Pith. sign in

REVIEW 14 cited by

CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.13725 v1 pith:VTBU3L2X submitted 2025-06-16 cs.RO

CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding

classification cs.RO
keywords decodingdistillationinferenceaccelerationceed-vlaconsistencyearly-exitefficient
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

In recent years, Vision-Language-Action (VLA) models have become a vital research direction in robotics due to their impressive multimodal understanding and generalization capabilities. Despite the progress, their practical deployment is severely constrained by inference speed bottlenecks, particularly in high-frequency and dexterous manipulation tasks. While recent studies have explored Jacobi decoding as a more efficient alternative to traditional autoregressive decoding, its practical benefits are marginal due to the lengthy iterations. To address it, we introduce consistency distillation training to predict multiple correct action tokens in each iteration, thereby achieving acceleration. Besides, we design mixed-label supervision to mitigate the error accumulation during distillation. Although distillation brings acceptable speedup, we identify that certain inefficient iterations remain a critical bottleneck. To tackle this, we propose an early-exit decoding strategy that moderately relaxes convergence conditions, which further improves average inference efficiency. Experimental results show that the proposed method achieves more than 4 times inference acceleration across different baselines while maintaining high task success rates in both simulated and real-world robot tasks. These experiments validate that our approach provides an efficient and general paradigm for accelerating multimodal decision-making in robotics. Our project page is available at https://irpn-eai.github.io/CEED-VLA/.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 14 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models

    cs.CV 2026-06 unverdicted novelty 7.0

    Mix-QVLA is a task-evidence-aware mixed-precision PTQ framework for VLA models that preserves task-relevant evidence via evidence-mass and attribution-distribution metrics to guide bit allocation under memory and BitO...

  2. DFM-VLA: Iterative Action Refinement for Robot Manipulation via Discrete Flow Matching

    cs.RO 2026-03 conditional novelty 7.0

    DFM-VLA uses discrete flow matching to iteratively refine action tokens in VLA models, outperforming autoregressive and diffusion baselines with 4.44 average success length on CALVIN and 95.7% success on LIBERO.

  3. HeiSD: Hybrid Speculative Decoding for Embodied Vision-Language-Action Models with Kinematic Awareness

    cs.RO 2026-03 unverdicted novelty 7.0

    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.

  4. KERV: Kinematic-Rectified Speculative Decoding for Embodied VLA Models

    cs.RO 2026-03 unverdicted novelty 7.0

    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.

  5. PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models

    cs.CV 2026-06 unverdicted novelty 6.0

    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.

  6. Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

    cs.CV 2026-05 conditional novelty 6.0

    VLA-AD distills 7B VLA teachers into 158M students using offline VLM semantic guidance on task phases and directions, matching teacher performance on LIBERO with 44x size reduction and 3.28x speedup.

  7. VLA-InfoEntropy: A Training-Free Vision-Attention Information Entropy Approach for Vision-Language-Action Models Inference Acceleration and Success

    cs.CV 2026-04 unverdicted novelty 6.0

    VLA-InfoEntropy accelerates Vision-Language-Action model inference by using visual entropy, attention entropy, and timestep cues to prune redundant tokens while preserving task-critical content.

  8. FASTER: Rethinking Real-Time Flow VLAs

    cs.RO 2026-03 conditional novelty 6.0

    FASTER uses a horizon-aware flow sampling schedule to compress immediate-action denoising to one step, slashing effective reaction latency in real-robot VLA deployments.

  9. FASTER: Rethinking Real-Time Flow VLAs

    cs.RO 2026-03 unverdicted novelty 6.0

    FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.

  10. ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models

    cs.CV 2025-11 conditional novelty 6.0

    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 spe...

  11. Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models

    cs.CV 2026-06 conditional novelty 5.0

    Biasing the training time distribution toward high-noise states enables one-step action generation in VLA models that matches or exceeds ten-step decoding on LIBERO benchmarks and real-robot tasks.

  12. Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models

    cs.CV 2026-06 conditional novelty 5.0

    High-noise flow-matching training makes one-step VLA action decoding competitive with multi-step decoding because actions are compact targets under rich observations.

  13. Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performance

    cs.RO 2026-03 unverdicted novelty 5.0

    Parameter differences from two training runs on a small task set are treated as auxiliary capability vectors that are merged into a pretrained VLA model, yielding auxiliary-task gains at the cost of ordinary supervise...

  14. OmniVLA-RL: A Vision-Language-Action Model with Spatial Understanding and Online RL

    cs.RO 2026-04 unverdicted novelty 4.0

    OmniVLA-RL uses a mix-of-transformers architecture and flow-matching reformulated as SDE with group segmented policy optimization to surpass prior VLA models on LIBERO benchmarks.