When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited | Paper Citation Record

Observation d0d4d1fa-72ac-44a1-8a10-08e9089a879f · outbound

This paper cites GPT-4 Technical Report.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited GPT-4 Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.227469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6b594a39-a039-41c1-93d5-66378995b896 · outbound

This paper cites Policy optimization for strictly batch imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Policy optimization for strictly batch imitation learning

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.480886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ad85ab56-bc0c-41dc-85da-32727521cdb4 · outbound

This paper cites Balance equation-based distributionally robust offline imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Balance equation-based distributionally robust offline imitation learning

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.243799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 302bfe2f-eefd-4144-8475-bf65bba86c62 · outbound

This paper cites Markov balance satisfac- tion improves performance in strictly batch offline imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Markov balance satisfac- tion improves performance in strictly batch offline imitation learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.384325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation ee1ed0ad-ad01-46bb-929b-e16a65c7d7ee · outbound

This paper cites Conditional kernel imi- tation learning for continuous state environments.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Conditional kernel imi- tation learning for continuous state environments

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.420817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 487ef4bc-5f82-4855-8dec-f8c8aad86676 · outbound

This paper cites The reality gap in robotics: Challenges, solutions, and best practices.Annual Review of Control, Robotics, and Autonomous Systems, 9.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited The reality gap in robotics: Challenges, solutions, and best practices.Annual Review of Control, Robotics, and Autonomous Systems, 9

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.467158Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a41a4d34-9230-4bcf-a88b-e3b3e55c4217 · outbound

This paper cites Routledge.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Routledge

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.460648Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5dfda726-48b1-4576-a946-4737464ce04f · outbound

This paper cites Dexterous manipulation through imitation learning: A survey.arXiv preprint arXiv:2504.03515.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Dexterous manipulation through imitation learning: A survey.arXiv preprint arXiv:2504.03515

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.247159Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 228cb673-8608-4c24-82b6-5d25f4f6eadc · outbound

This paper cites Layer Normalization.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Layer Normalization

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.208281Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 92ae4e73-b072-47c6-a1e8-26fa7684f8fc · outbound

This paper cites Successor features for transfer in reinforcement learning.Advances in neural information processing systems, 30.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Successor features for transfer in reinforcement learning.Advances in neural information processing systems, 30

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.457022Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fb48cde2-afe1-4053-a90d-38dd781e6fc2 · outbound

This paper cites Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Learning Successor States and Goal-Dependent Values: A Mathematical Viewpoint

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.250688Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 64dd5017-b8dc-4058-beee-a8b6ce7b01de · outbound

This paper cites an unresolved cited work.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-05-19T20:37:45.473195Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1ab9efc2-4114-43f8-8069-bfd5fc90ee35 · outbound

This paper cites Universal Successor Features Approximators.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Universal Successor Features Approximators

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.218909Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 2e29fd85-b5c7-453c-a1ea-42ad438d8318 · outbound

This paper cites Cambridge university press.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Cambridge university press

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.471280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5652da79-0a06-42a5-bcc0-dd081280835f · outbound

This paper cites Exploration by Random Network Distillation.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Exploration by Random Network Distillation

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.204809Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9e877939-3746-4fa2-a1fb-32e6723da8fb · outbound

This paper cites Robust imitation learning against variations in environment dynamics.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust imitation learning against variations in environment dynamics

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.399415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4afc57c0-b27d-4c63-a0ff-626bf1971e85 · outbound

This paper cites Meta-controller: Few- shot imitation of unseen embodiments and tasks in continuous control.Advances in Neural Information Processing Systems, 37:134250–134286.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Meta-controller: Few- shot imitation of unseen embodiments and tasks in continuous control.Advances in Neural Information Processing Systems, 37:134250–134286

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.405710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6228e72e-00b0-4b5e-ad24-1202315af337 · outbound

This paper cites Exploring the limitations of behavior cloning for autonomous driving.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Exploring the limitations of behavior cloning for autonomous driving

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.476994Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation b87c1f00-298d-46dd-8336-9eeb1327cb38 · outbound

This paper cites Improving generalization for temporal difference learning: The successor repre- sentation.Neural computation, 5(4):613–624.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Improving generalization for temporal difference learning: The successor repre- sentation.Neural computation, 5(4):613–624

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.386414Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 24e13565-6d03-4ccc-97e2-e510605aff4e · outbound

This paper cites Distributional Robustness and Regularization in Reinforcement Learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Distributional Robustness and Regularization in Reinforcement Learning

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.201601Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f5046859-1083-4769-b3e5-ef14f7a7de0c · outbound

This paper cites One-shot imitation learning.Advances in neural information processing systems, 30.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited One-shot imitation learning.Advances in neural information processing systems, 30

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.440659Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation c5452bd8-cae7-435e-92e9-1edcc1050f52 · outbound

This paper cites One-shot visual imitation learning via meta-learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited One-shot visual imitation learning via meta-learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.382009Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6ba05ca4-bd91-4d6d-aff7-57f2953542dd · outbound

This paper cites Off-policy deep reinforcement learning without exploration.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Off-policy deep reinforcement learning without exploration

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.426795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 99cec878-a7fa-4459-a115-744b1b939329 · outbound

This paper cites Generative adversarial imitation learning.Advances in neural information processing systems, 29.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Generative adversarial imitation learning.Advances in neural information processing systems, 29

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.479093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0d91f97e-a76b-4d5d-a47d-c38da7fe7d7e · outbound

This paper cites Impact of static friction on sim2real in robotic reinforcement learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Impact of static friction on sim2real in robotic reinforcement learning

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.483082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6c5ba828-78d9-42db-a5e2-8cb2bbf7ee81 · outbound

This paper cites Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Generalization in Dexterous Manipulation via Geometry-Aware Multi-Task Learning

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.240783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 0d047c0d-3735-4310-bd08-cfe3c3680000 · outbound

This paper cites Robust dynamic programming.Mathematics of Operations Research, 30(2): 257–280.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust dynamic programming.Mathematics of Operations Research, 30(2): 257–280

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.448336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 98381b2b-238d-4c93-851f-71cae5e58330 · outbound

This paper cites Task-embedded control networks for few-shot imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Task-embedded control networks for few-shot imitation learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.436718Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 378fad2b-e5ab-4632-8947-ff4dff9d057b · outbound

This paper cites Zero-shot reinforcement learning from low quality data.Advances in Neural Information Processing Systems, 37:16894–16942.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Zero-shot reinforcement learning from low quality data.Advances in Neural Information Processing Systems, 37:16894–16942

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.446451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 50626c59-d028-4721-9d66-d21892112808 · outbound

This paper cites Zero-Shot Reinforcement Learning Under Partial Observability.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Zero-Shot Reinforcement Learning Under Partial Observability

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.263201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation cf8a8014-4bfd-45e0-bdb5-3388cfdcd377 · outbound

This paper cites DemoDICE: Offline imitation learning with supplementary imperfect demonstrations.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited DemoDICE: Offline imitation learning with supplementary imperfect demonstrations

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.465187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4ad56f9f-6830-4ff8-b09c-952e52aeb184 · outbound

This paper cites Adam: A Method for Stochastic Optimization.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Adam: A Method for Stochastic Optimization

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.211845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation db98591e-ab21-47e6-acf0-34767a58ea0b · outbound

This paper cites Imitation learning via off-policy dis- tribution matching.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Imitation learning via off-policy dis- tribution matching

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.388740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f2a2b538-4dc1-4432-9774-c4c15e14b055 · outbound

This paper cites Dart: Noise injection for robust imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Dart: Noise injection for robust imitation learning

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.444273Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6479bbc1-6330-49b3-a89c-6476e218d57e · outbound

This paper cites Aps: Active pretraining with successor features.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Aps: Active pretraining with successor features

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.432581Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 75cd7414-a16c-4562-963a-64584be505f7 · outbound

This paper cites ODICE: Revealing the mystery of distribution correction estimation via orthogonal-gradient update.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited ODICE: Revealing the mystery of distribution correction estimation via orthogonal-gradient update

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.428799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 9cdbc2f0-11e1-49fd-a1b2-c6a2ac670762 · outbound

This paper cites Robust control of markov decision processes with uncertain transition matrices.Operations Research, 53(5):780–798.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust control of markov decision processes with uncertain transition matrices.Operations Research, 53(5):780–798

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.407854Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fa3fb249-47d4-4c57-8b27-b7f15190c9fa · outbound

This paper cites Robust rein- forcement learning using offline data.Advances in neural information processing systems, 35: 32211–32224.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust rein- forcement learning using offline data.Advances in neural information processing systems, 35: 32211–32224

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.422808Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fb042fcd-6bd1-43e9-b11c-e517380ea1f0 · outbound

This paper cites Distributionally robust behavioral cloning for robust imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Distributionally robust behavioral cloning for robust imitation learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.442452Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 62cd58ac-d32e-4a0f-9343-f87a6f9bfd63 · outbound

This paper cites Bridging distributionally robust learning and offline rl: An approach to mitigate distribution shift and partial data coverage.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Bridging distributionally robust learning and offline rl: An approach to mitigate distribution shift and partial data coverage

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.418899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 574bbc35-79a0-496e-86ad-02e0a0e73f6b · outbound

This paper cites an unresolved cited work.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Unresolved cited work

Reference 41

Resolution: unresolved; raw_fallback, observed 2026-05-19T20:37:45.379771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation e75e58e1-1c3f-4fb7-9b0e-6ae28fec41b7 · outbound

This paper cites Foundation Policies with Hilbert Representations.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Foundation Policies with Hilbert Representations

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.260277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 943e97fa-5103-46ed-a4e8-f0fd51a4797d · outbound

This paper cites Sim-to-real transfer of robotic control with dynamics randomization.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Sim-to-real transfer of robotic control with dynamics randomization

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.450503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6296c59f-de0d-4fcc-a7ff-564032571456 · outbound

This paper cites Fast imitation via behavior foundation models.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Fast imitation via behavior foundation models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.416519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 78a8279a-4c1b-4e6b-8394-f162292754f2 · outbound

This paper cites Alvinn: An autonomous land vehicle in a neural network.Advances in neural information processing systems, 1:305–313.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Alvinn: An autonomous land vehicle in a neural network.Advances in neural information processing systems, 1:305–313

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.475117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d12b7caa-c795-4f9b-bde8-bbe684d72502 · outbound

This paper cites John Wiley & Sons.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited John Wiley & Sons

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.455086Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 01daf410-b0ef-4a1b-8d5f-76a6ea800942 · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Direct preference optimization: Your language model is secretly a reward model

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.469388Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f35253c3-497b-45e8-83da-eb0a5e51bb58 · outbound

This paper cites Efficient reductions for imitation learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Efficient reductions for imitation learning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.414549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation a28e4146-e314-41d0-a4dd-85afdb424bed · outbound

This paper cites A reduction of imitation learning and structured prediction to no-regret online learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited A reduction of imitation learning and structured prediction to no-regret online learning

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.393345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7c383441-5117-4f1e-ab5f-f8714705626f · outbound

This paper cites Optimistic task inference for behavior foundation models.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Optimistic task inference for behavior foundation models

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.253766Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation fc100694-45d1-4f1b-9c80-ef3002ea55cd · outbound

This paper cites Universal value function ap- proximators.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Universal value function ap- proximators

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.434432Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation d99a6ea9-0443-419f-932f-0e0dd452b71f · outbound

This paper cites Mitigating covariate shift in behavioral cloning via robust stationary distribution correction.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Mitigating covariate shift in behavioral cloning via robust stationary distribution correction

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.412160Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation f5636eb2-1e3e-4256-845e-33a4420257d6 · outbound

This paper cites Robust imitation learning from noisy demonstrations.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust imitation learning from noisy demonstrations

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.395347Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 6b9b9ee6-4c1e-4bcb-a4cc-03d53e307c5f · outbound

This paper cites DeepMind Control Suite.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited DeepMind Control Suite

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-05-19T20:37:45.221781Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1c7145c7-2773-4847-adb6-c71c870065c9 · outbound

This paper cites Reinforcement learning in robotic systems: A review on sim-to-real transfer.Robotics and Autonomous Systems, page 105327.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Reinforcement learning in robotic systems: A review on sim-to-real transfer.Robotics and Autonomous Systems, page 105327

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.430698Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 1052ee08-149a-4832-9563-f5105b549d23 · outbound

This paper cites Learning one representation to optimize all rewards.Advances in Neural Information Processing Systems, 34:13–23.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Learning one representation to optimize all rewards.Advances in Neural Information Processing Systems, 34:13–23

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.397343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3433b48f-2f43-4459-b30c-2adcf64eba0e · outbound

This paper cites Does Zero-Shot Reinforcement Learning Exist?.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Does Zero-Shot Reinforcement Learning Exist?

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.215435Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 3effa551-61e8-468e-9836-92311e9f06a6 · outbound

This paper cites Does zero-shot reinforcement learning exist? InThe Eleventh International Conference on Learning Representations.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Does zero-shot reinforcement learning exist? InThe Eleventh International Conference on Learning Representations

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.390719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation eb69b31f-c4dc-4f5d-a0f6-7e2414c2811f · outbound

This paper cites Robust Behavior Cloning Via Global Lipschitz Regularization.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Robust Behavior Cloning Via Global Lipschitz Regularization

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-05-19T20:37:45.237389Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 35f7b247-f627-4613-90f3-a994d1b43aa9 · outbound

This paper cites Imitation learning from imperfect demonstration.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Imitation learning from imperfect demonstration

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.424655Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 020a3c53-7333-4145-8845-3298c8553e63 · outbound

This paper cites Reinforcement learning with prototypical representations.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Reinforcement learning with prototypical representations

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.458883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 7559b3af-2cf4-49f2-a0d9-7b751ff62f0a · outbound

This paper cites Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Don't Change the Algorithm, Change the Data: Exploratory Data for Offline Reinforcement Learning

Reference 62

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T20:37:45.256980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 4a8932c8-14f1-4f78-a180-820a028518e6 · outbound

This paper cites Fast bellman updates for wasserstein distributionally robust mdps.Advances in Neural Information Processing Systems, 36:30554–30578.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Fast bellman updates for wasserstein distributionally robust mdps.Advances in Neural Information Processing Systems, 36:30554–30578

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.452636Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 03a0514b-17c6-4b7d-90ef-2e363b93740a · outbound

This paper cites Breeze: Towards robust zero-shot reinforcement learning.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Breeze: Towards robust zero-shot reinforcement learning

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.403660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 64fb654f-2f22-4e0d-93ca-ce25d5c5da15 · outbound

This paper cites Watch, try, learn: Meta-learning from demonstrations and rewards.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Watch, try, learn: Meta-learning from demonstrations and rewards

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.401664Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 43c4731a-31b9-4401-8556-fb6e8b54f1a8 · outbound

This paper cites 13 Appendices A Missing Proofs 16 B Extended Related Work 19 C Experimental Setup 20 C.1 ExORL Domains.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited 13 Appendices A Missing Proofs 16 B Extended Related Work 19 C Experimental Setup 20 C.1 ExORL Domains

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.438751Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 5e7491df-18cb-4e9d-adb8-d40f92e8c373 · outbound

This paper cites 17 Proof.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited 17 Proof

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.462443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Observation 619bf793-8a40-4e38-a338-b1102454590d · outbound

This paper cites Pretrained on RND data.

When Dynamics Shift, Robust Task Inference Wins: Offline Imitation Learning with Behavior Foundation Models Revisited Pretrained on RND data

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T20:37:45.410152Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers