相关论文: Generalising unit-refutation completeness and SLUR…

We present a novel unity of logic, viz., a single sequent calculus that embodies classical, intuitionistic and linear logics. Concretely, we define classical linear logic negative (CLL$^-$), a new logic that is classical and linear yet…

The time-series forecasting (TSF) problem is a traditional problem in the field of artificial intelligence. Models such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and GRU (Gate Recurrent Units) have contributed to…

Despite the success of convolution- and attention-based models in vision tasks, their rigid receptive fields and complex architectures limit their ability to model irregular spatial patterns and hinder interpretability, therefore posing…

A K-theoretic analogue of RSK insertion and Knuth equivalence relations was first introduced in 2006 by Buch, Kresch, Shimozono, Tamvakis, and Yong. The resulting K-Knuth equivalence relations on words and increasing tableaux on [n] has…

Recent advancements in deep models have highlighted the need for intelligent systems that combine continual learning (CL) for knowledge acquisition with machine unlearning (MU) for data removal, forming the Continual Learning-Unlearning…

Reinforcement learning from verifiable rewards (RLVR) has shown strong promise for LLM reasoning, but outcome-based RLVR remains inefficient on hard problems because correct final-answer rollouts are rare and sample-level credit assignment…

This paper evaluates the utility of Rhetorical Structure Theory (RST) trees and relations in discourse coherence evaluation. We show that incorporating silver-standard RST features can increase accuracy when classifying coherence. We…

Supervised learning has traditionally focused on inductive learning by observing labeled examples of a task. In contrast, humans have the ability to learn new concepts from language. Here, we explore training zero-shot classifiers for…

We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent on compositional learning. We propose Tree Stack Memory…

We introduce the "Incremental Implicitly-Refined Classi-fication (IIRC)" setup, an extension to the class incremental learning setup where the incoming batches of classes have two granularity levels. i.e., each sample could have a…

Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models. However, there exists a gap between…

We propose a new calculus SCL(EQ) for first-order logic with equality that only learns non-redundant clauses. Following the idea of CDCL (Conflict Driven Clause Learning) and SCL (Clause Learning from Simple Models) a ground literal model…

The LLM unlearning aims to eliminate the influence of undesirable data without affecting causally unrelated information. This process typically involves using a forget set to remove target information, alongside a retain set to maintain…

ULLER (Unified Language for LEarning and Reasoning) offers a unified first-order logic (FOL) syntax, enabling its knowledge bases to be used directly across a wide range of neurosymbolic systems. The original specification endows this…

In the 1970s Alain Connes identified the appropriate notion of amenabilty for von Neumann algebras, and used it to obtain a deep internal finite dimensional approximation structure for these algebras. This structure is exactly what is…

This paper describes a design that can be used for Explainable AI. The lower level is a nested ensemble of patterns created by self-organisation. The upper level is a hierarchical tree, where nodes are linked through individual concepts, so…

Explainable recommendation systems (RSs) are designed to explicitly uncover the rationale of each recommendation, thereby enhancing the transparency and credibility of RSs. Previous methods often jointly predicted ratings and generated…

Low Rank Approximation is among most fundamental subjects of numerical linear algebra having important applications to various areas of modern computing and %they range from machine learning theory and %neural networks to data mining and…

Recurrent neural networks (RNNs) are a popular choice for modeling sequential data. Modern RNN architectures assume constant time-intervals between observations. However, in many datasets (e.g. medical records) observation times are…

User-defined keyword spotting on a resource-constrained edge device is challenging. However, keywords are often bounded by a maximum keyword length, which has been largely under-leveraged in prior works. Our analysis of keyword-length…