HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.
Rapid: Redundancy-aware and compatibility- optimal edge-cloud partitioned inference for diverse vla models
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
A communication-aware execution method uses a request-response window and available connectivity maps to select request points during primitive execution, yielding best or tied-best task success with fewer attempts and lower failure rates in measured indoor scenarios.
FreqCache uses frequency domain properties to adaptively select, refresh, and budget token caches in VLN models, delivering 1.59x speedup with negligible overhead.
RoboECC delivers up to 3.28x speedup for VLA model inference via co-aware segmentation and network-aware adjustment with 2.55-2.62% overhead.
citing papers explorer
-
HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness
HeiSD delivers up to 2.45x faster inference for embodied VLA models by hybridizing speculative decoding with kinematic boundary detection and error-mitigation tricks while preserving task success rates.
-
Communication-Aware Robot Execution for Cloud Inference under Spatially Heterogeneous Connectivity
A communication-aware execution method uses a request-response window and available connectivity maps to select request points during primitive execution, yielding best or tied-best task success with fewer attempts and lower failure rates in measured indoor scenarios.
-
FreqCache: Accelerating Embodied VLN Models with Adaptive Frequency-Guided Token Caching
FreqCache uses frequency domain properties to adaptively select, refresh, and budget token caches in VLN models, delivering 1.59x speedup with negligible overhead.
-
RoboECC: Multi-Factor-Aware Edge-Cloud Collaborative Deployment for VLA Models
RoboECC delivers up to 3.28x speedup for VLA model inference via co-aware segmentation and network-aware adjustment with 2.55-2.62% overhead.