A two-stage framework enables multimodal LLMs to learn shared latent representations from pairwise modality data and achieve cross-modal generation when incorporating new modalities.
Cambridge university press (2009)
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Defines retrospective counterfactual responsibility in concurrent stochastic multi-player games, allocates it via Shapley values satisfying fairness and consistency, and uses Nash equilibria for stable responsibility-reward tradeoffs.
AGEL-Comp is a neuro-symbolic framework that builds an explicit causal world model and uses a deduction-abduction cycle to improve compositional generalization in interactive agents over pure LLM baselines.
citing papers explorer
-
Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
Defines retrospective counterfactual responsibility in concurrent stochastic multi-player games, allocates it via Shapley values satisfying fairness and consistency, and uses Nash equilibria for stable responsibility-reward tradeoffs.