world model
world-model-879365e2·5 events·first seen 1mo agoAliases: world model, world models
Co-occurring entities
More like this (12)
Recent events (5)
GRASP: Gradient-based Planning for World Models at Longer Horizons
Researchers from Berkeley, Meta, and collaborators introduce GRASP, a gradient-based planner designed to make long-horizon planning with learned world models more robust. The method addresses three core failure modes: ill-conditioned computation graphs from backpropagation through time, non-greedy loss landscapes with many local minima, and brittle gradients through high-dimensional vision models. GRASP lifts trajectory optimization into virtual states for parallel optimization across time, injects stochasticity into state iterates for exploration, and reshapes gradients to avoid problematic state-input gradient paths. The work is positioned in the context of scaling world models toward general-purpose simulators usable for control and planning.
DeepMind's Vision for Building a Universal AI Assistant
DeepMind has published a vision statement for evolving Gemini into a universal AI assistant by extending it into a world model capable of planning and simulating aspects of the world. The announcement signals a strategic direction toward agents that can imagine and reason about future states rather than purely responding to prompts. This positions Gemini as a long-term platform for agentic and embodied AI capabilities.
Roundtables: Can AI Learn to Understand the World?
MIT Technology Review hosts a roundtable discussion on whether AI systems can develop genuine world understanding, addressing the limitations of current LLMs. The conversation, led by editor Mat Honan and senior AI editor Will Douglas Heaven, focuses on world models as a potential path beyond current language model constraints. The piece reflects growing industry and research interest in world models as a next frontier for AI capability.
AMRS: Rollout-Based World Model for Offline Affective Music Recommendation with DPO
LUCID's Affective Music Recommendation System (AMRS) uses a causal transformer world model trained on logged listening data to jointly predict engagement, ratings, and self-reported valence/arousal, enabling offline policy optimization without ethically problematic online experimentation. A recommender policy is initialized via behavior cloning and fine-tuned with Direct Preference Optimization (DPO) against a multi-objective utility function. The system is deployed on LUCID's health-and-wellness platforms serving clinical users (older adults with neurocognitive conditions) and consumer-wellness users across four modes. Under cold-start conditions, DPO improves predicted affective signals over the cloned baseline while maintaining diversity and avoiding distributional collapse.
Why Video Agent Models Are Next — Ethan He, xAI Grok Imagine
Latent Space interviews Ethan He, the lead behind xAI's Grok Imagine video generation product, covering its development in roughly three months. The discussion explores the distinction between video generation models and world models, and positions video agents as a significant near-term frontier. He argues Grok Imagine is underrated relative to its capabilities.