Self-distillation from a caption-conditioned video diffusion model to an image-and-prompt-conditioned executor, enhanced by RL from VLM feedback, enables task solving in world models.
Pre-trained video generative models as world simulators
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
unclear 1representative citing papers
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
CLAW is an end-to-end self-supervised method that learns semantically meaningful continuous latent actions and predictive world models from action-free videos to support imitation learning and goal-directed planning.
DiLA uses content-structure disentanglement driven by predictive bottlenecks to create semantically structured latent actions for high-fidelity video world models.
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
CoLA-World jointly trains latent action models and world models with a warm-up phase to achieve co-evolution, matching or exceeding prior two-stage methods in video simulation quality and visual planning performance.
A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.
WorldVLA unifies VLA and world models in one autoregressive system, shows they boost each other, and adds an attention mask to stop error buildup when generating action chunks.
Zero-shot MLLMs on ShanghaiTech and CHAD exhibit strong conservative bias with high precision but collapsed recall; class-specific prompts raise peak F1 from 0.09 to 0.64 yet recall remains the bottleneck.
citing papers explorer
-
World Model Self-Distillation: Training World Models to Solve General Tasks
Self-distillation from a caption-conditioned video diffusion model to an image-and-prompt-conditioned executor, enhanced by RL from VLM feedback, enables task solving in world models.
-
Render, Don't Decode: Weight-Space World Models with Latent Structural Disentanglement
NOVA represents world states as INR weights for decoder-free rendering, compactness, and unsupervised disentanglement of background, foreground, and motion in video world models.
-
CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization
CLAW is an end-to-end self-supervised method that learns semantically meaningful continuous latent actions and predictive world models from action-free videos to support imitation learning and goal-directed planning.
-
DiLA: Disentangled Latent Action World Models
DiLA uses content-structure disentanglement driven by predictive bottlenecks to create semantically structured latent actions for high-fidelity video world models.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
Co-Evolving Latent Action World Models
CoLA-World jointly trains latent action models and world models with a warm-up phase to achieve co-evolution, matching or exceeding prior two-stage methods in video simulation quality and visual planning performance.
-
Ctrl-World: A Controllable Generative World Model for Robot Manipulation
A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.
-
WorldVLA: Towards Autoregressive Action World Model
WorldVLA unifies VLA and world models in one autoregressive system, shows they boost each other, and adds an attention mask to stop error buildup when generating action chunks.
-
Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild
Zero-shot MLLMs on ShanghaiTech and CHAD exhibit strong conservative bias with high precision but collapsed recall; class-specific prompts raise peak F1 from 0.09 to 0.64 yet recall remains the bottleneck.