Generative AI
Meet LLMRouter: An Intelligent Routing System Designed to Improve LLM Inference by Dynamically Selecting the Best Fit Model for Each Question.
December 30, 2025
Meet LLMRouter: An Intelligent Routing System Designed to Improve LLM Inference by Dynamically Selecting the Best Fit Model for Each Question.
LLMRouter is an open source routing library from the U Lab at the University of Illinois Urbana Champaign that treats…
How to Build a Powerful Multi-Agent Pipeline Using CAMEL for Scheduling, Web-Enhanced Thinking, Decoding, and Persistent Memory
December 30, 2025
How to Build a Powerful Multi-Agent Pipeline Using CAMEL for Scheduling, Web-Enhanced Thinking, Decoding, and Persistent Memory
In this tutorial, we build a workflow for advanced multi-agent research using CAMEL frame. We are building an integrated community…
How to Build Contract-First Decision Systems with PydanticAI's Risk-Aware, Policy-Compliant Business AI
December 29, 2025
How to Build Contract-First Decision Systems with PydanticAI's Risk-Aware, Policy-Compliant Business AI
In this tutorial, we show how to design an agent-first decision system using PydanticAIit treats structured schemas as negotiable governance…
NVIDIA AI Researchers Release NitroGen: An Open Concept Base Model for Generalist Gaming Agents
December 28, 2025
NVIDIA AI Researchers Release NitroGen: An Open Concept Base Model for Generalist Gaming Agents
The NVIDIA AI research team released NitroGen, an open concept base model for casual game agents that learn to play…
Liquid AI's LFM2-2.6B-Exp Uses RL for Pure Reinforcement Learning and Dynamic Hybrid Reasoning to Reinforce the Behavior of a Small Model
December 28, 2025
Liquid AI's LFM2-2.6B-Exp Uses RL for Pure Reinforcement Learning and Dynamic Hybrid Reasoning to Reinforce the Behavior of a Small Model
Liquid AI has launched LFM2-2.6B-Exp, an experimental testbed for its LFM2-2.6B language model trained by pure reinforcement learning on top…
How to Build Production-Grade Workflows with GraphBit Using Deterministic Tools, Validated Workflow Graphs, and Optional LLM Orchestration
December 27, 2025
How to Build Production-Grade Workflows with GraphBit Using Deterministic Tools, Validated Workflow Graphs, and Optional LLM Orchestration
In this tutorial, we create an end-to-end workflow, using a production style GraphBit which shows how graphical execution, tool calling,…
From Gemma 3 270M to FunctionGemma, How Google AI Is Building a Collaborative Task Calling Expert for Edge Workloads
December 26, 2025
From Gemma 3 270M to FunctionGemma, How Google AI Is Building a Collaborative Task Calling Expert for Edge Workloads
Google has released FunctionGemma, a special version of the Gemma 3 270M model that is specially trained for calling and…
Training a Model on Multiple GPUs with Data Parallelism
December 26, 2025
Training a Model on Multiple GPUs with Data Parallelism
import dataclasses import os import datasets import tqdm import tokenizers import torch import torch.distributed as dist import torch.nn as…
Code Implementation for Self-Organizing Zettelkasten Information Graphs and Sleep Integration Methods
December 26, 2025
Code Implementation for Self-Organizing Zettelkasten Information Graphs and Sleep Integration Methods
In this tutorial, we dive into the edge of Agentic AI by building a “Zettelkasten” memory system, a “living” architecture…
MiniMax Releases M2.1: An Enhanced Version of M2 with Features Like Multi-Coding Language Support, API Integration, and Improved Structured Coding Tools
December 25, 2025
MiniMax Releases M2.1: An Enhanced Version of M2 with Features Like Multi-Coding Language Support, API Integration, and Improved Structured Coding Tools
A few months after releasing the M2—a fast, low-cost model designed for agents and code—MiniMax has introduced an improved version:…