中文
相关论文

相关论文: Towards Generative Abstract Reasoning: Completing …

200 篇论文

Research on emergent communication between deep-learning-based agents has received extensive attention due to its inspiration for linguistics and artificial intelligence. However, previous attempts have hovered around emerging communication…

How should future neural reasoning systems implement extended computation? Recursive Reasoning Models (RRMs) offer a promising alternative to autoregressive sequence extension by performing iterative latent-state refinement with shared…

人工智能 · 计算机科学 2026-05-21 Junyeob Baek , Mingyu Jo , Minsu Kim , Mengye Ren , Yoshua Bengio , Sungjin Ahn

We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting…

The ability to hypothesise, develop abstract concepts based on concrete observations and apply these hypotheses to justify future actions has been paramount in human development. An existing line of research in outfitting intelligent…

人工智能 · 计算机科学 2021-08-06 Nicholas Quek Wei Kiat , Duo Wang , Mateja Jamnik

Raven's Progressive Matrices are a benchmark originally designed to test the cognitive abilities of humans. It has recently been adapted to test relational reasoning in machine learning systems. For this purpose the so-called Procedurally…

机器学习 · 计算机科学 2020-03-27 Marius Jahrens , Thomas Martinetz

While generative video models have achieved remarkable visual fidelity, their capacity to internalize and reason over implicit world rules remains a critical yet under-explored frontier. To bridge this gap, we present RISE-Video, a…

计算机视觉与模式识别 · 计算机科学 2026-02-06 Mingxin Liu , Shuran Ma , Shibei Meng , Xiangyu Zhao , Zicheng Zhang , Shaofeng Zhang , Zhihang Zhong , Peixian Chen , Haoyu Cao , Xing Sun , Haodong Duan , Xue Yang

In abstract visual reasoning, monolithic deep learning models suffer from limited interpretability and generalization, while existing neuro-symbolic approaches fall short in capturing the diversity and systematicity of attributes and…

人工智能 · 计算机科学 2025-01-23 Zhong-Hua Sun , Ru-Yuan Zhang , Zonglei Zhen , Da-Hui Wang , Yong-Jie Li , Xiaohong Wan , Hongzhi You

This paper thoroughly investigates the challenges of enhancing AI's abstract reasoning capabilities, with a particular focus on Raven's Progressive Matrices (RPM) tasks involving complex human-like concepts. Firstly, it dissects the…

机器学习 · 计算机科学 2025-06-04 Ruizhuo Song , Beiming Yuan

We develop a behavioural theory of reflective parallel algorithms (RAs), i.e. synchronous parallel algorithms that can modify their own behaviour. The theory comprises a set of postulates defining the class of RAs, an abstract machine…

计算机科学中的逻辑 · 计算机科学 2025-08-13 Klaus-Dieter Schewe , Flavio Ferrarotti

Humans excel at discovering regular structures from limited samples and applying inferred rules to novel settings. We investigate whether modern generative models can similarly learn underlying rules from finite samples and perform…

机器学习 · 计算机科学 2024-11-13 Binxu Wang , Jiaqi Shang , Haim Sompolinsky

We introduce the Neural State Machine, seeking to bridge the gap between the neural and symbolic views of AI and integrate their complementary strengths for the task of visual reasoning. Given an image, we first predict a probabilistic…

人工智能 · 计算机科学 2019-11-26 Drew A. Hudson , Christopher D. Manning

Abstract reasoning ability reflects the intelligence and generalization capacity of LLMs to extract and apply abstract rules. However, accurately measuring this ability remains challenging: existing benchmarks either rely on expensive…

人工智能 · 计算机科学 2026-05-19 Qingchuan Ma , Yuexiao Ma , Yongkang Xie , Tianyu Xie , Xiawu Zheng , Rongrong Ji

A Retrieval-Augmented Generation (RAG) model powered by a large language model (LLM) provides a faster and more cost-effective solution for adapting to new data and knowledge. It also delivers more specialized responses compared to…

计算与语言 · 计算机科学 2025-01-29 Zheng Zheng , Xinyi Ni , Pengyu Hong

Deep neural networks are being used increasingly to automate data analysis and decision making, yet their decision-making process is largely unclear and is difficult to explain to the end users. In this paper, we address the problem of…

计算机视觉与模式识别 · 计算机科学 2018-09-27 Vitali Petsiuk , Abir Das , Kate Saenko

Recent text-to-image (T2I) diffusion models achieve remarkable realism, yet faithful prompt-image alignment remains challenging, particularly for complex prompts with multiple objects, relations, and fine-grained attributes. Existing…

计算机视觉与模式识别 · 计算机科学 2026-03-03 Liyao Jiang , Ruichen Chen , Chao Gao , Di Niu

In this work we explore the generalization characteristics of unsupervised representation learning by leveraging disentangled VAE's to learn a useful latent space on a set of relational reasoning problems derived from Raven Progressive…

机器学习 · 计算机科学 2018-11-13 Xander Steenbrugge , Sam Leroux , Tim Verbelen , Bart Dhoedt

Learning abstractions directly from data is a core challenge in robotics. Humans naturally operate at an abstract level, reasoning over high-level subgoals while delegating execution to low-level motor skills -- an ability that enables…

机器人学 · 计算机科学 2026-03-23 Abhiroop Ajith , Constantinos Chamzas

Despite the growing reasoning capabilities of recent large language models (LLMs), their internal mechanisms during the reasoning process remain underexplored. Prior approaches often rely on human-defined concepts (e.g., overthinking,…

计算与语言 · 计算机科学 2026-01-01 Zhenyu Zhang , Shujian Zhang , John Lambert , Wenxuan Zhou , Zhangyang Wang , Mingqing Chen , Andrew Hard , Rajiv Mathews , Lun Wang

The Abstract Meaning Representation (AMR) is a representation for open-domain rich semantics, with potential use in fields like event extraction and machine translation. Node generation, typically done using a simple dictionary lookup, is…

计算与语言 · 计算机科学 2015-06-11 Keenon Werling , Gabor Angeli , Christopher Manning

"Thinking in pictures," [1] i.e., spatial-temporal reasoning, effortless and instantaneous for humans, is believed to be a significant ability to perform logical induction and a crucial factor in the intellectual history of technology…

计算机视觉与模式识别 · 计算机科学 2019-12-03 Chi Zhang , Baoxiong Jia , Feng Gao , Yixin Zhu , Hongjing Lu , Song-Chun Zhu