SpatioRoute introduces dynamic prompt routing that improves zero-shot spatial VQA accuracy by up to 5% on the SQA3D benchmark across VLMs without 3D inputs or fine-tuning.
Enhancing spatial reasoning in vision-language models via chain-of-thought prompting and reinforcement learning,
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
RLVR on synthetic mazes enables VLMs to solve spatial reasoning tasks unreachable by the base model and generalizes to real-world navigation benchmarks.
EyeVLM benchmark finds that current VLMs underperform specialized visual models on gaze following and social gaze prediction, with fine-tuning narrowing but not closing the gap.
citing papers explorer
-
SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial Reasoning
SpatioRoute introduces dynamic prompt routing that improves zero-shot spatial VQA accuracy by up to 5% on the SQA3D benchmark across VLMs without 3D inputs or fine-tuning.
-
Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models
RLVR on synthetic mazes enables VLMs to solve spatial reasoning tasks unreachable by the base model and generalizes to real-world navigation benchmarks.
-
Eyes on VLM: Benchmarking Gaze Following and Social Gaze Prediction in Vision Language Models
EyeVLM benchmark finds that current VLMs underperform specialized visual models on gaze following and social gaze prediction, with fine-tuning narrowing but not closing the gap.