This work introduces answer-distribution trajectories, a stochastic-dynamics-inspired representation that tracks the model's full predictive distribution over answers as reasoning unfolds, and suggests that answer-distribution trajectories provide a rich framework for analysing and evaluating the dynamics of LLM reason...
M. Catala, Haitz Sáez de Ocáriz Borde, D. Murari et al.· 0 citations
This work constructs and analyzes a class of 1-Lipschitz neural networks on Hadamard manifolds, and shows improved results from the nonexpansive denoiser over static, data-only, and Log-Euclidean denoising baselines, and empirically test its convergence properties.
D. Murari, Marta Ghirardelli, Ben Adcock et al.· arXiv.org· 0 citations
This work presents a modular framework for discovering piecewise-smooth dynamical systems by first estimating switching hyperplanes from data and then learning smooth dynamics within each region using geometry-constrained neural networks.
D. Murari, Erik Jansson, Chris Budd Obe et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.