OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
Towards omnidi- rectional reasoning with 360-r1: A dataset, benchmark, and GRPO-based method.preprint
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5representative citing papers
MLLMs display a large perception-reasoning gap on perspective-conditioned spatial reasoning tasks from omnidirectional images, with sharp accuracy drops on advanced tasks like egocentric rotation, though partial gains are possible via RL reward shaping.
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
A survey diagnosing panoramic scene understanding as a field that converged on compatibility-preserving geometric adaptation rather than sphere-native modeling, while its evaluation protocols systematically fail to measure spherical understanding.
FireScope trains a VLM on US data to output wildfire risk rasters with reasoning traces and shows improved cross-continental performance on European events compared with prior approaches.
citing papers explorer
-
OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning
OmniCoT is a new panoramic reasoning benchmark with 6.7K eval, 1K real, and 14.3K training examples plus a two-stage SFT+GRPO training method to enforce global 360-degree consistency.
-
Beyond Localization: A Comprehensive Diagnosis of Perspective-Conditioned Spatial Reasoning in MLLMs from Omnidirectional Images
MLLMs display a large perception-reasoning gap on perspective-conditioned spatial reasoning tasks from omnidirectional images, with sharp accuracy drops on advanced tasks like egocentric rotation, though partial gains are possible via RL reward shaping.
-
PanoWorld: Towards Spatial Supersensing in 360$^\circ$ Panorama World
PanoWorld adds spherical spatial cross-attention and pano-native training data to MLLMs for improved spatial reasoning on ERP panoramas, outperforming baselines on new and existing benchmarks.
-
Panoramic Scene Understanding: A Survey from Distortion-Aware Engineering to Sphere-Native Modeling
A survey diagnosing panoramic scene understanding as a field that converged on compatibility-preserving geometric adaptation rather than sphere-native modeling, while its evaluation protocols systematically fail to measure spherical understanding.
-
FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle
FireScope trains a VLM on US data to output wildfire risk rasters with reasoning traces and shows improved cross-continental performance on European events compared with prior approaches.