Résultats de recherche auteurs

1

Active Learning with Task-Driven Representations for Messy Pools Autoría: Ashouritaklimi, Kianoosh, Rainforth, Tom

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
2

On the Expected Size of Conformal Prediction Sets Autoría: Dhillon, Guneet S., Deligiannidis, George, Rainforth, Tom

Publié 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
3

In-Context Learning Learns Label Relationships but Is Not Conventional Learning Autoría: Kossen, Jannik, Gal, Yarin, Rainforth, Tom

Publié 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
4

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support Autoría: Reichelt, Tim, Ong, Luke, Rainforth, Tom

Publié 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
5

Making Better Use of Unlabelled Data in Bayesian Active Learning Autoría: Smith, Freddie Bickford, Foster, Adam, Rainforth, Tom

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
6

A Geometric Approach to Optimal Experimental Design Autoría: Kerrigan, Gavin, Naesseth, Christian A., Rainforth, Tom

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
7

Loss-Driven Bayesian Active Learning Autoría: Huang, Zhuoyue, Smith, Freddie Bickford, Rainforth, Tom

Publié 2026

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
8

Incorporating Unlabelled Data into Bayesian Neural Networks Autoría: Sharma, Mrinank, Rainforth, Tom, Teh, Yee Whye, Fortuin, Vincent

Publié 2023

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
9

Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design Autoría: Hedman, Marcel, Ivanova, Desi R., Guan, Cong, Rainforth, Tom

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
10

Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design Autoría: Campbell, Andrew, Yim, Jason, Barzilay, Regina, Rainforth, Tom, Jaakkola, Tommi

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
11

Prediction-Oriented Subsampling from Data Streams Autoría: Mussati, Benedetta Lavinia, Smith, Freddie Bickford, Rainforth, Tom, Roberts, Stephen

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
12

Scaling Up Active Testing to Large Language Models Autoría: Berrada, Gabrielle, Kossen, Jannik, Smith, Freddie Bickford, Razzak, Muhammed, Gal, Yarin, Rainforth, Tom

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
13

Rethinking Aleatoric and Epistemic Uncertainty Autoría: Smith, Freddie Bickford, Kossen, Jannik, Trollope, Eleanor, van der Wilk, Mark, Foster, Adam, Rainforth, Tom

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
14

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design Autoría: Choudhury, Deepro, Williamson, Sinead, Goliński, Adam, Miao, Ning, Smith, Freddie Bickford, Kirchhof, Michael, Zhang, Yizhe, Rainforth, Tom

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
15

Shh, don't say that! Domain Certification in LLMs Autoría: Emde, Cornelius, Paren, Alasdair, Arvind, Preetham, Kayser, Maxime, Rainforth, Tom, Lukasiewicz, Thomas, Ghanem, Bernard, Torr, Philip H. S., Bibi, Adel

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
16

Kosmos: An AI Scientist for Autonomous Discovery Autoría: Mitchener, Ludovico, Yiu, Angela, Chang, Benjamin, Bourdenx, Mathieu, Nadolski, Tyler, Sulovari, Arvis, Landsness, Eric C., Barabasi, Daniel L., Narayanan, Siddharth, Evans, Nicky, Reddy, Shriya, Foiani, Martha, Kamal, Aizad, Shriver, Leah P., Cao, Fang, Wassie, Asmamaw T., Laurent, Jon M., Melville-Green, Edwin, Caldas, Mayk, Bou, Albert, Roberts, Kaleigh F., Zagorac, Sladjana, Orr, Timothy C., Orr, Miranda E., Zwezdaryk, Kevin J., Ghareeb, Ali E., McCoy, Laurie, Gomes, Bruna, Ashley, Euan A., Duff, Karen E., Buonassisi, Tonio, Rainforth, Tom, Bateman, Randall J., Skarlinski, Michael, Rodriques, Samuel G., Hinks, Michaela M., White, Andrew D.

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:

Active Learning with Task-Driven Representations for Messy Pools Autoría: Ashouritaklimi, Kianoosh, Rainforth, Tom

On the Expected Size of Conformal Prediction Sets Autoría: Dhillon, Guneet S., Deligiannidis, George, Rainforth, Tom

In-Context Learning Learns Label Relationships but Is Not Conventional Learning Autoría: Kossen, Jannik, Gal, Yarin, Rainforth, Tom

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support Autoría: Reichelt, Tim, Ong, Luke, Rainforth, Tom

Making Better Use of Unlabelled Data in Bayesian Active Learning Autoría: Smith, Freddie Bickford, Foster, Adam, Rainforth, Tom

A Geometric Approach to Optimal Experimental Design Autoría: Kerrigan, Gavin, Naesseth, Christian A., Rainforth, Tom

Loss-Driven Bayesian Active Learning Autoría: Huang, Zhuoyue, Smith, Freddie Bickford, Rainforth, Tom

Incorporating Unlabelled Data into Bayesian Neural Networks Autoría: Sharma, Mrinank, Rainforth, Tom, Teh, Yee Whye, Fortuin, Vincent

Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design Autoría: Hedman, Marcel, Ivanova, Desi R., Guan, Cong, Rainforth, Tom

Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design Autoría: Campbell, Andrew, Yim, Jason, Barzilay, Regina, Rainforth, Tom, Jaakkola, Tommi

Prediction-Oriented Subsampling from Data Streams Autoría: Mussati, Benedetta Lavinia, Smith, Freddie Bickford, Rainforth, Tom, Roberts, Stephen

Scaling Up Active Testing to Large Language Models Autoría: Berrada, Gabrielle, Kossen, Jannik, Smith, Freddie Bickford, Razzak, Muhammed, Gal, Yarin, Rainforth, Tom

Rethinking Aleatoric and Epistemic Uncertainty Autoría: Smith, Freddie Bickford, Kossen, Jannik, Trollope, Eleanor, van der Wilk, Mark, Foster, Adam, Rainforth, Tom

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design Autoría: Choudhury, Deepro, Williamson, Sinead, Goliński, Adam, Miao, Ning, Smith, Freddie Bickford, Kirchhof, Michael, Zhang, Yizhe, Rainforth, Tom

Shh, don't say that! Domain Certification in LLMs Autoría: Emde, Cornelius, Paren, Alasdair, Arvind, Preetham, Kayser, Maxime, Rainforth, Tom, Lukasiewicz, Thomas, Ghanem, Bernard, Torr, Philip H. S., Bibi, Adel

Résultats de la recherche - Rainforth, Tom

Active Learning with Task-Driven Representations for Messy Pools Autoría: Ashouritaklimi, Kianoosh, Rainforth, Tom

On the Expected Size of Conformal Prediction Sets Autoría: Dhillon, Guneet S., Deligiannidis, George, Rainforth, Tom

In-Context Learning Learns Label Relationships but Is Not Conventional Learning Autoría: Kossen, Jannik, Gal, Yarin, Rainforth, Tom

Beyond Bayesian Model Averaging over Paths in Probabilistic Programs with Stochastic Support Autoría: Reichelt, Tim, Ong, Luke, Rainforth, Tom

Making Better Use of Unlabelled Data in Bayesian Active Learning Autoría: Smith, Freddie Bickford, Foster, Adam, Rainforth, Tom

A Geometric Approach to Optimal Experimental Design Autoría: Kerrigan, Gavin, Naesseth, Christian A., Rainforth, Tom

Loss-Driven Bayesian Active Learning Autoría: Huang, Zhuoyue, Smith, Freddie Bickford, Rainforth, Tom

Incorporating Unlabelled Data into Bayesian Neural Networks Autoría: Sharma, Mrinank, Rainforth, Tom, Teh, Yee Whye, Fortuin, Vincent

Step-DAD: Semi-Amortized Policy-Based Bayesian Experimental Design Autoría: Hedman, Marcel, Ivanova, Desi R., Guan, Cong, Rainforth, Tom

Generative Flows on Discrete State-Spaces: Enabling Multimodal Flows with Applications to Protein Co-Design Autoría: Campbell, Andrew, Yim, Jason, Barzilay, Regina, Rainforth, Tom, Jaakkola, Tommi

Prediction-Oriented Subsampling from Data Streams Autoría: Mussati, Benedetta Lavinia, Smith, Freddie Bickford, Rainforth, Tom, Roberts, Stephen

Scaling Up Active Testing to Large Language Models Autoría: Berrada, Gabrielle, Kossen, Jannik, Smith, Freddie Bickford, Razzak, Muhammed, Gal, Yarin, Rainforth, Tom

Rethinking Aleatoric and Epistemic Uncertainty Autoría: Smith, Freddie Bickford, Kossen, Jannik, Trollope, Eleanor, van der Wilk, Mark, Foster, Adam, Rainforth, Tom

BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design Autoría: Choudhury, Deepro, Williamson, Sinead, Goliński, Adam, Miao, Ning, Smith, Freddie Bickford, Kirchhof, Michael, Zhang, Yizhe, Rainforth, Tom

Shh, don't say that! Domain Certification in LLMs Autoría: Emde, Cornelius, Paren, Alasdair, Arvind, Preetham, Kayser, Maxime, Rainforth, Tom, Lukasiewicz, Thomas, Ghanem, Bernard, Torr, Philip H. S., Bibi, Adel

Outils de recherche: