Resultados de búsqueda - Labrak, Yanis

A Zero-shot and Few-shot Study of Instruction-Finetuned Large Language Models Applied to Clinical and Biomedical Tasks por Labrak, Yanis, Rouvier, Mickael, Dufour, Richard

Enlace del recurso
Enlace del recurso

An Empirical Analysis of Discrete Unit Representations in Speech Language Modeling Pre-training por Labrak, Yanis, Dufour, Richard, Rouvier, Mickaël

Enlace del recurso
Enlace del recurso

Zero-Shot End-To-End Spoken Question Answering In Medical Domain por Labrak, Yanis, Moumen, Adel, Dufour, Richard, Rouvier, Mickael

Enlace del recurso
Enlace del recurso

How Important Is Tokenization in French Medical Masked Language Models? por Labrak, Yanis, Bazoge, Adrien, Daille, Beatrice, Rouvier, Mickael, Dufour, Richard

Enlace del recurso
Enlace del recurso

Synthetic Lyrics Detection Across Languages and Genres por Labrak, Yanis, Frohmann, Markus, Meseguer-Brocal, Gabriel, Epure, Elena V.

Enlace del recurso
Enlace del recurso

Beyond the Benchmark: Conditioning, Domains and Failure Modes of Qwen3-TTS por Baroudi, Séverin, Labrak, Yanis, Motlicek, Petr, Bredin, Hervé, Marxer, Ricard

Enlace del recurso
Enlace del recurso

BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains por Labrak, Yanis, Bazoge, Adrien, Morin, Emmanuel, Gourraud, Pierre-Antoine, Rouvier, Mickael, Dufour, Richard

Enlace del recurso
Enlace del recurso

DrBERT: A Robust Pre-trained Model in French for Biomedical and Clinical domains por Labrak, Yanis, Bazoge, Adrien, Dufour, Richard, Rouvier, Mickael, Morin, Emmanuel, Daille, Béatrice, Gourraud, Pierre-Antoine

Enlace del recurso
Enlace del recurso

FrenchMedMCQA: A French Multiple-Choice Question Answering Dataset for Medical domain por Labrak, Yanis, Bazoge, Adrien, Dufour, Richard, Rouvier, Mickael, Morin, Emmanuel, Daille, Béatrice, Gourraud, Pierre-Antoine

Enlace del recurso
Enlace del recurso

Pseudo-Labels as Rewards, Not Targets: Group-Relative Policy Optimization for Semi-Supervised ASR por Kumar, Shashi, Labrak, Yanis, Burdisso, Sergio, Villatoro-Tello, Esaú, Motlicek, Petr, Hacioglu, Kadri, Stolcke, Andreas

Enlace del recurso
Enlace del recurso

LF${}^{2}$AR: Accounting for Layerwise Dynamics to Improve Multimodal Adaptation of Language Models por Cuervo, Santiago, Moumen, Adel, Labrak, Yanis, Khurana, Sameer, Laurent, Antoine, Rouvier, Mickael, Woodland, Phil, Marxer, Ricard

Enlace del recurso
Enlace del recurso

Steering Speech-Language Models: Training-Free Task Specialization via Contrastive Activation Addition por Baroudi, Séverin, Labrak, Yanis, Melucci, Pierfrancesco, Burdisso, Sergio, Motlicek, Petr, Bredin, Hervé, Ravanelli, Mirco, Marxer, Ricard

Enlace del recurso
Enlace del recurso

DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents por Burdisso, Sergio, Villatoro-Tello, Esaú, Sánchez-Cortés, Dairazalia, Labrak, Yanis, Luque, Jordi, Cernak, Milos, Motlicek, Petr

Enlace del recurso
Enlace del recurso

When Synthetic Speech Is All You Have: Better Call GRPO por Kumar, Shashi, Labrak, Yanis, Watawana, Hasindri, Burdisso, Sergio, Villatoro-Tello, Esaú, Hacioğlu, Kadri, Motlicek, Petr, Stolcke, Andreas

Enlace del recurso
Enlace del recurso

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation por Burdisso, Sergio, Baroudi, Séverin, Labrak, Yanis, Grunert, David, Cyrta, Pawel, Chen, Yiyang, Madikeri, Srikanth, Villatoro-Tello, Esaú, Schaaf, Thomas, Marxer, Ricard, Motlicek, Petr

Enlace del recurso
Enlace del recurso

SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation por Burdisso, Sergio, Baroudi, Séverin, Labrak, Yanis, Grunert, David, Cyrta, Pawel, Chen, Yiyang, Madikeri, Srikanth, Schaaf, Thomas, Villatoro-Tello, Esaú, Hassoon, Ahmed, Marxer, Ricard, Motlicek, Petr

Enlace del recurso
Enlace del recurso

DrBenchmark: A Large Language Understanding Evaluation Benchmark for French Biomedical Domain por Labrak, Yanis, Bazoge, Adrien, Khettari, Oumaima El, Rouvier, Mickael, Beaufils, Pacome Constant dit, Grabar, Natalia, Daille, Beatrice, Quiniou, Solen, Morin, Emmanuel, Gourraud, Pierre-Antoine, Dufour, Richard

Enlace del recurso
Enlace del recurso

How to Leverage Synthetic Speech for LLM-Based ASR Systems? por Labrak, Yanis, Sanchez-Cortes, Dairazalia, Burdisso, Sergio, Baroudi, Séverin, Kumar, Shashi, Villatoro-Tello, Esaú, Madikeri, Srikanth, E, Manjunath K, Plchot, Oldřich, Hacioğlu, Kadri, Motlicek, Petr, Stolcke, Andreas

Enlace del recurso
Enlace del recurso

Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization por Labrak, Yanis, Grünert, David, Baroudi, Séverin, Chun, Jiyun, Cyrta, Pawel, Burdisso, Sergio, Hassoon, Ahmed, Liu, David, Rothschild, Adam, Van Deusen, Reed, Motlicek, Petr, Perrault, Andrew, Marxer, Ricard, Schaaf, Thomas

Enlace del recurso
Enlace del recurso

Multi-label classification for biomedical literature: an overview of the BioCreative VII LitCovid Track for COVID-19 literature topic annotations por Chen, Qingyu, Allot, Alexis, Leaman, Robert, Doğan, Rezarta Islamaj, Du, Jingcheng, Fang, Li, Wang, Kai, Xu, Shuo, Zhang, Yuefu, Bagherzadeh, Parsa, Bergler, Sabine, Bhatnagar, Aakash, Bhavsar, Nidhir, Chang, Yung-Chun, Lin, Sheng-Jie, Tang, Wentai, Zhang, Hongtong, Tavchioski, Ilija, Pollak, Senja, Tian, Shubo, Zhang, Jinfeng, Otmakhova, Yulia, Yepes, Antonio Jimeno, Dong, Hang, Wu, Honghan, Dufour, Richard, Labrak, Yanis, Chatterjee, Niladri, Tandon, Kushagri, Laleye, Fréjus, Rakotoson, Loïc, Chersoni, Emmanuele, Gu, Jinghang, Friedrich, Annemarie, Pujari, Subhash Chandra, Chizhikova, Mariia, Sivadasan, Naveen, Sivadasan, Naveen, Lu, Zhiyong

Enlace del recurso
Enlace del recurso