Tag
Opposable 推出可在 Android 手机本地运行的 GUI 智能体：使用 4-bit 量化的 GUI-Owl 1.5 2B 模型（基于 Qwen3-VL，Alibaba Mobile-Agent 团队出品），通过 llama.cpp 在设备上直接读屏并操作任意应用，无需服务器。通过裁剪状态栏、丢弃平坦背景图像 token 等优化，Mac M2 CPU 上单步耗时从 10.6 秒降至 7.3 秒，且在 36 屏测试集上精度不降。
提出一种无需人工偏好标注的多模态奖励建模方法：在冻结的 Qwen3-VL 骨干网络的中间层上训练线性探针，通过扰动字幕对比进行训练，在多个基准上达到或超过 GPT-4o，且微调计算量仅为千分之一。
Unitree released UnifoLM-WLA-1.0, a 6B-parameter whole-body vision-language-action foundation model trained on ~2,500 hours of real robot data that handles 64 tasks on the Unitree G1 humanoid, using an MMDiT action expert on top of an embodied reasoner based on Qwen3-VL.
The paper introduces FORESIGHT, a training-free dual-stream architecture using two Siamese LLMs to anticipate future context and dynamically reconfigure computation in streaming vision-language models. With a frozen Qwen3-VL-8B backbone, it achieves 23.0 mean joint F1 on OmniPro Online and improves StreamingBench by 6.7 and OVO-Bench by 15.4 over the base model.
Release of an NVFP4-quantized uncensored MiniMax-H3 text encoder (Qwen3-VL-32B Heretic) that fits on a single 16GB GPU and serves as a drop-in replacement in ComfyUI workflows.
A Hugging Face repository providing ComfyUI safetensors checkpoints of an uncensored Qwen3-VL-32B variant, with BF16 and INT8 ConvRot H3 conditioning encoders plus an optional generation tail.
This repository provides INT8 ConvRot-quantized ComfyUI safetensors of Qwen3-VL-32B, including a MiniMax-H3 conditioning encoder with layers 0-49 and an optional prompt-enhancement tail for layers 50-63, designed for use in ComfyUI on 32GB GPUs.
This paper introduces MMIR-TCM, a novel framework that integrates multimodal large language models with memory-augmented segmentation and retrieval-augmented generation to support Traditional Chinese Medicine clinical decision making, along with a new dataset MedTCM and evaluation metric TDEU.
This article introduces Qwen3-VL, a state-of-the-art vision-language model with comprehensive enhancements in visual perception, reasoning, and agent capabilities, available in various architectures for flexible deployment.