Lihu Chen - Exploring Factuality and Interpretability in LLMs: Confidence Estimation and Key Neuron Analysis
- Date: 16 décembre 2024 à 13h
- Salle: 65-66 304
Clement Rambour - Strengthening Model Robustness Through Structural Priors
Clement Rambour - Strengthening Model Robustness Through Structural Priors
- Date: 09 décembre 2024 à 13h
- Salle: 65-66 304
Présentation des nouveaux arrivants -
Raphael Gervillie - Learning Relational Decomposition of Queries for Question Answering from Tables
Raphael Gervillie - Learning Relational Decomposition of Queries for Question Answering from Tables
- Date: 25 novembre 2024 à 13h
- Salle: 65-66 304
Marc Lafon - GalLoP: Learning Global and Local Prompts for Vision-Language Models
Marc Lafon - GalLoP: Learning Global and Local Prompts for Vision-Language Models
- Date: 18 novembre 2024 à 13h
- Salle: 65-66 304
Ziqian Peng - Difficulties in translating long documents: impact of input length and token position
Ziqian Peng - Difficulties in translating long documents: impact of input length and token position
- Date: 21 octobre 2024 à 13h
- Salle: 65-66 304
Zakariae El Asri - Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Zakariae El Asri - Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
- Date: 14 octobre 2024 à 13h
- Salle: 65-66 304
Joao Maria Janeiro - MEXMA: Token-level objectives improve sentence representations
Joao Maria Janeiro - MEXMA: Token-level objectives improve sentence representations
- Date: 07 octobre 2024 à 13h
- Salle: 65-66 304
Ruben Ohana - Building foundation models for science
Ruben Ohana - Building foundation models for science
- Date: 30 septembre 2024 à 13h
- Salle: 65-66 304
Salim Aissi - Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Salim Aissi - Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
- Date: 23 septembre 2024 à 13h
- Salle: SCAI