8 citations · 13 across the 13 of their papers we have counts for
8 papers · 1 filter
Multiple Token Divergence: Measuring and Steering In-Context Computation Density
Vincent Herrmann, Eric Alcaide, Michael Wand +1
Measuring the in-context computational effort of language models is a key challenge, as metrics like next-token loss fail to capture reasoning complexity. Prior methods based on la…
Measuring In-Context Computation Complexity via Hidden State Prediction
Vincent Herrmann, Róbert Csordás, Jürgen Schmidhuber
Detecting when a neural sequence model does "interesting" computation is an open problem. The next token prediction loss is a poor indicator: Low loss can stem from trivially predi…
Upside Down Reinforcement Learning with Policy Generators
Jacopo Di Ventura, Dylan R. Ashley, Vincent Herrmann +2
Upside Down Reinforcement Learning (UDRL) is a promising framework for solving reinforcement learning problems which focuses on learning command-conditioned policies. In this work,…
Automatic Album Sequencing
Vincent Herrmann, Dylan R. Ashley, Jürgen Schmidhuber
Album sequencing is a critical part of the album production process. Recently, a data-driven approach was proposed that sequences general collections of independent media by extrac…
Learning Useful Representations of Recurrent Neural Network Weight Matrices
Vincent Herrmann, Francesco Faccio, Jürgen Schmidhuber
Recurrent Neural Networks (RNNs) are general-purpose parallel-sequential computers. The program of an RNN is its weight matrix. How to learn useful representations of RNN weights t…
Learning One Abstract Bit at a Time Through Self-Invented Experiments Encoded as Neural Networks
Vincent Herrmann, Louis Kirsch, Jürgen Schmidhuber
There are two important things in science: (A) Finding answers to given questions, and (B) Coming up with good questions. Our artificial scientists not only learn to answer given q…
Goal-Conditioned Generators of Deep Policies
Francesco Faccio, Vincent Herrmann, Aditya Ramesh +2
Goal-conditioned Reinforcement Learning (RL) aims at learning optimal policies, given goals encoded in special command inputs. Here we study goal-conditioned neural nets (NNs) that…
General Policy Evaluation and Improvement by Learning to Identify Few But Crucial States
Francesco Faccio, Aditya Ramesh, Vincent Herrmann +2
Learning to evaluate and improve policies is a core problem of Reinforcement Learning (RL). Traditional RL algorithms learn a value function defined for a single policy. A recently…