Author: Tanya Malhotra

205 POSTS0 COMMENTS
Tanya Malhotra is a final year undergrad from the University of Petroleum & Energy Studies, Dehradun, pursuing BTech in Computer Science Engineering with a specialization in Artificial Intelligence and Machine Learning. She is a Data Science enthusiast with good analytical and critical thinking, along with an ardent interest in acquiring new skills, leading groups, and managing work in an organized manner.

Researchers from UCI and Zhejiang University Introduce Lossless Large Language Model Acceleration via Self-Speculative Decoding Using Drafting And Verifying Stages

Large Language Models (LLMs) based on transformers, such as GPT, PaLM, and LLaMA, have become widely used in a variety of real-world applications. These...

Meet AudioSR: A Plug & Play and One-for-All AI Solution for Upsampling Audio to Incredible 48kHz Quality

A key challenge in the field of digital audio processing is audio super-resolution. It aims to enhance the quality of audio signals by anticipating...

Researchers from the University of Pennsylvania Introduce Kani: A Lightweight, Flexible, and Model-Agnostic Open-Source AI Framework for Building Language Model Applications

Large Language model applications have witnessed a surge in popularity. With their amazing capabilities, they are becoming increasingly sophisticated. By incorporating features like tool...

Can Large Language Models Self-Evaluate for Safety? Meet RAIN: A Novel Inference Method Transforming AI Alignment and Defense Without Finetuning

Pre-trained Large Language Models (LLMs), like GPT-3, have proven to have extraordinary aptitudes for comprehending and replying to questions from humans, helping with coding...

Meet DiffBIR: An AI Approach That Addresses The Blind Image Restoration Problem Using Pretrained Text-To-Image Diffusion Models

With the significant advancement in the field of Artificial Intelligence, the sub-fields of AI, including Natural Language Processing, Natural Language Understanding, Computer Vision, etc.,...

Google DeepMind Research Explores the Puzzling Phenomenon of Grokking in Neural Networks: Unveiling the Interplay Between Memorization and Generalization

The traditional theory of how neural networks learn and generalize is put to the test by the occurrence of grokking in neural networks. When...

Enhancing GPT-4 Summarization Through Chain of Density Prompts

Large Language Models have gained a lot of attention in recent times due to their excellent capabilities. LLMs are capable of everything from question...

Google DeepMind Researchers Propose Optimization by PROmpting (OPRO): Large Language Models as Optimizers

With the constant advancements in the field of Artificial Intelligence, its subfields, including Natural Language Processing, Natural Language Generation, Natural Language Understanding, and Computer...

Researchers from Sony Propose BigVSAN: Revolutionizing Audio Quality with Slicing Adversarial Networks in GAN-Based Vocoders

The development of neural networks and their constantly increasing popularity have led to substantial improvements in speech synthesis technologies. The majority of speech synthesis...

A New AI Research from Apple and Equall AI Uncovers Redundancies in Transformer Architecture: How Streamlining the Feed Forward Network Boosts Efficiency and Accuracy

Transformer design that has recently become popular has taken over as the standard method for Natural Language Processing (NLP) activities, particularly Machine Translation (MT)....

Bridging the Gap Between Clinicians and Language Models in Healthcare: Meet MedAlign, a Clinician-Generated Dataset for Instruction Following Electronic Medical Records

Large Language Models (LLMs) have utilized the capabilities of Natural Language Processing in a great way. From language production and reasoning to reading comprehension,...

Meet CityDreamer: A Compositional Generative Model for Unbounded 3D Cities

The creation of 3D natural settings has been the subject of a lot of research in recent years. Significant advancements have been made in...