English
Related papers

Related papers: ORCHARD: A Benchmark For Measuring Systematic Gene…

200 papers

Robots frequently face complex tasks that require more than one action, where sequential decision-making (SDM) capabilities become necessary. The key contribution of this work is a robot SDM framework, called LCORPP, that supports the…

Artificial Intelligence · Computer Science 2019-12-11 Saeid Amiri , Mohammad Shokrolah Shirazi , Shiqi Zhang

Transformers have been shown to be able to perform deductive reasoning on a logical rulebase containing rules and statements written in English natural language. While the progress is promising, it is currently unclear if these models…

Computation and Language · Computer Science 2022-11-09 Soumya Sanyal , Zeyi Liao , Xiang Ren

Many classical and learning-based optical flow methods rely on hierarchical concepts to improve both accuracy and robustness. However, one of the currently most successful approaches -- RAFT -- hardly exploits such concepts. In this work,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Azin Jahedi , Lukas Mehl , Marc Rivinius , Andrés Bruhn

We propose a novel method for hierarchical entity classification that embraces ontological structure at both training and during prediction. At training, our novel multi-level learning-to-rank loss compares positive types against negative…

Computation and Language · Computer Science 2020-04-07 Tongfei Chen , Yunmo Chen , Benjamin Van Durme

Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist to evaluate compositional generalization, when it comes to…

Artificial Intelligence · Computer Science 2022-04-12 Santiago Ontanon , Joshua Ainslie , Vaclav Cvicek , Zachary Fisher

Modern highly-concurrent search data structures, such as search trees, obtain multi-core scalability and performance by having operations traverse the data structure without any synchronization. As a result, however, these algorithms are…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-01-12 Yotam M. Y. Feldman , Artem Khyzha , Constantin Enea , Adam Morrison , Aleksandar Nanevski , Noam Rinetzky , Sharon Shoham

Language models based on the Transformer architecture achieve excellent results in many language-related tasks, such as text classification or sentiment analysis. However, despite the architecture of these models being well-defined, little…

Computation and Language · Computer Science 2025-04-14 Miguel López-Otal , Jorge Gracia , Jordi Bernad , Carlos Bobed , Lucía Pitarch-Ballesteros , Emma Anglés-Herrero

Transformer-based large language models (LLM) have been widely used in language processing applications. However, due to the memory constraints of the devices, most of them restrict the context window. Even though recurrent models in…

Computation and Language · Computer Science 2025-02-07 Zifan He , Yingqi Cao , Zongyue Qin , Neha Prakriya , Yizhou Sun , Jason Cong

We present ACCORD, a framework and benchmark suite for disentangling the commonsense grounding and reasoning abilities of large language models (LLMs) through controlled, multi-hop counterfactuals. ACCORD introduces formal elements to…

Artificial Intelligence · Computer Science 2025-02-10 François Roewer-Després , Jinyue Feng , Zining Zhu , Frank Rudzicz

Neural network architectures have been augmented with differentiable stacks in order to introduce a bias toward learning hierarchy-sensitive regularities. It has, however, proven difficult to assess the degree to which such a bias is…

Computation and Language · Computer Science 2019-06-05 William Merrill , Lenny Khazan , Noah Amsel , Yiding Hao , Simon Mendelsohn , Robert Frank

Standard Transformers excel at semantic modeling but struggle with rigid sequential logic and state tracking. Theoretical work establishes that self-attention is limited to $\AC^0$ (under hard attention) or $\TC^0$ (under soft attention),…

Machine Learning · Computer Science 2026-02-10 Mehryar Mohri

Extracting abstract causal structures and applying them to novel situations is a hallmark of human intelligence. While Large Language Models (LLMs) and Vision Language Models (VLMs) have shown strong performance on a wide range of reasoning…

Artificial Intelligence · Computer Science 2026-04-28 Liangru Xiang , Yuxi Ma , Zhihao Cao , Yixin Zhu , Song-Chun Zhu

We consider multi-class classification where the predictor has a hierarchical structure that allows for a very large number of labels both at train and test time. The predictive power of such models can heavily depend on the structure of…

Machine Learning · Statistics 2017-03-06 Yacine Jernite , Anna Choromanska , David Sontag

The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradigm, reliant on end-to-end generation or explicit,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-11 Yiming Zhang , Qiangyu Yan , Borui Jiang , Kai Han

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the…

Machine Learning · Computer Science 2025-05-29 Zachary Shinnick , Liangze Jiang , Hemanth Saratchandran , Anton van den Hengel , Damien Teney

Recurrent neural networks (RNNs) have long been an architecture of interest for computational models of human sentence processing. The recently introduced Transformer architecture outperforms RNNs on many natural language processing tasks…

Computation and Language · Computer Science 2022-03-31 Danny Merkx , Stefan L. Frank

Latent tree learning models learn to parse a sentence without syntactic supervision, and use that parse to build the sentence representation. Existing work on such models has shown that, while they perform well on tasks like sentence…

Computation and Language · Computer Science 2018-04-18 Nikita Nangia , Samuel R. Bowman

Recent work in NLP shows that LSTM language models capture hierarchical structure in language data. In contrast to existing work, we consider the \textit{learning} process that leads to their compositional behavior. For a closer look at how…

Computation and Language · Computer Science 2020-10-12 Naomi Saphra , Adam Lopez

Compositional generalization remains a foundational weakness of modern neural networks, limiting their robustness and applicability in domains requiring out-of-distribution reasoning. A central, yet unverified, assumption in neuro-symbolic…

Artificial Intelligence · Computer Science 2026-04-30 Mahnoor Shahid , Hannes Rothe

In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all…

Neural and Evolutionary Computing · Computer Science 2016-05-03 Rohollah Soltani , Hui Jiang