T3R: Training-Free Two-Stage Token Refinement Towards Efficient and Robust VLA Models
cs.RO, cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Terminology
Sources
- SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Token Merging: Your ViT But Faster
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- RT-1: Robotics Transformer for Real-World Control at Scale
- An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models
- The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
- OpenVLA: An Open-Source Vision-Language-Action Model
- Segment Anything
- CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
- Evaluating Real-World Robot Manipulation Policies in Simulation
- ATLAS: Verifier-Guided Adaptive Latent Activation Steering for Efficient LLM Reasoning
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification
- SAM 2: Segment Anything in Images and Videos
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
- LLaVA-PruMerge: Adaptive Token Reduction for Efficient Large Multimodal Models
- Efficient Track Anything
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