X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
hub Mixed citations
Behavior generation with latent actions
Mixed citation behavior. Most common role is background (40%).
32
Pith papers citing it
Background
40% of classified citations
hub tools
citation-role summary
background 3
dataset 1
method 1
citation-polarity summary
representative citing papers
VLA architectures exhibit architecture-specific failure signatures at the motor-command level, with direction reversal as a universal predictor and velocity monitoring ineffective for continuous models.
PRISM replaces Markov or fixed-window intention models in multi-intention IRL with a recurrent network, proving an exact EM decomposition into closed-form per-intention reward problems and reporting highest held-out likelihood on gridworld, mouse, and robotic tasks.
Soft RTC uses partially denoised states for overlap tokens and token-wise blending to reduce action delta and jerk by ~9% versus hard RTC while matching solve rates on Kinetix levels.
The paper identifies distinct failure mechanisms: excessive posterior-prior regularization erases mode information in latent policies, while smooth base-to-action maps limit mode coverage in generative policies.
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.
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.
ReV is a referring-aware visuomotor policy using coupled diffusion heads for real-time trajectory replanning in robotic manipulation, trained solely via targeted perturbations to expert demonstrations and achieving higher success rates in simulated and real tasks.
Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
Modern imitation learning methods including Diffusion Policy and Implicit Behavior Cloning are highly vulnerable to universal adversarial perturbations, with successful black-box transfer attacks across algorithms.
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.
GLAM learns a shared latent action space grounded in consistent future observation prediction across heterogeneous data sources to train improved behavioral cloning policies for robot manipulation tasks.
AxisGuide augments RGB images with rendered robot base-frame axis cues to improve generalization of visuomotor manipulation policies under distribution shifts.
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
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.
COBALT enables scalable crowdsourced teleoperation of robots using smartphones, supporting concurrent users with low latency and yielding a 7500+ demonstration dataset validated on imitation learning tasks.
ALAM introduces algebraic consistency regularization on latent action transitions from videos, raising VLA success rates from 47.9% to 85.0% on MetaWorld MT50 and 94.1% to 98.1% on LIBERO.
A unified comparison of latent action supervision strategies for VLA models reveals task-specific benefits, with image-based approaches aiding reasoning and generalization, action-based aiding motor control, and discrete tokens proving most effective.
UniT creates a unified physical language via visual anchoring and tri-branch reconstruction to enable scalable human-to-humanoid transfer for policy learning and world modeling.
Discrete action tokenization in VLA models creates an information bottleneck that prevents vision encoder scaling from improving performance, unlike continuous policies, as validated on the LIBERO benchmark.
Stellar VLA achieves continual learning in VLA models by maintaining a growing knowledge space and routing tasks to specialized experts conditioned on semantic relations, delivering strong LIBERO benchmark results with only 1% data replay and successful real-world transfer on dual-arm hardware.
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
SmolVLA is a small efficient VLA model that achieves performance comparable to 10x larger models while training on one GPU and deploying on consumer hardware via community data and chunked asynchronous action prediction.
citing papers explorer
-
X-Tokenizer: A Multimodal Action Tokenizer for Vision-Language-Action Pretraining
X-Tokenizer creates semantic action tokens via asymmetric residual quantization and contrastive pretraining on large trajectory data, outperforming prior methods like FAST on robotic tasks.
-
How VLAs Fail Differently: Black-Box Action Monitoring Reveals Architecture-Specific Failure Signatures
VLA architectures exhibit architecture-specific failure signatures at the motor-command level, with direction reversal as a universal predictor and velocity monitoring ineffective for continuous models.
-
Probabilistic Recurrent Intention Switching Model
PRISM replaces Markov or fixed-window intention models in multi-intention IRL with a recurrent network, proving an exact EM decomposition into closed-form per-intention reward problems and reporting highest held-out likelihood on gridworld, mouse, and robotic tasks.
-
Action-Prior Denoising for Smooth Real-Time Chunking
Soft RTC uses partially denoised states for overlap tokens and token-wise blending to reduce action delta and jerk by ~9% versus hard RTC while matching solve rates on Kinetix levels.
-
Understanding Multimodal Failure in Action-Chunking Behavioral Cloning
The paper identifies distinct failure mechanisms: excessive posterior-prior regularization erases mode information in latent policies, while smooth base-to-action maps limit mode coverage in generative policies.
-
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.
-
Beyond World-Frame Action Heads: Motion-Centric Action Frames for Vision-Language-Action Models
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.
-
Referring-Aware Visuomotor Policy Learning for Closed-Loop Manipulation
ReV is a referring-aware visuomotor policy using coupled diffusion heads for real-time trajectory replanning in robotic manipulation, trained solely via targeted perturbations to expert demonstrations and achieving higher success rates in simulated and real tasks.
-
VLAs are Confined yet Capable of Generalizing to Novel Instructions
Averaging and temporally interpolating text latents in VLAs enables 83% success on novel task combinations in the libero-ood benchmark where SOTA models achieve under 15%.
-
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
Modern imitation learning methods including Diffusion Policy and Implicit Behavior Cloning are highly vulnerable to universal adversarial perturbations, with successful black-box transfer attacks across algorithms.
-
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.
-
Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models
GLAM learns a shared latent action space grounded in consistent future observation prediction across heterogeneous data sources to train improved behavioral cloning policies for robot manipulation tasks.
-
AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation
AxisGuide augments RGB images with rendered robot base-frame axis cues to improve generalization of visuomotor manipulation policies under distribution shifts.
-
PHASOR: Phase-Anchored Universal Action Representations for Humanoid Embodiments
PHASOR factorizes motion into an FFT-based phase manifold and pose branch with semantic distillation to produce a cross-embodiment, human-anchored action embedding space for humanoid robots.
-
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
IDP generates one-step robot actions by adaptively weighting a scalar potential objective using conditional expert geometry derived from local variations of observation-similar expert actions, combined with expert-proximal terminal evaluation.
-
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.
-
COBALT: Crowdsourcing Robot Learning via Cloud-Based Teleoperation with Smartphones
COBALT enables scalable crowdsourced teleoperation of robots using smartphones, supporting concurrent users with low latency and yielding a 7500+ demonstration dataset validated on imitation learning tasks.
-
ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models
ALAM introduces algebraic consistency regularization on latent action transitions from videos, raising VLA success rates from 47.9% to 85.0% on MetaWorld MT50 and 94.1% to 98.1% on LIBERO.
-
From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models
A unified comparison of latent action supervision strategies for VLA models reveals task-specific benefits, with image-based approaches aiding reasoning and generalization, action-based aiding motor control, and discrete tokens proving most effective.
-
UniT: Toward a Unified Physical Language for Human-to-Humanoid Policy Learning and World Modeling
UniT creates a unified physical language via visual anchoring and tri-branch reconstruction to enable scalable human-to-humanoid transfer for policy learning and world modeling.
-
The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling
Discrete action tokenization in VLA models creates an information bottleneck that prevents vision encoder scaling from improving performance, unlike continuous policies, as validated on the LIBERO benchmark.
-
Continually Evolving Skill Knowledge in Vision Language Action Model
Stellar VLA achieves continual learning in VLA models by maintaining a growing knowledge space and routing tasks to specialized experts conditioned on semantic relations, delivering strong LIBERO benchmark results with only 1% data replay and successful real-world transfer on dual-arm hardware.
-
Real-Time Execution of Action Chunking Flow Policies
Real-time chunking (RTC) allows diffusion- and flow-based action chunking policies to execute smoothly and asynchronously, maintaining high success rates on dynamic tasks even with significant inference latency.
-
SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
SmolVLA is a small efficient VLA model that achieves performance comparable to 10x larger models while training on one GPU and deploying on consumer hardware via community data and chunked asynchronous action prediction.
-
Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Unified World Models couple video and action diffusion inside one transformer with independent timesteps, enabling pretraining on heterogeneous robot datasets that include action-free video and producing more generalizable policies than imitation learning alone.
-
FAST: Efficient Action Tokenization for Vision-Language-Action Models
FAST applies discrete cosine transform to robot action sequences for efficient tokenization, enabling autoregressive VLAs to succeed on high-frequency dexterous tasks and scale to 10k hours of data while matching diffusion VLA performance with up to 5x faster training.
-
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
PGT optimizes latent goal embeddings for frozen policies via trajectory-level preference objectives, reporting 72-81.6% relative gains on 17 Minecraft tasks and 13.4% better OOD performance than fine-tuning.
-
DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning
DINO-WM builds world models on pre-trained DINOv2 features to enable zero-shot planning from offline data without rewards or demonstrations.
-
Diffusion Policy Policy Optimization
DPPO fine-tunes diffusion policies via policy gradients and outperforms prior RL approaches for diffusion policies and PG-tuned alternatives on robot benchmarks while enabling stable training and hardware deployment.
-
Wall-OSS-0.5 Technical Report
Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.
-
DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization
DyGRO-VLA is a two-stage optimization framework for cross-task scaling of Vision-Language-Action models via dynamic grouped residual optimization in RL.
-
From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model
BehaviorVLA learns long-horizon behavioral representations via causal Mamba encoder and phase-conditioned decoder, reporting SOTA results of 58% on RoboTwin 2.0, 98% on LIBERO, 4.36 on CALVIN, and matching OpenVLA-OFT performance with 50% data in sim-to-real transfer.