Picture for Jannik Kossen

Jannik Kossen

Estimating the Hallucination Rate of Generative AI

Jun 11, 2024
Viaarxiv icon

Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities

Add code
May 30, 2024
Viaarxiv icon

In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning

Add code
Aug 07, 2023
Figure 1 for In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
Figure 2 for In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
Figure 3 for In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
Figure 4 for In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning
Viaarxiv icon

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Add code
May 29, 2023
Figure 1 for Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Figure 2 for Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Figure 3 for Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Figure 4 for Three Towers: Flexible Contrastive Learning with Pretrained Image Models
Viaarxiv icon

Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task

Add code
Nov 09, 2022
Figure 1 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Figure 2 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Figure 3 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Figure 4 for Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task
Viaarxiv icon

Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling

May 18, 2022
Figure 1 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling
Figure 2 for Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling
Viaarxiv icon

Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation

Add code
Feb 14, 2022
Figure 1 for Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Figure 2 for Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Figure 3 for Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Figure 4 for Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation
Viaarxiv icon

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

Add code
Jun 04, 2021
Figure 1 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 2 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 3 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Figure 4 for Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
Viaarxiv icon

Active Testing: Sample-Efficient Model Evaluation

Add code
Mar 09, 2021
Figure 1 for Active Testing: Sample-Efficient Model Evaluation
Figure 2 for Active Testing: Sample-Efficient Model Evaluation
Figure 3 for Active Testing: Sample-Efficient Model Evaluation
Figure 4 for Active Testing: Sample-Efficient Model Evaluation
Viaarxiv icon

Structured Object-Aware Physics Prediction for Video Modeling and Planning

Add code
Oct 06, 2019
Figure 1 for Structured Object-Aware Physics Prediction for Video Modeling and Planning
Figure 2 for Structured Object-Aware Physics Prediction for Video Modeling and Planning
Figure 3 for Structured Object-Aware Physics Prediction for Video Modeling and Planning
Figure 4 for Structured Object-Aware Physics Prediction for Video Modeling and Planning
Viaarxiv icon