Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning Paper • 2606.24548 • Published 13 days ago • 11
DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment Paper • 2605.03327 • Published May 8
HiMAC: Hierarchical Macro-Micro Learning for Long-Horizon LLM Agents Paper • 2603.00977 • Published Mar 1