AI Agents
AI Agent technology and applications
Articles
Building a MiniMax-H3 Multimodal Video and Audio Generation Pipeline with ComfyUI APIsβ9
Learn to build an automated MiniMax-H3 video and audio generation pipeline using ComfyUI APIs, covering setup, graph construction, and multimodal output.
webAI Releases TwIL-LM: 1.7B and 3B Formal-Logic Models for Local Autoformalizationβ7
webAI releases TwIL-LM, compact 1.7B and 3B models for local formal-logic reasoning and autoformalization, outpacing larger systems on benchmarks.
Meta AI Unveils Muse Glimmer: A 30B Open-Weight Agentic Model That Runs on a Single Consumer GPUβ7
Metaβs Muse Glimmer is a 30B open-weight agentic model running on a single consumer GPU via 4-bit compression and speculative decoding.
NVIDIA Releases NemotronLabs VoiceChat 11B: An Open Full-Duplexβ7
NVIDIA releases NemotronLabs VoiceChat 11B, an open full-duplex speech model with 448ms turn-taking, live tool calling, and barge-inβideal for research pilots.
ByteDance Seed Unveils SeedRealtime: A Unified Audio-Visualβ8
ByteDance Seed unveils SeedRealtime, a unified audio-visual full-duplex LLM enabling real-time, proactive multimodal interaction for next-gen AI assistants.
Top LLM Observability and Evaluation Platforms in 2026:β9
Compare 2026's top LLM observability platformsβLangfuse, LangSmith, Braintrust, Arizeβfor tracing, evaluation, and production AI monitoring.
IMDb Sentiment Analysis with DistilBERT LoRA, TF-IDF Baselines,β9
Explore IMDb sentiment analysis with DistilBERT LoRA, TF-IDF baselines, calibration, robustness tests, and semi-supervised learning.
Pokee AI Releases Pokee-Isaac 28B: A 10M-Token Context Agenticβ7
Pokee AI's Pokee-Isaac 28B offers a 10M-token context, on-premise deployment, and 93.3% RULER score for regulated industries.
Mistral AI Releases Shieldstral 1.0 3B: An Open-Weightsβ7
Shieldstral 1.0 3B is an open-weights multimodal safety classifier with adaptive policies, matching models 7x its size for efficient content moderation.
Building a Multimodal RAG Pipeline with NVIDIA NeMo Retriever,β8
Build a multimodal RAG pipeline using NVIDIA NeMo Retriever, hosted NIMs, LanceDB, reranking, and grounded generation. Step-by-step tutorial included.