arXiv:2608. 14379v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation.
StreamPI introduces a streaming multimodal temporal modeling framework that enhances Vision‑Language‑Action models by adding temporal reasoning without extra parameters. It anchors each visual observation and language instruction pair as a temporal unit, using bidirectional attention for cross‑modal fusion and causal attention for autoregressive streaming inference. The method employs random‑interval streaming training to improve robustness and leverages the LLM backbone’s length extrapolation to inherit pretrained weights, achieving superior performance over pi0.5 on real‑robot and simulation tasks.
Vision-Language-Action (VLA) models have demonstrated effectiveness in robot manipulation, yet state-of-the-art models such as pi0.5 operate under a single-frame paradigm, limiting their ability to re...
PaceVLA introduces adaptive temporal action quantization for Vision‑Language‑Action models, enabling faster robot execution by aggregating low‑level actions into coarser steps when appropriate. The framework combines mode‑specific action decoders with a quantizability‑guided mode selection and a context‑conditioned router to decide execution granularity at each inference step. Experiments on simulation benchmarks and real‑world tasks demonstrate that PaceVLA improves execution efficiency while preserving task success rates across diverse embodiments.
DynamicVLA is a latency‑aware Vision‑Language‑Action model designed for dynamic object manipulation, featuring a compact 0.4B architecture and a convolutional vision encoder for efficient multimodal inference. It employs a continuous inference schedule that overlaps reasoning and execution, and a Latent‑aware Action Streaming mechanism that discards stale action prefixes to maintain action‑time alignment. The authors also introduce the Dynamic Object Manipulation (DOM) benchmark, comprising 200K synthetic episodes and 2K real‑world episodes, and demonstrate that DynamicVLA improves dynamic manipulation success in simulation and on real robots.
Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execu...
arXiv:2607. 15275v1 Announce Type: cross Abstract: Recent robot foundation models operate with single-step or short-history visuomotor context.
arXiv:2606. 09811v1 Announce Type: cross Abstract: World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical priors into policy learning.
The paper presents Real‑Time EXPO‑FT, a reinforcement learning framework that fine‑tunes large Vision‑Language‑Action models for real‑time robotic control. It separates slow, expressive action generation from fast, reactive edits, allowing a lightweight policy to adjust actions based on the latest observation. Experiments on the Kinetix benchmark and four dynamic real‑world tasks show that Real‑Time EXPO‑FT achieves superior performance, improving policy success rates from 42% to 97% with only ten minutes of online data and no human intervention.
arXiv:2606. 20246v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models pre-trained on massive video-robot datasets have revolutionized robotic manipulation, yet their multi-billion parameter architectures impose prohibitive computational burdens during downstream fine-tuning and real-time inference.
VLA‑Δ introduces a framework that explicitly learns physical state transitions for vision‑language‑action models, using changes between current and future states as learning targets. The authors build a large‑scale pretraining dataset with physical state‑transition annotations that cover task‑relevant semantics and visual motion changes, providing direct supervision for continuous action generation. The resulting model performs competitively on LIBERO and RoboTwin benchmarks and outperforms π₀.₅ in real‑robot experiments, while requiring no extra inference overhead.
The paper introduces Action–Future Coupled Effect Learning (AFCE), a method that shifts the primary prediction target of vision‑language‑action (VLA) policies from action chunks to future‑grounded physical Effects. AFCE constructs temporally ordered Effect tokens from demonstrations, robot responses, and visual transitions, and uses reconstruction objectives to preserve executable detail and physical change. On the DexJoCo benchmark, AFCE achieves a 50.97% overall success rate, outperforming baseline policies by 11.82 and 15.21 percentage points and excelling on all five bimanual tasks, underscoring the benefit of Effect supervision for coordinated dexterous manipulation.