Artificial intelligence (AI) has advanced rapidly, especially in multi-modal large language models (MLLMs), which integrate visual and textual data for diverse applications. These models are increasingly applied in video analysis, high-resolution image processing, and multi-modal agents. Their capacity to process and understand vast amounts of information from different sources is essential for applications in healthcare,… →
Supervised learning in medical image classification faces challenges due to the scarcity of labeled data, as expert annotations are difficult to obtain. Vision-Language Models (VLMs) address this issue by leveraging visual-text alignment, allowing unsupervised learning, and reducing reliance on labeled data. Pre-training on large medical image-text datasets enables VLMs to generate accurate labels and captions,… →
Graph-based methods have become increasingly important in data retrieval and machine learning, particularly in nearest neighbor (NN) search. NN search helps identify data points closest to a given query, which becomes critical with high-dimensional data such as text, images, or audio. Approximate nearest neighbor (ANN) methods emerged due to the inefficiency of exact searches in… →
The release of Reader-LM-0.5B and Reader-LM-1.5B by Jina AI marks a significant milestone in small language model (SLM) technology. These models are designed to solve a unique and specific challenge: converting raw, noisy HTML from the open web into clean markdown format. While seemingly straightforward, this task poses complex challenges, particularly in handling the vast… →
OpenBMB recently released the MiniCPM3-4B, the third-generation model in the MiniCPM series. This model marks a great step forward in the capabilities of smaller-scale language models. Designed to deliver powerful performance with relatively modest resources, the MiniCPM3-4B model demonstrates a range of enhancements over its predecessors, particularly in functionality and versatility. Model Overview The MiniCPM3-4B… →
One important tactic for improving large language models’ (LLMs’) capacity for reasoning is the Chain-of-Thought (CoT) paradigm. By encouraging models to divide tasks into intermediate steps, much like humans methodically approach complex problems, CoT improves the problem-solving process. This method has proven to be extremely effective in a number of applications, earning it a key… →
Generative modeling, particularly diffusion models (DMs), has significantly advanced in recent years, playing a crucial role in generating high-quality images, videos, and audio. Diffusion models operate by introducing noise into the data and then gradually reversing this process to generate data from noise. They have demonstrated significant potential in various applications, from creating visual artwork… →
Hebrew University Researchers addressed the challenge of understanding how information flows through different layers of decoder-based large language models (LLMs). Specifically, it investigates whether the hidden states of previous tokens in higher layers are as crucial as believed. Current LLMs, such as transformer-based models, use the attention mechanism to process tokens by attending to all previous… →
Multi-agent pathfinding (MAPF), within computer science and robotics, deals with the problem of routing multiple agents, such as robots, to their individual goals within a shared environment. These agents must find collision-free paths while maintaining a high level of efficiency. MAPF is crucial for applications such as automated warehouses, traffic management, and drone fleets. The… →