Name: Kalpesh Krishna
Type: User
Company: Research Scientist, Google
Bio: Research Scientist at Google Gemini/Bard, PhD graduate from UMass. Formerly undergrad at IIT Bombay (@wncc), and intern @google, @allenai, @mozilla, TTIC
Location: New York, NY
Blog: martiansideofthemoon.github.io
Kalpesh Krishna's Projects
A GNURadio implementation of an 8 PSK Costas Loop.
Official repository for our NeurIPS 2023 paper "Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense" (https://arxiv.org/abs/2303.13408).
A homework assignment on probe tasks designed in AllenNLP for UMass Amherst's graduate NLP course (690D).
A VHDL implementation of an interfacing with an ADC which stores data in a hitachi SRAM. This data can be retrieved later on at a rate of one sample per millisecond. Designed to store upto 8 seconds of data.
An augmented reality robotic arm built using an IK chain.
Code.Fun.Do
An organized list of papers and resources used by me in ASR and Language Modelling.
An implementation of the ICCP '16 paper "Blind Dehazing Using Internal Patch Recurrence".
The jekyll website for WnCC Blogs.
bugzilla.mozilla.org source
An implementation of the paper http://graphics.berkeley.edu/papers/Obrien-GMA-1999-08/
Python scripts to download course videos off CDEEP
Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow
A set of assignments for the CS475m course in IIT Bombay.
Statistics of acceptance rate for the main AI conference
contrastive decoding
Repository to store CS213 Assignments
A Pyraminx utility kit, consisting of an android app, basic Java server and Allegro based utilities to help speed cubers. It makes use of BFS to compute shortest solutions to the Pyraminx
Deep Averaging Networks
An implementation of M-best diversity sampling for Interactive Segmentation and Language Generation using Neural Language Models..
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
A simple Django based server to find your Department rank or your institute rank.
ECG analysis to classify anterior myocardial infarction cases.