Asif Razzaq    How do you build one open model that can reliably understand text, images, audio and video while still running efficiently? A team of researchers from Harbin Institute of Technology, Shenzhen introduced Uni-MoE-2.0-Omni, a fully open omnimodal large model that pushes Lychee’s Uni-MoE line toward...

Arham Islam    Binary cross-entropy (BCE) is the default loss function for binary classification but it breaks down badly on imbalanced datasets. The reason is subtle but important: BCE weighs mistakes from both classes equally, even when one class is extremely rare. Imagine two predictions: a minority-class...

Michal Sutter    Google DeepMind Research have introduced WeatherNext 2, an AI based medium range global weather forecasting system that now powers upgraded forecasts in Google Search, Gemini, Pixel Weather and Google Maps Platform’s Weather API, with Google Maps integration coming next. It combines a new...

Asif Razzaq    Reinforcement learning RL for large language model LLM agents looks attractive on paper, but in practice it breaks on cost, infrastructure and reward noise. Training an agent that clicks through web pages or completes multi step tool use can easily need tens of thousands of real interactions, each...

Asif Razzaq    In this tutorial, we implement an advanced Optuna workflow that systematically explores pruning, multi-objective optimization, custom callbacks, and rich visualization. Through each snippet, we see how Optuna helps us shape smarter search spaces, speed up experiments, and extract insights that...

Asif Razzaq    Google DeepMind has released SIMA 2 to test how far generalist embodied agents can go inside complex 3D game worlds. SIMA’s (Scalable Instructable Multiworld Agent) new version upgrades the original instruction follower into a Gemini driven system that reasons about goals, explains its plans, and...

Arham Islam    In this part of the Interview Series, we’ll look at some of the common security vulnerabilities in the Model Context Protocol (MCP) a framework designed to let LLMs safely interact with external tools and data sources. While MCP brings structure and transparency to how models access context, it...

Michal Sutter    Agentic AI browsers are moving the model from answering about the web’ to operating on the web. In 2025, four AI browsers define this space: OpenAI’s ChatGPT Atlas, Microsoft Edge with Copilot Mode, The Browser Company’s Dia, and Perplexity’s Comet. Each makes different design choices around...

Asif Razzaq    In this tutorial, we explore how to build agentic systems that think beyond a single interaction by utilizing memory as a core capability. We walk through how we design episodic memory to store experiences and semantic memory to capture long-term patterns, allowing the agent to evolve its behaviour...

Asif Razzaq    Cerebras has released MiniMax-M2-REAP-162B-A10B, a compressed Sparse Mixture-of-Experts (SMoE) Causal Language Model derived from MiniMax-M2, using the new Router weighted Expert Activation Pruning (REAP) method. The model keeps the behavior of the original 230B total, 10B active MiniMax M2, while...