AIBearisharXiv – CS AI · 9h ago7/10
🧠Researchers reveal that vision-language models (VLMs) fail to recognize when spatial questions cannot be reliably answered due to occlusion or perspective ambiguity, instead producing overconfident incorrect responses. The study introduces SpatialUncertain, a benchmark showing that current VLMs achieve only 30% accuracy under occlusion and below 10% under perspective challenges, highlighting a critical gap between answer correctness and epistemic awareness.
AIBullisharXiv – CS AI · 3d ago7/10
🧠JAEGER is a new AI framework that extends audio-visual large language models from 2D to 3D space, enabling spatial grounding and reasoning in physical environments through RGB-D observations and multi-channel audio. The researchers introduce Neural Intensity Vector (Neural IV) for enhanced directional audio analysis and release SpatialSceneQA, a 61k-sample benchmark for training and evaluation.
AIBullisharXiv – CS AI · 4d ago7/10
🧠Researchers introduce Tensor Memory, a fixed-size recurrent module that augments Transformers with persistent 3D spatial state for improved long-sequence processing. The approach enables better video understanding and occlusion reasoning by decoupling memory capacity from input length while maintaining computational efficiency.
AIBearisharXiv – CS AI · May 127/10
🧠Researchers unveiled KnotBench, a comprehensive benchmark testing vision-language models' ability to reason about knot diagrams, revealing that current models like Claude Opus and GPT-5 struggle fundamentally with spatial reasoning and symbolic operations despite perceiving visual details. The benchmark demonstrates a critical gap between perception and reasoning capabilities, with most tasks scoring near or below random chance, suggesting VLMs lack mechanisms to simulate geometric transformations.
🧠 GPT-5🧠 Claude🧠 Opus
AIBullisharXiv – CS AI · May 127/10
🧠Flame3D introduces a training-free framework that enables large language models to reason about 3D scenes compositionally without requiring 3D-specific training data. The system represents scenes as editable visual-textual memories and allows agents to synthesize custom spatial programs at inference time, achieving competitive results on existing benchmarks while opening new possibilities for multi-hop spatial reasoning.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers introduce GazeVLM, a vision-language model that implements active attention control mechanisms mimicking human visual reasoning. The 4B-parameter model autonomously generates gaze tokens to dynamically focus on task-relevant visual details, achieving 4-5% performance improvements over comparable VLMs without increasing context window size.
AIBullisharXiv – CS AI · May 77/10
🧠Researchers present JoyAI-Image, a unified multimodal foundation model that combines visual understanding, text-to-image generation, and image editing through a spatially enhanced architecture. The model achieves state-of-the-art performance across multiple benchmarks while advancing spatial reasoning capabilities, positioning unified visual models as promising infrastructure for future applications like vision-language-action systems.
AIBullisharXiv – CS AI · May 17/10
🧠Researchers introduce SpatialGrammar, a domain-specific language designed to improve LLM-based 3D indoor scene generation by representing layouts as bird's-eye-view grid placements with compiler validation. The approach, paired with SG-Agent (an iterative refinement system) and SG-Mini (a 104M-parameter model), significantly reduces spatial errors and collision issues that plague existing natural language-to-3D scene generation methods.
AIBearisharXiv – CS AI · Apr 207/10
🧠Researchers found that Chain-of-Thought prompting, a technique that improves logical reasoning in multimodal AI models, actually degrades performance on visual spatial tasks. The study evaluated seventeen models across thirteen benchmarks and discovered these systems suffer from shortcut learning, hallucinating visual details from text even when images are absent, indicating a fundamental limitation in current AI reasoning paradigms.
AIBullisharXiv – CS AI · Apr 157/10
🧠Researchers introduce Ariadne, a framework demonstrating that Reinforcement Learning with Verifiable Rewards (RLVR) expands spatial reasoning capabilities in Vision-Language Models beyond their base distribution. Testing on synthetic mazes and real-world navigation benchmarks shows the technique enables models to solve previously unsolvable problems, suggesting genuine capability expansion rather than sampling efficiency.
AIBearisharXiv – CS AI · Apr 147/10
🧠Researchers tested whether large language models develop spatial world models through maze-solving tasks, finding that leading models like Gemini, GPT-4, and Claude struggle with spatial reasoning. Performance varies dramatically (16-86% accuracy) depending on input format, suggesting LLMs lack robust, format-invariant spatial understanding rather than building true internal world models.
🧠 GPT-5🧠 Claude🧠 Gemini
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce LAST, a framework that enhances multimodal large language models' spatial reasoning by integrating specialized vision tools through an interactive sandbox interface. The approach achieves ~20% performance improvements over baseline models and outperforms proprietary closed-source LLMs on spatial reasoning tasks by converting complex tool outputs into consumable hints for language models.
AIBullisharXiv – CS AI · Apr 147/10
🧠Researchers introduce SpatialScore, a comprehensive benchmark with 5K samples across 30 tasks to evaluate multimodal language models' spatial reasoning capabilities. The work includes SpatialCorpus, a 331K-sample training dataset, and SpatialAgent, a multi-agent system with 12 specialized tools, demonstrating significant improvements in spatial intelligence without additional model training.
AIBullisharXiv – CS AI · Mar 177/10
🧠Researchers developed RieMind, a new AI framework that improves spatial reasoning in indoor scenes by 16-50% by separating visual perception from logical reasoning using explicit 3D scene graphs. The system grounds language models in structured geometric representations rather than processing videos end-to-end, achieving significantly better performance on spatial understanding benchmarks.
AIBullisharXiv – CS AI · Mar 117/10
🧠Researchers introduce World2Mind, a training-free spatial intelligence toolkit that enhances foundation models' 3D spatial reasoning capabilities by up to 18%. The system uses 3D reconstruction and cognitive mapping to create structured spatial representations, enabling text-only models to perform complex spatial reasoning tasks.
🧠 GPT-5
AIBullisharXiv – CS AI · Mar 97/10
🧠Researchers introduce BEVLM, a framework that integrates Large Language Models with Bird's-Eye View representations for autonomous driving. The approach improves LLM reasoning accuracy in cross-view driving scenarios by 46% and enhances end-to-end driving performance by 29% in safety-critical situations.
AIBullisharXiv – CS AI · Mar 56/10
🧠Researchers propose PROSPECT, a new AI system that combines semantic understanding with spatial modeling for improved Vision-Language Navigation. The system uses streaming 3D spatial encoding and predictive representation learning to achieve state-of-the-art performance in robot navigation tasks.
AINeutralarXiv – CS AI · Mar 57/10
🧠Researchers introduce SpatialBench, a comprehensive benchmark for evaluating spatial cognition in multimodal large language models (MLLMs). The framework reveals that while MLLMs excel at perceptual grounding, they struggle with symbolic reasoning, causal inference, and planning compared to humans who demonstrate more goal-directed spatial abstraction.
AIBullisharXiv – CS AI · Mar 57/10
🧠Researchers have developed TIGeR, a framework that enhances Vision-Language Models with precise geometric reasoning capabilities for robotics applications. The system enables VLMs to execute centimeter-level accurate computations by integrating external computational tools, moving beyond qualitative spatial reasoning to quantitative precision required for real-world robotic manipulation.
AINeutralarXiv – CS AI · Mar 57/10
🧠Research shows that static word embeddings like GloVe and Word2Vec can recover substantial geographic and temporal information from text co-occurrence patterns alone, challenging assumptions that such capabilities require sophisticated world models in large language models. The study found these simple embeddings could predict city coordinates and historical birth years with high accuracy, suggesting that linear probe recoverability doesn't necessarily indicate advanced internal representations.
AIBullisharXiv – CS AI · Mar 47/103
🧠Researchers developed Unveiler, a robotic manipulation framework that uses object-centric spatial reasoning to retrieve items from cluttered environments. The system achieves up to 97.6% success in simulation by separating high-level spatial reasoning from low-level action execution, and demonstrates zero-shot transfer to real-world scenarios.
AIBearisharXiv – CS AI · Mar 46/103
🧠Researchers introduce SpatialText, a diagnostic framework to test whether large language models can truly reason about spatial relationships or merely rely on linguistic patterns. The study reveals that current AI models fail at egocentric perspective reasoning despite proficiency in basic spatial fact retrieval.
AINeutralarXiv – CS AI · Feb 277/107
🧠Researchers developed Compositional-ARC, a dataset to test AI models' ability to systematically generalize abstract spatial reasoning tasks. A small 5.7M parameter transformer model trained with meta-learning outperformed large language models like GPT-4o and Gemini 2.0 Flash on novel geometric transformation combinations.
AINeutralarXiv – CS AI · 9h ago6/10
🧠Researchers introduce SpatialAct, a benchmark testing whether vision-language models (VLMs) can understand 3D spatial layouts, reason about them coherently, and act upon that reasoning over multiple turns. The study reveals VLMs excel at isolated spatial reasoning tasks but fail to maintain consistent spatial understanding and produce reliable actions when environments change, indicating a significant gap between perception and practical action capabilities.
AINeutralarXiv – CS AI · 9h ago6/10
🧠Researchers propose a framework to evaluate how linguistic structures and contextual features shape Large Language Model behavior in spatial reasoning tasks. The study reveals that topological information provides robust navigation planning, linguistic format effectiveness depends on model size, and semantic errors can critically undermine performance.
