A multimodal transformer generates and caches interleaved text-image traces to guide closed-loop actions, achieving 92.4% success on LIBERO-Long and 95.5% average on LIBERO.
dvla: Diffusion vision-language-action model with multimodal chain-of-thought.arXiv preprint arXiv:2509.25681
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 3
baseline 1
citation-polarity summary
verdicts
UNVERDICTED 13representative citing papers
Discrete diffusion policies act as natural asynchronous executors for robotics by treating action generation as iterative unmasking, yielding higher success rates and lower computation than flow-matching real-time chunking in dynamic tasks.
PAMAE adds a phase-aware router and expert mixture to flow-matching VLA models, yielding up to 9.2% higher task success on multi-stage manipulation simulations via two-stage training.
dVLA-RL models denoising as an MDP to enable RL on dVLAs via trajectory probabilities, reporting 99.7% success on LIBERO and 30.6% gains over SFT on RoboTwin 2.0.
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.
Continuous Reasoning for VLA introduces a shared Gaussian latent for continuous thoughts, trained with self-verification to improve action prediction on LIBERO-PRO and real robots.
Fast-dDrive is a block-diffusion VLA that reports SOTA accuracy on WOD-E2E and nuScenes driving benchmarks together with 12x throughput over autoregressive baselines via section scaffolds and test-time averaging.
GuidedVLA improves VLA generalization by supervising individual attention heads with manually defined auxiliary signals for three task-relevant factors.
RePO-VLA raises average adversarial success rates in VLA manipulation from 20% to 75% by using recovery-aware initialization, a progress-aware semantic value function, and value-conditioned refinement on success and corrective trajectories.
A discrete diffusion model tokenizes multimodal robotic data and uses a progress token to predict future states and task completion for scalable policy evaluation.
Legato trains flow-based VLA policies with schedule-shaped action-noise mixtures and randomized conditions to achieve smoother trajectories and ~10% faster task completion than real-time chunking across five real-world manipulation tasks.
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
SyVLA uses Intention Decoupling and similar-sample guided RL on diversified experiences to improve VLA model task success and out-of-distribution generalization while keeping vision-language abilities.
citing papers explorer
No citing papers match the current filters.