REVIEW 24 cited by
3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Manipulation has long been a challenging task for robots, while humans can effortlessly perform complex interactions with objects, such as hanging a cup on the mug rack. A key reason is the lack of a large and uniform dataset for teaching robots manipulation skills. Current robot datasets often record robot action in different action spaces within a simple scene. This hinders the robot to learn a unified and robust action representation for different robots within diverse scenes. Observing how humans understand a manipulation task, we find that understanding how the objects should move in the 3D space is a critical clue for guiding actions. This clue is embodiment-agnostic and suitable for both humans and different robots. Motivated by this, we aim to learn a 3D flow world model from both human and robot manipulation data. This model predicts the future movement of the interacting objects in 3D space, guiding action planning for manipulation. Specifically, we synthesize a large-scale 3D optical flow dataset, named ManiFlow-110k, through a moving object auto-detect pipeline. A video diffusion-based world model then learns manipulation physics from these data, generating 3D optical flow trajectories conditioned on language instructions. With the generated 3D object optical flow, we propose a flow-guided rendering mechanism, which renders the predicted final state and leverages GPT-4o to assess whether the predicted flow aligns with the task description. This equips the robot with a closed-loop planning ability. Finally, we consider the predicted 3D optical flow as constraints for an optimization policy to determine a chunk of robot actions for manipulation. Extensive experiments demonstrate strong generalization across diverse robotic manipulation tasks and reliable cross-embodiment adaptation without hardware-specific training.
Forward citations
Cited by 24 Pith papers
-
Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer
A taxonomy of eight foundation-model priors organizes HOI reconstruction, generation, and embodied transfer, mapping what knowledge large models inject and where.
-
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
-
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
Pace-and-Path Correction decomposes a quadratic cost minimization into orthogonal pace and path channels to correct chunked actions in VLA models, raising success rates by up to 28.8% in dynamic settings.
-
Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action Policies
Track4Action distills a frozen 3D tracker's pooled feature over demonstration clips into track queries that condition a VLA action head, reporting gains on LIBERO, LIBERO-Plus, RoboTwin 2.0, and physical bimanual task...
-
SG-WAM: Self-Guided World Modeling in Geometry-Aware Policy Space
A 0.9B policy that couples action generation with latent future-state prediction in its own representation space, plus geometric supervision, reaches 98.5% LIBERO and 73% LIBERO-Plus.
-
ContactFlow: A video action conditioning that transfers across embodiments
A contact-point-based action representation lets a video world model transfer manipulation knowledge across human and robot embodiments.
-
Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations
A framework learns invariant symbolic reward functions from few demonstrations that generalize zero-shot to variations in robotic manipulation tasks.
-
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
GEM-4D improves video world models for robot manipulation by distilling 4D geometric correspondences into training and adding an inverse dynamics module, achieving SOTA geometric consistency and 81% real-world success.
-
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.
-
GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
GuidedVLA improves VLA success rates by manually supervising separate attention heads in the action decoder with auxiliary signals for task-relevant factors.
-
Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
Pace-and-Path Correction is a closed-form inference-time operator that decomposes a quadratic cost minimization into orthogonal pace compression and path offset channels to correct dynamics-blindness in chunked-action...
-
LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior
Dense 3D scene flow as a one-step latent motion prior, fused by gated cross-attention, yields higher VLA success rates and OOD robustness than baselines under matched training budgets.
-
3PoinTr: 3D Point Tracks for Learning Manipulation from Unconstrained Human Videos
Dense 3D point-track prediction from unconstrained human videos plus a track-conditioned closed-loop policy yields large sample-efficiency gains over BC and video-pretraining baselines.
-
A Comprehensive Survey on World Models for Embodied AI
A unified three-axis taxonomy — functionality, temporal modeling, spatial representation — organizes the world-model literature for embodied AI.
-
Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer
Foundation-model HOI work is organized into eight geometric, semantic, and visual sub-priors that enter six reconstruction/generation tasks and three robot-transfer routes.
-
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos learns and maintains control-sufficient world states via a cross-embodiment curriculum, hybrid linear temporal attention, and deployment-aware co-design for Physical AI.
-
Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI
Kairos is a native world model stack using cross-embodiment pretraining, hybrid linear temporal attention with theoretical error bounds, and deployment-aware co-design, reporting top performance on embodied benchmarks.
-
GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation
GEM-4D is a video world model that injects 4D correspondence supervision to improve geometric consistency and robot manipulation success from 61% to 81%.
-
From World Models to World Action Models: A Concise Tutorial for Robotics
World models are action-conditioned predictors of task-relevant futures; world action models couple those futures to robot actions via four paradigms: imagine-then-execute, feature-conditioned, joint, and auxiliary pr...
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
From World Models to World Action Models: A Concise Tutorial for Robotics
A tutorial defining world models and world action models for robotics, with design axes and a four-paradigm taxonomy of prediction-action coupling.
-
From World Models to World Action Models: A Concise Tutorial for Robotics
A tutorial that categorizes world models into observation-space and state-space types and outlines four paradigms for world action models connecting predictions to robot actions.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
-
From World Models to World Action Models: A Concise Tutorial for Robotics
A tutorial taxonomizes world models for robotics into observation-space and state-space types and introduces world action models via four paradigms linking predictions to executable actions.
Discussion (0). Sign in to comment.