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 Canonical reference
Igniting vlms toward the embodied space
Canonical reference. 75% of citing Pith papers cite this work as background.
29
Pith papers citing it
Background
75% of classified citations
hub tools
citation-role summary
background 7
method 1
citation-polarity summary
representative citing papers
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.
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.
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
OpenEAI-Platform delivers an open-source low-cost robotic arm and VLA model that outperforms commercial arms and matches large pretrained baselines on four real-world manipulation tasks using limited open data.
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.
XRZero-G0 enables 2000-hour robot-free datasets that, when mixed 10:1 with real-robot data, match full real-robot performance at 1/20th the cost and support zero-shot transfer.
A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.
VAG is a synchronized dual-stream flow-matching framework that generates aligned video-action pairs for synthetic embodied data synthesis and policy pretraining.
A1 is a transparent VLA framework achieving state-of-the-art robot manipulation success with up to 72% lower latency via adaptive layer truncation and inter-layer flow matching.
OxyGen unifies KV cache management in MoT VLAs to enable cross-task KV sharing and cross-frame continuous batching, delivering up to 3.7x speedup with 200+ tokens/s language and 70 Hz action on on-device platforms.
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
LingBot-VLA is a VLA foundation model trained on massive real robot data that shows superior generalization across tasks and platforms with fast training throughput.
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
SyVLA uses Intention Decoupling and similar-sample guided RL on diversified experiences to improve VLA model task success and out-of-distribution generalization while keeping vision-language abilities.
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 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 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.
StableIDM stabilizes inverse dynamics models under manipulator truncation by combining robot-centric masking, directional spatial feature aggregation, and temporal dynamics refinement, yielding 12.1% higher strict action accuracy on AgiBot and 9.7-17.6% gains in real-robot tasks.
LingBot-VLA 2.0 combines 60k hours of multi-embodiment pretraining data, an expanded whole-body action space, and dual-query distillation from depth and video teachers to improve VLA performance on GM-100 and long-horizon mobile manipulation tasks.
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.
-
From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
-
NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation
Repurposing a VLA’s vision encoder to emit one action-supervised memory token per historical frame-view yields long-horizon manipulation with large success gains and low latency.
-
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.
-
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
-
OpenEAI-Platform: An Open-source Embodied Artificial Intelligence Hardware-Software Unified Platform
OpenEAI-Platform delivers an open-source low-cost robotic arm and VLA model that outperforms commercial arms and matches large pretrained baselines on four real-world manipulation tasks using limited open data.
-
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.
-
XRZero-G0: Pushing the Frontier of Dexterous Robotic Manipulation with Interfaces, Quality and Ratios
XRZero-G0 enables 2000-hour robot-free datasets that, when mixed 10:1 with real-robot data, match full real-robot performance at 1/20th the cost and support zero-shot transfer.
-
Grounded World Model for Semantically Generalizable Planning
A vision-language-aligned world model turns visuomotor MPC into a language-following planner that reaches 87% success on 288 unseen semantic tasks where standard VLAs drop to 22%.
-
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.
-
A1: A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model
A1 is a transparent VLA framework achieving state-of-the-art robot manipulation success with up to 72% lower latency via adaptive layer truncation and inter-layer flow matching.
-
OxyGen: Unified KV Cache Management for VLA Inference under Multi-Task Parallelism
OxyGen unifies KV cache management in MoT VLAs to enable cross-task KV sharing and cross-frame continuous batching, delivering up to 3.7x speedup with 200+ tokens/s language and 70 Hz action on on-device platforms.
-
RoboStereo: Dual-Tower 4D Embodied World Models for Unified Policy Optimization
A dual-tower 4D embodied world model called RoboStereo reduces geometric hallucinations and delivers over 97% relative improvement on manipulation tasks via test-time augmentation, imitative learning, and open exploration.
-
Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
-
A Pragmatic VLA Foundation Model
LingBot-VLA is a VLA foundation model trained on massive real robot data that shows superior generalization across tasks and platforms with fast training throughput.
-
AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
-
Native Video-Action Pretraining for Generalizable Robot Control
A video-action foundation model pretrained natively with a causal diffusion transformer and semantic visual-action tokenizer reports improved few-shot robot manipulation and 225 Hz asynchronous closed-loop control.
-
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
-
Scaling by Diversified Experience for Vision-Language-Action Models
SyVLA uses Intention Decoupling and similar-sample guided RL on diversified experiences to improve VLA model task success and out-of-distribution generalization while keeping vision-language abilities.
-
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.
-
StableIDM: Stabilizing Inverse Dynamics Model against Manipulator Truncation via Spatio-Temporal Refinement
StableIDM stabilizes inverse dynamics models under manipulator truncation by combining robot-centric masking, directional spatial feature aggregation, and temporal dynamics refinement, yielding 12.1% higher strict action accuracy on AgiBot and 9.7-17.6% gains in real-robot tasks.
-
From Foundation to Application: Improving VLA Models in Practice
LingBot-VLA 2.0 combines 60k hours of multi-embodiment pretraining data, an expanded whole-body action space, and dual-query distillation from depth and video teachers to improve VLA performance on GM-100 and long-horizon mobile 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.
-
Trust Region Q Adjoint Matching
TRQAM adds a trust region to QAM by optimizing λ in SOC dynamics to achieve closed-form control of path-space KL, yielding 68% success rate on 50 OGBench tasks versus 46% for the strongest baseline.
-
Vision-and-Language Navigation for UAVs: Progress, Challenges, and a Research Roadmap
A survey of UAV vision-and-language navigation that establishes a methodological taxonomy, reviews resources and challenges, and proposes a forward-looking research roadmap.
-
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
OpenWorldLib defines world models as perception-centered systems with interaction and long-term memory, and provides a modular inference codebase unifying interactive video, 3D, reasoning, and VLA tasks.
- SpatialVAM:Spatial-Aware Multi-View Video Diffusion as a Data-Efficient Robot Policy