Author: Janhavi Lande

39 POSTS0 COMMENTS
Janhavi Lande, is an Engineering Physics graduate from IIT Guwahati, class of 2023. She is an upcoming data scientist and has been working in the world of ml/ai research for the past two years. She is most fascinated by this ever changing world and its constant demand of humans to keep up with it. In her pastime she enjoys traveling, reading and writing poems.

This AI Paper from GSAi China Presents a Comprehensive Study of LLM-based Autonomous Agents

Autonomous agents represent self-operating systems that exhibit varying degrees of independence. Recent research highlights the remarkable capacity of LLMs to imitate human intelligence, a...

Researchers from CMU and Tsinghua University Propose Prompt2Model: A General Purpose Method that Generates Deployable AI Models from Natural Language Instructions

Imagine you wish to build an NLP model to solve a given problem. You need to define the task scope, then find or create...

Researchers at Tencent AI Lab Introduces IP-Adapter: A Text-Compatible Image Prompt Adapter for Text-to-Image Diffusion Models

"Apple," and immediately, the image of an apple popped right into your head. And as fascinating as it is how our brains work, Generative...

This AI Paper from NTU Singapore Introduces MeVIS: A Large-scale Benchmark for Video Segmentation with Motion Expressions

Language-guided video segmentation is a developing domain that focuses on segmenting and tracking specific objects in videos using natural language descriptions. Current datasets for...

Meet EasyEdit: An Easy-to-Use Knowledge Editing AI Framework for LLMs

We constantly need to keep up with this ever-changing world, as do machine learning models, to produce precise output. Large Language Models often suffer...

Unveiling Bayesian Flow Networks: A New Frontier in Generative Modeling

Generative Modeling falls under unsupervised machine learning, where the model learns to discover the patterns in input data. Using this knowledge, the model can...

Unlocking the Power of Context with Google AI: A Showdown Between prefixLM and causalLM in In-Context Learning

The War of Troy is famous, where Achilles etched his name in history forever by defeating Prince Hector once and for all, but today,...

Beyond Photoshop: How Inst-Inpaint is Shaking Up Object Removal with Diffusion Models

Image inpainting is an ancient art. It is the process of removing unwanted objects and filling missing pixels in an image so that the...

Meta AI’s Humpback! Making a Splash with Self-Alignment of LLMs with Instruction Backtranslation

Large Language Models (LLMs) have shown excellent generalization capabilities such as in-context-learning and chain-of-thoughts reasoning. To enable LLMs to follow natural language instructions and...

Master Key to Audio Source Separation: Introducing AudioSep to Separate Anything You Describe

Computational Auditory Scene Analysis (CASA) is a field within audio signal processing that focuses on separating and understanding individual sound sources in complex auditory...

Attention Gaming Industry! No More Weird Mirrors With Mirror-NeRF

NeRFs or Neural Radiance Fields use a combination of RNN and CNN to capture the physical characteristics of an object, such as the shape,...

Breakthrough in the Intersection of Vision-Language: Presenting the All-Seeing Project

Powering the meteoric rise of AI chatbots, LLMs are the talk of the town. They are showing mind-blowing capabilities in user-tailored natural language processing...