Jannik Kossen

29 papers A* 9Journal 19Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
Towards a Neural Debugger for Python.
CoRR
Maximilian Beck, Jonas Gehring, Jannik Kossen, Gabriel Synnaeve
2025 J jnl
CWM: An Open-Weights LLM for Research on Code Generation with World Models.
CoRR
FAIR CodeGen team, Jade Copet, Quentin Carbonneaux, Gal Cohen, Jonas Gehring, Jacob Kahn, Jannik Kossen, Felix Kreuk, Emily McMilin, Michel Meyer, Yuxiang Wei, David Zhang, Kunhao Zheng, Jordi Armengol-Estapé, Pedram Bashiri, Maximilian Beck, Pierre Chambon, Abhishek Charnalia, Chris Cummins, Juliette Decugis, Zacharias V. Fisches, François Fleuret, Fabian Gloeckle, Alex Gu, Michael Hassid, Daniel Haziza, Badr Youbi Idrissi, Christian Keller, Rahul Kindi, Hugh Leather, Gallil Maimon, Aram H. Markosyan, Francisco Massa, Pierre-Emmanuel Mazaré, Vegard Mella, Naila Murray, Keyur Muzumdar, Peter W. O'Hearn, Matteo Pagliardini, Dmitrii Pedchenko, Tal Remez, Volker Seeker, Marco Selvi, Oren Sultan, Sida Wang, Luca Wehrstedt, Ori Yoran, Lingming Zhang, Taco Cohen, Yossi Adi, Gabriel Synnaeve
2025 J jnl
Reducing Large Language Model Safety Risks in Women's Health using Semantic Entropy.
CoRR
Jahan C. Penny-Dimri, Magdalena Bachmann, William R. Cooke, Sam Mathewlynn, Samuel Dockree, John Tolladay, Jannik Kossen, Lin Li, Yarin Gal, Gabriel Davis Jones
2025 A* conf
Rethinking Aleatoric and Epistemic Uncertainty.
ICML
Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster, Tom Rainforth
2025 J jnl
Scaling Up Active Testing to Large Language Models.
CoRR
Gabrielle Berrada, Jannik Kossen, Muhammed Razzak, Freddie Bickford Smith, Yarin Gal, Tom Rainforth
2025 — conf
Simple Factuality Probes Detect Hallucinations in Long-Form Natural Language Generation.
EMNLP (Findings)
Jiatong Han, Neil Band, Muhammed Razzak, Jannik Kossen, Tim G. J. Rudner, Yarin Gal
2024 J jnl
Detecting hallucinations in large language models using semantic entropy.
Nat.
Sebastian Farquhar, Jannik Kossen, Lorenz Kuhn, Yarin Gal
2024 A* conf
Estimating the Hallucination Rate of Generative AI.
NeurIPS
Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David M. Blei
2024 J jnl
Estimating the Hallucination Rate of Generative AI.
CoRR
Andrew Jesson, Nicolas Beltran-Velez, Quentin Chu, Sweta Karlekar, Jannik Kossen, Yarin Gal, John P. Cunningham, David M. Blei
2024 J jnl
Fine-Tuning Large Language Models to Appropriately Abstain with Semantic Entropy.
CoRR
Benedict Aaron Tjandra, Muhammed Razzak, Jannik Kossen, Kunal Handa, Yarin Gal
2024 A* conf
In-Context Learning Learns Label Relationships but Is Not Conventional Learning.
ICLR
Jannik Kossen, Yarin Gal, Tom Rainforth
2024 A* conf
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities.
NeurIPS
Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen
2024 J jnl
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities.
CoRR
Alexander Nikitin, Jannik Kossen, Yarin Gal, Pekka Marttinen
2024 J jnl
Rethinking Aleatoric and Epistemic Uncertainty.
CoRR
Freddie Bickford Smith, Jannik Kossen, Eleanor Trollope, Mark van der Wilk, Adam Foster, Tom Rainforth
2024 J jnl
Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs.
CoRR
Jannik Kossen, Jiatong Han, Muhammed Razzak, Lisa Schut, Shreshth A. Malik, Yarin Gal
2023 J jnl
Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task.
Trans. Mach. Learn. Res.
Jannik Kossen, Catalina Cangea, Eszter Vértes, Andrew Jaegle, Viorica Patraucean, Ira Ktena, Nenad Tomasev, Danielle Belgrave
2023 J jnl
In-Context Learning in Large Language Models Learns Label Relationships but Is Not Conventional Learning.
CoRR
Jannik Kossen, Tom Rainforth, Yarin Gal
2023 A* conf
Three Towers: Flexible Contrastive Learning with Pretrained Image Models.
NeurIPS
Jannik Kossen, Mark Collier, Basil Mustafa, Xiao Wang, Xiaohua Zhai, Lucas Beyer, Andreas Steiner, Jesse Berent, Rodolphe Jenatton, Effrosyni Kokiopoulou
2023 J jnl
Three Towers: Flexible Contrastive Learning with Pretrained Image Models.
CoRR
Jannik Kossen, Mark Collier, Basil Mustafa, Xiao Wang, Xiaohua Zhai, Lucas Beyer, Andreas Steiner, Jesse Berent, Rodolphe Jenatton, Efi Kokiopoulou
2022 J jnl
Active Acquisition for Multimodal Temporal Data: A Challenging Decision-Making Task.
CoRR
Jannik Kossen, Catalina Cangea, Eszter Vértes, Andrew Jaegle, Viorica Patraucean, Ira Ktena, Nenad Tomasev, Danielle Belgrave
2022 A* conf
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation.
NeurIPS
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Thomas Rainforth
2022 J jnl
Active Surrogate Estimators: An Active Learning Approach to Label-Efficient Model Evaluation.
CoRR
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2022 J jnl
Marginal and Joint Cross-Entropies & Predictives for Online Bayesian Inference, Active Learning, and Active Sampling.
CoRR
Andreas Kirsch, Jannik Kossen, Yarin Gal
2021 A* conf
Active Testing: Sample-Efficient Model Evaluation.
ICML
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021 J jnl
Active Testing: Sample-Efficient Model Evaluation.
CoRR
Jannik Kossen, Sebastian Farquhar, Yarin Gal, Tom Rainforth
2021 A* conf
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning.
NeurIPS
Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Thomas Rainforth, Yarin Gal
2021 J jnl
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning.
CoRR
Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Tom Rainforth, Yarin Gal
2020 A* conf
Structured Object-Aware Physics Prediction for Video Modeling and Planning.
ICLR
Jannik Kossen, Karl Stelzner, Marcel Hussing, Claas Voelcker, Kristian Kersting
2019 J jnl
Structured Object-Aware Physics Prediction for Video Modeling and Planning.
CoRR
Jannik Kossen, Karl Stelzner, Marcel Hussing, Claas Voelcker, Kristian Kersting