The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 11 days ago • 157
Hallucination in World Models is Predictable and Preventable Paper • 2606.27326 • Published 14 days ago • 9
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models Paper • 2606.19750 • Published 21 days ago • 3
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models Paper • 2606.19750 • Published 21 days ago • 3 • 2
Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models Paper • 2606.19750 • Published 21 days ago • 3