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.
super hub Mixed citations
Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
Mixed citation behavior. Most common role is background (64%).
128
Pith papers citing it
Background
64% of classified citations
abstract
Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these successes, VLAs struggle with novel robot setups and require fine-tuning to achieve good performance, yet how to most effectively fine-tune them is unclear given many possible strategies. In this work, we study key VLA adaptation design choices such as different action decoding schemes, action representations, and learning objectives for fine-tuning, using OpenVLA as our representative base model. Our empirical analysis informs an Optimized Fine-Tuning (OFT) recipe that integrates parallel decoding, action chunking, a continuous action representation, and a simple L1 regression-based learning objective to altogether improve inference efficiency, policy performance, and flexibility in the model's input-output specifications. We propose OpenVLA-OFT, an instantiation of this recipe, which sets a new state of the art on the LIBERO simulation benchmark, significantly boosting OpenVLA's average success rate across four task suites from 76.5% to 97.1% while increasing action generation throughput by 26$\times$. In real-world evaluations, our fine-tuning recipe enables OpenVLA to successfully execute dexterous, high-frequency control tasks on a bimanual ALOHA robot and outperform other VLAs ($\pi_0$ and RDT-1B) fine-tuned using their default recipes, as well as strong imitation learning policies trained from scratch (Diffusion Policy and ACT) by up to 15% (absolute) in average success rate. We release code for OFT and pretrained model checkpoints at https://openvla-oft.github.io/.
hub tools
citation-role summary
background 34
baseline 10
method 6
other 3
citation-polarity summary
claims ledger
- abstract Recent vision-language-action models (VLAs) build upon pretrained vision-language models and leverage diverse robot datasets to demonstrate strong task execution, language following ability, and semantic generalization. Despite these successes, VLAs struggle with novel robot setups and require fine-tuning to achieve good performance, yet how to most effectively fine-tune them is unclear given many possible strategies. In this work, we study key VLA adaptation design choices such as different action decoding schemes, action representations, and learning objectives for fine-tuning, using OpenVLA
authors
co-cited works
representative citing papers
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.
PCM uses success-failure action variance to probabilistically select and mask chunks for gradient updates in GRPO, matching standard success rates with 2.38x wall-clock speedup and 60% lower memory on LIBERO benchmarks.
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.
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.
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.
Capability vectors extracted from parameter differences between standard and auxiliary-finetuned VLA models can be merged into pretrained weights to match auxiliary-training performance while reducing computational overhead during adaptation.
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.
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.
VUDA enables spatial sharing between CUDA and Vulkan on GPUs via channel redirection and page-table grafting, achieving up to 85% higher throughput than temporal baselines in embodied AI tasks.
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.
Libra-VLA introduces a coarse-to-fine dual-system architecture for VLA models that decouples discrete macro-directional planning from continuous micro-pose refinement, with performance peaking at balanced learning difficulty.
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
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.
HazardArena shows VLA models trained on safe data frequently produce unsafe actions in semantically risky but visually similar settings, and a training-free Safety Option Layer reduces those failures with little performance cost.
STRONG-VLA uses decoupled two-stage training to improve VLA model robustness, yielding up to 16% higher task success rates under seen and unseen perturbations on the LIBERO benchmark.
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.
citing papers explorer
-
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.
-
Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR
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.
-
Learn Where Outcomes Diverge: Efficient VLA RL via Probabilistic Chunk Masking
PCM uses success-failure action variance to probabilistically select and mask chunks for gradient updates in GRPO, matching standard success rates with 2.38x wall-clock speedup and 60% lower memory on LIBERO benchmarks.
-
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.
-
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.
-
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.
-
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.
-
CapVector: Learning Transferable Capability Vectors in Parametric Space for Vision-Language-Action Models
Capability vectors extracted from parameter differences between standard and auxiliary-finetuned VLA models can be merged into pretrained weights to match auxiliary-training performance while reducing computational overhead during adaptation.
-
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.
-
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.
-
VUDA: Breaking CUDA-Vulkan Isolation for Spatial Sharing of Compute and Graphics on the Same GPU
VUDA enables spatial sharing between CUDA and Vulkan on GPUs via channel redirection and page-table grafting, achieving up to 85% higher throughput than temporal baselines in embodied AI tasks.
-
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.
-
Libra-VLA: Achieving Learning Equilibrium via Asynchronous Coarse-to-Fine Dual-System
Libra-VLA introduces a coarse-to-fine dual-system architecture for VLA models that decouples discrete macro-directional planning from continuous micro-pose refinement, with performance peaking at balanced learning difficulty.
-
SpecRLBench: A Benchmark for Generalization in Specification-Guided Reinforcement Learning
SpecRLBench is a new benchmark evaluating generalization of LTL-guided RL methods across navigation and manipulation domains with static/dynamic environments and varied robot dynamics.
-
CF-VLA: Efficient Coarse-to-Fine Action Generation for Vision-Language-Action Policies
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
-
Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents
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.
-
HazardArena: Evaluating Semantic Safety in Vision-Language-Action Models
HazardArena shows VLA models trained on safe data frequently produce unsafe actions in semantically risky but visually similar settings, and a training-free Safety Option Layer reduces those failures with little performance cost.
-
STRONG-VLA: Decoupled Robustness Learning for Vision-Language-Action Models under Multimodal Perturbations
STRONG-VLA uses decoupled two-stage training to improve VLA model robustness, yielding up to 16% higher task success rates under seen and unseen perturbations on the LIBERO benchmark.
-
CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation
CT-1 transfers spatial reasoning from vision-language models to estimate camera trajectories, which are then used in a video diffusion model with wavelet regularization to produce controllable videos, claiming 25.7% better accuracy than prior methods.
-
BiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination
BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.
-
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.
-
Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Control
GeCO replaces time-dependent flow matching with time-unconditional optimization, enabling adaptive inference and intrinsic OOD detection for robotic imitation learning.
-
Towards Generalizable Robotic Manipulation in Dynamic Environments
DOMINO dataset and PUMA architecture enable better dynamic robotic manipulation by incorporating motion history, delivering 6.3% higher success rates than prior VLA models.
-
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.
-
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
RL-VLA³ is an asynchronous RL framework for VLA training that delivers up to 85.2% higher throughput than synchronous baselines while preserving identical sample efficiency and scaling to 256 GPUs.
-
Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models
Agentic-VLA enables efficient online adaptation of VLA models, delivering +12.3% on long-horizon tasks, +28.5% in 1-shot learning, and 2.4x faster convergence on LIBERO through three new components.
-
FrameSkip: Learning from Fewer but More Informative Frames in VLA Training
FrameSkip improves VLA policy training success from 66.50% to 76.15% by selecting high-importance frames and retaining only 20% of unique frames across three benchmarks.
-
Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Models
GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.
-
Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
VLAs-as-Tools pairs a VLM planner with specialized VLA executors via a new interface and Tool-Aligned Post-Training to raise long-horizon robot success rates on LIBERO-Long and RoboTwin benchmarks.
-
Reinforcing VLAs in Task-Agnostic World Models
RAW-Dream disentangles world-model learning from task data by using a pre-trained task-agnostic world model and VLM rewards, with dual-noise filtering, to enable zero-shot VLA adaptation in simulation and real settings.
-
HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Models
HarmoWAM unifies predictive and reactive control in world action models via an adaptive gating mechanism to deliver improved zero-shot generalization and precision in robotic manipulation.
-
Unified Noise Steering for Efficient Human-Guided VLA Adaptation
UniSteer unifies human corrective actions and noise-space RL for VLA adaptation by inverting actions to noise targets, raising success rates from 20% to 90% in 66 minutes across four real-world manipulation 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.
-
Adaptive Action Chunking via Multi-Chunk Q Value Estimation
ACH lets RL policies dynamically pick action chunk lengths by jointly estimating Q-values for all candidate lengths via a single Transformer pass.
-
When to Re-Commit: Temporal Abstraction Discovery for Long-Horizon Vision-Language Reasoning
Learns state-conditioned commitment depth in a 7B vision-language policy that jointly predicts actions and replan intervals, outperforming fixed-depth baselines and larger models on Sliding Puzzle and Sokoban while providing a theoretical dominance result.
-
ElasticFlow: One-Step Physics-Consistent Policy with Elastic Time Horizons for Language-Guided Manipulation
ElasticFlow delivers one-step physics-consistent diffusion policies for language-guided robot control by modeling average velocity fields and using elastic time horizons to overcome spectral bias.
-
ForgeVLA: Federated Vision-Language-Action Learning without Language Annotations
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
-
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
Anchor-Centric Adaptation escapes the diversity trap by prioritizing repeated demonstrations at core anchors over broad coverage, yielding higher success rates under fixed data budgets in robotic manipulation.
-
Predictive but Not Plannable: RC-aux for Latent World Models
RC-aux corrects spatiotemporal mismatch in reconstruction-free latent world models by adding multi-horizon prediction and reachability supervision, improving planning performance on goal-conditioned pixel-control tasks.
-
TriRelVLA: Triadic Relational Structure for Generalizable Embodied Manipulation
TriRelVLA introduces triadic object-hand-task relational representations and a task-grounded graph transformer with a relational bottleneck to improve generalization in robotic manipulation across scenes, objects, and tasks.
-
ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation
ConsisVLA-4D adds cross-view semantic alignment, cross-object geometric fusion, and cross-scene dynamic reasoning to VLA models, delivering 21.6% and 41.5% gains plus 2.3x and 2.4x speedups on LIBERO and real-world tasks.
-
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.
-
ReflectDrive-2: Reinforcement-Learning-Aligned Self-Editing for Discrete Diffusion Driving
ReflectDrive-2 combines masked discrete diffusion with RL-aligned self-editing to generate and refine driving trajectories, reaching 91.0 PDMS on NAVSIM camera-only and 94.8 in best-of-6.
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
MolmoAct2 is an open VLA model that outperforms baselines like Pi-05 on 7 benchmarks and whose backbone surpasses GPT-5 on 13 embodied-reasoning tasks through new datasets, specialized training, and architecture changes for lower latency.
-
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
-
LaST-R1: Reinforcing Robotic Manipulation via Adaptive Physical Latent Reasoning
LaST-R1 introduces a RL post-training method called LAPO that optimizes latent Chain-of-Thought reasoning in vision-language-action models, yielding 99.9% success on LIBERO and up to 22.5% real-world gains.