REVIEW 37 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
Hume: Introducing System-2 Thinking in Visual-Language-Action Model
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.
Forward citations
Cited by 37 Pith papers
-
PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space
PearlVLA achieves SOTA on LIBERO by separating VLM representations into visual grounding and an iterative latent plan branch refined via world model queries and RefineNet with process-reward RL.
-
Q-VGM: Q-Value-Gradient Matching for Off-Policy Reinforcement Learning of Flow-Matching VLA
Q-VGM introduces value-gradient matching via VGG-Flow to improve flow-matching VLA policies with a Cal-QL critic, achieving success rate lifts on LIBERO, RoboTwin, and real-robot 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.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
HDP3 is a pocket-scale 3D diffusion policy with a Diffusion Mixer decoder that achieves state-of-the-art visuomotor control using two-step DDIM inference and under 1% of the parameters of prior 3D diffusion policies.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Frequency analysis of smooth robot actions bounds denoising error to low-frequency modes, enabling a sub-1% parameter 3D diffusion policy with two-step inference that reaches SOTA on manipulation benchmarks.
-
Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving
PaIR-Drive runs IL and RL in parallel branches with a tree-structured sampler to reach 91.2 PDMS and 87.9 EPDMS on NAVSIM benchmarks while outperforming sequential RL fine-tuning and correcting some human errors.
-
AR-VLA: True Autoregressive Action Expert for Vision-Language-Action Models
AR-VLA introduces a standalone autoregressive action expert with long-lived memory that generates context-aware continuous actions for VLAs, replacing chunk-based heads with smoother trajectories and maintained task success.
-
Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation
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.
-
CosFly-VLA: A Spatially Aware Vision-Language-Action Model for UAV Tracking
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.
-
ABot-N1: Toward a General Visual Language Navigation Foundation Model
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.
-
ABot-N1: Toward a General Visual Language Navigation Foundation Model
ABot-N1 decouples navigation into a slow CoT-plus-pixel-goal reasoner and a fast waypoint controller, claiming state-of-the-art results on five VLN benchmarks and releasing two new urban navigation benchmarks.
-
ABot-N1: Toward a General Visual Language Navigation Foundation Model
ABot-N1 decouples VLN into a slow CoT reasoner that outputs pixel goals and a fast action expert, claiming large SOTA gains on urban POI and multi-task navigation.
-
Look Before You Leap: Distilling Tree Search into Action Evaluation for Frozen VLA Models
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.
-
ROSA: A Robotics Foundation Model Serving System for Robot Factories
ROSA introduces shared GPU-pool serving, robotics-aware abstractions for multi-model pipelines, and factory-productivity scheduling that improves output by up to 12.06x over dedicated per-robot systems.
-
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.
-
UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models
UniFS achieves 98.3% success on LIBERO with 2.1x lower latency than prior fast-slow VLA models by stratifying VLM layer update frequencies, inverting latent interactions, and applying multi-level supervision.
-
Recursive Self-Evolving Agents via Held-Out Selection
RSEA adds a strict held-out keep-better gate to recursive self-evolution of agent artifacts, yielding monotone-safe gains or parity with the base ReAct agent on ALFWorld, GAIA, τ-bench, and WebShop.
-
Q-VGM: Q-Value-Gradient Matching for Off-Policy Reinforcement Learning of Flow-Matching VLA
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%.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Hydra-DP3 is a lightweight 3D diffusion policy that uses frequency analysis of smooth action trajectories to enable two-step DDIM inference and achieves state-of-the-art results with under 1% of prior parameters.
-
Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control
Hydra-DP3 achieves SOTA visuomotor performance with under 1% of prior 3D diffusion policy parameters by using frequency analysis to justify a lightweight decoder and two-step DDIM inference.
-
VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model
VLA-ATTC equips VLA models with adaptive test-time compute via an uncertainty clutch and relative action critic, cutting failure rates by over 50% on LIBERO-LONG.
-
Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
Sentinel-VLA adds metacognitive status monitoring to VLA models for on-demand reasoning and error recovery, reporting over 30% higher real-world task success than prior SOTA.
-
Sentinel-VLA: A Metacognitive VLA Model with Active Status Monitoring for Dynamic Reasoning and Error Recovery
Sentinel-VLA introduces a metacognitive VLA model with a sentinel module for real-time status monitoring, dynamic reasoning, and error recovery, plus a self-evolving continual learning method, raising real-world task ...
-
Adaptive Action Chunking at Inference-time for Vision-Language-Action Models
Adaptive Action Chunking uses action entropy to dynamically adjust chunk sizes in VLA models, improving performance on simulated and real robotic manipulation tasks.
-
UAV-Track VLA: Embodied Aerial Tracking via Vision-Language-Action Models
UAV-Track VLA modifies the π0.5 VLA architecture with temporal compression and dual-branch decoding to reach 61.76% success and 269.65 average frames in long-distance pedestrian tracking on a new 890K-frame UAV datase...
-
Deep Image Clustering Based on Curriculum Learning and Density Information
IDCL adds density-based curriculum learning and density-core guidance to deep image clustering, claiming superior robustness, faster convergence, and flexibility on benchmark datasets.
-
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
InternVLA-M1 uses spatially guided pre-training on 2.3M examples followed by action post-training to deliver up to 17% gains on robot manipulation benchmarks and 20.6% on unseen objects.
-
F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions
F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 avera...
-
FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving
FSDrive uses a generated future scene frame as visual spatio-temporal CoT to improve VLA models for safer autonomous driving trajectory prediction.
-
Position: Vision-Language-Action Models Cannot Be Verified to Perform Physical Reasoning
VLA benchmark success rates cannot distinguish semantic generalization from physical reasoning due to an identifiability gap in current evaluation protocols.
-
FORCE: Efficient VLA Reinforcement Fine-Tuning via Value-Calibrated Warm-up and Self-Distillation
FORCE is a 3-stage RL fine-tuning method for VLA models that stabilizes Q-function via on-policy warm-up and filters high-value actions for updates, claiming 79% success rate gains and 32.5% faster training without hu...
-
ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Data
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.
-
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
VGAS uses best-of-N selection with a geometrically grounded critic and explicit regularization to improve success rates of few-shot VLA policies under limited data and distribution shifts.
-
StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
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.
-
Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
A survey that groups VLA efficiency techniques into four categories: model architecture, perception features, action generation, and training/inference strategies.
-
Spatial navigation in preclinical Alzheimer's disease: A review
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...
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.