VLALagBench: Understanding When and Why VLA Inference Latency Matters
cs.RO
Submitted: 2026-11-02
Updated: 2026-11-16
Code: https://github.com/NVIDIA/Isaac-GR00T
Terminology
Sources
- Dynamic Grasping with Reachability and Motion Awareness
- MolmoAct2: Action Reasoning Models for Real-world Deployment
- How Fast Can I Run My VLA? Demystifying VLA Inference Performance with VLA-Perf
- TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
- Running VLAs at Real-time Speed
- Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving
- VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
- DynamicVLA: A Vision-Language-Action Model for Dynamic Object Manipulation
- VLA-HWBench: Where the Time Goes When VLA Models Run on Edge Hardware
- Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization
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