Copertina

UniBERT: Adversarial Training for Language-Universal Representations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Avram, Andrei-Marius, Lupaşcu, Marian, Cercel, Dumitru-Clementin, Mironică, Ionuţ, Trăuşan-Matu, Ştefan
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

RoQLlama: A Lightweight Romanian Adapted Language Model
di: Dima, George-Andrei, et al.
Pubblicazione: (2024)

MoRoVoc: A Large Dataset for Geographical Variation Identification of the Spoken Romanian Language
di: Avram, Andrei-Marius, et al.
Pubblicazione: (2025)

Parameter Efficient Multimodal Instruction Tuning for Romanian Vision Language Models
di: Dima, George-Andrei, et al.
Pubblicazione: (2025)

RoIt-XMASA: Multi-Domain Multilingual Sentiment Analysis Dataset for Romanian and Italian
di: Avram, Andrei-Marius, et al.
Pubblicazione: (2026)

Investigating the Impact of Semi-Supervised Methods with Data Augmentation on Offensive Language Detection in Romanian Language
di: Nicola, Elena-Beatrice, et al.
Pubblicazione: (2024)

RoLegalGEC: Legal Domain Grammatical Error Detection and Correction Dataset for Romanian
di: Timpuriu, Mircea, et al.
Pubblicazione: (2026)

RoLargeSum: A Large Dialect-Aware Romanian News Dataset for Summary, Headline, and Keyword Generation
di: Avram, Andrei-Marius, et al.
Pubblicazione: (2024)

Neural Contrast: Leveraging Generative Editing for Graphic Design Recommendations
di: Lupascu, Marian, et al.
Pubblicazione: (2024)

Enhancing Romanian Offensive Language Detection through Knowledge Distillation, Multi-Task Learning, and Data Augmentation
di: Matei, Vlad-Cristian, et al.
Pubblicazione: (2024)

MuSaRoNews: A Multidomain, Multimodal Satire Dataset from Romanian News Articles
di: Smădu, Răzvan-Alexandru, et al.
Pubblicazione: (2025)

A Fast Text-Driven Approach for Generating Artistic Content
di: Lupascu, Marian, et al.
Pubblicazione: (2022)

GRAF: Graph Retrieval Augmented by Facts for Romanian Legal Multi-Choice Question Answering
di: Crăciun, Cristian-George, et al.
Pubblicazione: (2024)

Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups
di: Smădu, Răzvan-Alexandru, et al.
Pubblicazione: (2024)

Multimodal Learning with Augmentation Techniques for Natural Disaster Assessment
di: Urse, Adrian-Dinu, et al.
Pubblicazione: (2025)

Scaling Federated Learning Solutions with Kubernetes for Synthesizing Histopathology Images
di: Preda, Andrei-Alexandru, et al.
Pubblicazione: (2025)

Explainability-Driven Leaf Disease Classification Using Adversarial Training and Knowledge Distillation
di: Echim, Sebastian-Vasile, et al.
Pubblicazione: (2023)

RoD-TAL: A Benchmark for Answering Questions in Romanian Driving License Exams
di: Man, Andrei Vlad, et al.
Pubblicazione: (2025)

SaRoHead: Detecting Satire in a Multi-Domain Romanian News Headline Dataset
di: Vîrlan, Mihnea-Alexandru, et al.
Pubblicazione: (2025)

A Cross-Lingual Meta-Learning Method Based on Domain Adaptation for Speech Emotion Recognition
di: Ion, David-Gabriel, et al.
Pubblicazione: (2024)

HistNERo: Historical Named Entity Recognition for the Romanian Language
di: Avram, Andrei-Marius, et al.
Pubblicazione: (2024)

SeLeRoSa: Sentence-Level Romanian Satire Detection Dataset
di: Smădu, Răzvan-Alexandru, et al.
Pubblicazione: (2025)

IGAff: Benchmarking Adversarial Iterative and Genetic Affine Algorithms on Deep Neural Networks
di: Echim, Sebastian-Vasile, et al.
Pubblicazione: (2025)

Deep learning for music generation. Four approaches and their comparative evaluation
di: Paroiu, Razvan, et al.
Pubblicazione: (2025)

Air Pollution Forecasting in Bucharest
di: Şerban, Dragoş-Andrei, et al.
Pubblicazione: (2025)

MultiMatch: Multihead Consistency Regularization Matching for Semi-Supervised Text Classification
di: Sirbu, Iustin, et al.
Pubblicazione: (2025)

RoCoISLR: A Romanian Corpus for Isolated Sign Language Recognition
di: Rîpanu, Cătălin-Alexandru, et al.
Pubblicazione: (2025)

Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification
di: Gheorghiu, Adrian, et al.
Pubblicazione: (2024)

RELATE: A Modern Processing Platform for Romanian Language
di: Păiş, Vasile, et al.
Pubblicazione: (2024)

Language Detection by Means of the Minkowski Norm: Identification Through Character Bigrams and Frequency Analysis
di: Pogăcean, Paul-Andrei, et al.
Pubblicazione: (2025)

Large Multimodal Models for Low-Resource Languages: A Survey
di: Lupascu, Marian, et al.
Pubblicazione: (2025)

Unified Scaling Laws for Compressed Representations
di: Panferov, Andrei, et al.
Pubblicazione: (2025)

Healing Powers of BERT: How Task-Specific Fine-Tuning Recovers Corrupted Language Models
di: Han, Shijie, et al.
Pubblicazione: (2024)

CultureBERT: Measuring Corporate Culture With Transformer-Based Language Models
di: Koch, Sebastian, et al.
Pubblicazione: (2022)

RoBiologyDataChoiceQA: A Romanian Dataset for improving Biology understanding of Large Language Models
di: Ghinea, Dragos-Dumitru, et al.
Pubblicazione: (2025)

Symmetric Dot-Product Attention for Efficient Training of BERT Language Models
di: Courtois, Martin, et al.
Pubblicazione: (2024)

PairUni: Pairwise Training for Unified Multimodal Language Models
di: Zheng, Jiani, et al.
Pubblicazione: (2025)

Arabic Synonym BERT-based Adversarial Examples for Text Classification
di: Alshahrani, Norah, et al.
Pubblicazione: (2024)

LaDe: Unified Multi-Layered Graphic Media Generation and Decomposition
di: Lungu-Stan, Vlad-Constantin, et al.
Pubblicazione: (2026)

MaxPoolBERT: Enhancing BERT Classification via Layer- and Token-Wise Aggregation
di: Behrendt, Maike, et al.
Pubblicazione: (2025)

LLMic: Romanian Foundation Language Model
di: Bădoiu, Vlad-Andrei, et al.
Pubblicazione: (2025)