X-World 1.6: Building Controllable Virtual Cities with World Models
cs.AI
Submitted: 2026-10-31
Updated: 2026-10-31
Terminology
Sources
- Cosmos 3: Omnimodal World Models for Physical AI
- Qwen3-VL Technical Report
- SAM 3: Segment Anything with Concepts
- M$^\text{4}$World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming
- GAIA-1: A Generative World Model for Autonomous Driving
- ZYT-World: A Real-Time Controllable World Model for Closed-Loop Autonomous-Driving Simulation
- RoXDrive: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving via Action-Faithful Rollouts
- Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
- GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving
- FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
- FG-CLIP 2: A Bilingual Fine-grained Vision-Language Alignment Model
- X-Cache: Cross-Chunk Block Caching for Few-Step Autoregressive World Models Inference
- Connected Self Forcing: Beyond Local Learning in Video Autoregression
- ByteTrack: Multi-Object Tracking by Associating Every Detection Box
- Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation
- X-World: Controllable Ego-Centric Multi-Camera World Models for Scalable End-to-End Driving
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents