Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
cs.CV
Submitted: 2026-10-04
Updated: 2026-10-12
Project page: https://tudneurips2026.github.io/Abstract
Sources
- PaliGemma: A versatile 3B VLM for transfer
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
- Towards Synergistic, Generalized, and Efficient Dual-System for Robotic Manipulation
- HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers
- OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation
- Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
- OneTwoVLA: A Unified Vision-Language-Action Model with Adaptive Reasoning
- VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Models
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
- EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
- CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsification
- BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning
- SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead
- Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
- QuantVLA: Scale-Calibrated Post-Training Quantization for Vision-Language-Action Models
- CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models