Pith. sign in

REVIEW 20 cited by

OpenHelix: A Short Survey, Empirical Analysis, and Open-Source Dual-System VLA Model for Robotic Manipulation

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2505.03912 v1 pith:N4KIGEJW submitted 2025-05-06 cs.RO cs.CV

classification cs.ROcs.CV
keywords dual-systemopen-sourcearchitectureswillanalysisempiricalexistingfurther
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Dual-system VLA (Vision-Language-Action) architectures have become a hot topic in embodied intelligence research, but there is a lack of sufficient open-source work for further performance analysis and optimization. To address this problem, this paper will summarize and compare the structural designs of existing dual-system architectures, and conduct systematic empirical evaluations on the core design elements of existing dual-system architectures. Ultimately, it will provide a low-cost open-source model for further exploration. Of course, this project will continue to update with more experimental conclusions and open-source models with improved performance for everyone to choose from. Project page: https://openhelix-robot.github.io/.

Discussion (0). Sign in to comment.

Forward citations

Cited by 20 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Towards Generalizable Robotic Manipulation in Dynamic Environments

    cs.CV 2026-03 unverdicted novelty 7.0 of 10

    DOMINO supplies 110K+ dynamic dual-arm trajectories across 35 tasks, and PUMA’s optical-flow history plus object-centric future queries raise dynamic success rate by 6.3 points over strong VLA baselines.

  2. Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Streaming intermediate hidden states from a slow VLM to a fast flow-matching planner, token by token, improves dynamic social VLN success and reduces observation staleness.

  3. Generalizable VLA Finetuning via Representation Anchoring and Language-Action Alignment

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Preserving pretrained VLM features with layer-wise distillation plus supervising the language head on discretized action directions improves OOD generalization of VLA policies on LIBERO, CALVIN, and a real xArm7.

  4. $M^2$-VLA: Boosting Vision-Language Models for Generalizable Manipulation via Layer Mixture and Meta-Skills

    cs.RO 2026-04 unverdicted novelty 6.0 of 10

    M²-VLA shows that generalized VLMs can serve as direct backbones for robotic manipulation by selectively extracting task-critical features via Mixture of Layers and adding Meta Skill Modules for efficient trajectory learning.

  5. AsyncMDE: Real-Time Monocular Depth Estimation via Asynchronous Spatial Memory

    cs.RO 2026-03 conditional novelty 6.0 of 10

    A lightweight fast path fusing foundation-model spatial memory reaches 237 FPS monocular depth, recovering 77% of the accuracy gap with bounded lag degradation and 161 FPS on Jetson Orin.

  6. Optimization landscapes of variational quantum algorithms

    quant-ph 2026-03 unverdicted novelty 6.0 of 10

    For multi-term VQA objectives (M>1), false traps can emerge from loss of spectral-order compatibility among terms, even with parameter-sufficient ansatze, unlike the trap-free M=1 case under standard assumptions.

  7. UAOR: Uncertainty-aware Observation Reinjection for Vision-Language-Action Models

    cs.CV 2026-02 conditional novelty 6.0 of 10

    Uncertainty-aware observation reinjection into FFN layers improves VLA manipulation success rates across LIBERO, SIMPLER, CALVIN, and real-robot tasks with no training.

  8. Mixture of Horizons in Action Chunking

    cs.RO 2025-11 conditional novelty 6.0 of 10

    A gated mixture of multiple action-chunk horizons in a shared full-attention transformer improves VLA manipulation success and enables consensus-based early stopping.

  9. Bridging the Semantic-Action Gap in Visual Token Pruning for Efficient VLA Inference

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Token pruning for VLA models should use both prefill semantic attention and temporally smoothed action-decode attention; VLA-Pruner does this and preserves manipulation performance at high prune ratios.

  10. Galaxea Open-World Dataset and G0 Dual-System VLA Model

    cs.RO 2025-08 conditional novelty 6.0 of 10

    A new open-world mobile manipulation dataset and a dual-system VLA model show that single-embodiment pre-training, not cross-embodiment pre-training, drives strong downstream task performance.

  11. ChatVLA-2: Vision-Language-Action Model with Open-World Embodied Reasoning from Pretrained Knowledge

    cs.RO 2025-05 conditional novelty 6.0 of 10

    ChatVLA-2 uses dynamic mixture-of-experts and a two-stage training recipe to let a vision-language-action model retain pretrained reasoning while following robot instructions.

  12. WorldEval: World Model as Real-World Robot Policies Evaluator

    cs.RO 2025-05 conditional novelty 6.0 of 10

    WorldEval conditions a video generation model on a policy's internal action embeddings (Policy2Vec) and shows generated-video success rates correlate with real-world robot success rates.

  13. Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details

    cs.AI 2026-08 conditional novelty 5.0 of 10

    For Other-Play in Yokai, agents trained with different implementation details coordinate across implementations about as well as across seeds, supporting inter-seed cross-play as a proxy for cross-implementation evaluation.

  14. Towards Human-like Physical Intelligence: Lifelong Vision-Language-Action Learning for Robotic Manipulation

    cs.RO 2026-07 conditional novelty 5.0 of 10

    LifelongVLA pairs dual-timescale LoRA gating with stochastic cached-prefix replay to cut catastrophic forgetting in VLA policies, reporting 83.2% average success and 11.4% forgetting on a 10-task LIBERO stream.

  15. TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging

    cs.RO 2026-07 conditional novelty 5.0 of 10

    A 0.5B VLA with bridge-conditioned discrete diffusion and 2D temporal–spatial action masking reaches 95.7% LIBERO success and 4.19 CALVIN average length.

  16. When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs

    cs.CV 2026-02 conditional novelty 5.0 of 10

    VLAs fail most counterfactual instructions because vision shortcuts dominate language; the new LIBERO-CF benchmark quantifies this, and CAG, an inference-time action mixer, improves grounding and success.

  17. RationalVLA: A Rational Vision-Language-Action Model with Dual System

    cs.RO 2025-06 conditional novelty 5.0 of 10

    RAMA, a new benchmark with defective instructions, and RationalVLA, a dual-system model with <ACT> and <REJ> tokens, let a robot reject infeasible commands while still performing unseen executable tasks, with higher s...

  18. On the Dual-Use Dilemma in Physical Reasoning and Force

    cs.RO 2025-05 conditional novelty 5.0 of 10

    Adding Asimov-style safety prompts to vision-language models lowers both harmful and helpful force generation for contact-rich robotic tasks.

  19. Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey

    cs.RO 2025-10 conditional novelty 4.0 of 10

    A survey that groups VLA efficiency techniques into four categories: model architecture, perception features, action generation, and training/inference strategies.

  20. ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

    cs.RO 2025-08 unverdicted novelty 4.0 of 10

    Adding a reconstruction target that redraws the object region makes a vision-language-action model focus its attention on the right object and manipulate more precisely.

Pith tools