Modern autonomous agents improve themselves through structured updates to models and their infrastructure, requiring systematic approaches for production deployment.
Soofi S 30B-A3B is an open-source language model trained on German data with a mixture-of-experts architecture that provides throughput advantages for long contexts through selective parameter activation (3B/30B).
WARP reconstructs the training source mixtures of language models from their weights, achieving mean absolute errors of 0.046 for BERT and 0.104 for GPT-2.
The Model Profiler aggregates model metadata from seven data sources into a single web interface with filtering, comparison, and availability maps to accelerate model selection for CTOs.
Orca combines video, speech and visual questions in a unified latent space, demonstrating that this unified world model can outperform specialized models in text, image and action forecasting tasks.
Orca learns a shared world representation from videos and language annotations, enabling text generation, image prediction, and agent control with a frozen backbone and modular decoders.
Qwen-AgentWorld trains language models on over 10 million interaction trajectories as an environment simulator to train AI agents through virtual environments and improve their performance across seven benchmarks.
Qwen-AgentWorld leverages language models as learned environment simulations to efficiently train autonomous agents and improve their reasoning through chain-of-thought prompting.
InternVideo3 enables foundation models to analyze longer video sequences with iterative reasoning and tool use while avoiding efficiency problems in KV cache management.
NVIDIA automates workflows in Physical AI research through new Agent Skills that make scene reconstruction, data generation, and policy training for autonomous vehicles, robotics, and Vision AI scalable.
Small persistent adapters on shared base models can form a practical infrastructure for millions of personalized AI models when scaling, identity management, and serving requirements are systematically addressed.
