VLA models from VLM adaptation can be pruned 12-30% via multi-module joint scheme based on divergence signals while keeping ~90% performance on LIBERO without post-pruning recovery, unlike standard criteria that collapse.
hub
arXiv preprint arXiv:2502.02175 (2025)
22 Pith papers cite this work. Polarity classification is still indexing.
22
Pith papers citing it
hub tools
citation-role summary
background 3
baseline 1
citation-polarity summary
representative citing papers
Latent Bridge predicts VLM feature deltas to reduce VLM calls by 50-75% in dual-system VLA models while retaining 95-100% performance and achieving 1.65-1.73x speedup across LIBERO, RoboCasa, and ALOHA benchmarks.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
VLA models exhibit a compute-bound VLM phase followed by a memory-bound action phase on edge hardware; DP-Cache and V-AEFusion reduce redundancy and enable pipeline parallelism for up to 6x speedup on NPUs with marginal task degradation.
VLN-Cache delivers up to 1.52x faster inference in VLN models by using view-aligned remapping for geometric consistency and a task-relevance saliency filter to manage semantic changes during navigation.
KERV integrates kinematic Kalman Filter predictions with speculative decoding in VLA models to achieve 27-37% faster inference while maintaining nearly the same task success rates.
QuantVLA is the first post-training quantization framework for VLA models that quantizes the diffusion transformer action head and reports higher task success rates than full-precision baselines with roughly 70% memory savings on the quantized components.
TISED decomposes inference optimization effects on embodied tasks and identifies paradoxical outcomes where faster per-step inference can increase task completion time on static tasks or raise success rates on dynamic tasks.
SSI-Policy uses an RGB-only Structured Scene Interface to improve LIBERO benchmark performance by nearly 15% with only 10 demonstrations per task compared to prior methods.
Kamera stores a low-rank patch with each position-free KV chunk to restore cross-chunk conditioning lost in naive reuse, enabling cheap reordering, sliding windows, and recall across attention mechanisms.
PolicyTrim is an RL post-training framework that boosts VLA policy efficiency by 3x chunk utilization and 51.4% fewer steps, yielding up to 5.83x speedup.
A video transfer pipeline augments simulated VLA data into realistic videos while preserving actions, yielding consistent performance gains on robot benchmarks such as 8% on Robotwin 2.0.
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
Sentinel-VLA adds metacognitive status monitoring to VLA models for on-demand reasoning and error recovery, reporting over 30% higher real-world task success than prior SOTA.
FreqCache uses frequency domain properties to adaptively select, refresh, and budget token caches in VLN models, delivering 1.59x speedup with negligible overhead.
A1 is a transparent VLA framework achieving state-of-the-art robot manipulation success with up to 72% lower latency via adaptive layer truncation and inter-layer flow matching.
OxyGen unifies KV cache management in MoT VLAs to enable cross-task KV sharing and cross-frame continuous batching, delivering up to 3.7x speedup with 200+ tokens/s language and 70 Hz action on on-device platforms.
ActDistill transfers action knowledge from heavy VLA teacher models to lightweight students via graph-encapsulated hierarchies and action-guided dynamic routing, delivering over 50% computation reduction and 1.67x speedup with comparable or better performance on embodied tasks.
BAC accelerates transformer-based Diffusion Policy up to 3x by block-level adaptive feature caching using an Adaptive Caching Scheduler and Bubbling Union Algorithm to control error propagation.
AVA-VLA reformulates VLA learning as a POMDP using recurrent states and active visual attention to achieve state-of-the-art results on LIBERO, CALVIN, and real dual-arm tasks.
This survey organizes large VLM-based VLA models for robotic manipulation into monolithic and hierarchical paradigms, reviews their integrations and datasets, and outlines future directions.
AttenA+ reweights action training objectives in VLA and WAM models via inverse velocity attention to prioritize kinematically critical segments, yielding small benchmark gains.
citing papers explorer
-
Block-wise Adaptive Caching for Accelerating Diffusion Policy
BAC accelerates transformer-based Diffusion Policy up to 3x by block-level adaptive feature caching using an Adaptive Caching Scheduler and Bubbling Union Algorithm to control error propagation.