Unverified50% confidenceFactExact time
The new benchmark CueClash renders scenes so that 2D cues for five spatial relations are correct in exactly half of the statements and wrong in the other half, thereby quantifying vision-language models' reliance on 2D shortcuts.
1
Sources
50%
Confidence
Long-term
Relevance
11/18/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSketches inherently contain spatial cues such as viewpoint, occlusion, and proportion, making them suitable as a medium for spatial reasoning tests.69% similarUnverifiedKuaishou's Kling uses a 3D causal attention mechanism to handle temporal frame relationships.69% similarUnverified3D-guided neural rendering uses geometric data such as depth buffers, normal maps, and motion vectors as explicit inputs to neural networks to better understand the spatial positional relationships of objects in a scene.69% similarUnverifiedThe paper conducted experiments on datasets such as ACID, and the results show that CoTL's compact, unstructured Token set not only supports competitive novel-view synthesis but can also serve as a latent space for generative models to generate 3D Gaussian scenes.69% similarUnverifiedGlimpse's visual draft space architecture requires the model to have two capabilities: metacognition to judge whether the current information is sufficient, and an interface to translate operations such as crop coordinates and frame timestamps into executable instructions; the cost is a significant increase in inference latency and computation.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1182626API
curl https://kongchang.com/api/v1/knowledge/claims/1182626MCP
get_claim(id=1182626)