3 papers
cs.RO2026
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
Dayu Xia, Yue Shi, Yao Mu +7
Vision-language models (VLMs) are increasingly explored as visual critics, reward generators, and failure detectors in robotic manipulation. These roles implicitly require models t…
cs.CV2026
FigEx2: Visual-Conditioned Panel Detection and Captioning for Scientific Compound Figures
Jifeng Song, Arun Das, Pan Wang +3
Scientific compound figures combine multiple labeled panels into a single image. However, in a PMC-scale crawl of 346,567 compound figures, 16.3% have no caption and 1.8% only have…
cs.LG2026
HERO: Hierarchical Evidential Reasoning Optimization for Radiology Report Generation via Reason-then-Summarize
Kun Zhao, Siyuan Dai, Guodong Liu +6
Multimodal Large Language Models (MLLMs) have substantially advanced Radiology Report Generation (RRG), yet aligning them through reinforcement learning (RL) remains challenging du…