Processed egocentric human video outperforms teleoperated real-robot trajectories as pretraining data for embodied foundation models, delivering 24% lower validation loss and 52.5-90% higher task success rates under matched post-training protocols.
hub Canonical reference
A Pragmatic VLA Foundation Model
Canonical reference. 73% of citing Pith papers cite this work as background.
48
Pith papers citing it
Background
73% of classified citations
abstract
Offering great potential in robotic manipulation, a capable Vision-Language-Action (VLA) foundation model is expected to faithfully generalize across tasks and platforms while ensuring cost efficiency (e.g., data and GPU hours required for adaptation). To this end, we develop LingBot-VLA with around 20,000 hours of real-world data from 9 popular dual-arm robot configurations. Through a systematic assessment on 3 robotic platforms, each completing 100 tasks with 130 post-training episodes per task, our model achieves clear superiority over competitors, showcasing its strong performance and broad generalizability. We have also built an efficient codebase, which delivers a throughput of 261 samples per second with an 8-GPU training setup, representing a 1.5~2.8$\times$ (depending on the relied VLM base model) speedup over existing VLA-oriented codebases. The above features ensure that our model is well-suited for real-world deployment. To advance the field of robot learning, we provide open access to the code, base model, and benchmark data, with a focus on enabling more challenging tasks and promoting sound evaluation standards.
hub tools
citation-role summary
background 8
baseline 2
method 1
citation-polarity summary
years
2026 48representative citing papers
MuseVLA adds on-demand sensor selection via tokens and converts readings into grounded sensor images for multimodal fusion, reporting 80.6% average success on real-robot dexterous tasks that need non-visual sensing.
FTP-1 is the first foundation tactile policy pretrained on ~3000 hours of data from 26 sources across 21 sensors that improves performance on seen setups by 17.2% and transfers to unseen sensors with 31% success rate gain.
RLDT fine-tunes pretrained flow-matching policies for continuous control by aligning them to a max-entropy RL transport field constructed via SVGD, using expected-target estimation for stable multi-step updates.
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.
EvoScene-VLA maintains an action-updated scene prior across control chunks in VLA policies, raising success rates on RoboTwin tasks from 87.2% to 89.1% fixed and 86.1% to 88.5% randomized while outperforming baselines on a real robot.
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.
RIO introduces a lightweight open-source framework that abstracts real-time robot I/O to support easy switching between embodiments and platforms for collecting data and deploying VLAs.
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.
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
ZR-0 is a dual-stream VLA model trained with dense ECoT supervision on 60M frames from 400K trajectories to enable cross-embodiment transfer in simulation and real-world settings.
An automatic single-demo VLM trajectory labelling pipeline enables keypose-guided diffusion policies that match baseline performance and show preliminary benefits for cross-embodiment transfer on robomimic tasks.
A relative wrist translation bridging action with a vision-language-action model using interleaved tokens and attention masking transfers human manipulation skills to robots more effectively than 6DoF actions.
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
CaR uses attention with viewpoint positional encoding and context compression for flexible memory retrieval in video world models, backed by a new SceneFly dataset, and reports SOTA results with open-domain generalization.
Fine-tuning VLMs with pairwise progress supervision from policy rollouts improves fine-grained failure detection and boosts robot manipulation success by 11% real-world and 5.9% in simulation.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
ACE-Ego-0 is a VLA pretraining framework that turns egocentric human videos into robot-format pseudo-actions via a video-to-action pipeline and trains jointly with robot data under a reliability-aware objective.
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
APT pretrains the action expert as a vision-action prior on frozen VLM features then adds language through gated fusion to improve OOD instruction generalization in continuous-action VLA policies.
FineVLA unifies robot datasets into 47k fine-grained trajectories, adds a VLM annotator and benchmark, and shows that mixing fine-grained and goal-level instructions improves steerable control without hurting task success.
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
citing papers explorer
-
HumanScale: Egocentric Human Video Can Outperform Real-Robot Data for Embodied Pretraining
Processed egocentric human video outperforms teleoperated real-robot trajectories as pretraining data for embodied foundation models, delivering 24% lower validation loss and 52.5-90% higher task success rates under matched post-training protocols.
-
MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation
MuseVLA adds on-demand sensor selection via tokens and converts readings into grounded sensor images for multimodal fusion, reporting 80.6% average success on real-robot dexterous tasks that need non-visual sensing.
-
FTP-1: A Generalist Foundation Tactile Policy Across Tactile Sensors for Contact-Rich Manipulation
FTP-1 is the first foundation tactile policy pretrained on ~3000 hours of data from 26 sources across 21 sensors that improves performance on seen setups by 17.2% and transfers to unseen sensors with 31% success rate gain.
-
Reinforcement Learning for Flow-Matching Policies with Density Transport
RLDT fine-tunes pretrained flow-matching policies for continuous control by aligning them to a max-entropy RL transport field constructed via SVGD, using expected-target estimation for stable multi-step updates.
-
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.
-
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.
-
RIO: Flexible Real-Time Robot I/O for Cross-Embodiment Robot Learning
RIO introduces a lightweight open-source framework that abstracts real-time robot I/O to support easy switching between embodiments and platforms for collecting data and deploying VLAs.
-
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.
-
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.
-
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
VLAFlow shows that combining language-supervised co-training with future latent alignment produces the most stable transfer performance for vision-language-action models trained on mixed robot data.
-
Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision
ZR-0 is a dual-stream VLA model trained with dense ECoT supervision on 60M frames from 400K trajectories to enable cross-embodiment transfer in simulation and real-world settings.
-
Keypose Exploration: Efficient Automatic Trajectory Labelling and Cross-Embodiment Policy Transfer
An automatic single-demo VLM trajectory labelling pipeline enables keypose-guided diffusion policies that match baseline performance and show preliminary benefits for cross-embodiment transfer on robomimic tasks.
-
Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots
A relative wrist translation bridging action with a vision-language-action model using interleaved tokens and attention masking transfers human manipulation skills to robots more effectively than 6DoF actions.
-
Reflective VLA: In-Context Action Consequences Make VLAs Generalize
Reflective VLA improves VLA generalization on LIBERO-Plus and LIBERO-Plus-Hard by 5.4 and 4.2 percentage points by conditioning on action consequences instead of reactive single-frame inputs.
-
Compression and Retrieval: Implicit Memory Retrieval for Video World Models
CaR uses attention with viewpoint positional encoding and context compression for flexible memory retrieval in video world models, backed by a new SceneFly dataset, and reports SOTA results with open-domain generalization.
-
Robot Critics that Sweat the Small Stuff
Fine-tuning VLMs with pairwise progress supervision from policy rollouts improves fine-grained failure detection and boosts robot manipulation success by 11% real-world and 5.9% in simulation.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
-
ACE-Ego-0: Unifying Egocentric Human and Robotic Data for VLA Pretraining
ACE-Ego-0 is a VLA pretraining framework that turns egocentric human videos into robot-format pseudo-actions via a video-to-action pipeline and trains jointly with robot data under a reliability-aware objective.
-
MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
-
APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
APT pretrains the action expert as a vision-action prior on frozen VLM features then adds language through gated fusion to improve OOD instruction generalization in continuous-action VLA policies.
-
FineVLA: Fine-Grained Instruction Alignment for Steerable Vision-Language-Action Policies
FineVLA unifies robot datasets into 47k fine-grained trajectories, adds a VLM annotator and benchmark, and shows that mixing fine-grained and goal-level instructions improves steerable control without hurting task success.
-
HumanNet: Scaling Human-centric Video Learning to One Million Hours
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
-
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
-
Long-Horizon Manipulation via Trace-Conditioned VLA Planning
LoHo-Manip enables robust long-horizon robot manipulation by using a receding-horizon VLM manager to output progress-aware subtask sequences and 2D visual traces that condition a VLA executor for automatic replanning.
-
Human Cognition in Machines: A Unified Perspective of World Models
The paper introduces a unified framework for world models that fully incorporates all cognitive functions from Cognitive Architecture Theory, highlights under-researched areas in motivation and meta-cognition, and proposes Epistemic World Models as a new category for scientific discovery agents.
-
VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis
VAG is a synchronized dual-stream flow-matching framework that generates aligned video-action pairs for synthetic embodied data synthesis and policy pretraining.
-
SABER: A Stealthy Agentic Black-Box Attack Framework for Vision-Language-Action Models
SABER uses a trained ReAct agent to produce bounded adversarial edits to robot instructions, cutting task success by 20.6% and increasing execution length and violations on the LIBERO benchmark across six VLA models.
-
FASTER: Rethinking Real-Time Flow VLAs
FASTER adds a Horizon-Aware Schedule to flow VLAs that compresses immediate-action denoising to one step while keeping long-horizon trajectory quality, lowering real-robot reaction latency.
-
Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation
A visuo-tactile policy learning method that exploits tactile motion correlation for contact state distinction and Mixture-of-Transformers for cross-modal fusion.
-
TSD: A Physics-Inspired Trajectory Saliency Detector for Efficient Imitation Learning
TSD applies two physics metrics to identify salient trajectory segments for dataset compression and expansion in robotic imitation learning, yielding comparable performance with 25% less data on average.
-
Kairos: A Native World Model Stack for Physical AI
Kairos is a native world model stack using cross-embodiment pretraining, hybrid linear temporal attention with theoretical error bounds, and deployment-aware co-design, reporting top performance on embodied benchmarks.
-
Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imagination
Efficient-WAM delivers 30x lower latency than prior WAMs at 100 ms per chunk while keeping competitive manipulation performance by treating coarse future video as guidance rather than high-fidelity output.
-
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.
-
DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable Manipulation
DeMaVLA is a VLA foundation model using a pruned action expert and flow matching, pre-trained on 5000 hours of real demonstrations and post-trained on multi-task folding data with human-in-the-loop correction, reporting competitive benchmark and real-world folding performance.
-
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.
-
GEM: Generative Supervision Helps Embodied Intelligence
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
-
Pelican-Unify 1.0: A Unified Embodied Intelligence Model for Understanding, Reasoning, Imagination and Action
A unified embodied foundation model uses one VLM for understanding and reasoning plus a joint video-action future generator, reporting competitive scores on VLM, world modeling, and robot benchmarks without apparent compromise.
-
Preserving Foundational Capabilities in Flow-Matching VLAs through Conservative SFT
ConSFT is a gradient-scaling fine-tuning objective for flow-matching VLAs that bounds parameter disruption via model-confidence weighting, yielding over 20% better capability retention than vanilla SFT on LIBERO and RoboTwin.
-
Goal2Skill: Long-Horizon Manipulation with Adaptive Planning and Reflection
A dual VLM-VLA framework for long-horizon robot manipulation achieves 32.4% success on RMBench tasks versus 9.8% for the strongest baseline via structured memory and closed-loop adaptive replanning.
-
CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.
-
DMuon: Efficient Distributed Muon Training with Near-Adam Overhead
DMuon delivers 1.48x-3.01x end-to-end and 6.85x-163x optimizer-step speedups for Muon on embodied foundation models and LLMs while matching AdamW per-step latency.
-
WALL-WM: Carving World Action Modeling at the Event Joints
WALL-WM introduces event-grounded Vision-Language-Action pretraining that uses semantic events as the atomic unit to address granularity mismatch in world action models and reports state-of-the-art generalization.
-
Evo-Depth: A Lightweight Depth-Enhanced Vision-Language-Action Model
Evo-Depth is a compact VLA model using a lightweight implicit depth encoder from RGB views plus progressive alignment to boost manipulation performance without added hardware.
-
JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy
JoyAI-RA is a multi-source pretrained VLA model that claims to bridge human-to-robot embodiment gaps via data unification and outperforms prior methods on generalization-heavy robotic tasks.
-
RhinoVLA Technical Report
RhinoVLA cuts VLM tokens with a Qwen3-VL backbone and continuous action expert, adds a unified cross-robot interface, and reaches real-time 11.69 Hz on Huixi R1 while matching π0.5 downstream performance.
-
World Model for Robot Learning: A Comprehensive Survey
A comprehensive survey that organizes the literature on world models in robot learning, their roles in policy learning, planning, simulation, and video-based generation, with connections to navigation, driving, datasets, and benchmarks.