, including real-world data.

Bayesian Inference

On the challenges of detecting MCI using EEG in the wild

1 code implementation15 Jan 2025 Aayush Mishra, David Joffe, Sankara Surendra Telidevara, David S Oakley, Anqi Liu

Recent studies have shown promising results in the detection of Mild Cognitive Impairment (MCI) using easily accessible Electroencephalogram (EEG) data which would help administer early and effective treatment for dementia patients.

Domain Generalization EEG

Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation

no code implementations19 Jan 2024 Prakhar Kaushik, Aayush Mishra, Adam Kortylewski, Alan Yuille

We focus on individual locally robust mesh vertex features and iteratively update them based on their proximity to corresponding features in the target domain even when the global pose is not correct.

Pose Estimation Unsupervised Domain Adaptation

Do pretrained Transformers Learn In-Context by Gradient Descent?

no code implementations12 Oct 2023 Lingfeng Shen, Aayush Mishra, Daniel Khashabi

Furthermore, the theoretical hand-constructed weights used in these studies have properties that don't match those of real LLMs.

In-Context Learning

Stress Testing Chain-of-Thought Prompting for Large Language Models

no code implementations28 Sep 2023 Aayush Mishra, Karan Thakkar

This report examines the effectiveness of Chain-of-Thought (CoT) prompting in improving the multi-step reasoning abilities of large language models (LLMs).

DECODE: Data-driven Energy Consumption Prediction leveraging Historical Data and Environmental Factors in Buildings

no code implementations6 Sep 2023 Aditya Mishra, Haroon R. Lone, Aayush Mishra

In summary, our research contributes to energy prediction by offering a robust LSTM model that outperforms alternative methods and operates with remarkable efficiency, generalizability, and reliability.

energy management Management +1

Repeated Environment Inference for Invariant Learning

1 code implementation26 Jul 2022 Aayush Mishra, Anqi Liu

The EI step uses a reference model which focuses on spurious correlations to efficiently reach a good environment partition.

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