TAVIS is a released benchmark showing active vision improves imitation learning in a task-dependent manner, multi-task policies struggle with shifts, and imitation produces human-like anticipatory gaze.
hub Mixed citations
LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
Mixed citation behavior. Most common role is background (46%).
89
Pith papers citing it
Background
46% of classified citations
abstract
Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing controlled perturbations across seven dimensions: objects layout, camera viewpoints, robot initial states, language instructions, light conditions, background textures and sensor noise. We comprehensively analyzed multiple state-of-the-art models and revealed consistent brittleness beneath apparent competence. Our analysis exposes critical weaknesses: models exhibit extreme sensitivity to perturbation factors, including camera viewpoints and robot initial states, with performance dropping from 95% to below 30% under modest perturbations. Surprisingly, models are largely insensitive to language variations, with further experiments revealing that models tend to ignore language instructions completely. Our findings challenge the assumption that high benchmark scores equate to true competency and highlight the need for evaluation practices that assess reliability under realistic variation.
hub tools
citation-role summary
background 15
dataset 7
baseline 3
method 1
citation-polarity summary
claims ledger
- abstract Visual-Language-Action (VLA) models report impressive success rates on robotic manipulation benchmarks, yet these results may mask fundamental weaknesses in robustness. We perform a systematic vulnerability analysis by introducing controlled perturbations across seven dimensions: objects layout, camera viewpoints, robot initial states, language instructions, light conditions, background textures and sensor noise. We comprehensively analyzed multiple state-of-the-art models and revealed consistent brittleness beneath apparent competence. Our analysis exposes critical weaknesses: models exhibit
- background However, standard VLA models do not explicitly model world dynamics ithey learn direct observation-to- action mappings without predicting how the environment changes under intervention[ 4]. This absence of predictive physical reasoning limits their generalization, where anticipating future states is essential. Equip- ping embodied policy models with world modeling capabilities thus emerges as a natural direction [ 5]. A growing body of recent work has begun integrating world models into the embo
co-cited works
representative citing papers
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.
LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
DuoBench introduces eleven bimanual manipulation tasks with stage-based evaluation and human datasets to benchmark imitation-learning and vision-language-action policies on dual-arm robots in sim and real settings.
PROBEACT is a plug-and-play intervention framework that combines hidden-state probing, kinematic failure detection, and CBF-based correction to boost success rates of pre-trained VLA models on the LIBERO-plus benchmark from 69.6% to 74.1%.
MetaFine reconstructs benchmarks into diagnostic scenarios to evaluate vision-language-action models on fine-grained manipulation, exposing dimension-specific failures and identifying the visual encoder as a key bottleneck.
Pion modifies Muon's Newton-Schulz iterations into a controllable high-pass filter that anchors dominant singular values at 1 while suppressing noisy tails, outperforming Muon and AdamW in VLA and RLVR regimes.
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
GridS is a plug-and-play differentiable module for geometry-aware visual token resampling in VLA models that achieves under 10% token retention and 76% FLOPs reduction with no success-rate loss.
MCF-Proto adds a motion-centric local action frame and prototype parameterization to VLA models, inducing emergent geometric structure and improved robustness from standard demonstrations alone.
LoopVLA adds recurrent refinement and learned sufficiency estimation to VLA models, cutting parameters 45% and raising throughput 1.7x while matching baseline task success on LIBERO and VLA-Arena.
ECHO organizes VLA experiences into a hierarchical memory tree in hyperbolic space via autoencoder and entailment constraints, delivering a 12.8% success-rate gain on LIBERO-Long over the pi0 baseline.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
Introduces ISS and NMR as interventional metrics to diagnose causal misalignment in VLA policies and link it to generalization performance.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
Mini-BEHAVIOR-Gran benchmark reveals a U-shaped effect of instruction granularity on embodied agent performance, with planning-width correlating best and coarse instructions linked to vision-dominant shallow policies.
VP-VLA decouples high-level reasoning from low-level control in VLA models by rendering spatial anchors as visual prompts directly in the RGB observation space, outperforming end-to-end baselines.
PlayWorld learns high-fidelity robot world models from unsupervised self-play, producing physically consistent video predictions that outperform models trained on human data and enabling 65% better real-world policy performance via model-based RL.
TAP uses two-stage pretraining on unlabeled data to learn physical competence before language grounding, matching 1M-expert models with far less labeled data and showing robustness on real robots.
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
ABot-M0.5 proposes a unified mobility-and-manipulation world action model using three alignment strategies that achieves state-of-the-art performance on mobile and fine-grained manipulation benchmarks.
3D HAMSTER adds depth encoding and reconstruction to VLMs to produce 3D waypoint sequences that feed directly into pointcloud policies, claiming better generalization than 2D baselines under shifts.
SPARK reaches 43.7% success on six LIBERO-PRO cells by LLM-generated typed behavior trees plus multi-prompt perception and recovery, more than doubling CaP-Agent0 and VLA baselines.
Direct 3D point grounding injected into the action head via a two-layer MLP and adaptive layer norm boosts VLA success rates by 32-46 points on spatial and task perturbations in LIBERO-PRO.
citing papers explorer
-
HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic Manipulation
HiMem-WAM integrates hierarchical latent actions and boundary-aware memory gates into world action models to enhance robustness and performance on memory-dependent long-horizon robotic tasks.
-
MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Models
MemoryVLA++ integrates a perceptual-cognitive memory bank and denoising world model into VLA models to enable temporal reasoning, yielding performance gains on manipulation benchmarks and real-robot tasks.
-
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
PointACT proposes a 3D-aware dual-system VLA policy using multi-scale point-action interaction with bottleneck window self-attention, achieving 10% higher success rates on RLBench-10Tasks over prior pretrained VLAs.
-
RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Models
RoVLA enforces instructional, evolutionary, and observational consistency to improve robustness of VLA policies on manipulation benchmarks and real robots.
-
Key-Gram: Extensible World Knowledge for Embodied Manipulation
Key-Gram uses a memory module with key-grams and hashed lookup to inject static linguistic priors into vision-language-action backbones, yielding reported gains on manipulation benchmarks.
-
VLAMotor: Test-Guided Enhancement of Vision-Language-Action Models via Agent-BasedData Synthesis
VLAMotor exposes VLA failures via distance-aware uncertainty testing and synthesizes agent-planned repair data to fine-tune models, reporting 49.25% success rate gains in simulation and 57.5% on hardware.
-
Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulation
The method uses multi-view diffusion priors and action manifold learning to resolve depth ambiguity and improve action prediction in VLA robotic manipulation models, reporting higher success rates than baselines on LIBERO, RoboTwin, and real-robot tasks.
-
CKT-WAM: Parameter-Efficient Context Knowledge Transfer Between World Action Models
CKT-WAM transfers teacher WAM knowledge to students via compressed text-embedding contexts using LQCA and adapters, reaching 86.1% success on LIBERO-Plus with 1.17% trainable parameters and 83.3% in real-world tasks.
-
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
-
PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
PokeVLA is a lightweight VLA model pre-trained on 2.4M samples for spatial grounding and reasoning, then adapted via multi-view semantics and geometry alignment to achieve state-of-the-art robot manipulation performance.
-
Bridge-WA: Predicting Where and How the World Changes for Robotic Action
Bridge-WA introduces a lightweight distillation-based world-action model that uses future-change priors to improve robotic task success and robustness without deployment-time dense rollouts.
-
Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies
Guided Action Flow applies a rollout-trained critic to steer frozen flow-matching VLA policies at inference time via action gradients, reporting success rate gains on LIBERO manipulation tasks.
-
Unleashing More Actions via Action Compositional Training for VLA Models
ACT-VLA synthesizes novel demonstrations from existing VLA tasks via latent representations to reduce overfitting and improve generalization on manipulation tasks in simulation.
-
World Action Models: The Next Frontier in Embodied AI
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
-
Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform
Real-robot trials with OpenVLA on a UR5e arm show consistent offline-to-closed-loop gaps driven by action semantics, coordinate conventions, temporal alignment, image preprocessing, and dataset quality rather than model capacity.
-
Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines
A survey of VLA robotics research identifies data infrastructure as the primary bottleneck and distills four open challenges in representation alignment, multimodal supervision, reasoning assessment, and scalable data generation.