Thomas Schmied

LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities

pLSTM: parallelizable Linear Source Transition Mark networks

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

Parameter Efficient Fine-tuning via Explained Variance Adaptation

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

One Initialization to Rule them All: Fine-tuning via Explained Variance Adaptation

Retrieval-Augmented Decision Transformer: External Memory for In-context RL