Showing papers from Mila / Université de Montréal Show all papers
Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Predictive representation learning combined with high-capacity value approximation drives scalable multitask RL, with the simple model-free MR.Q outperforming world-model methods across continuous control tasks.
Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Bidirectional Information Flow enables continuous two-way communication in hierarchical Gaussian processes for Bayesian optimization, improving sample efficiency, training robustness, and modular subtask reuse while significantly outperforming unidirectional and vanilla methods.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Looped reasoning models converge to cyclic fixed points that stabilize attention and repeat feedforward inference stages iteratively, with recurrence size and normalization affecting stability.
Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 1 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Gaussian trust region reshaping replaces monotonic divergence penalties with bounded non-monotonic constraints, unlocking efficient behavior transitions in non-stationary reinforcement learning.
Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.