Deep learning has made advances in various fields, and it has made its way into material sciences as well. From tasks like predicting material properties to optimizing compositions, deep learning has accelerated material design and facilitated exploration in expansive materials spaces. However, explainability is an issue as they are ‘black boxes,’ so to say, hiding… →

Artificial Intelligence (AI) has revolutionized numerous industries, from healthcare to finance. It empowers machines to learn from data, make intelligent decisions, and solve complex problems. Let’s understand a fundamental technique in AI, Artificial Intelligence (AI) clustering. As the term “clustering” suggests, it involves grouping similar data points. AI clustering is discovering underlying patterns and structures… →

As the world is evolving towards a personal digital experience, recommendation systems, while being a must, from e-commerce to media streaming, fail to simulate users’ preferences to make better recommendations. Conventional models do not capture the subtlety of reasons behind user-item interactions thus generalized recommendations are presented. With such restrictions on the limited rationale, large… →

The rise of large language models has been accompanied by significant challenges, particularly around ensuring the factuality of generated responses. One persistent issue is that these models can produce outputs that are factually incorrect or even misleading, a phenomenon often called “hallucination.” These hallucinations occur when models generate confident-sounding but incorrect or unverifiable information. Given… →

Transformer-based architectures have revolutionized natural language processing, delivering exceptional performance across diverse language modeling tasks. However, they still face major challenges when handling long-context sequences. The self-attention mechanism in Transformers suffers from quadratic computational complexity, and their memory requirement grows linearly with context length during inference. These factors impose practical constraints on sequence length due… →

Understanding and analyzing long videos has been a significant challenge in AI, primarily due to the vast amount of data and computational resources required. Traditional Multimodal Large Language Models (MLLMs) struggle to process extensive video content because of limited context length. This challenge is especially evident with hour-long videos, which need hundreds of thousands of… →