{"componentChunkName":"component---src-pages-repositories-js","path":"/repositories/","result":{"data":{"githubData":{"data":{"viewer":{"name":"Kunjal Panchal","avatarUrl":"https://avatars.githubusercontent.com/u/32832266?u=edacdeefbe47b1815085878d3197e0b7bb7be384&v=4","repositories":{"nodes":[{"name":"ChemistryCanvas","description":null,"homepageUrl":null,"resourcePath":"/Astuary/ChemistryCanvas","forkCount":0,"createdAt":"2022-02-05T23:05:59Z","updatedAt":"2022-02-05T23:41:42Z","languages":{"edges":[{"node":{"name":"ShaderLab","color":"#222c37"}}]},"licenseInfo":null,"stargazers":{"totalCount":0}},{"name":"Surestart_Spring_2023_VAIL","description":null,"homepageUrl":null,"resourcePath":"/Astuary/Surestart_Spring_2023_VAIL","forkCount":3,"createdAt":"2022-12-29T22:05:14Z","updatedAt":"2022-12-29T16:42:21Z","languages":{"edges":[{"node":{"name":"Jupyter Notebook","color":"#DA5B0B"}}]},"licenseInfo":null,"stargazers":{"totalCount":0}},{"name":"Kunjal","description":"Template for my portfolio website, built using GatsbyJS.","homepageUrl":"https://astuary.github.io/Kunjal/","resourcePath":"/Astuary/Kunjal","forkCount":0,"createdAt":"2023-09-25T01:21:52Z","updatedAt":"2026-04-26T22:25:59Z","languages":{"edges":[{"node":{"name":"JavaScript","color":"#f1e05a"}}]},"licenseInfo":{"name":"Other"},"stargazers":{"totalCount":0}},{"name":"PhotometricStereo","description":"A basic shape-from-shading algorithm as described in Richard Szeliski. This is also described in the “shape from shading” section (Sec 2.2) in Forsyth and Ponce book. The input to the algorithm is a set of photographs taken with known lighting directions and the output of the algorithm is the albedo (paint), normal directions, and the height map. The data/ photometricStereo directory consists of 64 images each of four subjects from the Yale Face database. The light source directions are encoded in the file names.","homepageUrl":null,"resourcePath":"/Astuary/PhotometricStereo","forkCount":1,"createdAt":"2019-11-09T21:25:00Z","updatedAt":"2025-10-15T05:39:16Z","languages":{"edges":[{"node":{"name":"MATLAB","color":"#e16737"}}]},"licenseInfo":null,"stargazers":{"totalCount":1}},{"name":"ModernComputerArchitectureResearchReviews","description":"My reviews of the research published for computer architecture which includes: Methodology, Experience, Wearout, Memory, Cache, Multithreading, Prediction, Pipelining, Instruction-level Parallelism, Branch Prediction, Virtualization, Secondary Storage, Security, Parallelism, Data Parallelism, Data Centers","homepageUrl":null,"resourcePath":"/Astuary/ModernComputerArchitectureResearchReviews","forkCount":0,"createdAt":"2019-11-09T22:33:03Z","updatedAt":"2024-05-09T17:07:29Z","languages":{"edges":[]},"licenseInfo":null,"stargazers":{"totalCount":1}},{"name":"Gradient_Estimation","description":null,"homepageUrl":null,"resourcePath":"/Astuary/Gradient_Estimation","forkCount":0,"createdAt":"2025-04-29T00:09:34Z","updatedAt":"2025-09-24T17:43:40Z","languages":{"edges":[{"node":{"name":"Python","color":"#3572A5"}}]},"licenseInfo":null,"stargazers":{"totalCount":1}},{"name":"ColorImageDemosaicing","description":"In digital cameras the red, blue, and green sensors are interlaced in the Bayer pattern. The missing values are interpolated to obtain a full color image. In this project, I implemented several interpolation algorithms.","homepageUrl":null,"resourcePath":"/Astuary/ColorImageDemosaicing","forkCount":0,"createdAt":"2019-11-09T21:41:02Z","updatedAt":"2024-03-03T19:52:24Z","languages":{"edges":[{"node":{"name":"C++","color":"#f34b7d"}}]},"licenseInfo":null,"stargazers":{"totalCount":2}},{"name":"LSTMVariantsForTimeSeriesForecasting","description":"I have used the ExtraSensory data set. This is a human activity recognition data set containing data from 60 individuals. The task that I will focus on, is probabilistic activity forecasting. Given a sub-dataframe consisting of between one and 30 consecutive observations for a single individual and a timestamp value t, the objective is to predict the (log) probability that each of the five labels (label:LYING_DOWN, label:SITTING, label:FIX_walking, label:TALKING, label:OR_standing) is active (e.g., takes the value 1) at the future specified time, t.","homepageUrl":null,"resourcePath":"/Astuary/LSTMVariantsForTimeSeriesForecasting","forkCount":0,"createdAt":"2019-12-08T11:01:26Z","updatedAt":"2024-09-12T14:17:47Z","languages":{"edges":[{"node":{"name":"Python","color":"#3572A5"}}]},"licenseInfo":null,"stargazers":{"totalCount":2}},{"name":"MultimodalFusion","description":"A novel multimodal fusion model to classify 6 classes of emotions from visual, verbal, and vocal features of a person’s speech in CMU-MOSEI dataset.","homepageUrl":"","resourcePath":"/Astuary/MultimodalFusion","forkCount":0,"createdAt":"2020-09-18T22:13:25Z","updatedAt":"2025-10-13T15:37:13Z","languages":{"edges":[{"node":{"name":"Jupyter Notebook","color":"#DA5B0B"}}]},"licenseInfo":null,"stargazers":{"totalCount":6}},{"name":"SkinCancer","description":"Final Year Project (BEngg at MSU, Vadodara) on Skin Cancer Detection using Matlab Image Processing Toolbox","homepageUrl":"","resourcePath":"/Astuary/SkinCancer","forkCount":6,"createdAt":"2019-05-23T09:17:31Z","updatedAt":"2025-08-23T11:06:37Z","languages":{"edges":[{"node":{"name":"MATLAB","color":"#e16737"}}]},"licenseInfo":null,"stargazers":{"totalCount":7}},{"name":"Flow","description":"Code for \"Flow: Per-Instance Personalized Federated Learning\" (NeurIPS 2023). Flow addresses the challenge of statistical heterogeneity in federated learning through creating a dynamic personalized model for each input instance through a routing mechanism.","homepageUrl":"","resourcePath":"/Astuary/Flow","forkCount":1,"createdAt":"2023-09-25T17:55:37Z","updatedAt":"2024-11-29T13:23:52Z","languages":{"edges":[{"node":{"name":"Python","color":"#3572A5"}}]},"licenseInfo":null,"stargazers":{"totalCount":9}},{"name":"Spry","description":"Code for \"Thinking Forward: Memory-Efficient Federated Finetuning of Language Models\" (NeurIPS 2024).     Spry is a federated learning algorithm that enables finetuning LLMs using Forward-mode Auto Differentiation; to achieve low memory footprint, high accuracy, and fast convergence.","homepageUrl":"","resourcePath":"/Astuary/Spry","forkCount":1,"createdAt":"2024-05-24T13:18:24Z","updatedAt":"2025-10-27T14:21:16Z","languages":{"edges":[{"node":{"name":"Python","color":"#3572A5"}}]},"licenseInfo":null,"stargazers":{"totalCount":12}}]}}}}},"pageContext":{}},"staticQueryHashes":["3649515864","63159454"]}