OccludeBench: Can VLMs Find What's Missing?
How well can vision-language models (VLMs) reason about what is missing from an image?
ProofPaper ↗
Key points
- We study this question with OccludeBench, a manually curated benchmark for recovering fully occluded objects from the visual evidence that remains.
- OccludeBench distinguishes direct cases, where the hidden object must be recovered from a specific physical cue such as a shadow or reflection, from inferential cases, where it can be inferred from broader scene context.
- To locate this failure, we introduce OccludeTrace, a four-stage diagnostic that isolates where the visual reasoning process breaks down.
- Together, our results establish a tractable, controlled diagnostic for isolating how VLMs reason about visual content that is missing from an image.
Sources (1)
- [1]OccludeBench: Can VLMs Find What's Missing?arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 04:04 PM
How well can vision-language models (VLMs) reason about what is missing from an image?
We study this question with OccludeBench, a manually curated benchmark for recovering fully occluded objects from the visual evidence that remains.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 9, 2026AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories
- Oct 9, 2026Minions: A Dynamic and Distributed Virtual GPU Cloud Built on Idle Apple Silicon Devices
- Oct 9, 2026Rethinking Relative Policy Differences Transfer of On-Policy Distillation
- Oct 9, 2026InstantFusion: A Shared Latent Interface for Heterogeneous Image Generators
- Oct 8, 2026ConwayResearch/Underdog-Saluki-27B-1.0
- Oct 7, 2026[AINews] Claude Haiku 5.5 — better than GPT-6 Luna at the same pricing