FlowHijack is the first dynamics-aware backdoor attack on flow-matching VLAs that achieves high success rates with stealthy triggers while preserving benign performance and making malicious actions kinematically indistinguishable from normal ones.
hub Canonical reference
Vision-language- action models: Concepts, progress, applications and chal- lenges.arXiv preprint arXiv:2505.04769
Canonical reference. 100% of citing Pith papers cite this work as background.
33
Pith papers citing it
Background
100% of classified citations
hub tools
citation-role summary
background 6
citation-polarity summary
roles
background 6polarities
background 6representative citing papers
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.
4DLidarOpen is a new open dataset providing synchronized 4D FMCW Lidar velocity measurements, multi-Lidar and camera data, and 3D bounding-box annotations with track IDs to support benchmarks on 3D detection, BEV segmentation, flow prediction, and motion forecasting.
RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.
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.
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
A vision-language model classifies road surface and visibility conditions from front-camera images, parametrizing a context-adaptive safety envelope that couples braking and steering through a shared friction budget, achieving 100% trial success in CARLA simulation across adverse conditions.
UniFS achieves 98.3% success on LIBERO with 2.1x lower latency than prior fast-slow VLA models by stratifying VLM layer update frequencies, inverting latent interactions, and applying multi-level supervision.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
Guava harness enables 4B open-source models to achieve performance comparable to frontier models on embodied manipulation tasks by distilling capabilities from under 2K simulation trajectories using three identified design principles.
A systematic study of hierarchical VLA agents identifies design principles that improve robot manipulation performance over flat and naive hierarchical baselines in simulation and real-world experiments.
SceneDiver introduces a coarse-to-fine focus plan generation approach for VLMs that constructs holistic scene graphs then iteratively decomposes tasks, plus a distillation adapter for VLAs, to reduce visual hallucinations in embodied AI benchmarks.
A structured perturbation framework applied to VLA driving models reveals evaluation-dependent visual grounding patterns and uneven dependency across abstraction levels.
A unified learnable KV eviction policy with cross-layer calibration reduces memory and matches or exceeds full-cache performance on long-context tasks by retaining useful tokens and limiting attention dilution.
ThermoAct integrates thermal imaging into VLA models via a VLM planner to enable robots to perceive physical properties like heat and improve safety over vision-only systems.
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.
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.
DeepThinkVLA shows CoT improves VLA models only under decoding and causal alignment, delivering 97% success on LIBERO and 21.7-point gains via hybrid attention and SFT-RL training.
SimpleVLA-RL applies tailored reinforcement learning to VLA models, reaching SoTA on LIBERO, outperforming π₀ on RoboTwin, and surpassing SFT in real-world tasks while reducing data needs and identifying a 'pushcut' phenomenon.
PhysMani couples a physics-principled 3D Gaussian world model with a future-aware policy to achieve higher success rates on dynamic manipulation tasks in simulation and real robots.
PhysReflect-VLA augments VLA policies with a Feasibility Operator, Action Explanation Operator, and LLM Reflection Module to improve success rates by an average of 5.4% on contact-rich multi-stage robotic tasks.
AdaWAM introduces an adaptive router that triggers textual or visual reasoning as needed in world action models, claiming better efficiency and performance than prior embodied policies on simulated and real tasks.
ImagineUAV is a 1.3B-parameter cascaded world-action framework that generates instruction-conditioned future observations via latent video diffusion, infers motions, and applies kinodynamic planning to outperform VLN/VLA baselines in aerial navigation.
citing papers explorer
-
RotVLA: Rotational Latent Action for Vision-Language-Action Model
RotVLA models latent actions as continuous SO(n) rotations with triplet-frame supervision and flow-matching to reach 98.2% success on LIBERO and 89.6%/88.5% on RoboTwin2.0 using a 1.7B-parameter model.
-
CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation
CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.
-
ViVa: A Video-Generative Value Model for Robot Reinforcement Learning
ViVa turns a video generator into a value model for robot RL that jointly forecasts future states and task value, yielding better performance on real-world box assembly when integrated with RECAP.
-
FASTER: Rethinking Real-Time Flow VLAs
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.
-
Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Survey
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.
-
Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.