Pith. sign in

REVIEW 10 cited by

Hume: Introducing System-2 Thinking in Visual-Language-Action Model

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 2505.21432 v4 pith:B426X3KH submitted 2025-05-27 cs.RO cs.AI

classification cs.ROcs.AI
keywords thinkingsystemactionhumemodelsvalue-guidedvision-language-actionactions
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Humans practice slow thinking before performing actual actions when handling complex tasks in the physical world. This thinking paradigm, recently, has achieved remarkable advancement in boosting Large Language Models (LLMs) to solve complex tasks in digital domains. However, the potential of slow thinking remains largely unexplored for robotic foundation models interacting with the physical world. In this work, we propose Hume: a dual-system Vision-Language-Action (VLA) model with value-guided System-2 thinking and cascaded action denoising, exploring human-like thinking capabilities of Vision-Language-Action models for dexterous robot control. System 2 of Hume implements value-Guided thinking by extending a Vision-Language-Action Model backbone with a novel value-query head to estimate the state-action value of predicted actions. The value-guided thinking is conducted by repeat sampling multiple action candidates and selecting one according to state-action value. System 1 of Hume is a lightweight reactive visuomotor policy that takes System 2 selected action and performs cascaded action denoising for dexterous robot control. At deployment time, System 2 performs value-guided thinking at a low frequency while System 1 asynchronously receives the System 2 selected action candidate and predicts fluid actions in real time. We show that Hume outperforms the existing state-of-the-art Vision-Language-Action models across multiple simulation benchmark and real-robot deployments.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Q-VGM: Q-Value-Gradient Matching for Off-Policy Reinforcement Learning of Flow-Matching VLA

    cs.RO 2026-06 unverdicted novelty 7.0 of 10

    Q-VGM offline RL fine-tuning converts critic Q-gradients into residual velocity targets for flow-matching VLAs, raising LIBERO success from 75.0% to 92.5%.

  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. CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking

    cs.RO 2026-07 conditional novelty 6.0 of 10

    CosFly-VLA, a spatially grounded VLA trained with CPT, curriculum SFT, CoT, and RL, reports 34–35% lower open-loop waypoint error and higher closed-loop success than OpenVLA in simulated UAV occlusion tracking.

  4. ABot-N1: Toward a General Visual Language Navigation Foundation Model

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    A slow–fast VLN model that routes five navigation tasks through CoT plus image-space pixel goals reaches SOTA on established and new urban benchmarks, including 77.3% POI arrival.

  5. Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Distilling MCTS returns into a lightweight Q-model lets frozen VLAs select higher-return actions at test time, lifting success rates and letting a 9B model beat a 27B baseline at lower latency.

  6. ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data

    cs.RO 2026-03 conditional novelty 5.0 of 10

    An open-loop generation-then-tracking system maps one egocentric image plus language into Unitree G1 whole-body interactions using only human egocentric motion data.

  7. Skill-Nav: Enhanced Navigation with Versatile Quadrupedal Locomotion via Waypoint Interface

    cs.RO 2025-06 conditional novelty 5.0 of 10

    A waypoint-based interface between planners and a trained quadrupedal locomotion policy enables navigation over diverse obstacles in simulation and on a real robot.

  8. StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation

    cs.RO 2026-02 reject novelty 4.0 of 10

    StemVLA supervises a GPT-2-based VLA with predicted future 3D-geometry features (VGGT) and temporally aggregated history, reporting 86.0% on LIBERO-Long - but its CALVIN results and equations are placeholders.

  9. 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.

  10. Spatial navigation in preclinical Alzheimer's disease: A review

    q-bio.NC 2026-03 unverdicted novelty 3.0 of 10

    Spatial navigation performance, particularly path integration and wayfinding, correlates with AD biomarkers such as p-tau in cognitively unimpaired at-risk individuals and may enable earlier detection than episodic me...

Pith tools