Benjamin Riviere — accepted AI-conference papers

2026

Spectral Decomposition of Inverse Dynamics for Fast Exploration in Model-Based Manipulation

Solvin Sigurdson, Benjamin Riviere, Joel Burdick

ICRA 2026poster

Planning long duration robotic manipulation sequences is challenging because of the complexity of exploring feasible trajectories through nonlinear contact dynamics and many contact modes. Moreover, this complexity grows with the problem's horizon length. We propose a search tree method that generat…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

DISC: Dynamic Decomposition Improves LLM Inference Scaling

Jonathan Light, Wei Cheng, Benjamin Riviere, Yue Wu, Masafumi Oyamada, Mengdi Wang +3

NeurIPS 2025poster

Inference scaling methods for LLMs often rely on decomposing problems into steps (or groups of tokens), followed by sampling and selecting the best next steps. However, these steps and their sizes are often predetermined or manually designed based on domain knowledge. We propose dynamic decompositio…

Cited by 0 Source ↗Scholar ↗