707 citations · 1.7k across the 45 of their papers we have counts for
48 papers
Eagle and Finch: RWKV with Matrix-Valued States and Dynamic Recurrence
Bo Peng, Daniel Goldstein, Quentin Anthony +27
We present Eagle (RWKV-5) and Finch (RWKV-6), sequence models improving upon the RWKV (RWKV-4) architecture. Our architectural design advancements include multi-headed matrix-value…
Personalized Large Language Models
Stanisław Woźniak, Bartłomiej Koptyra, Arkadiusz Janz +2
Large language models (LLMs) have significantly advanced Natural Language Processing (NLP) tasks in recent years. However, their universal nature poses limitations in scenarios req…
Into the Unknown: Self-Learning Large Language Models
Teddy Ferdinan, Jan Kocoń, Przemysław Kazienko
We address the main problem of self-learning LLM: the question of what to learn. We propose a self-learning LLM framework that enables an LLM to independently learn previously unkn…
Scaling Representation Learning from Ubiquitous ECG with State-Space Models
Kleanthis Avramidis, Dominika Kunc, Bartosz Perz +5
Ubiquitous sensing from wearable devices in the wild holds promise for enhancing human well-being, from diagnosing clinical conditions and measuring stress to building adaptive hea…
RWKV: Reinventing RNNs for the Transformer Era
Bo Peng, Eric Alcaide, Quentin Anthony +31
Transformers have revolutionized almost all natural language processing (NLP) tasks but suffer from memory and computational complexity that scales quadratically with sequence leng…
ChatGPT: Jack of all trades, master of none
Jan Kocoń, Igor Cichecki, Oliwier Kaszyca +17
OpenAI has released the Chat Generative Pre-trained Transformer (ChatGPT) and revolutionized the approach in artificial intelligence to human-model interaction. Several publication…
Temporal Network Epistemology: on Reaching Consensus in Real World Setting
Radosław Michalski, Damian Serwata, Mateusz Nurek +3
This work develops the concept of temporal network epistemology model enabling the simulation of the learning process in dynamic networks. The results of the research, conducted on…
Consumer Wearables and Affective Computing for Wellbeing Support
Stanisław Saganowski, Przemysław Kazienko, Maciej Dzieżyc +7
Wearables equipped with pervasive sensors enable us to monitor physiological and behavioral signals in our everyday life. We propose the WellAff system able to recognize affective…
Emotion Recognition Using Wearables: A Systematic Literature Review Work in progress
Stanisław Saganowski, Anna Dutkowiak, Adam Dziadek +6
Wearables like smartwatches or wrist bands equipped with pervasive sensors enable us to monitor our physiological signals. In this study, we address the question whether they can h…
Extracting Aspects Hierarchies using Rhetorical Structure Theory
Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko
We propose a novel approach to generate aspect hierarchies that proved to be consistently correct compared with human-generated hierarchies. We present an unsupervised technique us…
Aspect Detection using Word and Char Embeddings with (Bi)LSTM and CRF
Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko
We proposed a~new accurate aspect extraction method that makes use of both word and character-based embeddings. We have conducted experiments of various models of aspect extraction…
Comprehensive Analysis of Aspect Term Extraction Methods using Various Text Embeddings
Łukasz Augustyniak, Tomasz Kajdanowicz, Przemysław Kazienko
Recently, a variety of model designs and methods have blossomed in the context of the sentiment analysis domain. However, there is still a lack of wide and comprehensive studies of…
FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings
Piotr Bielak, Kamil Tagowski, Maciej Falkiewicz +2
Representation learning on graphs has emerged as a powerful mechanism to automate feature vector generation for downstream machine learning tasks. The advances in representation on…
Probing Limits of Information Spread with Sequential Seeding
Jaroslaw Jankowski, Boleslaw K. Szymanski, Przemyslaw Kazienko +2
We consider here information spread which propagates with certain probability from nodes just activated to their not yet activated neighbors. Diffusion cascades can be triggered by…
Social Networks through the Prism of Cognition
Radosław Michalski, Bolesław K. Szymański, Przemysław Kazienko +3
Human relations are driven by social events-people interact, exchange information, share knowledge and emotions, and gather news from mass media. These events leave traces in human…
Entropy Measures of Human Communication Dynamics
Marcin Kulisiewicz, Przemysław Kazienko, Bolesław K. Szymański +1
Human communication is commonly represented as a temporal social network, and evaluated in terms of its uniqueness. We propose a set of new entropy-based measures for human communi…
Priority Attachment: a Comprehensive Mechanism for Generating Networks
Mikołaj Morzy, Tomasz Kajdanowicz, Przemysław Kazienko +2
We claim that networks are created according to the priority attachment mechanism and we show a simple model which uses the priority attachment to generate both synthetic and close…
Analysis of group evolution prediction in complex networks
Stanisław Saganowski, Piotr Bródka, Michał Koziarski +1
In the world, in which acceptance and the identification with social communities are highly desired, the ability to predict evolution of groups over time appears to be a vital but…
Seeds Buffering for Information Spreading Processes
Jarosław Jankowski, Piotr Bródka, Radosław Michalski +1
Seeding strategies for influence maximization in social networks have been studied for more than a decade. They have mainly relied on the activation of all resources (seeds) simult…
Balancing Speed and Coverage by Sequential Seeding in Complex Networks
Jarosław Jankowski, Piotr Bródka, Przemysław Kazienko +3
Information spreading in complex networks is often modeled as diffusing information with certain probability from nodes that possess it to their neighbors that do not. Information…
WordNet2Vec: Corpora Agnostic Word Vectorization Method
Roman Bartusiak, Łukasz Augustyniak, Tomasz Kajdanowicz +2
A complex nature of big data resources demands new methods for structuring especially for textual content. WordNet is a good knowledge source for comprehensive abstraction of natur…
Community Evolution
Stanisław Saganowski, Piotr Bródka, Przemysław Kazienko
The continuous interest in the social network area contributes to the fast development of this field. The new possibilities of obtaining and storing data facilitate deeper analysis…
Learning in Unlabeled Networks - An Active Learning and Inference Approach
Tomasz Kajdanowicz, Radosław Michalski, Katarzyna Musiał +1
The task of determining labels of all network nodes based on the knowledge about network structure and labels of some training subset of nodes is called the within-network classifi…
Knowledge Acquisition from Social Platforms Based on Network Distributions Fitting
Jarosław Jankowski, Radosław Michalski, Piotr Bródka +2
The uniqueness of online social networks makes it possible to implement new methods that increase the quality and effectiveness of research processes. While surveys are one of the…