Vision Language Models See What You Want but not What You See

• URL: http://arxiv.org/abs/2410.00324v1
• Date: Tue, 1 Oct 2024 01:52:01 GMT
• Title: Vision Language Models See What You Want but not What You See
• Authors: Qingying Gao, Yijiang Li, Haiyun Lyu, Haoran Sun, Dezhi Luo, Hokin Deng,
• Abstract summary: Knowing others' intentions and taking others' perspectives are two core components of human intelligence. In this paper, we investigate intentionality understanding and perspective-taking in Vision Language Models. Surprisingly, we find VLMs achieving high performance on intentionality understanding but lower performance on perspective-taking.
• Score: 9.268588981925234
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowing others' intentions and taking others' perspectives are two core components of human intelligence that are typically considered to be instantiations of theory-of-mind. Infiltrating machines with these abilities is an important step towards building human-level artificial intelligence. Recently, Li et al. built CogDevelop2K, a data-intensive cognitive experiment benchmark to assess the developmental trajectory of machine intelligence. Here, to investigate intentionality understanding and perspective-taking in Vision Language Models, we leverage the IntentBench and PerspectBench of CogDevelop2K, which contains over 300 cognitive experiments grounded in real-world scenarios and classic cognitive tasks, respectively. Surprisingly, we find VLMs achieving high performance on intentionality understanding but lower performance on perspective-taking. This challenges the common belief in cognitive science literature that perspective-taking at the corresponding modality is necessary for intentionality understanding.

Related papers

• Probing Mechanical Reasoning in Large Vision Language Models [9.268588981925234]
  Mechanical reasoning allows us to design tools, build bridges and canals, and construct houses which set the foundation of human civilization. We leverage the MechBench of CogDevelop2K to test understanding of mechanical system stability, gears and pulley systems, seesaw-like systems and leverage principle, inertia and motion.
  arXiv  Detail & Related papers  (2024-10-01T01:33:10Z)
• Visual Knowledge in the Big Model Era: Retrospect and Prospect [63.282425615863]
  Visual knowledge is a new form of knowledge representation that can encapsulate visual concepts and their relations in a succinct, comprehensive, and interpretable manner. As the knowledge about the visual world has been identified as an indispensable component of human cognition and intelligence, visual knowledge is poised to have a pivotal role in establishing machine intelligence.
  arXiv  Detail & Related papers  (2024-04-05T07:31:24Z)
• Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models [83.63242931107638]
  We propose four characteristics of generally intelligent agents. We argue that active engagement with objects in the real world delivers more robust signals for forming conceptual representations. We conclude by outlining promising future research directions in the field of artificial general intelligence.
  arXiv  Detail & Related papers  (2023-07-07T13:58:16Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• Beyond Interpretable Benchmarks: Contextual Learning through Cognitive and Multimodal Perception [0.0]
  This study contends that the Turing Test is misinterpreted as an attempt to anthropomorphize computer systems. It emphasizes tacit learning as a cornerstone of general-purpose intelligence, despite its lack of overt interpretability.
  arXiv  Detail & Related papers  (2022-12-04T08:30:04Z)
• EgoTaskQA: Understanding Human Tasks in Egocentric Videos [89.9573084127155]
  EgoTaskQA benchmark provides home for crucial dimensions of task understanding through question-answering on real-world egocentric videos. We meticulously design questions that target the understanding of (1) action dependencies and effects, (2) intents and goals, and (3) agents' beliefs about others. We evaluate state-of-the-art video reasoning models on our benchmark and show their significant gaps between humans in understanding complex goal-oriented egocentric videos.
  arXiv  Detail & Related papers  (2022-10-08T05:49:05Z)
• A World-Self Model Towards Understanding Intelligence [0.0]
  We will compare human and artificial intelligence, and propose that a certain aspect of human intelligence is the key to connect perception and cognition. We will present the broader idea of "concept", the principles and mathematical frameworks of the new model World-Self Model (WSM) of intelligence, and finally an unified general framework of intelligence based on WSM.
  arXiv  Detail & Related papers  (2022-03-25T16:42:23Z)
• Building Human-like Communicative Intelligence: A Grounded Perspective [1.0152838128195465]
  After making astounding progress in language learning, AI systems seem to approach the ceiling that does not reflect important aspects of human communicative capacities. This paper suggests that the dominant cognitively-inspired AI directions, based on nativist and symbolic paradigms, lack necessary substantiation and concreteness to guide progress in modern AI. I propose a list of concrete, implementable components for building "grounded" linguistic intelligence.
  arXiv  Detail & Related papers  (2022-01-02T01:43:24Z)
• Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning [78.13740873213223]
  Bongard problems (BPs) were introduced as an inspirational challenge for visual cognition in intelligent systems. We propose a new benchmark Bongard-LOGO for human-level concept learning and reasoning.
  arXiv  Detail & Related papers  (2020-10-02T03:19:46Z)
• Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense [142.53911271465344]
  We argue that the next generation of AI must embrace "dark" humanlike common sense for solving novel tasks. We identify functionality, physics, intent, causality, and utility (FPICU) as the five core domains of cognitive AI with humanlike common sense.
  arXiv  Detail & Related papers  (2020-04-20T04:07:28Z)

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.