Efficient VLA Inference via Retrieval-Based Speculation and Hardware Acceleration
cs.AR, cs.RO
Submitted: 2026-11-08
Updated: 2026-11-11
Terminology
Sources
- WorldVLA: Towards Autoregressive Action World Model
- Embodied AI: From LLMs to World Models
- VLA-0: Building State-of-the-Art VLAs with Zero Modification
- Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- OpenVLA: An Open-Source Vision-Language-Action Model
- LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning
- RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
- DINOv2: Learning Robust Visual Features without Supervision
- FAST: Efficient Action Tokenization for Vision-Language-Action Models
- SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
- Unified Vision-Language-Action Model
- A Survey on Efficient Vision-Language-Action Models
- KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models
- HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
- Characterizing Vision-Language-Action Models across XPUs: Constraints and Acceleration for On-Robot Deployment
Related papers
- Embedded Arena: Iterative Optimization via Hardware Feedback
- WitCert: Sound Runtime Risk Observability and Gating for KV-Cache Quantization
- SparsePixels: Efficient Convolution for Sparse Data on FPGAs
- Golden Ruler: A Numeric Format Catalog with Bit-Exact Conformance Vectors for FP8, BF16, MXFP4, and Microscaling Formats
- AMMA: A Multi-Chiplet Memory-Centric Architecture for Low-Latency 1M Context Attention Serving
- RFChipAgent: Multi-Agentic AI Flow for Analog/RF Chip Design