2 citations · 2 across the 4 of their papers we have counts for
3 papers · 1 filter
On Reparameterizing the Score Function
Mohammad Hossein Amani, Leonardo Bocchieri, Maxime Peyrard +2
Policy gradients for autoregressive sequence models differentiate each token's log-probability while holding the conditioning history fixed. This discards information about how ear…
RL for Reasoning by Adaptively Revealing Rationales
Mohammad Hossein Amani, Aryo Lotfi, Nicolas Mario Baldwin +4
Learning in the combinatorially large output space of sequence generation problems is challenging as providing expert demonstrations scales poorly with sequence length, and RL stru…
Symbolic Autoencoding for Self-Supervised Sequence Learning
Mohammad Hossein Amani, Nicolas Mario Baldwin, Amin Mansouri +3
Traditional language models, adept at next-token prediction in text sequences, often struggle with transduction tasks between distinct symbolic systems, particularly when parallel…