RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
Canonical reference
Back to the features: Dino as a foundation for video world models
Canonical reference. 100% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 4
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 11polarities
background 5representative citing papers
FR3D predicts a persistent 3D latent representation for future dynamic reconstruction by explicitly disentangling scene evolution from agent trajectory and using foundation-model distillation.
Envision4D presents a feed-forward 4D Gaussian Splatting framework with future pose prediction, temporal attention, and conditioned motion lifting for pose-free extrapolation in autonomous driving scenes.
TC-JEPA conditions masked feature prediction on text captions via sparse cross-attention to produce more semantically rich visual representations and outperforms contrastive methods on fine-grained tasks.
A 64x temporally compressed motion embedding learned from trackers enables efficient conditional flow-matching generation of long-term motions that outperform video models and task-specific methods.
Re2Pix decomposes video prediction into semantic feature forecasting followed by representation-conditioned diffusion synthesis, with nested dropout and mixed supervision to handle prediction errors.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
TC-WM converts foundation-model visual embeddings into parsimonious task-sufficient world model latents via linear projection, contrastive physical-state alignment, and embedding reconstruction, with a theoretical identification guarantee.
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.
citing papers explorer
-
Learning Visual Feature-Based World Models via Residual Latent Action
RLA-WM predicts residual latent actions via flow matching to create visual feature world models that outperform prior feature-based and diffusion approaches while enabling offline video-based robot RL.
-
Future Dynamic 3D Reconstruction: A 3D World Model with Disentangled Ego-Motion
FR3D predicts a persistent 3D latent representation for future dynamic reconstruction by explicitly disentangling scene evolution from agent trajectory and using foundation-model distillation.
-
Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving
Envision4D presents a feed-forward 4D Gaussian Splatting framework with future pose prediction, temporal attention, and conditioned motion lifting for pose-free extrapolation in autonomous driving scenes.
-
Text-Conditional JEPA for Learning Semantically Rich Visual Representations
TC-JEPA conditions masked feature prediction on text captions via sparse cross-attention to produce more semantically rich visual representations and outperforms contrastive methods on fine-grained tasks.
-
Learning Long-term Motion Embeddings for Efficient Kinematics Generation
A 64x temporally compressed motion embedding learned from trackers enables efficient conditional flow-matching generation of long-term motions that outperform video models and task-specific methods.
-
Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
Re2Pix decomposes video prediction into semantic feature forecasting followed by representation-conditioned diffusion synthesis, with nested dropout and mixed supervision to handle prediction errors.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
Back to Parsimonious Latents: Learning Task-Centric World Models from Visual Foundations
TC-WM converts foundation-model visual embeddings into parsimonious task-sufficient world model latents via linear projection, contrastive physical-state alignment, and embedding reconstruction, with a theoretical identification guarantee.
-
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
-
Video Generation with Predictive Latents
PV-VAE improves video latent spaces for generation by unifying reconstruction with future-frame prediction, reporting 52% faster convergence and 34.42 FVD gain over Wan2.2 VAE on UCF101.
-
What Drives Success in Physical Planning with Joint-Embedding Predictive World Models?
An empirical study of JEPA world models identifies architecture, training objective, and planning choices that yield a model outperforming DINO-WM and V-JEPA-2-AC on navigation and manipulation tasks.