Vision-Language Models Are Joint Denoisers in Robotic Action Generation
cs.RO, cs.AI, cs.CV
Submitted: 2026-10-31
Updated: 2026-11-05
Code: https://github.com/gxccc123/JADE
Terminology
Sources
- Cosmos 3: Omnimodal World Models for Physical AI
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RT-1: Robotics Transformer for Real-World Control at Scale
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- WorldVLA: Towards Autoregressive Action World Model
- BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
- RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
- Emerging Properties in Unified Multimodal Pretraining
- ActionCodec: What Makes for Good Action Tokenizers
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- OpenVLA: An Open-Source Vision-Language-Action Model
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Causal World Modeling for Robot Control
- RotVLA: Rotational Latent Action for Vision-Language-Action Model
- OAT: Ordered Action Tokenization
- G0.5: One Autoregressive Stream for Robot Reasoning and Action
- Transfer between Modalities with MetaQueries
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