Samuel Kaski

Efficient Autoregressive Inference for Transformer Probabilistic Models

In-Context Multi-Objective Optimization

Concept-based Adversarial Attack: a Probabilistic Perspective

An Axiomatic Framework for N-Agent Ad Hoc Teamwork: From Shapley Axioms to Learning

DIVIDE-AND-DENOISE: A GAME THEORETIC METHOD FOR FAIRLY COMPOSING DIFFUSION MODELS

Softly Constrained Denoisers for Diffusion Models

ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition

PABBO: Preferential Amortized Black-Box Optimization

When do GFlowNets learn the right distribution?

Robust and Computation-Aware Gaussian Processes

A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning

Generalization and Distributed Learning of GFlowNets

Attaining Human's Desirable Outcomes in Indirect Human-AI Interaction via Multi-Agent Influence Diagrams

LoKO: Low-Rank Kalman Optimizer for Online Fine-Tuning of Large Models