Act2Answer protocol reveals VLA models retain simple concepts but show larger gaps on complex semantics than source VLMs, with VQA co-training linked to better retention and knowledge signals peaking in middle layers.
super hub Mixed citations
SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
Mixed citation behavior. Most common role is background (64%).
128
Pith papers citing it
Background
64% of classified citations
abstract
In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation model. Specifically, we introduce Ego3D Position Encoding to inject 3D information into the input observations of the visual-language-action model, and propose Adaptive Action Grids to represent spatial robot movement actions with adaptive discretized action grids, facilitating learning generalizable and transferrable spatial action knowledge for cross-robot control. SpatialVLA is first pre-trained on top of a vision-language model with 1.1 Million real-world robot episodes, to learn a generalist manipulation policy across multiple robot environments and tasks. After pre-training, SpatialVLA is directly applied to perform numerous tasks in a zero-shot manner. The superior results in both simulation and real-world robots demonstrate its advantage of inferring complex robot motion trajectories and its strong in-domain multi-task generalization ability. We further show the proposed Adaptive Action Grids offer a new and effective way to fine-tune the pre-trained SpatialVLA model for new simulation and real-world setups, where the pre-learned action grids are re-discretized to capture robot-specific spatial action movements of new setups. The superior results from extensive evaluations demonstrate the exceptional in-distribution generalization and out-of-distribution adaptation capability, highlighting the crucial benefit of the proposed spatial-aware representations for generalist robot policy learning. All the details and codes will be open-sourced.
hub tools
citation-role summary
background 18
baseline 8
method 1
other 1
citation-polarity summary
claims ledger
- abstract In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation model. Specifically, we introduce Ego3D Position Encoding to inject 3D information into the input observations of the visual-language-action model, and propose Adaptive Action Grids to represent spatial robot movement actions with adaptive discretized action grids, facilitating learning generalizable and transferrable spatial action knowledge for cross-robot control. SpatialVLA is first pre-trained on top of a vis
authors
co-cited works
representative citing papers
A prompt-only attack called command-preserving trajectory redirection can steer VLA robot behavior to attacker-chosen physical outcomes while the text still appears to match the intended task.
ReCoVLA improves VLA policy reliability by using a VLM as a semantic reward selector to train residual recovery policies in simulation, raising average success from 36.7% to 66.7% in sim and achieving 61.7% in zero-shot sim-to-real physical tests.
TTT-VLA performs test-time training for VLA models by optimizing only a latent prompt on new interaction data via a proxy self-supervised signal, yielding higher task success rates on SimplerEnv in single- and multi-embodiment settings.
JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
DSSP is a history-conditioned diffusion state space policy that uses SSMs to encode full observation streams with an auxiliary dynamics objective and hierarchical fusion, achieving SOTA results with reduced model size in robot manipulation.
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.
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
GuardVLA embeds a stealthy backdoor watermark in VLAs via secret messages in visual data and uses a swap-and-detect mechanism for post-release ownership verification that preserves task performance.
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
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.
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
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.
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.
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
Orientation information is recoverable from MLLM visual encoder embeddings via linear regression, contradicting the hypothesis that failures originate in the encoders.
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.
UniLACT improves VLA models by adding depth-aware unified latent action pretraining that outperforms RGB-only baselines on seen and unseen manipulation tasks.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
LaMem-VLA reconstructs robotic history into dual short-term and long-term latent memory tokens that are woven directly into a VLA model's reasoning sequence to improve long-horizon manipulation.
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.
Object-centric key-pose memory plus closed-loop flow matching yields 85.6% success and 1033 Hz equivalent control on ten LIBERO-GOAL tasks with a 0.24M-parameter model.
StaKe adds lightweight auxiliary heads for manipulation stage identification and next-gripper-transition keyframe prediction to VLA fine-tuning, reporting relative success rate gains of 14% in bimanual simulation and 56% on single-arm real-robot tasks.
citing papers explorer
-
Does VLA Even Know the Basics? Measuring Commonsense and World Knowledge Retention in Vision-Language-Action Models
Act2Answer protocol reveals VLA models retain simple concepts but show larger gaps on complex semantics than source VLMs, with VQA co-training linked to better retention and knowledge signals peaking in middle layers.
-
Trajectory-Level Redirection Attacks on Vision-Language-Action Models
A prompt-only attack called command-preserving trajectory redirection can steer VLA robot behavior to attacker-chosen physical outcomes while the text still appears to match the intended task.
-
ReCoVLA: VLM-Guided Reward Compilation for Failure Recovery in Vision-Language-Action Policies
ReCoVLA improves VLA policy reliability by using a VLM as a semantic reward selector to train residual recovery policies in simulation, raising average success from 36.7% to 66.7% in sim and achieving 61.7% in zero-shot sim-to-real physical tests.
-
TTT-VLA: Test-Time Latent Prompt Optimization for Vision-Language-Action Models
TTT-VLA performs test-time training for VLA models by optimizing only a latent prompt on new interaction data via a proxy self-supervised signal, yielding higher task success rates on SimplerEnv in single- and multi-embodiment settings.
-
Point Tracking Improves World Action Models
JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.
-
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
-
DSSP: Diffusion State Space Policy with Full-History Encoding
DSSP is a history-conditioned diffusion state space policy that uses SSMs to encode full observation streams with an auxiliary dynamics objective and hierarchical fusion, achieving SOTA results with reduced model size in robot manipulation.
-
See What Matters: Differentiable Grid Sample Pruning for Generalizable Vision-Language-Action Model
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.
-
VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models
VEGA improves spatial reasoning in VLA models for robotics by aligning visual encoder features with 3D-supervised DINOv2 representations via a temporary projector and cosine similarity loss.
-
Towards Backdoor-Based Ownership Verification for Vision-Language-Action Models
GuardVLA embeds a stealthy backdoor watermark in VLAs via secret messages in visual data and uses a swap-and-detect mechanism for post-release ownership verification that preserves task performance.
-
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
Reducing visual input to one token per frame in VLA world models maintains or improves long-horizon performance on MetaWorld, LIBERO, and real-robot tasks.
-
OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation
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.
-
EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
EA-WM generates more accurate robot world rollouts by projecting actions as structured visual fields in camera space and using event-aware bidirectional fusion to better capture interaction dynamics.
-
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
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.
-
Being-H0.7: A Latent World-Action Model from Egocentric Videos
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.
-
VistaBot: View-Robust Robot Manipulation via Spatiotemporal-Aware View Synthesis
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
-
Why MLLMs Struggle to Determine Object Orientations
Orientation information is recoverable from MLLM visual encoder embeddings via linear regression, contradicting the hypothesis that failures originate in the encoders.
-
VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
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.
-
UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models
UniLACT improves VLA models by adding depth-aware unified latent action pretraining that outperforms RGB-only baselines on seen and unseen manipulation tasks.
-
Learning Physics from Pretrained Video Models: A Multimodal Continuous and Sequential World Interaction Models for Robotic Manipulation
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
-
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation
LaMem-VLA reconstructs robotic history into dual short-term and long-term latent memory tokens that are woven directly into a VLA model's reasoning sequence to improve long-horizon manipulation.
-
Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulation
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.
-
OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation Model
Object-centric key-pose memory plus closed-loop flow matching yields 85.6% success and 1033 Hz equivalent control on ten LIBERO-GOAL tasks with a 0.24M-parameter model.
-
Improving Vision-Language-Action Model Fine-Tuning with Structured Stage and Keyframe Supervision
StaKe adds lightweight auxiliary heads for manipulation stage identification and next-gripper-transition keyframe prediction to VLA fine-tuning, reporting relative success rate gains of 14% in bimanual simulation and 56% on single-arm real-robot tasks.
-
MANGO: Automated Multi-Agent Test Oracle Generation for Vision-Language-Action Models
MANGO uses Generator, Assessor, and Judge agents to create reusable atomic tasks and fine-grained oracles from natural language, evaluated on LIBERO_10 and RoboCasa benchmarks for comparable failure detection with better localization.
-
G$^3$VLA: Geometric inductive bias for Vision-Language-Action Models
G³VLA injects calibrated camera geometry into VLA visual tokens via intrinsic-conditioned ray embeddings, PRoPE, and bidirectional cross-view fusion, producing consistent gains on LIBERO, RoboCasa24, RoboTwin2.0, and real-robot tasks when added to π₀.
-
Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
GRA extracts 2D waypoints from synthetic videos to supervise VLA vision while restricting action training to real data, outperforming pseudo-action baselines on real-robot tasks.
-
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
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.
-
ARP: Enhancing Quantized Skill Abstractions via Visual Alignment and Iterative Refinement for Robotic Manipulation
ARP enhances quantized skill abstractions in imitation learning by coupling visual grounding via contrastive alignment with execution refinement via IRH, reporting SOTA results on LIBERO, Meta-World, and real-robot tasks.
-
Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos
A Hybrid Disentangled VQ-VAE with physical masks creates a cross-embodiment action codebook from human videos, allowing VLA pre-training that adapts to new embodiments with only 50 trajectories.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
Geometric Action Model for Robot Policy Learning
GAM splits a geometric foundation model to enable language-conditioned future geometry prediction and action decoding for robot policies, claiming superior performance on manipulation benchmarks.
-
RoboPIN: Grounded Embodied Reasoning via Pinned Chain-of-Thought
Training a 4B vision-language model to emit identity-tracked, visually grounded reasoning anchors improves embodied spatial, multi-view, and pointing task performance over 7B baselines.
-
VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models
VeriSpace is a 3D-aware action verifier that improves test-time action selection in VLA models by encoding scenes with visual and geometric information and reasoning over spatial relations and goal progress.
-
CT-VAM: A Cerebello-Thalamic-Inspired Vision-Action Model for Efficient Visuomotor Control
CT-VAM is a 68M-parameter cerebello-thalamic-inspired model that achieves competitive LIBERO success rates with lower inference latency than larger VLA models by using a stream-separated attention decoder called TARS.
-
MotionVLA: Injecting Geometric Motion into Vision-Language-Action Model
MotionVLA converts short past video windows into compact trajectory-field tokens to supply motion-consistent evidence for vision-language-action robot policies, improving long-horizon manipulation.
-
LARA: Latent Action Representation Alignment for Vision-Language-Action Models
LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.
-
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.
-
3DThinkVLA: Endowing Vision-Language-Action Models with Latent 3D Priors via 3D-Thinking-Guided Co-training
A 3D-thinking-guided co-training method disentangles geometry perception and spatial reasoning to inject latent 3D priors into VLA models via adapters, achieving SOTA on manipulation benchmarks while running on 2D images only.
-
FATE-VLA:Failue-aware test generation for vision-language-action models
FATE-VLA reframes VLA evaluation as active failure discovery and reports uncovering up to 29.7% more failures across four models while revealing diverse failure modes.
-
Continuous Reasoning for Vision-Language-Action
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.
-
ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation
ELAN4D introduces plug-and-play 4D keypoint track supervision from forward kinematics to enhance VLA policy generalization in robotic manipulation tasks.
-
VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policies
VISUALTHINK-VLA uses visual evidence tokens and selective routing to reach top success rates on VLA benchmarks while cutting reasoning latency from multi-second to sub-second levels.
-
ReasonBreak: Probing Vulnerabilities in Reasoning-Enabled Vision-Language-Action Models for Autonomous Driving
ReasonBreak demonstrates up to 89% attack success on reasoning and 72% on trajectories in NVIDIA Alpamayo VLA models via black-box textual perturbations, introducing a reasoning-aware evaluation framework and benchmark for autonomous driving.
-
PrimitiveVLA: Learning Reusable Motion Primitives for Efficient and Generalizable Robotic Manipulation
PrimitiveVLA improves VLA fine-tuning by splitting demonstrations into a fixed library of reusable motion primitives and reassembling them with a VLM/LLM planner and switch code, reporting higher data efficiency and zero-shot generalization on Libero, RLBench, and a UR5e.
-
VLA-Hijack: A Transferable Patch Attack against Vision-Language-Action Models via Visual Proprioception Hijacking
VLA-Hijack is a new adversarial patch attack on Vision-Language-Action models that suppresses real arm features and injects the patch as surrogate embodiment to achieve high cross-architecture transferability.
-
LAST: Bridging Vision-Language and Action Manifolds via Gromov-Wasserstein Alignment
LAST linearizes action manifolds with Lie-algebraic mapping and discretizes them into approximately isotropic charts to align with VL semantic geometry via Gromov-Wasserstein distance.
-
X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models
X-DiffVLA proposes a diffusion VLA model using Embodiment Forcing and Morphological Tree Diffusion to achieve SOTA cross-embodied performance on simulation benchmarks with 15.3% and 12.5% gains.
-
Afford-VLA: Action-Aligned Visual Planning via Internalized Affordance
Afford-VLA internalizes task-conditioned affordance as an explicit visual planning interface within VLA models via learnable <AFF> tokens, achieving SOTA on LIBERO and SimplerEnv benchmarks.
-
IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulation
History-conditioned short-horizon intent tokens stabilize chunked VLA policies under observation aliasing and raise success on AliasBench and standard robot benchmarks.