Related papers: TeXmacs-Reduce interface
Low-light image enhancement is challenging due to complex degradations, including amplified noise, artifacts, and color distortion. While Retinex-based deep learning methods have achieved promising results, they primarily rely on…
Although widely adopted, existing approaches for fine-tuning pre-trained language models have been shown to be unstable across hyper-parameter settings, motivating recent work on trust region methods. In this paper, we present a simplified…
AI agents that interact with graphical user interfaces (GUIs) require effective observation representations for reliable grounding. The accessibility tree is a commonly used text-based format that encodes UI element attributes, but it…
In this work, we study 'reduction monads', which are essentially the same as monads relative to the free functor from sets into multigraphs. Reduction monads account for two aspects of the lambda calculus: on the one hand, in the monadic…
This volume contains a final and revised selection of papers presented at Twelfth Workshop on Developments in Computational Models (DCM 2018) and the Ninth Workshop on Intersection Types and Related Systems (ITRS 2018), held on July 8, 2018…
This paper describes work performed withing the CRATER ({\em C}orpus {\em R}esources {\em A}nd {\em T}erminology {\em E}xt{\em R}action, MLAP-93/20) project, funded by the Commission of the European Communities. In particular, it addresses…
Motion forecasts of road users (i.e., agents) vary in complexity depending on the number of agents, scene constraints, and interactions. In particular, the output space of joint trajectory distributions grows exponentially with the number…
Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos…
We report on improvements to ACL2 made since the 2013 ACL2 Workshop.
RecBole has recently attracted increasing attention from the research community. As the increase of the number of users, we have received a number of suggestions and update requests. This motivates us to make some significant improvements…
This tutorial (https://tum-nlp.github.io/low-resource-tutorial) is designed for NLP practitioners, researchers, and developers working with multilingual and low-resource languages who seek to create more equitable and socially impactful…
To facilitate high quality interaction during the regular use of computing systems, it is essential that the user interface (UI) deliver content and components in an appropriate manner. Although extended reality (XR) is emerging as a new…
These are the revised versions of the papers presented at CICLOPS 2011, a workshop colocated with ICLP 2011.
Over the last two decades, significant advances have been made in the design and analysis of fixed-parameter algorithms for a wide variety of graph-theoretic problems. This has resulted in an algorithmic toolbox that is by now…
PLACES 2012 (full title: Programming Language Approaches to Concurrency- and Communication-Centric Software) is the fifth edition of the PLACES workshop series. After the first PLACES, which was affiliated to DisCoTec in 2008, the workshop…
We review a range of reduction methods that have been, or may be useful for connecting models of the Earth's climate system of differing complexity. We particularly focus on methods where rigorous reduction is possible. We aim to highlight…
We are proud to present the papers from the 17th Refinement Workshop, co-located with FM 2015 held in Oslo, Norway on June 22nd, 2015. Refinement is one of the cornerstones of a formal approach to software engineering: the process of…
High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG-INSTRUCT, a novel framework that enhances instruction…
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel method that operates on the hidden representations of a PLM to…
Large language model editing methods frequently suffer from overfitting, wherein factual updates can propagate beyond their intended scope, overemphasizing the edited target even when it's contextually inappropriate. To address this…