Related papers: SpatialEvo: Self-Evolving Spatial Intelligence via…
While Multimodal Large Language Models (MLLMs) have achieved impressive performance on semantic tasks, their spatial intelligence--crucial for robust and grounded AI systems--remains underdeveloped. Existing benchmarks fall short of…
With the current surge in spatial reasoning explorations, researchers have made significant progress in understanding indoor scenes, but still struggle with diverse applications such as robotics and autonomous driving. This paper aims to…
Humans excel at spatial reasoning tasks like Tangram puzzle assembly through cognitive processes involving mental rotation, iterative refinement, and visual feedback. Inspired by how humans solve Tangram puzzles through trial-and-error,…
Reasoning about motion and space is a fundamental cognitive capability that is required by multiple real-world applications. While many studies highlight that large multimodal language models (MLMs) struggle to reason about space, they only…
End-to-end autonomous driving methods built on vision language models (VLMs) have undergone rapid development driven by their universal visual understanding and strong reasoning capabilities obtained from the large-scale pretraining.…
Spatial intelligence is the ability of a machine to perceive, reason, and act in three dimensions within space and time. Recent advancements in large-scale auto-regressive models have demonstrated remarkable capabilities across various…
Online Reinforcement Learning (RL) offers a promising avenue for complex image editing but is currently constrained by the scarcity of reliable and fine-grained reward signals. Existing evaluators frequently struggle with a critical…
Multimodal Large Language Models (MLLMs) have significantly advanced vision-language understanding. However, even state-of-the-art models struggle with geometric reasoning, revealing a critical bottleneck: the extreme scarcity of…
Recent advances in point cloud perception have demonstrated remarkable progress in scene understanding through vision-language alignment leveraging large language models (LLMs). However, existing methods may still encounter challenges in…
Structural learning, a method to estimate the parameters for discrete energy minimization, has been proven to be effective in solving computer vision problems, especially in 3D scene parsing. As the complexity of the models increases,…
Visual Language Models (VLMs) are essential for various tasks, particularly visual reasoning tasks, due to their robust multi-modal information integration, visual reasoning capabilities, and contextual awareness. However, existing \VLMs{}'…
Recent advances in Visual Language Models (VLMs) have demonstrated exceptional performance in visual reasoning tasks. However, geo-localization presents unique challenges, requiring the extraction of multigranular visual cues from images…
Spatial world models, representations that support flexible reasoning about spatial relations, are central to developing computational models that could operate in the physical world, but their precise mechanistic underpinnings are nuanced…
Assessing teachers' geometric content knowledge is essential for geometry instructional quality and student learning, but difficult to scale. The Van Hiele model characterizes geometric reasoning through five hierarchical levels.…
Spatial reasoning is a critical capability for intelligent robots, yet current vision-language models (VLMs) still fall short of human-level performance in video-based spatial reasoning. This gap mainly stems from two challenges: a…
Bird's-Eye-View (BEV) perception serves as a cornerstone for autonomous driving, offering a unified spatial representation that fuses surrounding-view images to enable reasoning for various downstream tasks, such as semantic segmentation,…
Large vision-language models (VLMs) still struggle with reliable 3D spatial reasoning, a core capability for embodied and physical AI systems. This limitation arises from their inability to capture fine-grained 3D geometry and spatial…
Geospatial pixel reasoning aims to generate segmentation masks in remote sensing imagery directly from natural-language instructions. Most existing approaches follow a paradigm that fine-tunes multimodal large language models under…
Lightweight vision-language models perform competitively on standard benchmarks yet fail systematically in dense-scene reasoning, where multiple objects, attributes, and relations must be jointly grounded and resolved through multi-step…
Embodied reasoning is inherently viewpoint-dependent: what is visible, occluded, or reachable depends critically on where the agent stands. However, existing spatial memory systems for embodied agents typically store either multi-view…