Alert button
Picture for Adrian Łańcucki

Adrian Łańcucki

Alert button

Dynamic Memory Compression: Retrofitting LLMs for Accelerated Inference

Mar 14, 2024
Piotr Nawrot, Adrian Łańcucki, Marcin Chochowski, David Tarjan, Edoardo M. Ponti

Viaarxiv icon

Efficient Transformers with Dynamic Token Pooling

Nov 17, 2022
Piotr Nawrot, Jan Chorowski, Adrian Łańcucki, Edoardo M. Ponti

Figure 1 for Efficient Transformers with Dynamic Token Pooling
Figure 2 for Efficient Transformers with Dynamic Token Pooling
Figure 3 for Efficient Transformers with Dynamic Token Pooling
Figure 4 for Efficient Transformers with Dynamic Token Pooling
Viaarxiv icon

Variable-rate hierarchical CPC leads to acoustic unit discovery in speech

Jun 07, 2022
Santiago Cuervo, Adrian Łańcucki, Ricard Marxer, Paweł Rychlikowski, Jan Chorowski

Figure 1 for Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
Figure 2 for Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
Figure 3 for Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
Figure 4 for Variable-rate hierarchical CPC leads to acoustic unit discovery in speech
Viaarxiv icon

Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words

Oct 29, 2021
Santiago Cuervo, Maciej Grabias, Jan Chorowski, Grzegorz Ciesielski, Adrian Łańcucki, Paweł Rychlikowski, Ricard Marxer

Figure 1 for Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
Figure 2 for Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
Figure 3 for Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
Figure 4 for Contrastive prediction strategies for unsupervised segmentation and categorization of phonemes and words
Viaarxiv icon

Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw

Jun 22, 2021
Jan Chorowski, Grzegorz Ciesielski, Jarosław Dzikowski, Adrian Łańcucki, Ricard Marxer, Mateusz Opala, Piotr Pusz, Paweł Rychlikowski, Michał Stypułkowski

Figure 1 for Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Figure 2 for Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Figure 3 for Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Figure 4 for Information Retrieval for ZeroSpeech 2021: The Submission by University of Wroclaw
Viaarxiv icon

Aligned Contrastive Predictive Coding

Apr 29, 2021
Jan Chorowski, Grzegorz Ciesielski, Jarosław Dzikowski, Adrian Łańcucki, Ricard Marxer, Mateusz Opala, Piotr Pusz, Paweł Rychlikowski, Michał Stypułkowski

Figure 1 for Aligned Contrastive Predictive Coding
Figure 2 for Aligned Contrastive Predictive Coding
Figure 3 for Aligned Contrastive Predictive Coding
Figure 4 for Aligned Contrastive Predictive Coding
Viaarxiv icon

Named Entity Recognition and Linking Augmented with Large-Scale Structured Data

Apr 27, 2021
Paweł Rychlikowski, Bartłomiej Najdecki, Adrian Łańcucki, Adam Kaczmarek

Figure 1 for Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
Figure 2 for Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
Figure 3 for Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
Figure 4 for Named Entity Recognition and Linking Augmented with Large-Scale Structured Data
Viaarxiv icon

FastPitch: Parallel Text-to-speech with Pitch Prediction

Jun 11, 2020
Adrian Łańcucki

Figure 1 for FastPitch: Parallel Text-to-speech with Pitch Prediction
Figure 2 for FastPitch: Parallel Text-to-speech with Pitch Prediction
Figure 3 for FastPitch: Parallel Text-to-speech with Pitch Prediction
Figure 4 for FastPitch: Parallel Text-to-speech with Pitch Prediction
Viaarxiv icon

Robust Training of Vector Quantized Bottleneck Models

May 18, 2020
Adrian Łańcucki, Jan Chorowski, Guillaume Sanchez, Ricard Marxer, Nanxin Chen, Hans J. G. A. Dolfing, Sameer Khurana, Tanel Alumäe, Antoine Laurent

Figure 1 for Robust Training of Vector Quantized Bottleneck Models
Figure 2 for Robust Training of Vector Quantized Bottleneck Models
Figure 3 for Robust Training of Vector Quantized Bottleneck Models
Figure 4 for Robust Training of Vector Quantized Bottleneck Models
Viaarxiv icon

A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge

May 21, 2018
Jan Chorowski, Adrian Łańcucki, Szymon Malik, Maciej Pawlikowski, Paweł Rychlikowski, Paweł Zykowski

Figure 1 for A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge
Figure 2 for A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge
Figure 3 for A Talker Ensemble: the University of Wrocław's Entry to the NIPS 2017 Conversational Intelligence Challenge
Viaarxiv icon