Does Spatial Cognition Emerge in Frontier Models?

• URL: http://arxiv.org/abs/2410.06468v1
• Date: Wed, 9 Oct 2024 01:41:49 GMT
• Title: Does Spatial Cognition Emerge in Frontier Models?
• Authors: Santhosh Kumar Ramakrishnan, Erik Wijmans, Philipp Kraehenbuehl, Vladlen Koltun,
• Abstract summary: We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Results suggest that contemporary frontier models fall short of the spatial intelligence of animals.
• Score: 56.47912101304053
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Not yet. We present SPACE, a benchmark that systematically evaluates spatial cognition in frontier models. Our benchmark builds on decades of research in cognitive science. It evaluates large-scale mapping abilities that are brought to bear when an organism traverses physical environments, smaller-scale reasoning about object shapes and layouts, and cognitive infrastructure such as spatial attention and memory. For many tasks, we instantiate parallel presentations via text and images, allowing us to benchmark both large language models and large multimodal models. Results suggest that contemporary frontier models fall short of the spatial intelligence of animals, performing near chance level on a number of classic tests of animal cognition.

Related papers

• Mind the Gap: Benchmarking Spatial Reasoning in Vision-Language Models [14.442394137843923]
  We present a detailed analysis that first delineates the core elements of spatial reasoning. We then assesses the performance of these models in both synthetic and real-world images.
  arXiv  Detail & Related papers  (2025-03-25T14:34:06Z)
• Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces [34.809309396448654]
  We present a novel video-based visual-spatial intelligence benchmark (VSI-Bench) of over 5,000 question-answer pairs. We find that Multimodal Large Language Models (MLLMs) exhibit competitive - though subhuman - visual-spatial intelligence.
  arXiv  Detail & Related papers  (2024-12-18T18:59:54Z)
• SPHERE: Unveiling Spatial Blind Spots in Vision-Language Models Through Hierarchical Evaluation [7.659514491338669]
  Current vision-language models may grasp basic spatial cues but struggle with the multi-dimensional spatial reasoning necessary for human-like understanding and real-world applications. We develop SPHERE, a hierarchical evaluation framework supported by a new human-annotated dataset. Benchmark evaluation of state-of-the-art models reveals significant deficiencies, especially in reasoning about distance and proximity.
  arXiv  Detail & Related papers  (2024-12-17T09:10:55Z)
• Where Am I and What Will I See: An Auto-Regressive Model for Spatial Localization and View Prediction [60.964512894143475]
  We present Generative Spatial Transformer ( GST), a novel auto-regressive framework that jointly addresses spatial localization and view prediction. Our model simultaneously estimates the camera pose from a single image and predicts the view from a new camera pose, effectively bridging the gap between spatial awareness and visual prediction.
  arXiv  Detail & Related papers  (2024-10-24T17:58:05Z)
• Exploring Spatial Schema Intuitions in Large Language and Vision Models [8.944921398608063]
  We investigate whether large language models (LLMs) effectively capture implicit human intuitions about building blocks of language. Surprisingly, correlations between model outputs and human responses emerge, revealing adaptability without a tangible connection to embodied experiences. This research contributes to a nuanced understanding of the interplay between language, spatial experiences, and computations made by large language models.
  arXiv  Detail & Related papers  (2024-02-01T19:25:50Z)
• Neural feels with neural fields: Visuo-tactile perception for in-hand manipulation [57.60490773016364]
  We combine vision and touch sensing on a multi-fingered hand to estimate an object's pose and shape during in-hand manipulation. Our method, NeuralFeels, encodes object geometry by learning a neural field online and jointly tracks it by optimizing a pose graph problem. Our results demonstrate that touch, at the very least, refines and, at the very best, disambiguates visual estimates during in-hand manipulation.
  arXiv  Detail & Related papers  (2023-12-20T22:36:37Z)
• What's "up" with vision-language models? Investigating their struggle with spatial reasoning [76.2406963762722]
  Three new corpora quantify model comprehension of basic spatial relations. We evaluate 18 vision-language (VL) models, finding that all perform poorly. We conclude by studying causes of this surprising behavior.
  arXiv  Detail & Related papers  (2023-10-30T17:50:15Z)
• Generative Models as a Complex Systems Science: How can we make sense of large language model behavior? [75.79305790453654]
  Coaxing out desired behavior from pretrained models, while avoiding undesirable ones, has redefined NLP. We argue for a systematic effort to decompose language model behavior into categories that explain cross-task performance.
  arXiv  Detail & Related papers  (2023-07-31T22:58:41Z)
• Turning large language models into cognitive models [0.0]
  We show that large language models can be turned into cognitive models. These models offer accurate representations of human behavior, even outperforming traditional cognitive models in two decision-making domains. Taken together, these results suggest that large, pre-trained models can be adapted to become generalist cognitive models.
  arXiv  Detail & Related papers  (2023-06-06T18:00:01Z)
• Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities [54.26896306906937]
  We present OVEN-Wiki, where a model need to link an image onto a Wikipedia entity with respect to a text query. We show that a PaLI-based auto-regressive visual recognition model performs surprisingly well, even on Wikipedia entities that have never been seen during fine-tuning. While PaLI-based models obtain higher overall performance, CLIP-based models are better at recognizing tail entities.
  arXiv  Detail & Related papers  (2023-02-22T05:31:26Z)
• Things not Written in Text: Exploring Spatial Commonsense from Visual Signals [77.46233234061758]
  We investigate whether models with visual signals learn more spatial commonsense than text-based models. We propose a benchmark that focuses on the relative scales of objects, and the positional relationship between people and objects under different actions. We find that image synthesis models are more capable of learning accurate and consistent spatial knowledge than other models.
  arXiv  Detail & Related papers  (2022-03-15T17:02:30Z)
• The Right Spin: Learning Object Motion from Rotation-Compensated Flow Fields [61.664963331203666]
  How humans perceive moving objects is a longstanding research question in computer vision. One approach to the problem is to teach a deep network to model all of these effects. We present a novel probabilistic model to estimate the camera's rotation given the motion field.
  arXiv  Detail & Related papers  (2022-02-28T22:05:09Z)
• Self-supervised Secondary Landmark Detection via 3D Representation Learning [13.157012771922801]
  We present a method to learn the spatial relationship of the primary and secondary landmarks in three dimensional space. This learning can be applied to various multiview settings across diverse organisms, including macaques, flies, and humans.
  arXiv  Detail & Related papers  (2021-10-01T17:15:47Z)
• VisualEchoes: Spatial Image Representation Learning through Echolocation [97.23789910400387]
  Several animal species (e.g., bats, dolphins, and whales) and even visually impaired humans have the remarkable ability to perform echolocation. We propose a novel interaction-based representation learning framework that learns useful visual features via echolocation. Our work opens a new path for representation learning for embodied agents, where supervision comes from interacting with the physical world.
  arXiv  Detail & Related papers  (2020-05-04T16:16:58Z)
• Sparse Graphical Memory for Robust Planning [93.39298821537197]
  We introduce Sparse Graphical Memory (SGM), a new data structure that stores states and feasible transitions in a sparse memory. SGM aggregates states according to a novel two-way consistency objective, adapting classic state aggregation criteria to goal-conditioned RL. We show that SGM significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
  arXiv  Detail & Related papers  (2020-03-13T17:59:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.