LLMRouter is an open source routing library from the U Lab at the University of Illinois Urbana Champaign that treats model selection as a first class system problem. It sits between applications and ...

SAM Audio uses separate encoders for each conditioning signal, an audio encoder for the mixture, a text encoder for the natural language description, a span encoder for time anchors, and a visual ...

What is a weight sparse transformer? The models are GPT-2 style decoder only transformers trained on Python code. Sparsity is not added after training, it is enforced during optimization. After each ...

Can a 3B model deliver 30B class reasoning by fixing the training recipe instead of scaling parameters? Nanbeige LLM Lab at Boss Zhipin has released Nanbeige4-3B, a 3B parameter small language model ...

Everyone talks about LLMs—but today’s AI ecosystem is far bigger than just language models. Behind the scenes, a whole family of specialized architectures is quietly transforming how machines see, ...

In this tutorial, we build a fully local, API-free agentic storytelling system using Griptape and a lightweight Hugging Face model. We walk through creating an agent with tool-use abilities, ...

How do you keep RAG systems accurate and efficient when every query tries to stuff thousands of tokens into the context window and the retriever and generator are still optimized as 2 separate, ...

How can a small model learn to solve tasks it currently fails at, without rote imitation or relying on a correct rollout? A team of researchers from Google Cloud AI Research and UCLA have released a ...

DeepSeek-AI released 3B DeepSeek-OCR, an end to end OCR and document parsing Vision-Language Model (VLM) system that compresses long text into a small set of vision tokens, then decodes those tokens ...

Do you actually need a giant VLM when dense Qwen3-VL 4B/8B (Instruct/Thinking) with FP8 runs in low VRAM yet retains 256K→1M context and the full capability surface? Alibaba’s Qwen team has expanded ...