REFINER: Reasoning Feedback on Intermediate Representations

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

The recent advance of large language models (LLMs) demonstrates that these large-scale foundation models achieve remarkable capabilities across a wide range of language tasks and domains. The success of the statistical learning approach challenges our unde ...

A critical component of a successful language generation pipeline is the decoding algorithm. However, the general principles that should guide the choice of a decoding algorithm re- main unclear. Previous works only compare decoding algorithms in narrow sc ...

Artificial intelligence and machine learning algorithms have become ubiquitous. Although they offer a wide range of benefits, their adoption in decision-critical fields is limited by their lack of interpretability, particularly with textual data. Moreover, ...

Gas path fault diagnosis of a gas turbine is a complex task involving field data analysis and knowledge-based reasoning. In this paper, a data-knowledge hybrid driven method for gas path fault diagnosis is proposed by integrating a physical model-based gas ...

With the increasing complexity of engineered systems, digital twins (DTs) have been widely used to support integrated modeling, simulation, and decision-making of the system of systems (SoS). However, when integrating DTs of each constituent system, it is ...

One of the challenges faced by conversational agents is their inability to identify unstated presumptions of their users' commands, a task trivial for humans due to their common sense. In this paper, we propose a zeroshot commonsense reasoning system for c ...

Inductive reasoning is an important educational practice but can be difficult for teachers to support in the classroom due to the high level of preparation and classroom time needed to choose the teaching materials that challenge students' current views. I ...

Facial attributes are important since they provide a detailed description and determine the visual appearance of human faces. In this paper, we aim at converting a face image to a sketch while simultaneously generating facial attributes. To this end, we pr ...

Decision making and planning with partial state information is a problem faced by all forms of intelligent entities. The formulation of a problem under partial state information leads to an exorbitant set of choices with associated probabilistic outcomes m ...

Purpose - IEEE Ontologies for Robotics and Automation Working Group were divided into subgroups that were in charge of studying industrial robotics, service robotics and autonomous robotics. This paper aims to present the work in-progress developed by the ...

Satisfiability modulo theory solvers are increasingly being used to solve quantified formulas over structures such as integers and term algebras. Quantifier instantiation combined with ground decision procedure alone is insufficient to prove many formulas ...

We propose two expressive and complementary techniques for the verification of safety properties of infinite-state BIP models. Both our techniques deal with the full BIP specification, while the existing approaches impose con- siderable restrictions: they ...

Historical knowledge is fundamentally uncertain. A given account of an historical event is typically based on a series of sources and on sequences of interpretation and reasoning based on these sources. Generally, the product of this historical research ta ...

Today, enterprise applications provide large amounts of data and finding the right information on time for a given purpose is often a challenge. In these environments, users do not know what information is important, why it is important and finally, how to ...

Decision procedures are widely used in software development and verification. The goal of this dissertation is to increase the scope of properties that can be verified using decision procedures. To achieve this goal, we identify three improvements over the ...

A major obstacle to the development of ontologies in support of the Semantic Web is the poor capability of current ontology techniques to handle very large ontologies, in particular regarding scalability of reasoners. This paper builds on the assumption th ...

This thesis describes a successful application of advanced computational methods to tasks in the field of active structural control. The control-task involves finding good control movements for a highly coupled, non-linear structure. It is demonstrated how ...

REFINER: Reasoning Feedback on Intermediate Representations

Chat with Graph Search

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Monotonicity Reasoning in the Age of Neural Foundation Models

Language Model Decoding as Likelihood–Utility Alignment

Textual Explanations and Critiques in Recommendation Systems

A Data-Knowledge Hybrid Driven Method for Gas Turbine Gas Path Diagnosis

Cognitive twin construction for system of systems operation based on semantic integration and high-level architecture

Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules

A Bayesian Model of Individual Differences and Flexibility in Inductive Reasoning for Categorization of Examples

Attribute-Guided Sketch Generation

Learning Search Strategies from Human Demonstrations

Requirements for building an ontology for autonomous robots

Induction for SMT Solvers

Formal verification of infinite-state BIP models

Encoding metaknowledge for historical databases

Ontology-based approach for context modeling in enterprise applications

Decision Procedures for Program Synthesis and Verification

Reasoning with large ontologies stored in relational databases: The OntoMinD approach

Performance enhancement of active structures during service lives