Author: Khushboo Gupta

Khushboo Gupta
202 POSTS0 COMMENTS
Khushboo Gupta is a consulting intern at MarktechPost. She is currently pursuing her B.Tech from the Indian Institute of Technology(IIT), Goa. She is passionate about the fields of Machine Learning, Natural Language Processing and Web Development. She enjoys learning more about the technical field by participating in several challenges.

Researchers From Cambridge And Amazon Propose ‘TRANS-ENCODER’: An Unsupervised Approach of Training Bi- And Cross-Encoders For Sentence-Pair Tasks

This Article Is Based On The Research Article 'TRANS-ENCODER: UNSUPERVISED SENTENCE-PAIR MODELLING THROUGH SELF- AND MUTUAL-DISTILLATIONS'. All Credit For This Research Goes To The...

Deepmind Introduces Flamingo: An Open-Ended Single Visual Language Model (VLM) For Multimodal Machine Learning Research

This Article Is Based On The Research Paper 'Flamingo: a Visual Language Model for Few-Shot Learning'. All Credit For This Research Goes To The...

Zama Open-Sources Concrete ML v0.2 To Support Data Scientists Without Any Prior Cryptography Knowledge To Automatically Turn Classical Machine Learning (ML) Models Into Their...

This Article Is Based On The Zama Research Article 'Announcing Concrete ML v0.2'. All Credit For This Research Goes To The Researchers Of This...

Researchers From MIT and Cornell Develop STEGO (Self-Supervised Transformer With Energy-Based Graph Optimization): A Novel AI Framework That Distills Unsupervised Features Into High-Quality Discrete...

This Article Is Based On The Research Paper 'UNSUPERVISED SEMANTIC SEGMENTATION BY DISTILLING FEATURE CORRESPONDENCES'. All Credit For This Research Goes To The Researchers...

Microsoft AI Researchers Introduce PPE: A Mathematically Guaranteed Reinforcement learning (RL) Algorithm For Exogenous Noise

This Article Is Based On The Research Paper 'Provable RL with Exogenous Distractors via Multistep Inverse Dynamics' and Microsoft article. All Credit For This...

Google AI Researchers Propose A Structure-Aware Sequence Model, Called FormNet, To Mitigate The Sub-Optimal Serialization Of Forms For Document Information Extraction

This Article Is Based On The Research Paper 'FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction' and Google article. All Credit For...

Amazon Kickstarts Natural Language Understanding By Open-Sourcing ‘MASSIVE’ Speech Dataset

This Article Is Based On The Amazon article 'Amazon releases 51-language dataset for language understanding'. All Credit For This Research Goes To The Amazon...

Researchers Develop New Methods And Models Using Machine Learning (ML) To Reduce Noise in X-ray Data

This article is based on the research paper 'Noise reduction in X‑ray photon correlation spectroscopy with convolutional neural networks encoder–decoder models'. All credit...