Résultats de recherche auteurs

1

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Autoría: Nuti, Felipe, Franzmeyer, Tim, Henriques, João

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
2

Reinforcement Learning for Quantum Control under Physical Constraints Autoría: Ernst, Jan Ole, Chatterjee, Aniket, Franzmeyer, Tim, Kuhn, Axel

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
3

Select to Perfect: Imitating desired behavior from large multi-agent data Autoría: Franzmeyer, Tim, Elkind, Edith, Torr, Philip, Foerster, Jakob, Henriques, Joao

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
4

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection Autoría: Nasvytis, Linas, Sandbrink, Kai, Foerster, Jakob, Franzmeyer, Tim, de Witt, Christian Schroeder

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
5

Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval Autoría: Buoso, Davide, Robinson, Luke, Averta, Giuseppe, Torr, Philip, Franzmeyer, Tim, De Martini, Daniele

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
6

HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits Autoría: Franzmeyer, Tim, Shtedritski, Aleksandar, Albanie, Samuel, Torr, Philip, Henriques, João F., Foerster, Jakob N.

Publié 2024

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
7

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning Autoría: Franzmeyer, Tim, Sravankumar, Archie, Liu, Lijuan, Mao, Yuning, Hou, Rui, Wang, Sinong, Foerster, Jakob N., Zettlemoyer, Luke, Khabsa, Madian

Publié 2025

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:
8

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks Autoría: Franzmeyer, Tim, McAleer, Stephen, Henriques, João F., Foerster, Jakob N., Torr, Philip H. S., Bibi, Adel, de Witt, Christian Schroeder

Publié 2022

Fuente: arXiv

Tipo de material: Preprint

Acceso al recurso
Enlace del recurso

Standalone Record
Ajouter aux favoris

Enregistré dans:

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Autoría: Nuti, Felipe, Franzmeyer, Tim, Henriques, João

Reinforcement Learning for Quantum Control under Physical Constraints Autoría: Ernst, Jan Ole, Chatterjee, Aniket, Franzmeyer, Tim, Kuhn, Axel

Select to Perfect: Imitating desired behavior from large multi-agent data Autoría: Franzmeyer, Tim, Elkind, Edith, Torr, Philip, Foerster, Jakob, Henriques, Joao

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection Autoría: Nasvytis, Linas, Sandbrink, Kai, Foerster, Jakob, Franzmeyer, Tim, de Witt, Christian Schroeder

Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval Autoría: Buoso, Davide, Robinson, Luke, Averta, Giuseppe, Torr, Philip, Franzmeyer, Tim, De Martini, Daniele

HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits Autoría: Franzmeyer, Tim, Shtedritski, Aleksandar, Albanie, Samuel, Torr, Philip, Henriques, João F., Foerster, Jakob N.

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning Autoría: Franzmeyer, Tim, Sravankumar, Archie, Liu, Lijuan, Mao, Yuning, Hou, Rui, Wang, Sinong, Foerster, Jakob N., Zettlemoyer, Luke, Khabsa, Madian

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks Autoría: Franzmeyer, Tim, McAleer, Stephen, Henriques, João F., Foerster, Jakob N., Torr, Philip H. S., Bibi, Adel, de Witt, Christian Schroeder

Résultats de la recherche - Franzmeyer, Tim

TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs Autoría: Nuti, Felipe, Franzmeyer, Tim, Henriques, João

Reinforcement Learning for Quantum Control under Physical Constraints Autoría: Ernst, Jan Ole, Chatterjee, Aniket, Franzmeyer, Tim, Kuhn, Axel

Select to Perfect: Imitating desired behavior from large multi-agent data Autoría: Franzmeyer, Tim, Elkind, Edith, Torr, Philip, Foerster, Jakob, Henriques, Joao

Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection Autoría: Nasvytis, Linas, Sandbrink, Kai, Foerster, Jakob, Franzmeyer, Tim, de Witt, Christian Schroeder

Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval Autoría: Buoso, Davide, Robinson, Luke, Averta, Giuseppe, Torr, Philip, Franzmeyer, Tim, De Martini, Daniele

HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits Autoría: Franzmeyer, Tim, Shtedritski, Aleksandar, Albanie, Samuel, Torr, Philip, Henriques, João F., Foerster, Jakob N.

High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning Autoría: Franzmeyer, Tim, Sravankumar, Archie, Liu, Lijuan, Mao, Yuning, Hou, Rui, Wang, Sinong, Foerster, Jakob N., Zettlemoyer, Luke, Khabsa, Madian

Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks Autoría: Franzmeyer, Tim, McAleer, Stephen, Henriques, João F., Foerster, Jakob N., Torr, Philip H. S., Bibi, Adel, de Witt, Christian Schroeder

Outils de recherche: