2026-11-11 AI 日报

A library of Agent Skills designed to work with the Stitch MCP server. Each skill follows the Agent Skills open standard, for compatibility with coding agents…

Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

GitHub's official MCP Server

Repo for the Complete Agentic AI Engineering Course

A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.

Developer Asset Hub for NVIDIA Nemotron — A one-stop resource for training recipes, usage cookbooks, datasets, and full end-to-end reference examples to build…

GitHub Agentic Workflows

Repo to accompany my mastering LLM engineering course

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and…

Trained action policies write manipulation skill into network weights, tying what is learned to the distribution it is learned from. In-context learning (ICL)…

External memory enables LLM agents to improve from experience by distilling trajectories of past tasks into concise lessons for new tasks. However, memory can…

Weight-space programming, introduced in recent MIT work by Takehi et al., enables a frontier LLM agent to read a network's weights and write a repair. Their…

Discrete autoregressive modeling, notably through next-token prediction, has become a cornerstone of modern language models. Extending this paradigm to vision…

Few-step sampling reduces the cost of streaming video generation. Distribution Matching Distillation (DMD) supervises few-step generators with a separate…

System-1 Decision Models directly make structured probabilistic decisions over query-specified options given a state in a single forward pass, without…

Scaling depth is a key route to stronger large language models, but Pre-LN architectures often suffer from depth-wise information dilution, limiting the…

Dexterous manipulation requires rich spatial foresight over both the surrounding scene and the robot hand. Existing world-action models often acquire such…

This work proposes WaveGen, a fully end-to-end diffusion-based text-to-waveform framework based on Spectral Forcing, which jointly learns an internal spectral…

While modern video generative models achieve remarkable visual fidelity, they remain noticeably brittle when generating physically plausible dynamics and…

I overheard my manager on a call, presumably from HR, that someone in our office was making a lot of requests to Danbooru and might get us in trouble since it…

I've been working on PythonHere, a project that lets me run Python code on Android directly from Jupyter. Recently I added LiteRT-LM support, as I wanted to…

As part of our work on AI security, we've been asking ourselves ever since Jev was introduced, “Just how much can we actually trust decision models?”. Not…

We've got data we can't just put anywhere, and working out which GPU options actually pass a compliance review took way longer than I expected. First thing I…

couldn't find more details unfortunately, but looks like "the releasing begins" https://www.qwencloud.com

Most fallback code I've seen retries on the exception, which handles 429s and 500s fine because those fail before the response starts. The case it misses is a…

Playing with Fable 5.2 since launch, I wanted to see how far it could go on something that's mostly about feel: rain, lightning, clouds, colors, that Matrix…

Today, we’re making Gemini 4 Carbon available to developers, enterprises, scientists, and consumers.

Gemini Omni 1.2 Flash brings native 15-second video generation and editing, stronger consistency, and 30% lower pricing.

AlphaProof Code agents wrote three million lines of proofs in Lean to verify Signal’s core encryption.

We’ve launched fast mode for Claude Fable 5.2 in Messages API requests on the Claude API. Fast mode delivers up to 2.5x higher output tokens per second, at…

Manage your business information, get insights about how your business shows up, and turn interest into action in ChatGPT.

More than 20,000 veterans and transitioning service members have claimed a free year of ChatGPT Plus. See how they use it to prepare for civilian careers.

Business Hub gives business owners and authorized representatives a place to claim their business in ChatGPT. After your claim is approved, you can access…

text-generation

Both models require 30-day data retention, like Claude Fable 5.1 and Claude Mythos 5.1. They aren’t available under zero data retention unless expressly…