Building massive neural network models that replicate the activity of the brain has long been a cornerstone of computational neuroscience’s efforts to understand the complexities of brain function. These models, which are frequently intricate, are essential for comprehending how neural networks give rise to cognitive functions.  However, optimizing these models’ parameters to precisely mimic observed… →

Large language models (LLMs) have become a pivotal part of artificial intelligence, enabling systems to understand, generate, and respond to human language. These models are used across various domains, including natural language reasoning, code generation, and problem-solving. LLMs are usually trained on vast amounts of unstructured data from the internet, allowing them to develop broad… →

Using advanced artificial intelligence models, video generation involves creating moving images from textual descriptions or static images. This area of research seeks to produce high-quality, realistic videos while overcoming significant computational challenges. AI-generated videos find applications in diverse fields like filmmaking, education, and video simulations, offering an efficient way to automate video production. However, the… →

Previous 3D model generation from single images faced challenges. Feed-forward architectures produced simplistic objects due to limited 3D data. Gaussian splatting provided rapid coarse geometry but lacked fine details and view consistency. Naive gradient thresholding caused excessive densification and swollen geometries. Regularisation methods improved accuracy, but removal led to structural issues. User studies revealed view… →

Test-time aggregation strategies, such as generating and combining multiple answers, can enhance LLM performance but eventually hit diminishing returns. Refinement, where model feedback is used to improve answers iteratively, presents an alternative. However, it faces three challenges: (1) excessive refinement, which can lead to over-correction and reduced accuracy; (2) difficulty in identifying and addressing specific… →

Collaborative Multi-Agent Reinforcement Learning (MARL) has emerged as a powerful approach in various domains, including traffic signal control, swarm robotics, and sensor networks. However, MARL faces significant challenges due to the complex interactions between agents, which introduce non-stationarity in the environment. This non-stationarity complicates the learning process and makes it difficult for agents to adapt… →

One of the main challenges in cellular automata (CA) systems, particularly in Conway’s Game of Life (Life), lies in predicting their emergent behavior without explicitly knowing the underlying grid topology. Life and other CA algorithms are computationally simple, yet they generate complex and unpredictable dynamics highly sensitive to initial conditions. This unpredictability complicates the development… →

Federated learning (FL) is a powerful ML paradigm that enables multiple data owners to train models without centralizing their data collaboratively. This approach is particularly valuable in domains where data privacy is critical, such as healthcare, finance, and the energy sector. The core of federated learning lies in training models on decentralized data stored on… →

Governments and humanitarian organizations need reliable data on building and infrastructure changes over time to manage urbanization, allocate resources, and respond to crises. However, many regions across the Global South need more access to timely and accurate data on buildings, making it difficult to track urban growth and infrastructure development. The absence of this data… →