AdaGround adds adaptive zoom and a verifier for GUI grounding
On Qwen3-VL, the training-free method raises accuracy 7.4 to 20.6 points on OSWorld-G and ScreenSpot-Pro.
36
AI model
Qwen3-VL
- Mentions · 7d0
- Mentions · 30d5
- All mentions10
- First seenAug 31, 2026
- Last mentioned7d ago
Timeline
10 articles · newest firstFactorized vector quantization matches continuous visual tokens on understanding
The discrete model beats UniAR and Emu3-Chat by 22.8% and 59.2% on a nine-metric average.
58
HAD-VLM pairs diffusion with language for ultrasound measurements
It cuts four EchoNet-LVH measurement errors 21.4–37.6% versus a Vicuna baseline and lowers X-ray vertebral error from 11.4 to 6.7 pixels.
40
IGG benchmark asks GUI agents to reveal hidden targets before clicking
Humans score 94.6%, GPT-5.5 79.4%, and the best open-source VLM only 31.6% on 601 tasks.
46
CycleGRPO couples region captioning and localization with cycle rewards
On GroundingSuite, SAMTok overall gIoU rises from 57.5% to 68.2%; video tIoU on Charades reaches 51.9% versus 45.6% for Qwen3-VL.
48
Program-Verified Self-Evolution for Vision-Language Models
VQS generates program-verified vision questions, labeling 94% correctly and lifting Qwen3-VL by up to 3.84 points.
47
Alibaba Qwen Releases Qwen-Image-2.1: A 7B Open-Weight Model for Image Generation and Editing
Alibaba’s Qwen team released Qwen-Image-2.1, a 7B open-weight model for image generation and editing.
72
Cross-Modal Attention Acts as a Frequency Filter: Why Verbose Prompts Improve Robustness in Vision-Language Models
Study explains why verbose prompts make vision-language models more robust to image corruption, framing cross-modal attention as a frequency filter.
30
NVIDIA Vera Rubin NVL72 Delivers Leading Performance in MLPerf Inference v6.1 Debut
NVIDIA's Vera Rubin NVL72 debuts in MLPerf Inference v6.1 with up to 3.7x higher throughput than GB300 NVL72 and 99% scaling efficiency at 288 GPUs.
42
EmbodiedSkills: A Unified Framework for Orchestrating, Training, and Deploying VLA Agents
Researchers introduce EmbodiedSkills, a framework treating VLA skill decisions as verified execution proposals, reaching 86.2% success on RoboTwin 2.0.
46
Appears with
- Hugging Facevendor · 1
- RoboTwin 2.0product · 1
- SGLangproduct · 1
- GPT-5.5ai model · 1
- LLaVA-OneVisionai model · 1
- ComfyUIproduct · 1
- Emu3-Chatai model · 1
- AdaGroundai model · 1
- MLCommonsorganization · 1
- GB300 NVL72product · 1
- Vera Rubin NVL72product · 1
- SAMTokai model · 1
- LIBEROproduct · 1
- Qwen-Image-2.1ai model · 1
- Diffusersproduct · 1
- NVIDIAorganization · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.