AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

SpaceEra++: A Unified Framework Toward 3D Spatial Reasoning in Video

Weili Guan, H ZHANG, Meng Liu, Qianlong Xiang, Yue Wang, Liqiang Nie

TPAMI 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Spatial reasoning in VLMs · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add ScenePick frame samplingSpaceEra · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 43.9 -> 45.2Improved
add SpaceAlign RL trainingSpaceEra · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 43.9 -> 48.7Improved
combine ScenePick and SpaceAlignSpaceEra · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 43.9 -> 50.3Improved
add object semantics to ScenePick (not coverage only) (ablation)ScenePick · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 44.9 -> 45.2Improved
add spatial coverage to ScenePick (not object semantics only) (ablation)ScenePick · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 44.3 -> 45.2Improved
add space imagination rewards (R_abs and R_rel) (ablation)SpaceAlign · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 45.8 -> 48.7Improved
add absolute coordinate reward (ablation)SpaceAlign · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 46.3 -> 48.7Improved
add relative relation reward (ablation)SpaceAlign · VSI-Bench (Qwen2.5-VL-7B)average accuracy: 47.9 -> 48.7Improved
add ScenePick to SpaceEra on Gemini-1.5 ProSpaceEra · VSI-Bench (Gemini-1.5 Pro)average accuracy: 52.8 -> 49.0Hurt
add ScenePick to SpaceEra on Qwen2.5-VL-72BSpaceEra · VSI-Bench (Qwen2.5-VL-72B)average accuracy: 47.1 -> 50.0Improved
add SpaceAlign to SpaceEra on Qwen3-VL-8BSpaceEra · VSI-Bench (Qwen3-VL-8B)average accuracy: 44.2 -> 49.2Improved
replace GPT-4o recognizer with Qwen3-VL-8B in SpatialMind (ablation)SpatialMind · VSI-Bench (Qwen2.5-VL-72B)average accuracy: 44.0 -> 42.3Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy