mlsanityData to 7 Oct 2026

DEFT: Dexterous Fine-Tuning for Real-World Hand Policies

arXiv 2310.19797 ↗First posted 30 Oct 2023cs.RO cs.AI cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Dexterity is often seen as a cornerstone of complex manipulation. Humans are able to perform a host of skills with their hands, from making food to operating tools. In this paper, we investigate these challenges, especially in the case of soft, deformable objects as well as complex, relatively long-horizon tasks. However, learning such behaviors from scratch can be data inefficient. To circumvent this, we propose a novel approach, DEFT (DExterous Fine-Tuning for Hand Policies), that leverages human-driven priors, which are executed directly in the real world. In order to improve upon these priors, DEFT involves an efficient online optimization procedure. With the integration of human-based learning and online fine-tuning, coupled with a soft robotic hand, DEFT demonstrates success across various tasks, establishing a robust, data-efficient pathway toward general dexterous manipulation. Please see our website at https://dexterous-finetuning.github.io for video results.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 23 of its 79 references that are in the map. First posted on arXiv 30 Oct 2023.

Builds on

23 of 79 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  4. 2023Segment Anythingcited by 8,158
  5. 2013Auto-Encoding Variational Bayescited by 3,980
  6. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  7. 2017End-to-end Recovery of Human Shape and Posecited by 883
  8. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  9. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  10. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 678
  11. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 613
  12. 2022VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Trainingcited by 384
11 more
  1. 2021MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scalecited by 226
  2. 2022Rapid Locomotion via Reinforcement Learningcited by 130
  3. 2022Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapescited by 92
  4. 2022Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtubecited by 79
  5. 2017Data-efficient Deep Reinforcement Learning for Dexterous Manipulationcited by 61
  6. 2021ReSkin: versatile, replaceable, lasting tactile skinscited by 33
  7. 2014Stochastic Backpropagation and Approximate Inference in Deep Generative Modelscited by 30
  8. 2023ALAN: Autonomously Exploring Robotic Agents in the Real Worldcited by 23
  9. 2020Residual Learning from Demonstration: Adapting DMPs for Contact-rich Manipulationcited by 22
  10. 2015In Defense of the Direct Perception of Affordancescited by 9
  11. 2023RobotSweater: Scalable, Generalizable, and Customizable Machine-Knitted Tactile Skins for Robotscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 9; 2025: 4; 2026: 2.

15 papers.

Sort:

By area:

  1. 2024Latent Action Pretraining from Videoscited by 302
  2. 2025DreamGen: Unlocking Generalization in Robot Learning through Video World Modelscited by 168
  3. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  4. 2025FLARE: Robot Learning with Implicit World Modelingcited by 105
  5. 2024General Flow as Foundation Affordance for Scalable Robot Learningcited by 80
  6. 2024Robo-ABC: Affordance Generalization Beyond Categories via Semantic Correspondence for Robot Manipulationcited by 69
  7. 2024HRP: Human Affordances for Robotic Pre-Trainingcited by 40
  8. 2024Hand-Object Interaction Pretraining from Videoscited by 38
  9. 2024Adaptive Mobile Manipulation for Articulated Objects In the Open Worldcited by 30
  10. 2025ViPRA: Video Prediction for Robot Actionscited by 24
  11. 2024ScrewMimic: Bimanual Imitation from Human Videos with Screw Space Projectioncited by 16
  12. 2025MAPLE: Encoding Dexterous Robotic Manipulation Priors Learned From Egocentric Videoscited by 12
3 more
  1. 2026T-Rex: Tactile-Reactive Dexterous Manipulationcited by 10
  2. 2024DemoStart: Demonstration-led auto-curriculum applied to sim-to-real with multi-fingered robotscited by 7
  3. 2026Mana: Dexterous Manipulation of Articulated Toolscited by 0