SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows | Paper Citation Record

Observation 71f5a7c8-9934-4277-96bb-3ad95448799d · outbound

This paper cites Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:09.350819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ff7f9489-32a4-40a1-9647-c987f1b41fc4 · outbound

This paper cites Policyflow: Policy optimization with con- tinuous normalizing flow in reinforcement learning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Policyflow: Policy optimization with con- tinuous normalizing flow in reinforcement learning

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:13.860281Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 12daca46-37f1-4bfd-9924-be0669bb7637 · outbound

This paper cites Efficient online reinforcement learning with offline data.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Efficient online reinforcement learning with offline data

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:13.971382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 89260a7d-7d73-4d9d-ad97-af1777d7af74 · outbound

This paper cites Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Improving TD3-BC: Relaxed Policy Constraint for Offline Learning and Stable Online Fine-Tuning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.061010Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 134c3080-53b2-4137-a4ed-2487c59a5ee3 · outbound

This paper cites GR00T N1: An Open Foundation Model for Generalist Humanoid Robots.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows GR00T N1: An Open Foundation Model for Generalist Humanoid Robots

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.198220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5c4e392-2cbf-4046-acad-e4846cb7a160 · outbound

This paper cites Real-Time Execution of Action Chunking Flow Policies.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Real-Time Execution of Action Chunking Flow Policies

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.320957Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 83687396-7544-44cf-bb93-1ad1efd7008f · outbound

This paper cites $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.422579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e26714a-8ea8-4a19-ad4c-c53fa5e82bb5 · outbound

This paper cites Training-time action conditioning for efficient real-time chunking.arXiv preprint arXiv:2512.05964, 2025.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Training-time action conditioning for efficient real-time chunking.arXiv preprint arXiv:2512.05964, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.534069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a3fab07-8f2d-4c36-a29d-e9187697319d · outbound

This paper cites Maximum entropy reinforcement learning via energy-based normal- izing flow.Advances in Neural Information Processing Systems, 37:56136–56165, 2024.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Maximum entropy reinforcement learning via energy-based normal- izing flow.Advances in Neural Information Processing Systems, 37:56136–56165, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.657367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5942f5c4-574f-4c0f-a565-d6662b0c52e2 · outbound

This paper cites Diffusion Policy: Visuomotor Policy Learning via Action Diffusion.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.720586Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f94950b0-12ea-4937-8ee5-1a02012d7efa · outbound

This paper cites Christoph, Maximilian Eberlein, Filippos Katsimalis, Arturo Roberti, Aristotelis Sympetheros, Michel R.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Christoph, Maximilian Eberlein, Filippos Katsimalis, Arturo Roberti, Aristotelis Sympetheros, Michel R

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.798378Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a747729d-4a95-45ed-88db-adfbc1648481 · outbound

This paper cites The ingredients for robotic diffusion transformers.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows The ingredients for robotic diffusion transformers

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.889076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45651882-016c-40a2-b295-56a05dc2604f · outbound

This paper cites Density estimation using Real NVP.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Density estimation using Real NVP

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:14.957963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187113fe-a7d7-49d0-aed3-d7a03f715ffb · outbound

This paper cites Hyperparameters in reinforcement learning and how to tune them.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Hyperparameters in reinforcement learning and how to tune them

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.069207Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94defd6d-5c96-4f7e-98bd-d0d42e4ee0a4 · outbound

This paper cites Stop Regressing: Training Value Functions via Classification for Scalable Deep RL.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Stop Regressing: Training Value Functions via Classification for Scalable Deep RL

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.129472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eb39c09e-d1d7-408d-b62c-421242145b72 · outbound

This paper cites D4RL: Datasets for Deep Data-Driven Reinforcement Learning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows D4RL: Datasets for Deep Data-Driven Reinforcement Learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.220023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ef6e14c-dc7e-4a70-ab23-36db250a459e · outbound

This paper cites A minimalist approach to offline reinforcement learning.Advances in neural information processing systems, 34:20132–20145, 2021.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows A minimalist approach to offline reinforcement learning.Advances in neural information processing systems, 34:20132–20145, 2021

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.310444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf4a6611-997d-4015-a63d-f5cec87709c2 · outbound

This paper cites Normalizing Flows are Capable Models for Continuous Control.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Normalizing Flows are Capable Models for Continuous Control

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.393499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d7be578-7f31-4367-bd8f-da5e8e5f3d1e · outbound

This paper cites Dextreme: Transfer of agile in-hand manipulation from simulation to reality.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Dextreme: Transfer of agile in-hand manipulation from simulation to reality

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.614836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a333b06e-2776-48d0-90fe-79f3c6a0eb65 · outbound

This paper cites Deep Residual Learning for Image Recognition.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Deep Residual Learning for Image Recognition

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.761858Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 91e03d56-ccaa-484a-b157-72e9ca970545 · outbound

This paper cites Imitation Bootstrapped Reinforcement Learning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Imitation Bootstrapped Reinforcement Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.824747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64f6d4f7-0c47-4f64-bd65-6d5255821333 · outbound

This paper cites Improving regres- sion performance with distributional losses.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Improving regres- sion performance with distributional losses

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.934757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30299ff5-a561-4b6e-865d-6883cb23ea8c · outbound

This paper cites $\pi^{*}_{0.6}$: a VLA That Learns From Experience.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows $\pi^{*}_{0.6}$: a VLA That Learns From Experience

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:16.108040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e14a9a8-b0db-46fd-917c-51ac4d7493bd · outbound

This paper cites $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:16.234139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f26b2260-8424-481d-ac56-423caba05b27 · outbound

This paper cites Learning stable normalizing-flow control for robotic manipulation.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Learning stable normalizing-flow control for robotic manipulation

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:16.382202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1ab1d5a-5e1d-4232-bf97-38c71ff2fd44 · outbound

This paper cites Jet: A Modern Transformer-Based Normalizing Flow.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Jet: A Modern Transformer-Based Normalizing Flow

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:16.466532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfddc979-3e71-4b82-8edf-f7c9a5014c74 · outbound

This paper cites Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:16.595689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb5c1dcf-ab6a-48c8-b39a-f522c8b1eef6 · outbound

This paper cites Reinforcement Learning with Action Chunking.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Reinforcement Learning with Action Chunking

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T02:54:49.105148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc4abe7c-823f-45ca-893d-2ae1382e9783 · outbound

This paper cites Normalizing flows are capable visuo- motor policy learning models.CoRR, abs/2509.21073,.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Normalizing flows are capable visuo- motor policy learning models.CoRR, abs/2509.21073,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:48.801820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d647d90e-6476-481e-9cc3-114012608dcb · outbound

This paper cites Decoupled Weight Decay Regularization.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Decoupled Weight Decay Regularization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.506340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b23b7f2-c533-4a63-9e5c-7620726bcad0 · outbound

This paper cites URL https: //doi.org/10.48550/arXiv.2509.21073.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows URL https: //doi.org/10.48550/arXiv.2509.21073

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.482338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 767181dc-f935-436c-9d52-85a1ee797869 · outbound

This paper cites What Matters in Learning from Offline Human Demonstrations for Robot Manipulation.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.531636Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc9be043-e688-4165-9f1f-c951e2eef4cb · outbound

This paper cites SERL: A software suite for sample-efficient robotic reinforcement learn- ing.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows SERL: A software suite for sample-efficient robotic reinforcement learn- ing

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.518390Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02cc83af-386b-48db-be1b-38a7ae9bbf7a · outbound

This paper cites Flow Matching Policy Gradients.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Flow Matching Policy Gradients

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.559508Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e31bb1ab-0fed-4fb7-883a-42c63f121258 · outbound

This paper cites Leveraging exploration in off-policy algorithms via normalizing flows.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Leveraging exploration in off-policy algorithms via normalizing flows

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.543047Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6649bd35-e02d-4ddf-859c-a06a5b86b06e · outbound

This paper cites Carlson, Ji Yuan Feng, Ani- mesh Garg, Renato Gasoto, Lionel Gulich, Yijie Guo, M.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Carlson, Ji Yuan Feng, Ani- mesh Garg, Renato Gasoto, Lionel Gulich, Yijie Guo, M

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.589068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3a26140-9227-4249-b3fd-0736035272b3 · outbound

This paper cites Learning robust perceptive locomotion for quadrupedal robots in the wild.Science robotics, 7(62):eabk2822, 2022.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Learning robust perceptive locomotion for quadrupedal robots in the wild.Science robotics, 7(62):eabk2822, 2022

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.573986Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac006e3-666f-42cf-a077-61ed8f3fa571 · outbound

This paper cites Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning.Advances in Neural Information Processing Systems, 36:62244–62269, 2023.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Cal-ql: Calibrated offline rl pre-training for efficient online fine-tuning.Advances in Neural Information Processing Systems, 36:62244–62269, 2023

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.636256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d8fbbf-c451-4060-87cd-b3e92511b24e · outbound

This paper cites Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.596303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a937616-fd18-4884-9240-d248620516d5 · outbound

This paper cites AWAC: Accelerating Online Reinforcement Learning with Offline Datasets.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.617366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0971a15-1b6b-4324-a45d-07078c50e519 · outbound

This paper cites Ren, Justin Lidard, Anthony Simeonov, Lars Lien Ankile, Pulkit Agrawal, Anirudha Majumdar, Benjamin Burchfiel, Hongkai Dai, and Max Simchowitz.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Ren, Justin Lidard, Anthony Simeonov, Lars Lien Ankile, Pulkit Agrawal, Anirudha Majumdar, Benjamin Burchfiel, Hongkai Dai, and Max Simchowitz

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.681810Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e267106a-ecde-48ca-95ae-4e260bf5761d · outbound

This paper cites DINOv2: Learning Robust Visual Features without Supervision.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows DINOv2: Learning Robust Visual Features without Supervision

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.650040Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51faad8d-45e9-4094-90c7-8d8b21cb8b97 · outbound

This paper cites OGBench: Benchmarking Offline Goal-Conditioned RL.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows OGBench: Benchmarking Offline Goal-Conditioned RL

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.664859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ca42462-879a-4a24-9864-af2cf281f538 · outbound

This paper cites Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Robotic Telekinesis: Learning a Robotic Hand Imitator by Watching Humans on Youtube

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.724671Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65bbef3c-086a-460f-9520-f26c9dbd42bb · outbound

This paper cites Variational infer- ence with normalizing flows.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Variational infer- ence with normalizing flows

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.698532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b216fdfb-4ac4-42a6-9bf3-d87a189c4e08 · outbound

This paper cites RSL-RL: A Learning Library for Robotics Research.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows RSL-RL: A Learning Library for Robotics Research

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.711955Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d0b1dff-94ec-4416-bd03-a2b1cb757831 · outbound

This paper cites Corl: Research-oriented deep offline reinforcement learning library.Advances in Neural Information Processing Systems, 36:30997–31020, 2023.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Corl: Research-oriented deep offline reinforcement learning library.Advances in Neural Information Processing Systems, 36:30997–31020, 2023

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.775706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d0b0b0e8-b22e-47a1-9907-9cab4e547686 · outbound

This paper cites A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows A Walk in the Park: Learning to Walk in 20 Minutes With Model-Free Reinforcement Learning

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.745366Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0168f7c0-7023-473c-87d9-a1a1789ed304 · outbound

This paper cites Revisiting the minimalist ap- proach to offline reinforcement learning.Advances in Neural Information Processing Systems, 36:11592– 11620, 2023.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Revisiting the minimalist ap- proach to offline reinforcement learning.Advances in Neural Information Processing Systems, 36:11592– 11620, 2023

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.760001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f52746c-7015-44de-af1f-81e3c9ebd024 · outbound

This paper cites Nina: Normalizing flows in action.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Nina: Normalizing flows in action

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.816881Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4729479e-c980-4099-87b2-4c67855cfe07 · outbound

This paper cites Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Is Value Functions Estimation with Classification Plug-and-play for Offline Reinforcement Learning?

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.791145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3535bd9b-0478-4cba-b316-ca9feb83c891 · outbound

This paper cites The Role of Deep Learning Regularizations on Actors in Offline RL.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows The Role of Deep Learning Regularizations on Actors in Offline RL

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.805349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f7cb961-c0d0-4379-b261-37d78ea6daa1 · outbound

This paper cites 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.838179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b5c9968-f73a-480f-b37d-4c87eed3a36c · outbound

This paper cites Re- inflow: Fine-tuning flow matching policy with online re- inforcement learning.arXiv preprint arXiv:2505.22094, 2025.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Re- inflow: Fine-tuning flow matching policy with online re- inforcement learning.arXiv preprint arXiv:2505.22094, 2025

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.849119Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6038aa9-3332-468f-aa0a-a0954fcbbbed · outbound

This paper cites Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.885750Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3f72e00-7350-479e-9e50-c4c872928428 · outbound

This paper cites Places: A 10 million image database for scene recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Places: A 10 million image database for scene recognition.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.902474Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768baa4b-6f19-4446-8581-765c9f66e3e0 · outbound

This paper cites an unresolved cited work.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Unresolved cited work

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.916327Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab80c5b9-8273-476b-b9a1-b54141ae3b04 · outbound

This paper cites an unresolved cited work.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.933772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation affab780-9386-439a-96ba-5607fb615fdf · outbound

This paper cites Human finger postures are retargeted to the robotic hand joint angles using an energy-based retargeting method [44].

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Human finger postures are retargeted to the robotic hand joint angles using an energy-based retargeting method [44]

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.953491Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6d297ea-9b93-40b4-8a1b-11e90619c03d · outbound

This paper cites 7, the policy uses 1 step of observation and 3 steps of prefix actions following the observation and predicts a subsequent chunk of 10 steps of actions.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows 7, the policy uses 1 step of observation and 3 steps of prefix actions following the observation and predicts a subsequent chunk of 10 steps of actions

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:50.975256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6360661f-e133-420d-9e70-173538616bbf · outbound

This paper cites Specifically, we define 2 distinct test positions for the scissors and 5 distinct test positions for the tape holder.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Specifically, we define 2 distinct test positions for the scissors and 5 distinct test positions for the tape holder

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.003893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07f07909-04f5-40b4-bc27-04e44090ca1c · outbound

This paper cites Both the training and the inference runs on a desktop with NVIDIA RTX 4090 GPU.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Both the training and the inference runs on a desktop with NVIDIA RTX 4090 GPU

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.027469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f45c0e19-b4cf-4a67-a97b-7c84a80477b5 · outbound

This paper cites To estimate the cube pose, which is provided as input to the policy, we follow the same approach as in [19].

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows To estimate the cube pose, which is provided as input to the policy, we follow the same approach as in [19]

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.051740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc414a15-295c-4c68-90ff-4dc5f0e9c7cd · outbound

This paper cites an unresolved cited work.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Unresolved cited work

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.084056Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff513ce-de18-4b93-883f-610c1d6aaf1e · outbound

This paper cites a) Simulation setup.:Each environment instance con- tains an Orca hand and a rigid cube object placed above a small kinematic platform.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows a) Simulation setup.:Each environment instance con- tains an Orca hand and a rigid cube object placed above a small kinematic platform

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.101800Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d88abaf-e633-4efb-a125-183709fecb98 · outbound

This paper cites We follow the principle as in [35], with adaptation to chunked actions.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows We follow the principle as in [35], with adaptation to chunked actions

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.119781Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a937a74-abad-48c1-b128-f860a1898298 · outbound

This paper cites Each encoder follows the standard torchvision ResNet-18 up to the last convolutional stage (no global average pooling and no FC classifier).

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Each encoder follows the standard torchvision ResNet-18 up to the last convolutional stage (no global average pooling and no FC classifier)

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.131685Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b61e70a3-9eaf-4971-8d5f-de5efe9c9842 · outbound

This paper cites an unresolved cited work.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Unresolved cited work

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.145346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4217e3ab-7c1e-4728-9575-df0356122337 · outbound

This paper cites To ensure a fair comparison, the dataset, optimizer settings, data augmentation strategies, and image encoders are kept identical across all methods.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows To ensure a fair comparison, the dataset, optimizer settings, data augmentation strategies, and image encoders are kept identical across all methods

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.164429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b4362a39-9418-4b90-a4ae-8894c4a2c262 · outbound

This paper cites The ablations in this subsection are per- formed on simulated RoboMimic environments (Lift, Can, and Square).

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows The ablations in this subsection are per- formed on simulated RoboMimic environments (Lift, Can, and Square)

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.179820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5b171467-9343-4787-bdf5-d3ff80f53d1c · outbound

This paper cites Achieving a stable grasp is par- ticularly challenging due to the absence of tactile sensing and frequent occlusion of the index finger by the thumb in wrist- mounted camera views.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Achieving a stable grasp is par- ticularly challenging due to the absence of tactile sensing and frequent occlusion of the index finger by the thumb in wrist- mounted camera views

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.197706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f8fd1e7-30c9-408f-ad15-7310881b896b · outbound

This paper cites Normalizing Flows are Capable Models for Continuous Control.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Normalizing Flows are Capable Models for Continuous Control

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-03T02:53:15.515710Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15c15089-b1e3-48b2-80f7-756c7d62cee7 · outbound

This paper cites an unresolved cited work.

SERNF: Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows Unresolved cited work

Reference 4090

Resolution: unresolved; no resolver link, observed 2026-08-03T02:55:51.213516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers