DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
cs.RO, cs.LG
Submitted: 2026-05-28
Updated: 2026-11-03
Project page: https://dynaflip-robotics.github.io
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- Representation Learning with Contrastive Predictive Coding
- Language-Grounded Decoupled Action Representation for Robotic Manipulation
- Masked Visual Pre-training for Motor Control
- Towards Uniformity and Alignment for Multimodal Representation Learning
- PVI: Plug-in Visual Injection for Vision-Language-Action Models
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation