AdaJEPA: An Adaptive Latent World Model

Sensorimotor World Model: Learning Action-Aligned Representations via Inverse Dynamics Regularization

This paper introduces a Sensorimotor World Model (SMWM), a latent world model trained end-to-end with inverse dynamics regularization. The a

Qwen-AgentWorld: Language World Models for Simulating Agentic Environments Across 7 Domains

This paper introduces Qwen-AgentWorld, a family of language world models (35B-A3B and 397B-A17B) designed to simulate agentic environments a

Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons

ACM Transactions on Probabilistic Machine Learning (topml) Vol 2, Issue 2

ACM Transactions on Asian and Low-Resource Language Information Processing (tallip) Vol 25, Issue 6

Reinforcement Learning to Train Large Language Models to Explain Human Decisions