Auto Added by WPeMatico
The ChatGPT moment in 2022 taught AI to talk to people. One of its builders now bets the next moment is AI that talks to software, not people. TypeSafe AI released Jev. Jev is transformer-based, but it is not a large language model. It does not generate text. You send a state and typed questions. […]
Linkup research team releases SPARSEUP, an open-source learned sparse embedding model. The model runs on a 149M-parameter ModernBERT backbone and ships under Apache 2.0. Linkup team reports 56.4 average nDCG@10 on BEIR-13. It calls this the strongest public vocabulary-based sparse encoder it knows of under 150M parameters. Is it deployable? Yes. The weights are on
Linkup Research Releases SPARSEUP: A 149M-Parameter Open-Source Sparse Embedding Model Read More »
First, separate 2 ideas: containers vs. quantization methods Most confusion comes from mixing 2 layers. A container defines how tensors are stored on disk. A quantization method defines how weights are squeezed into fewer bits. Containers: safetensors, GGUF, PyTorch pickle (.bin / .pt). Methods: GPTQ, AWQ, bitsandbytes NF4, llama.cpp K-quants and I-quants. Both at once:
GGUF vs GPTQ vs AWQ vs EXL2: LLM Model Formats Explained (2026) Read More »
SpaceXAI has released Grok Voice Transcribe 2.0, its newest speech-to-text (STT) model. The development team claims it to be twice as accurate as Grok Voice Transcribe 1.0 at the same price. The model targets hard audio: noisy phone lines, competing voices, local accents, and spoken credentials. It runs in batch and real-time streaming modes through
PrismML has released Ternary Bonsai 2 27B, a ternary-weight version of Qwen3.8 27B. The language model occupies 5.93 GB, against 53.80 GB in FP16. PrismML reports that it keeps 98.2% of the parent model’s average across 20 benchmarks. The model accepts text and images and supports a 262K-token context. PrismML demos it driving Cline coding
Alibaba’s Qwen team has released Qwen3.8-Omni-Flash. They called it its first omni-modal model built around agentic capabilities. It accepts text, images, audio, and video, and it returns text. Audio-video understanding, reasoning, and tool use sit inside one model. The stated workflow is simple: understand the content, plan the task, execute with tools, deliver the result.
Nunchux AI has released VC-Attention, a training-free low-bit attention kernel built for video Diffusion Transformers (DiTs). It targets 2 problems at once: value quantization error and a slow softmax stage. Why Attention is the Video Bottleneck Video DiTs flatten a clip into 1 sequence of spatiotemporal tokens and run full self-attention at every layer. A
Computational papers ship code that readers must clone, install, configure and debug. That cost keeps useful methods locked inside PDFs. A Stanford team led by Jiacheng Miao and James Zou proposes a fix. Paper2Agent was published in Nature on 16 September 2026. It converts a paper and its codebase into a Model Context Protocol (MCP)
Google has introduced Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking, its most advanced live dialogue models to date. Both are native speech to speech models built for real time voice agents. They extend the Gemini Audio family that Google expanded last month with Gemini 3.5 Transcribe. The release targets a specific gap: voice
In most decoder-only LLMs, nothing computed at the last layer of token t feeds the first layer of token t+1; positions communicate only through attention over cached keys and values. A Princeton researcher’s (Yifan Zhang) technical report, Recurrent Looped Transformer (RLT), proposes closing that loop. The decoder’s final hidden state and its layerwise sliding-window attention
