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.
Prompting Large Language Models (LLMs) has emerged as a standard practice in Natural Language Processing (NLP) following the introduction of GPT-3. The scaling of...
Current challenges faced by large vision-language models (VLMs) include limitations in the capabilities of individual visual components and issues arising from excessively long visual...
In recent years, researchers in the field of robotic reinforcement learning (RL) have achieved significant progress, developing methods capable of handling complex image observations,...
In the enchanting world of language models and attention mechanisms, picture a daring quest to accelerate decoder inference and enhance the prowess of large...
Recent advances in language models showcase impressive zero-shot voice conversion (VC) capabilities. Nevertheless, prevailing VC models rooted in language models usually utilize offline conversion...
Mathematical reasoning, part of our advanced thinking, reveals the complexities of human intelligence. It involves logical thinking and specialized knowledge, not just in words...
You may have missed a big development in the ML weather forecasting revolution over the holidays: GenCast: Google DeepMind’s new generative model! The importance...
There has been a significant surge in the integration of language models (LMs) into mainstream applications within the fields of software engineering and programming....
Reconstructing 3D geometry from a single image represents a foundational undertaking within the domains of computer graphics and 3D computer vision, as evident in...
Artificial intelligence (AI), particularly deep learning (DL), has found growing applications in the field of medical imaging and healthcare. A substantial portion of the...
Language models trained on diverse mixtures of text display remarkably general language understanding and generation capabilities, serving as base models that are adapted to...
