How do you build a language model that grows in capacity but keeps the computation for each token almost unchanged? The Inclusion AI team from the Ant Group is pushing sparse large models in a methodical way by releasing Ling 2.0. Ling 2.0 is a reasoning based language model family built on the idea that each…
In this tutorial, we explore how we can build an autonomous agent that aligns its actions with ethical and organizational values. We use open-source Hugging Face models running locally in Colab to simulate a decision-making process that balances goal achievement with moral reasoning. Through this implementation, we demonstrate how we can integrate a “policy” model…
Small models are often blocked by poor instruction tuning, weak tool use formats, and missing governance. IBM AI team released Granite 4.0 Nano, a small model family that targets local and edge inference with enterprise controls and open licensing. The family includes 8 models in two sizes, 350M and about 1B, with both hybrid SSM…
How do you convert real agent traces into reinforcement learning RL transitions to improve policy LLMs without changing your existing agent stack? Microsoft AI team releases Agent Lightning to help optimize multi-agent systems. Agent Lightning is a open-sourced framework that makes reinforcement learning work for any AI agent without rewrites. It separates training from execution,…
Can a compact late interaction retriever index once and deliver accurate cross lingual search with fast inference? Liquid AI released LFM2-ColBERT-350M, a compact late interaction retriever for multilingual and cross-lingual search. Documents can be indexed in one language, queries can be written in many languages, and the system retrieves with high accuracy. The Liquid AI…
In this tutorial, we explore how exploration strategies shape intelligent decision-making through agent-based problem solving. We build and train three agents, Q-Learning with epsilon-greedy exploration, Upper Confidence Bound (UCB), and Monte Carlo Tree Search (MCTS), to navigate a grid world and reach a goal efficiently while avoiding obstacles. Also, we experiment with different ways of…
Can an open source MoE truly power agentic coding workflows at a fraction of flagship model costs while sustaining long-horizon tool use across MCP, shell, browser, retrieval, and code? MiniMax team has just released MiniMax-M2, a mixture of experts MoE model optimized for coding and agent workflows. The weights are published on Hugging Face under…
Can we render long texts as images and use a VLM to achieve 3–4× token compression, preserving accuracy while scaling a 128K context toward 1M-token workloads? A team of researchers from Zhipu AI release Glyph, an AI framework for scaling the context length through visual-text compression. It renders long textual sequences into images and processes…
Pyversity is a fast, lightweight Python library designed to improve the diversity of results from retrieval systems. Retrieval often returns items that are very similar, leading to redundancy. Pyversity efficiently re-ranks these results to surface relevant but less redundant items. It offers a clear, unified API for several popular diversification strategies, including Maximal Marginal Relevance…
In this tutorial, we create a fully interactive, visually compelling data visualization dashboard using Bokeh. We start by turning raw data into insightful plots, then enhance them with features such as linked brushing, color gradients, and real-time filters powered by dropdowns and sliders. As we progress, we bring our dashboard to life with Custom JavaScript…
