Papers Spatial Reasoning
“Spatial Reasoning” 태그가 달린 논문 1,272편 · 필터 해제
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 ReasoningImagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs handle single-image inputs effectively, they struggle to integrate evid…
Spatial ReasoningLeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning
Perspective taking is a fundamental component of spatial intelligence, requiring models interpret spatial relations from a specified viewpoint, such as that of another entity or an imagined observer. Despite the increasi…
Reinforcement Learning3D ReconstructionSpatial ReasoningHard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision
Frontier general-purpose systems are rapidly expanding beyond visual understanding into capabilities traditionally handled by dedicated computer-vision models. As these capabilities expand, a central question for the com…
Structured PredictionSpatial ReasoningWM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning
Humans often solve spatial problems by mentally simulating visual transformations. In contrast, conventional vision-language models (VLMs) reason primarily through language. We investigate whether VLMs can solve spatial …
Spatial ReasoningSpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning
Vision-language models (VLMs) can benefit from geometric priors for multi-view spatial reasoning, yet answer-only training does not directly supervise the intermediate geometric estimates and their use in deriving quanti…
Question AnsweringSpatial ReasoningWorld Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal
General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them indirectly, to predict constraints or write programs, or give them a v…
Robot ManipulationSpatial ReasoningSpatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World
Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion an…
Spatial ReasoningReasoning with Image Generation
Chain-of-thought reasoning has revolutionized natural language processing by enabling large language models (LLMs) to decompose problems into intermediate steps before answering. Yet confining reasoning to the textual do…
Spatial ReasoningImage GenerationDepth EstimationVisual ReasoningEgoSIS: From Factorized Visual Ego-Transitions to Motion-Canonical Spatial Evidence for UAV Reasoning
UAV video question answering requires separating camera motion from changes in the scene, but RGB-only multimodal models receive no explicit, stable reference for that separation. We present EgoSIS, a pose-free adapter t…
Video Question AnsweringSpatial ReasoningRoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?
Vision-Language-Action (VLA) models have shown promising progress in language-conditioned robotic manipulation. However, existing datasets and benchmarks mainly evaluate task completion under predefined settings, offerin…
Spatial ReasoningUnfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
Despite the remarkable prowess of Vision-Language Models (VLMs) in general multimodal tasks, they remain fundamentally ``flat'' when reasoning about the physical world. We argue that this spatial bottleneck stems from a …
Reinforcement LearningSpatial ReasoningAutoregressive Mosaics: Probing 2D Spatial Reasoning in Text-Only Language Models
Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or si…
Spatial ReasoningLightNav-0: Eliciting VLM Spatial Intelligence for Generalist Embodied Navigation
Embodied navigation requires agents to translate heterogeneous goals and visual observations into actions across tasks, environments, and robot embodiments. Modern vision-language models (VLMs) already encode spatial pri…
Zero-shot GeneralizationReinforcement LearningInstruction FollowingSpatial ReasoningUrbanGround: From Local Perception to Spatial Agency in a Real-Scale City
Multimodal large language models (MLLMs) can interpret a street view, but urban agency depends on whether such local evidence remains useful after the agent starts to move. In this paper, we investigate how far current M…
Spatial Reasoning