Multi-teacher on-policy distillation (MOPD) is used in two settings. In common-domain composition, several teachers score ...

We introduce UltraText Bench, a bilingual benchmark for dense text rendering with 432 prompts across 24 real-world scene categories. Evaluating 24 model configurations reveals a key challenge: ...

Author here. WebFovea is a vision-based web agent that placed 2nd in the WebRetriever Challenge 2026 (57.0/100). It works on live websites through their own UI: screenshots in, clicks and keystrokes ...

We introduce CheckerBench, an executable benchmark for evaluating whether coding agents can turn real-world vulnerabilities into reusable static-analysis checkers. CheckerBench contains 300 tasks ...

Note Try all four models in the browser: routing, PII and unsupported-claim spans, your own labels, verbatim evidence.

A Blog post by Ai2 on Hugging Face ...

Index-Translate-35B-A3B-preview is the 35B-total / 3B-active mixture-of-experts multilingual text model of the Index-Translate family, built on Qwen3.5. It supports text translation across 150 ...

This repository provides rh-qwen-image-2.1-viggle-turbo-4step-r64-comfyui-t8-lora weight files. You can load them on RunningHub.

The omlx GitHub repository seems deleted. Any new url ?

This is an automated message from the Librarian Bot. I found the following papers similar to this paper.

This repository contains the official weights for AuK-Flash, the distilled variant with fast 4-step inference. AuK exposes every task through the same natural-language instruction interface. The table ...

K2 Horizon models, datasets, and supporting resources. Upvote . 16 +6; Sort: Collection. IFM/K2-Horizon-375B-A23B. Text Generation • 379B • Updated about 2 hours ago • 9 ...