Suchergebnisse - Franzmeyer, Tim

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext

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

Volltext