analiza aiqbench
FloodReasonBench introduces a specialized dataset and benchmark for vision-language models operating in resource-constrained edge environments during flood response scenarios. By evaluating tradeoffs between accuracy, latency, and energy on hardware like the NVIDIA Jetson AGX Xavier, it addresses critical gaps where generic benchmarks fail to capture domain-specific constraints. This work advances embodied AI by providing actionable insights into deploying robust reasoning segmentation systems for real-world disaster relief operations.
FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge
arXiv:2608.15410v1 Announce Type: cross Abstract: Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents. However, existing benchmarks largely focus on generic visual scenes and overlook the domain and resource constraints encountered in flood-response platforms. We present FloodReasonBench, a benchmark for VLM reasoning segmentation for embodied flood response at the edge. At its core, FloodReasonBench introduces FloodResponseSeg, a flood-specific reasoning-segmentation dataset constructed from real-world scenes and response-relevant targets. Beyond task accuracy, the benchmark characterizes reasoning-segmentation pipelines under lightweight visual encoding, hierarchical split inference, and compressed intermediate representations. We observe strong partition-dependent accuracy variation in the generic pre-adaptation setting, while the flood-adapted target-workload design space exhibits a substantially more compact accuracy range across partitions. Evaluation on an NVIDIA Jetson AGX Xavier further exposes the tradeoffs among reasoning-segmentation accuracy, edge-side latency, energy, and communication footprint, enabling quality-constrained selection of edge operating points. Together, these results provide a task- and system-level characterization of reasoning segmentation for resource-constrained embodied flood response at the edge.
Abstract:Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents. However, existing benchmarks largely focus on generic visual scenes and overlook the domain and resource constraints encountered in flood-response platforms. We present FloodReasonBench, a benchmark for VLM reasoning segmentation for embodied flood response at the edge. At its core, FloodReasonBench introduces FloodResponseSeg, a flood-specific reasoning-segmentation dataset constructed from real-world scenes and response-relevant targets. Beyond task accuracy, the benchmark characterizes reasoning-segmentation pipelines under lightweight visual encoding, hierarchical split inference, and compressed intermediate representations. We observe strong partition-dependent accuracy variation in the generic pre-adaptation setting, while the flood-adapted target-workload design space exhibits a substantially more compact accuracy range across partitions. Evaluation on an NVIDIA Jetson AGX Xavier further exposes the tradeoffs among reasoning-segmentation accuracy, edge-side latency, energy, and communication footprint, enabling quality-constrained selection of edge operating points. Together, these results provide a task- and system-level characterization of reasoning segmentation for resource-constrained embodied flood response at the edge.
Paper is currently under review. The code and dataset will be made public upon acceptance
Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Systems and Control (eess.SY)
arXiv:2608.15410 [cs.DC]
(or arXiv:2608.15410v1 [cs.DC] for this version)
https://doi.org/10.48550/arXiv.2608.15410 arXiv-issued DOI via DataCite (pending registration)
Text integral sub licența deschisă a publicației · 219 cuvinte
Subiecte conexe
Stock Market Today Highlights, Sept 2: Sensex ends 373 pts lower at 76, 570, Nifty below 24, 000; Asian Paints, HDFC Bank fall most
thehindubusinessline.com · 2 sept. 2026
NVIDIA GTC Taipei at COMPUTEX: Live Updates on What’s Next in AI
NVIDIA · 21 mai 2026
[AINews] not much happened today
Latent Space · 3 oct. 2026
Artmarket.com: H1 2026 Financial Report -- One-of-a - Kind AI Systems Intuitive Artmarket and Blind Spot Will Drive the Next Phase of Growth for
australiannews.net · 29 sept. 2026