Qwen3‑VL: An AI that understands text, images, and video—at book length

Kari Jaaskelainen

27 Nov 2025 — 1 min read

Meet Qwen3-VL, our most capable vision-language model yet. It understands text, images, and video together—and keeps track of up to 256K tokens, so it can follow book-length docs and long videos without losing the thread.

What’s new

Stronger brains: Even better at pure text tasks, beating many text-only models.
Long attention: Natively handles very long, interleaved content and retrieves details accurately.
Smarter vision: Leads on tough multimodal tests (e.g., MMMU, MathVista/MathVision) across single images, albums, and video.
Right size for you: From 2B to 235B parameters, including MoE options for speed–quality trade‑offs.

How it works

Upgraded spatial–temporal modeling for images and video.
DeepStack uses multi-level vision features for tighter text–image alignment.
Text-based timestamp alignment for crisper video grounding.

Why it matters: stronger agents that can cite across slides, pages, scenes, and frames—for research, support, education, and code with visuals.

Paper: https://arxiv.org/abs/2511.21631v1

Paper: https://arxiv.org/abs/2511.21631v1

Register: https://www.AiFeta.com

#AI #Multimodal #LLM #ComputerVision #VideoUnderstanding #GenAI #Qwen #Research

Beyond URLs: Metadata That Makes LLMs Train Faster

Smarter LLMs, Faster—thanks to metadata What if training a large language model didn't just rely on text, but on the context around it? This study shows that adding fine-grained metadata—not just URLs—can meaningfully speed up pretraining and improve quality. * Beyond URLs: detailed quality signals (e.

Escaping the Verifier: Learning to Reason via Demonstrations

LLMs can learn to reason—without task verifiers Many real-world problems don’t have automatic checkers to grade answers, even though we have lots of expert solutions. RARO (Relativistic Adversarial Reasoning Optimization) shows how to train reasoning skills from those examples alone. How it works: * A policy (the model) tries

VacuumVLA: A Two-in-One Robot Hand That Grips and Suctions

Robots guided by Vision-Language-Action (VLA) AI are getting better at everyday tasks—but most still use simple two-finger grippers. That limits them on smooth, flat, or handleless objects. VacuumVLA is a low-cost robot hand that merges a standard two-finger gripper with a vacuum suction cup. The robot can switch between

ChatDRex: No‑Code, Conversational AI for Drug Repurposing

Meet ChatDRex Finding new uses for approved drugs can save years and millions. But making those predictions usually takes teams of specialists and a tangle of tools. ChatDRex changes that. It’s a conversation-based, no‑code, multi‑agent system that lets clinicians and researchers ask complex bioinformatics questions in plain