World Wire

Search and recommendation systems increasingly need to return a set of results, not one best match. A query like ‘camping gear’ should return a tent, a sleeping bag, a stove, and a headlamp. It should not return 10 near-identical tents. Google Research has introduced Retrieve-for-Train (R4T) for this problem. The framework uses reinforcement learning (RL) once, offline, to learn good query fan-out. It then distills that behavior into a small diffusion model that produces all retrieval directions in 1 pass. Why Standard Fan-Out Falls Short Query fan-out splits one broad prompt into several sub-queries. The research team identifies 2 problems when a generic LLM does this at inference time. The first is paraphrastic collapse. For ‘Bohemian festival style,’ zero-shot Qwen3-4B wrote ‘bohemian festival fashion’ and ‘festival bohemian clothes.’ These near-synonyms retrieve a homogeneous slate. The second is latency. Autoreg...

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 5-second 720p Wan2.2-14B clip spans about 70K tokens. On the RTX 5090, attention takes more than 64% of generation time. The research team states that attention is about two thirds of every MiniMax-H3 denoising step on a single B200. Low-bit Tensor Cores speed up the 2 matrix products, QK and PV. 2 obstacles remain. First, prior methods like SageAttention2 smooth queries and keys. After QK smoothing and rotation, the value term accounts for 82% of output error on Wan2.2. Second, the softmax between the products still runs in FP32. On B200 and H200, that exponential and its FP8 cast become the longest pipeline stage. ...

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) server. Any MCP-compatible agent, such as Claude Code , can then run the paper’s methods through natural language. The authors describe the result as a virtual corresponding author. Is it deployable? Yes. The code is MIT-licensed and installs as a skill for Claude Code or Codex. Prebuilt AlphaGenome , Scanpy and TISSUE servers run on Hugging Face Spaces. A hosted version is also available at paper2agent.ai . How the Pipeline Works Paper2Agent runs on Claude Code’s agent SDK. A central orchestrator dispatches specialized sub-agents through 6 steps: Locate and download the codebase. An environment manager builds an isol...