BestHub
Sign in
Tagged articles

Qwen3-VL-8B

3 articles · Page 1 of 1
Machine Heart
Machine Heart
Aug 11, 2026 · Artificial Intelligence

Why VLMs Miss Reference Images and How RefCaptioner Aligns Them Precisely

RefCaptioner tackles the blind spot of existing video-language models by jointly grounding video captions to multiple reference images, using a dual‑reward fine‑tuning scheme and a new benchmark (MRVBench) that evaluates factual accuracy, image selection, and grounding robustness across up to 22 reference images per video.

MRVBenchQwen3-VL-8BRefCaptioner
0 likes · 13 min read
Why VLMs Miss Reference Images and How RefCaptioner Aligns Them Precisely
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jul 10, 2026 · Artificial Intelligence

Annotation‑Free Mobile GUI Agents: How MobileForge Builds a Data‑Flywheel

MobileForge introduces an annotation‑free adaptation loop for mobile GUI agents that combines the MobileGym data‑generation platform with the HiFPO hierarchical feedback‑guided policy optimizer, achieving near‑state‑of‑the‑art performance on AndroidWorld and cross‑domain MobileWorld while eliminating manual task labeling and reward design.

GUI AgentGUI-Owl-1.5-8BHiFPO
0 likes · 19 min read
Annotation‑Free Mobile GUI Agents: How MobileForge Builds a Data‑Flywheel
Machine Heart
Machine Heart
Jul 9, 2026 · Artificial Intelligence

Annotation-Free GUI Agent Data Flywheel: MobileForge’s Self-Exploring, Self-Feedback Loop

MobileForge introduces an annotation‑free pipeline for adapting mobile GUI agents, combining MobileGym’s exploration‑to‑task generation with HiFPO’s hierarchical feedback‑guided policy optimization, achieving up to 77.6% Pass@3 on AndroidWorld and notable cross‑domain gains without any human‑written tasks or demonstrations.

GUI AgentGUI-OwlHierarchical Feedback
0 likes · 18 min read
Annotation-Free GUI Agent Data Flywheel: MobileForge’s Self-Exploring, Self-Feedback Loop