Picture for Nicolas Thome

Nicolas Thome

MLIA

VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making

Add code
Mar 19, 2025
Viaarxiv icon

Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting

Add code
Oct 29, 2024
Figure 1 for Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Figure 2 for Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Figure 3 for Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Figure 4 for Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
Viaarxiv icon

Supra-Laplacian Encoding for Transformer on Dynamic Graphs

Add code
Sep 26, 2024
Viaarxiv icon

Temporal receptive field in dynamic graph learning: A comprehensive analysis

Add code
Jul 19, 2024
Figure 1 for Temporal receptive field in dynamic graph learning: A comprehensive analysis
Figure 2 for Temporal receptive field in dynamic graph learning: A comprehensive analysis
Figure 3 for Temporal receptive field in dynamic graph learning: A comprehensive analysis
Figure 4 for Temporal receptive field in dynamic graph learning: A comprehensive analysis
Viaarxiv icon

ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation

Add code
Jul 03, 2024
Figure 1 for ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation
Figure 2 for ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation
Figure 3 for ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation
Figure 4 for ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation
Viaarxiv icon

Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning

Add code
Jul 02, 2024
Figure 1 for Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Figure 2 for Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Figure 3 for Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Figure 4 for Physics-Informed Model and Hybrid Planning for Efficient Dyna-Style Reinforcement Learning
Viaarxiv icon

GalLoP: Learning Global and Local Prompts for Vision-Language Models

Add code
Jul 01, 2024
Figure 1 for GalLoP: Learning Global and Local Prompts for Vision-Language Models
Figure 2 for GalLoP: Learning Global and Local Prompts for Vision-Language Models
Figure 3 for GalLoP: Learning Global and Local Prompts for Vision-Language Models
Figure 4 for GalLoP: Learning Global and Local Prompts for Vision-Language Models
Viaarxiv icon

Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features

Add code
Jun 05, 2024
Figure 1 for Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
Figure 2 for Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
Figure 3 for Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
Figure 4 for Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
Viaarxiv icon

Energy Correction Model in the Feature Space for Out-of-Distribution Detection

Add code
Mar 15, 2024
Figure 1 for Energy Correction Model in the Feature Space for Out-of-Distribution Detection
Figure 2 for Energy Correction Model in the Feature Space for Out-of-Distribution Detection
Figure 3 for Energy Correction Model in the Feature Space for Out-of-Distribution Detection
Figure 4 for Energy Correction Model in the Feature Space for Out-of-Distribution Detection
Viaarxiv icon

TRUSTED: The Paired 3D Transabdominal Ultrasound and CT Human Data for Kidney Segmentation and Registration Research

Add code
Oct 19, 2023
Viaarxiv icon