HABIT is a large-scale robot demonstration dataset for human-present environments that elicits spatiotemporal synchronization, yielding, and gesture grounding behaviors absent from robot-only training data.
super hub Canonical reference
OpenVLA: An Open-Source Vision-Language-Action Model
Canonical reference. 72% of citing Pith papers cite this work as background.
428
Pith papers citing it
Background
72% of classified citations
abstract
Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for adoption. Addressing these challenges, we introduce OpenVLA, a 7B-parameter open-source VLA trained on a diverse collection of 970k real-world robot demonstrations. OpenVLA builds on a Llama 2 language model combined with a visual encoder that fuses pretrained features from DINOv2 and SigLIP. As a product of the added data diversity and new model components, OpenVLA demonstrates strong results for generalist manipulation, outperforming closed models such as RT-2-X (55B) by 16.5% in absolute task success rate across 29 tasks and multiple robot embodiments, with 7x fewer parameters. We further show that we can effectively fine-tune OpenVLA for new settings, with especially strong generalization results in multi-task environments involving multiple objects and strong language grounding abilities, and outperform expressive from-scratch imitation learning methods such as Diffusion Policy by 20.4%. We also explore compute efficiency; as a separate contribution, we show that OpenVLA can be fine-tuned on consumer GPUs via modern low-rank adaptation methods and served efficiently via quantization without a hit to downstream success rate. Finally, we release model checkpoints, fine-tuning notebooks, and our PyTorch codebase with built-in support for training VLAs at scale on Open X-Embodiment datasets.
hub tools
citation-role summary
background 93
baseline 20
method 7
other 2
citation-polarity summary
claims ledger
- abstract Large policies pretrained on a combination of Internet-scale vision-language data and diverse robot demonstrations have the potential to change how we teach robots new skills: rather than training new behaviors from scratch, we can fine-tune such vision-language-action (VLA) models to obtain robust, generalizable policies for visuomotor control. Yet, widespread adoption of VLAs for robotics has been challenging as 1) existing VLAs are largely closed and inaccessible to the public, and 2) prior work fails to explore methods for efficiently fine-tuning VLAs for new tasks, a key component for ado
authors
co-cited works
representative citing papers
Introduces the TVR active viewpoint-matching task and TVRBench indoor simulation benchmark, where foundation models start at low single-digit success rates but reach 51.4% after visual-action SFT and multi-turn GRPO post-training.
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.
SARL optimizes language prompt inputs to generalist vision-language-action policies through online RL to solve complex long-horizon tasks by composing existing skills.
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.
Labimus is the first benchmark for humanoid dexterous manipulation in organic chemistry laboratories, exposing a gap between task completion and required experimental precision.
SWAM jointly generates intermediate RGB-D sequences and action trajectories from monocular RGB start/goal observations for embodied navigation.
SurgVLA-Bench supplies a hierarchical task taxonomy and multi-dimensional evaluation framework for VLA models in laparoscopic robotics simulation, showing autoregressive models excel at semantics while flow-matching models achieve higher precision but all fall short due to endoscopic view constraint
ForesightSafety-VLA creates a diagnostic benchmark for VLA safety with taxonomy across physical, language, and visual risks, showing perception and structure variations cause more safety degradation than language changes in tested models.
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
World models introduce a stealthy poisoning vector into robot learning pipelines where malicious prompts or dynamics in teleoperated data activate only during synthetic trajectory generation, enabling backdoors in downstream policies.
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.
Introduces a benchmark dataset with automated pipeline for evaluating VLMs on dynamic in-context human preferences, distinct from static benchmarks.
BOKBO is the first conformal abstention method for K-sample VLA policies that supplies finite-sample distribution-free guarantees on executed violation rates, with global and Mondrian per-task variants.
PhAIL provides an open benchmark and distributional evaluation method for real-robot VLA policies using time-to-success CDF, HRT scoring, and KS significance tests.
Omega-QVLA is a post-training quantization framework achieving uniform W4A4 for VLA models' LLM backbone and DiT action head via composite SVD-Hadamard rotation and per-step scaling, matching FP16 success rates on LIBERO.
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.
Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.
What-If World is a new paired-prompt benchmark showing that nine state-of-the-art video generation models achieve at most 52% on causal intervention tests and cluster near 28% for open-source systems.
Introduces Sentinel Challenge benchmark and CoSaR framework for cooperative spatial reasoning and planning among 3-5 decentralized embodied agents across 14 city-scale scenes.
GAMSI is a dual-pathway Geometry-Aware MLLM using Metric-Structure Decoupled Queries and Expert-Guided Visual Grounding on RGB inputs alone, trained on a new 152k-sample MTS dataset to reach SOTA on seven spatial benchmarks.
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.
VGenST-Bench is a new video benchmark for MLLM spatio-temporal reasoning built via generative synthesis, a multi-agent pipeline with human oversight, a 3x2x2 taxonomy, and hierarchical tasks separating perception from reasoning.
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.
citing papers explorer
-
Latent State Design for World Models under Sufficiency Constraints
World models succeed when their latent states are built to meet task-specific sufficiency constraints rather than preserving the maximum amount of information.
-
How Far Are Large Multimodal Models from Human-Level Spatial Action? A Benchmark for Goal-Oriented Embodied Navigation in Urban Airspace
Large multimodal models display emerging but limited spatial action capabilities in goal-oriented urban 3D navigation, remaining far from human-level performance with errors diverging rapidly after critical decision points.
-
The Cartesian Cut in Agentic AI
LLM agents use a Cartesian split between learned prediction and engineered control, enabling modularity but creating sensitivity and bottlenecks unlike integrated biological systems.
-
Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
A survey of physical AI that distinguishes theoretical physics reasoning from applied understanding and synthesizes advances in symbolic reasoning, embodied systems, and generative models to advocate for physics-grounded world models.