DIVA: Dual-Space Intent-Aware Visual Attenuation for Vision-Language-Action Policies
cs.AI
Submitted: 2026-10-06
Updated: 2026-10-06
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
- LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
- The Better You Learn, The Smarter You Prune: Towards Efficient Vision-language-action Models via Differentiable Token Pruning
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models
- Vision-Language Foundation Models as Effective Robot Imitators
- RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
- Gaze-Regularized Vision-Language-Action Models for Robotic Manipulation
- Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver
- Interactive Post-Training for Vision-Language-Action Models
- ETA-VLA: Efficient Token Adaptation via Temporal Fusion and Intra-LLM Sparsification for Vision-Language-Action Models
- Unified Vision-Language-Action Model
- AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
- FILIP: Fine-grained Interactive Language-Image Pre-Training
- Robotic Control via Embodied Chain-of-Thought Reasoning
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems