A 4D latent predictive model encodes scenes holistically to generate 3D-consistent futures that an inverse dynamics module converts into robot actions, outperforming video-based planners on manipulation tasks.
Latent diffusion planning for imitation learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A Goal-Conditioned Inverse Dynamics Model amortizes planning in pretrained world model latents, matching or exceeding CEM in seven of eight settings at 100-130x lower per-decision cost.
SimDist pretrains world models in simulation and adapts them to real-world robots by updating only the latent dynamics model, enabling rapid improvement on contact-rich tasks where prior methods fail.
Sharing one discrete codebook between visual-dynamics and robot-motion branches and using the codes as auxiliary supervision improves cross-embodiment VLA success rates in the authors' real-robot tests.
OASIS improves robotic manipulation success and generalization by predicting camera-frame SE(3) end-effector trajectories to condition the action decoder on pose-supervised states.
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.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
citing papers explorer
-
Structured 4D Latent Predictive Model for Robot Planning
A 4D latent predictive model encodes scenes holistically to generate 3D-consistent futures that an inverse dynamics module converts into robot actions, outperforming video-based planners on manipulation tasks.
-
Latent Geometry Beyond Search: Amortizing Planning in World Models
A Goal-Conditioned Inverse Dynamics Model amortizes planning in pretrained world model latents, matching or exceeding CEM in seven of eight settings at 100-130x lower per-decision cost.
-
Simulation Distillation: Pretraining World Models in Simulation for Rapid Real-World Adaptation
SimDist pretrains world models in simulation and adapts them to real-world robots by updating only the latent dynamics model, enabling rapid improvement on contact-rich tasks where prior methods fail.
-
XR-1: Towards Versatile Vision-Language-Action Models via Learning Unified Vision-Motion Representations
Sharing one discrete codebook between visual-dynamics and robot-motion branches and using the codes as auxiliary supervision improves cross-embodiment VLA success rates in the authors' real-robot tests.
-
OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation
OASIS improves robotic manipulation success and generalization by predicting camera-frame SE(3) end-effector trajectories to condition the action decoder on pose-supervised states.
-
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.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.