OVRSISBenchV2 is a realistic benchmark expanding scene and category coverage for open-vocabulary remote sensing segmentation, with Pi-Seg baseline showing strong transfer via positive-incentive noise perturbations.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.
FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.
VOTE-RAG applies retrieval voting across diverse queries and response voting across independent generations to mitigate hallucination-on-hallucination in RAG, matching or exceeding complex baselines on six benchmarks with a parallelizable design.
citing papers explorer
-
Towards Realistic Open-Vocabulary Remote Sensing Segmentation: Benchmark and Baseline
OVRSISBenchV2 is a realistic benchmark expanding scene and category coverage for open-vocabulary remote sensing segmentation, with Pi-Seg baseline showing strong transfer via positive-incentive noise perturbations.
-
Learning Vision-Language-Action World Models for Autonomous Driving
VLA-World improves autonomous driving by using action-guided future image generation followed by reflective reasoning over the imagined scene to refine trajectories.
-
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.
-
Mitigating Hallucination on Hallucination in RAG via Ensemble Voting
VOTE-RAG applies retrieval voting across diverse queries and response voting across independent generations to mitigate hallucination-on-hallucination in RAG, matching or exceeding complex baselines on six benchmarks with a parallelizable design.