Spatial Reasoning
2개 벤치마크 · 논문 1,272편 · 이 태스크의 논문 보기 →
Benchmarks
6-DoF SpatialBench
EmbSpatial-Bench
Most implemented
Spatial Memory for Context Reasoning in Object Detection
Visual Instruction Tuning
GPT-4 Technical Report
Improved Baselines with Visual Instruction Tuning
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
Long Range Arena: A Benchmark for Efficient Transformers
Papers
GeoLatent: Geometry-Guided Latent Structuring with Routed Optimization for 3D Reasoning
Despite progress in vision-language models, 3D spatial reasoning from 2D images remains challenging. Text-based methods describe intermediate geometry with discrete tokens, limiting fidelity for continuous spatial relati…
Spatial ReasoningFrom Reasoning Failures to Composable Video Spatial Intelligence
Spatial reasoning benchmarks evaluate vision-language models across diverse tasks, but task-level scores do not reveal which underlying capabilities account for success or failure. Each task requires recovering spatial e…
Spatial ReasoningCoEvolve: Construct-to-Edit Visual Grounding with Bidirectional State Refinement
Visual grounding localizes an object described by language with a bounding box. Most multimodal grounding models compress target identification, spatial reasoning, and boundary estimation into one terminal prediction. Fr…
Spatial ReasoningVisual GroundingSpatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
Long-video generation and world models have shown strong potential for interactive entertainment and embodied simulation by predicting future observations conditioned on user actions and historical memory. However, as me…
Spatial ReasoningVideo GenerationSpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models
Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions that require reasoning over visual space. R…
Spatial ReasoningSoft Spatial Reasoning
Large Vision-Language Models (LVLMs) commonly perform spatial reasoning through chain-of-thought (CoT), encoding intermediate reasoning as autoregressive sequences of discrete language tokens. Such hard thinking requires…
Spatial Reasoning