中文
相关论文

相关论文: Infusing Lattice Symmetry Priors in Attention Mech…

200 篇论文

The Abstraction and Reasoning Corpus (ARC) poses a stringent test of general AI capabilities, requiring solvers to infer abstract patterns from only a handful of examples. Despite substantial progress in deep learning, state-of-the-art…

人工智能 · 计算机科学 2025-05-28 Woochang Sim , Hyunseok Ryu , Kyungmin Choi , Sungwon Han , Sundong Kim

Can a Large Language Model (LLM) solve simple abstract reasoning problems? We explore this broad question through a systematic analysis of GPT on the Abstraction and Reasoning Corpus (ARC), a representative benchmark of abstract reasoning…

计算与语言 · 计算机科学 2024-02-16 Yudong Xu , Wenhao Li , Pashootan Vaezipoor , Scott Sanner , Elias B. Khalil

The Abstraction and Reasoning Corpus (ARC) is a popular benchmark focused on visual reasoning in the evaluation of Artificial Intelligence systems. In its original framing, an ARC task requires solving a program synthesis problem over small…

计算机视觉与模式识别 · 计算机科学 2025-07-17 Wenhao Li , Yudong Xu , Scott Sanner , Elias Boutros Khalil

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

计算与语言 · 计算机科学 2019-06-05 Matthias Sperber , Graham Neubig , Ngoc-Quan Pham , Alex Waibel

The attention mechanism is the computational core of modern Transformer architectures, but its quadratic complexity in the input sequence length is the bottleneck for large-scale inference. This has motivated a rapidly growing body of work…

The Abstraction and Reasoning Corpus (ARC) is designed to assess generalization beyond pattern matching, requiring models to infer symbolic rules from very few examples. In this work, we present a transformer-based system that advances ARC…

The Abstraction and Reasoning Corpus (ARC) is designed to promote research on abstract reasoning, a fundamental aspect of human intelligence. Common approaches to ARC treat it as a language-oriented problem, addressed by large language…

计算机视觉与模式识别 · 计算机科学 2025-11-19 Keya Hu , Ali Cy , Linlu Qiu , Xiaoman Delores Ding , Runqian Wang , Yeyin Eva Zhu , Jacob Andreas , Kaiming He

Transformers have proven highly effective across modalities, but standard softmax attention scales quadratically with sequence length, limiting long context modeling. Linear attention mitigates this by approximating attention with kernel…

机器学习 · 计算机科学 2026-02-10 Ashkan Shahbazi , Chayne Thrash , Yikun Bai , Keaton Hamm , Navid NaderiAlizadeh , Soheil Kolouri

Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. This conventional approach treats tokens…

计算机视觉与模式识别 · 计算机科学 2025-10-07 Lixuan He , Shikang Zheng , Linfeng Zhang

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

The Abstraction and Reasoning Corpus (ARC) is a general artificial intelligence benchmark that poses difficulties for pure machine learning methods due to its requirement for fluid intelligence with a focus on reasoning and abstraction. In…

人工智能 · 计算机科学 2024-01-17 Chao Lei , Nir Lipovetzky , Krista A. Ehinger

Large Language Models (LLMs) tend to generate a long reasoning chain when solving complex tasks. However, as the reasoning chain extends, critical intermediate steps and the original prompt will be buried in the context, receiving…

计算与语言 · 计算机科学 2026-03-30 Hongxiang Zhang , Yuan Tian , Tianyi Zhang

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

MANAR (Memory-augmented Attention with Navigational Abstract Conceptual Representation), contextualization layer generalizes standard multi-head attention (MHA) by instantiating the principles of Global Workspace Theory (GWT). While MHA…

人工智能 · 计算机科学 2026-03-20 Zuher Jahshan , Ben Ben Ishay , Leonid Yavits

In the context of online education, designing an automatic solver for geometric problems has been considered a crucial step towards general math Artificial Intelligence (AI), empowered by natural language understanding and traditional…

计算机与社会 · 计算机科学 2024-03-25 Xiuqin Zhong , Shengyuan Yan , Gongqi Lin , Hongguang Fu , Liang Xu , Siwen Jiang , Lei Huang , Wei Fang

Recent advancements in Large Language Models (LLMs) have generated growing interest in their structured reasoning capabilities, particularly in tasks involving abstraction and pattern recognition. The Abstraction and Reasoning Corpus (ARC)…

人工智能 · 计算机科学 2025-04-25 Nikhil Khandalkar , Pavan Yadav , Krishna Shinde , Lokesh B. Ramegowda , Rajarshi Das

Recent advances in sequence modeling have highlighted the strengths of the transformer architecture, especially in achieving state-of-the-art machine translation results. However, depending on the up-stream systems, e.g., speech…

计算与语言 · 计算机科学 2019-06-14 Pei Zhang , Boxing Chen , Niyu Ge , Kai Fan

Most state-of-the-art techniques for Language Models (LMs) today rely on transformer-based architectures and their ubiquitous attention mechanism. However, the exponential growth in computational requirements with longer input sequences…

计算与语言 · 计算机科学 2024-11-26 Kaustubh Ponkshe , Venkatapathy Subramanian , Natwar Modani , Ganesh Ramakrishnan

The Transformer architecture has become a cornerstone of modern artificial intelligence, but its core self-attention mechanism suffers from a complexity bottleneck that scales quadratically with sequence length, severely limiting its…

机器学习 · 计算机科学 2025-08-29 Zhongpan Tang

While artificial intelligence (AI) models have achieved human or even superhuman performance in many well-defined applications, they still struggle to show signs of broad and flexible intelligence. The Abstraction and Reasoning Corpus…

人工智能 · 计算机科学 2023-06-23 Giacomo Camposampiero , Loic Houmard , Benjamin Estermann , Joël Mathys , Roger Wattenhofer
‹ 上一页 1 2 3 10 下一页 ›