Gaze Prompts: Temporally Dense Human Attention for Vision-Language-Action Fine-Tuning
cs.RO
Submitted: 2026-09-28
Updated: 2026-09-28
Project page: https://gazemani.github.io
Terminology
Sources
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models
- Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policy
- Stable Language Guidance for Vision-Language-Action Models
- Grounding Hierarchical Vision-Language-Action Models Through Explicit Language-Action Alignment
- Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation
- FocusVLA: Focused Visual Utilization for Vision-Language-Action Models
- AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
- TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models
- AimBot: A Simple Auxiliary Visual Cue to Enhance Spatial Awareness of Visuomotor Policies
- VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
- Efficiently Guiding Imitation Learning Agents with Human Gaze
- Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers
- Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop
- PaliGemma: A versatile 3B VLM for transfer
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving