Generative AI
Liquid AI Releases LFM2.5-350M: A Compact 350M Parametric Model Trained on 28T Tokens with Trimmed Reinforcement Learning
April 1, 2026
Liquid AI Releases LFM2.5-350M: A Compact 350M Parametric Model Trained on 28T Tokens with Trimmed Reinforcement Learning
In the current state of productive AI, 'scaling laws' have generally dictated that more parameters equal more intelligence. However, Liquid…
How to Build and Evolve a Custom OpenAI Agent with A-Evolve Using Benchmarks, Skills, Memory, and Workspace Transformations
March 31, 2026
How to Build and Evolve a Custom OpenAI Agent with A-Evolve Using Benchmarks, Skills, Memory, and Workspace Transformations
In this lesson, we work directly with Evolve framework at Colab and build a complete agent pipeline for evolution from…
Alibaba Qwen Team Releases Qwen3.5 Omni: A Native Multimodal Model for Text, Audio, Video, and Real-Time Interaction
March 31, 2026
Alibaba Qwen Team Releases Qwen3.5 Omni: A Native Multimodal Model for Text, Audio, Video, and Real-Time Interaction
The landscape of large multimodal linguistic models (MLLMs) has shifted from experimental 'wrappers'—where separate visual or audio encoders are sewn…
Microsoft AI Releases Harrier-OSS-v1: A New Family of Multilingual Embedding Models Beats SOTA in Multilingual MTEB v2
March 30, 2026
Microsoft AI Releases Harrier-OSS-v1: A New Family of Multilingual Embedding Models Beats SOTA in Multilingual MTEB v2
Microsoft announced the release of the Harrier-OSS-v1a family of three multilingual text embedding models designed to provide high-quality semantic representations…
Salesforce AI Research Releases VoiceAgentRAG: A Dual-Agent Memory Router That Cuts Voice RAG Retrieval Latency by 316x
March 30, 2026
Salesforce AI Research Releases VoiceAgentRAG: A Dual-Agent Memory Router That Cuts Voice RAG Retrieval Latency by 316x
In the world of voice AI, the difference between a helpful assistant and a negative interaction is measured in milliseconds.…
Agent-Infra Releases AIO Toolbox: All-in-One Runtime for AI Agents with Browser, Shell, Shared Filesystem, and MCP
March 30, 2026
Agent-Infra Releases AIO Toolbox: All-in-One Runtime for AI Agents with Browser, Shell, Shared Filesystem, and MCP
In the development of autonomous agents, the technical bottleneck is changing from the model to the implementation area. Although Large-scale…
Meet A-Evolve: PyTorch's Time for Agent AI Systems That Replaces Manual Tuning with Automatic State Evolution and Self-Adaptation
March 29, 2026
Meet A-Evolve: PyTorch's Time for Agent AI Systems That Replaces Manual Tuning with Automatic State Evolution and Self-Adaptation
A research team associated with Amazon has released it Evolvea universal infrastructure designed to automate the development of autonomous AI…
Chroma Releases Context-1: A 20B Agentic Search Model for Multi-Hop Retrieval, Content Management, and Predictive Generation of Tasks
March 29, 2026
Chroma Releases Context-1: A 20B Agentic Search Model for Multi-Hop Retrieval, Content Management, and Predictive Generation of Tasks
In the current state of AI, the 'content window' has become a blunt instrument. We were told that if we…
Google-Agent vs Googlebot: Google Defines the Technological Boundary Between User-Activated AI Access and Search Engine Optimization Today
March 29, 2026
Google-Agent vs Googlebot: Google Defines the Technological Boundary Between User-Activated AI Access and Search Engine Optimization Today
As Google integrates AI capabilities into all of its products, a new tech venture has appeared in the server log:…
Coding Guide to the Complete Nanobot Agent Test Pipeline, from wiring and memory tools to skills, Subagents, and Cron scheduling
March 29, 2026
Coding Guide to the Complete Nanobot Agent Test Pipeline, from wiring and memory tools to skills, Subagents, and Cron scheduling
In this lesson, we go deeper nanobotis a lightweight personal AI agent framework from HKUDS that packs complete agent capabilities…