4 citations · 5 across the 12 of their papers we have counts for
16 papers
Task Vector Descent: Learning from Non-IID Batches
Anton Baumann, Jonas Hübotter, Zeynep Akata +1
A central challenge in continual learning is to acquire new knowledge without forgetting what the model has already learned. This challenge appears in language model training when…
Deep Epistemic Value Functions for Optimistic Exploration
Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter +1
Principled exploration in reinforcement learning requires an agent to quantify its epistemic uncertainty and act to resolve it. Uncertainty over the value function provides a natur…
On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation
Anton Baumann, Akmal Ashirmatov, Leo Schmidt-Traub +4
On-policy self-distillation provides dense, token-level supervision by conditioning a model on privileged information and distilling the resulting teacher distribution back into th…
Majority Voting for Code Generation
Tim Launer, Jonas Hübotter, Marco Bagatella +2
We investigate Functional Majority Voting (FMV), a method based on functional consensus for code generation with Large Language Models, which identifies a representative solution f…
Reinforcement Learning via Self-Distillation
Jonas Hübotter, Frederike Lübeck, Lejs Behric +8
Large language models are increasingly post-trained with reinforcement learning in verifiable domains such as code and math. Yet, current methods for reinforcement learning with ve…
Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
Marco Bagatella, Thomas Rupf, Georg Martius +1
Recent advancements in zero-shot reinforcement learning (RL) have facilitated the extraction of diverse behaviors from unlabeled, offline data sources. In particular, forward-backw…
Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learning
Jonas Hübotter, Leander Diaz-Bone, Ido Hakimi +2
Humans are good at learning on the job: We learn how to solve the tasks we face as we go along. Can a model do the same? We propose an agent that assembles a task-specific curricul…
Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Models
Jonas Hübotter, Patrik Wolf, Alexander Shevchenko +3
Recent empirical studies have explored the idea of continuing to train a model at test-time for a given task, known as test-time training (TTT), and have found it to yield signific…
Maximizing Prefix-Confidence at Test-Time Efficiently Improves Mathematical Reasoning
Matthias Otth, Jonas Hübotter, Ido Hakimi +1
Recent work has shown that language models can self-improve by maximizing their own confidence in their predictions, without relying on external verifiers or reward signals. In thi…
Test-time Offline Reinforcement Learning on Goal-related Experience
Marco Bagatella, Mert Albaba, Jonas Hübotter +2
Foundation models compress a large amount of information in a single, large neural network, which can then be queried for individual tasks. There are strong parallels between this…
DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learning
Leander Diaz-Bone, Marco Bagatella, Jonas Hübotter +1
Sparse-reward reinforcement learning (RL) can model a wide range of highly complex tasks. Solving sparse-reward tasks is RL's core premise, requiring efficient exploration coupled…
Local Mixtures of Experts: Essentially Free Test-Time Training via Model Merging
Ryo Bertolissi, Jonas Hübotter, Ido Hakimi +1
Mixture of expert (MoE) models are a promising approach to increasing model capacity without increasing inference cost, and are core components of many state-of-the-art language mo…
Probabilistic Artificial Intelligence
Andreas Krause, Jonas Hübotter
Artificial intelligence commonly refers to the science and engineering of artificial systems that can carry out tasks generally associated with requiring aspects of human intellige…
Efficiently Learning at Test-Time: Active Fine-Tuning of LLMs
Jonas Hübotter, Sascha Bongni, Ido Hakimi +1
Recent efforts in fine-tuning language models often rely on automatic data selection, commonly using Nearest Neighbors retrieval from large datasets. However, we theoretically show…
Active Fine-Tuning of Multi-Task Policies
Marco Bagatella, Jonas Hübotter, Georg Martius +1
Pre-trained generalist policies are rapidly gaining relevance in robot learning due to their promise of fast adaptation to novel, in-domain tasks. This adaptation often relies on c…
Directed Exploration in Reinforcement Learning from Linear Temporal Logic
Marco Bagatella, Andreas Krause, Georg Martius
Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning, as it allows describing objectives beyond the expressivity of conventional disc…