ReRe boosts open-source MLLMs on spatial reasoning benchmarks VSI-Bench and STI-Bench to rival proprietary SOTA by using a two-phase Reason then Re-reason process with Geometry-to-Video novel view synthesis.
arXiv preprint arXiv:2307.13236 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.
citing papers explorer
-
Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
ReRe boosts open-source MLLMs on spatial reasoning benchmarks VSI-Bench and STI-Bench to rival proprietary SOTA by using a two-phase Reason then Re-reason process with Geometry-to-Video novel view synthesis.
-
LightAVSeg: Lightweight Audio-Visual Segmentation
LightAVSeg decouples semantic filtering and spatial grounding to achieve linear-cost cross-modal interaction in audio-visual segmentation, reaching 50.4 mIoU on MS3 with 20.5M parameters as a new lightweight state-of-the-art.