Paper Citation Record · LEDGER

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

As of 10 August 2026, this Paper Citation Record lists 69 of 69 outbound references and 15 inbound Pith citation observations for arXiv:2502.01828.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2502.01828 v3

Coverage vector

measured 69 of 69 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T14:27:41.185161Z

measured 84 of 84 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 15 of 15 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-07T13:52:12.773873Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: arxiv_reference, observed 2026-07-04T13:09:50.104673Z

Reference resolution

69 of 69 outbound references displayed

verified exact2
verified fuzzy45
unresolved22
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 8b589a07-d766-4520-a45d-36ff9a022fca · outbound

This paper cites Unpacking failure modes of generative policies: Runtime monitoring of consistency and progress.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Unpacking failure modes of generative policies: Runtime monitoring of consistency and progress

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.510508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4939cea9-0537-4b07-b364-3a64607abeff · outbound

This paper cites Anonymous title.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Anonymous title

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.496820Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5610a58e-881f-404d-bab5-66c38e0b8f41 · outbound

This paper cites Policy search by dynamic programming.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Policy search by dynamic programming

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.482960Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a3f063cd-8682-4b32-81a6-bd9afebf7ac7 · outbound

This paper cites RT-1: Robotics Transformer for Real-World Control at Scale.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment RT-1: Robotics Transformer for Real-World Control at Scale

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.915216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 84edf15a-0331-4ac3-8a42-b324757204a8 · outbound

This paper cites RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.920085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 163aa7f5-81cd-4f82-93a6-5c6530c37eb7 · outbound

This paper cites Diffusion policy: Visuomotor policy learning via action diffusion.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Diffusion policy: Visuomotor policy learning via action diffusion

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.924859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 756d77b4-ce36-4aee-93fe-55aac4b37b75 · outbound

This paper cites Universal manipulation interface: In- the-wild robot teaching without in-the-wild robots.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Universal manipulation interface: In- the-wild robot teaching without in-the-wild robots

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.929885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 814dc27f-aa7d-47a2-850e-720e9bd79542 · outbound

This paper cites Agibot world colosseum.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Agibot world colosseum

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.934232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8419f360-de04-48a5-98cd-233a762884b1 · outbound

This paper cites The complexity of theorem-proving procedures.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The complexity of theorem-proving procedures

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.442408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1a827c34-c1b2-45c5-98f3-2000790e90cc · outbound

This paper cites Aha: A vision- language-model for detecting and reasoning over failures in robotic manipulation.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Aha: A vision- language-model for detecting and reasoning over failures in robotic manipulation

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.429294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c8ae09d-3ebe-4103-a2dc-dec892ea20ac · outbound

This paper cites The Llama 3 Herd of Models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The Llama 3 Herd of Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.947290Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9ceea0d6-912b-4ddc-97c6-e599a2b5e76d · outbound

This paper cites Efficient Imitation under Misspecification.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Efficient Imitation under Misspecification

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.951522Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4057891c-f703-44c0-ad0e-4adfbdf713ca · outbound

This paper cites Rh20t: A robotic dataset for learning diverse skills in one-shot.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Rh20t: A robotic dataset for learning diverse skills in one-shot

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.417197Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 02b8ebf6-7c3c-409f-8292-b3ce412bdc6b · outbound

This paper cites Zhao, and Chelsea Finn.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Zhao, and Chelsea Finn

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.404070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2264474e-7fb7-4ee9-bba1-bf8f95cc88e0 · outbound

This paper cites Letter to john von neumann, 1956.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Letter to john von neumann, 1956

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.390958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 88eab4e3-1eac-4a74-ae05-a78cf9932e6f · outbound

This paper cites Task success is not enough: Investigating the use of video-language models as behavior critics for catching undesirable agent behav- iors.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Task success is not enough: Investigating the use of video-language models as behavior critics for catching undesirable agent behav- iors

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.377554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b574df31-06e6-4515-8b46-a66648f4099a · outbound

This paper cites Inverse reward design.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Inverse reward design

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.363397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e8641933-51fc-4a0d-a8f5-37a9b77a8c88 · outbound

This paper cites Mastering Diverse Domains through World Models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Mastering Diverse Domains through World Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.974991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ce77235-0230-4751-ad79-d126cc403196 · outbound

This paper cites Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Run-time Observation Interventions Make Vision-Language-Action Models More Visually Robust

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.978978Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 995493b8-dd95-4762-a7cc-8689aa7f4ef1 · outbound

This paper cites LoRA: Low-rank adaptation of large language models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment LoRA: Low-rank adaptation of large language models

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.349383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bae29f8b-e45c-4959-8d52-57c7a8c6fc1b · outbound

This paper cites Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:40.986804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08f89959-cb68-415c-ae06-42db6a63530d · outbound

This paper cites Future Success Prediction in Open-Vocabulary Object Manipulation Tasks Based on End-Effector Trajectories.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Future Success Prediction in Open-Vocabulary Object Manipulation Tasks Based on End-Effector Trajectories

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-08-09T14:27:41.694875Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5fd43d77-c435-4628-94fd-96ecc74c377e · outbound

This paper cites Behavior generation with latent actions.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Behavior generation with latent actions

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.335295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ada5ad8c-03a0-4f70-a6c6-a8f565440a57 · outbound

This paper cites Model-based runtime monitoring with interac- tive imitation learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Model-based runtime monitoring with interac- tive imitation learning

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.320888Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e3c5044-ce33-49b8-9e34-78ccd7ac6f90 · outbound

This paper cites Multi-task interactive robot fleet learning with visual world models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Multi-task interactive robot fleet learning with visual world models

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.307056Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation db3ba704-e8e2-4b2a-9c7d-6537307fdffe · outbound

This paper cites Reflect: Summarizing robot experiences for failure explanation and correction.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Reflect: Summarizing robot experiences for failure explanation and correction

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.291819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa27cf27-99c3-45e1-a031-7dd0b76381a2 · outbound

This paper cites Steering your generalists: Improving robotic foundation models via value guidance.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Steering your generalists: Improving robotic foundation models via value guidance

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.276220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 290f5333-c69b-4b1e-8b17-512f6fd39f3c · outbound

This paper cites Algorithms for inverse reinforcement learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Algorithms for inverse reinforcement learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.263294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 33f88971-d952-4f22-9ced-e1124a191cbd · outbound

This paper cites GPT-4 Technical Report.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment GPT-4 Technical Report

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.018516Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cdaa777-3366-49a6-a27b-eaa3290f47c2 · outbound

This paper cites Dinov2: Learning robust visual features without supervision.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Dinov2: Learning robust visual features without supervision

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.249505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b995d317-1f22-406a-8eac-4771d8292d77 · outbound

This paper cites Learning to search: Functional gradient techniques for imitation learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Learning to search: Functional gradient techniques for imitation learning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.236428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d5c73c1f-6834-4082-b65e-c70b808a7ace · outbound

This paper cites Hybrid Inverse Reinforcement Learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Hybrid Inverse Reinforcement Learning

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.031294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51b14143-d27a-4c57-8211-92751485e476 · outbound

This paper cites Multimodal diffusion transformer: Learning versatile behavior from multimodal goals.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Multimodal diffusion transformer: Learning versatile behavior from multimodal goals

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.223132Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4db534f7-4a9a-4530-baf3-cbb4b00151f4 · outbound

This paper cites Efficient reductions for imitation learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Efficient reductions for imitation learning

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.040059Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4b4c681-031b-4c51-b24c-b93c314caa19 · outbound

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

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment A reduction of imitation learning and structured prediction to no-regret online learning

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.044257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd7f8b25-e4c9-4a17-9b8c-c0c4df64830f · outbound

This paper cites Motionlm: Multi-agent mo- tion forecasting as language modeling.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Motionlm: Multi-agent mo- tion forecasting as language modeling

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.190859Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 56d26b11-195b-433e-bb05-7dced5f8c6fb · outbound

This paper cites Shafiullah, Siyuan.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Shafiullah, Siyuan

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.177466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 830ee759-6941-415a-89d7-067b2ea4ccce · outbound

This paper cites On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.057081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 137493bb-d8fb-40e7-8cd6-87423367d4b3 · outbound

This paper cites Real-time anomaly detection and reactive planning with large lan- guage models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Real-time anomaly detection and reactive planning with large lan- guage models

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.161527Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4ee7bc27-b8b3-44e2-be21-0238b4b01c53 · outbound

This paper cites Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Hybrid RL: Using Both Offline and Online Data Can Make RL Efficient

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.065666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94c2e2c4-c045-46fb-ae27-15595efc8776 · outbound

This paper cites Of moments and matching: A game- theoretic framework for closing the imitation gap.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Of moments and matching: A game- theoretic framework for closing the imitation gap

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.144725Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0cbeca50-09bc-41b5-abb5-1905d698c784 · outbound

This paper cites Inverse reinforcement learning without reinforcement learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Inverse reinforcement learning without reinforcement learning

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.129334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e2e98ee7-1f1e-44b6-836b-cf99b9424741 · outbound

This paper cites All roads lead to likelihood: The value of reinforcement learning in fine- tuning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment All roads lead to likelihood: The value of reinforcement learning in fine- tuning

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.077554Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11ef39d3-0b49-42a4-b3d9-4367073cd1c9 · outbound

This paper cites Open X-Embodiment: Robotic learning datasets and RT-X models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Open X-Embodiment: Robotic learning datasets and RT-X models

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.114493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 290dbfa2-7fc9-4760-81a0-7a1a4188cc67 · outbound

This paper cites The virtues of laziness in model-based rl: A unified objective and algorithms.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The virtues of laziness in model-based rl: A unified objective and algorithms

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.099643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3de94b86-33af-427f-be63-d3c9f4388217 · outbound

This paper cites Vincent, Haruki Nishimura, Masha Itkina, Paarth Shah, Mac Schwager, and Thomas Kollar.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Vincent, Haruki Nishimura, Masha Itkina, Paarth Shah, Mac Schwager, and Thomas Kollar

Reference 46

Resolution: verified exact; arxiv_id_nonexistent, observed 2026-08-09T14:27:41.440863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 15ffe3ec-6a88-4c52-a879-af091929eb3d · outbound

This paper cites Inference-Time Policy Steering through Human Interactions.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Inference-Time Policy Steering through Human Interactions

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.091991Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 121590dc-976e-49aa-9b31-4996f59e3dc5 · outbound

This paper cites I can tell what i am doing: Toward real-world natural language grounding of robot experiences.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment I can tell what i am doing: Toward real-world natural language grounding of robot experiences

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.084987Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 590503f7-1599-4a35-aa29-bb2b1d56f542 · outbound

This paper cites ivideogpt: Inter- active videogpts are scalable world models.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment ivideogpt: Inter- active videogpts are scalable world models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.099593Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c651721-e6bb-439b-9278-ed7ceb05b698 · outbound

This paper cites Daydreamer: World models for physical robot learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Daydreamer: World models for physical robot learning

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.061410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b6e45317-302e-4b13-8fca-0ab7eaba9a8c · outbound

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

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-09T14:27:41.107736Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c8988b6-4fe9-4f9a-9c16-0a1e7e019331 · outbound

This paper cites Maximum entropy inverse reinforcement learning.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Maximum entropy inverse reinforcement learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.048246Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4246158a-a597-4fd8-abe4-ef8ae97f2088 · outbound

This paper cites Rollouts from Demonstration Dataset Cup Task Bag Task Fork Task Fig.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Rollouts from Demonstration Dataset Cup Task Bag Task Fork Task Fig

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.034947Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3e5e1362-f299-4b1d-803a-3c2d98623638 · outbound

This paper cites Each mode has 25 demonstrations.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Each mode has 25 demonstrations

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.021710Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 834a5348-24e4-47be-a5cc-e02f8ffaccab · outbound

This paper cites The effectiveness of world models has been demonstrated across various embodied domains [25, 50].

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The effectiveness of world models has been demonstrated across various embodied domains [25, 50]

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:42.008450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 685454a3-965f-43a9-9232-448851f66816 · outbound

This paper cites The robot aims to grasp the cup. Describe the behavior.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The robot aims to grasp the cup. Describe the behavior

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.995019Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d472b462-4da8-4c97-a9f0-fd799ade0acb · outbound

This paper cites We use Llama-3.2-11B-Vision-Instruct model as our VLM backbone.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment We use Llama-3.2-11B-Vision-Instruct model as our VLM backbone

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.981561Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 275ea7af-e10b-4a5f-a2f7-a3e44ef48adf · outbound

This paper cites handle, rim.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment handle, rim

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.969456Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3503ccaa-341b-4174-99e7-f7b9518f4a5b · outbound

This paper cites The first three dimensions are the x, y, z positions of the robot gripper.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment The first three dimensions are the x, y, z positions of the robot gripper

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.954803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8ced2037-f41c-4b47-a20f-0af641754e1e · outbound

This paper cites Do not include any additional text, explanations, or information.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Do not include any additional text, explanations, or information

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.940597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d24188e7-655d-4f36-8500-9d5ecd9db2e0 · outbound

This paper cites This baseline is an ablated version of FORE- W ARNwithout the explicit world model.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment This baseline is an ablated version of FORE- W ARNwithout the explicit world model

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.925803Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6166e67c-4580-40e8-b0ab-67439d791d10 · outbound

This paper cites an unresolved cited work.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Unresolved cited work

Reference 62

Resolution: unresolved; raw_fallback, observed 2026-08-09T14:27:41.911276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8802b02-3b33-4eeb-b3e9-86dc5aebab7e · outbound

This paper cites an unresolved cited work.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment Unresolved cited work

Reference 63

Resolution: unresolved; raw_fallback, observed 2026-08-09T14:27:41.897180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 97a04988-ccc1-4909-bf11-400e36f3b93b · outbound

This paper cites handle, inner surface, etc.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment handle, inner surface, etc

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.881476Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9b0645c8-aea2-4033-ab4c-1326999f8c46 · outbound

This paper cites If the cup is not grasped in the robot's gripper, the sentence should describe the failure.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment If the cup is not grasped in the robot's gripper, the sentence should describe the failure

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.865428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 48f0af90-85f3-480e-a7c5-60cb0ec5776c · outbound

This paper cites 15 demonstrates the setup of our real-world experiments.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment 15 demonstrates the setup of our real-world experiments

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.850605Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b1cfd582-4974-45d4-a5a4-21d5acda715e · outbound

This paper cites We include additional qualitative examples for Cup and Bag tasks in Fig 16.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment We include additional qualitative examples for Cup and Bag tasks in Fig 16

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.837085Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d6e2a521-79e8-4b0a-85b6-23c558f2e3fa · outbound

This paper cites V-A and queries the VLM again to decide if the behavior is a success or failure within the context of the task description ℓ.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment V-A and queries the VLM again to decide if the behavior is a success or failure within the context of the task description ℓ

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.823502Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1e289fe1-11f1-4f50-8886-14a0e0b6cb36 · outbound

This paper cites grasp- ing the cup.

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment grasp- ing the cup

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T14:27:41.809872Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation 1d242b21-9e3d-4f4d-8f34-46a78bc0a80c · inbound

Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation cites this paper.

Cross from Left to Right Brain: Adaptive Text Dreamer for Vision-and-Language Navigation From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-07T13:52:12.773873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bde91d5-ee5e-4bfc-b3bb-ef3d5ec8dc41 · inbound

Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence cites this paper.

Adapting by Analogy: OOD Generalization of Visuomotor Policies via Functional Correspondence From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T00:48:49.489677Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 216ce25f-48eb-4a3c-8dee-35ce4f13e195 · inbound

Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution cites this paper.

Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-05T23:06:33.877275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86e1d926-f588-4dd3-a39f-fbc0046a07b9 · inbound

Learn from What We HAVE: History-Aware VErifier that Reasons about Past Interactions Online cites this paper.

Learn from What We HAVE: History-Aware VErifier that Reasons about Past Interactions Online From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T13:52:52.539441Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726db4cb-2725-42bb-baaf-08956206569f · inbound

EVE: A Generator-Verifier System for Generative Policies cites this paper.

EVE: A Generator-Verifier System for Generative Policies From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-03T14:10:36.253138Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b2a703c-f0ff-41bf-89aa-ade26ebe71fc · inbound

Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control cites this paper.

Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-15T22:06:42.942117Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4eca8077-1d50-42af-bf21-787a67b6195b · inbound

Position: Good Embodied Reward Models Need Bad Behavior Data cites this paper.

Position: Good Embodied Reward Models Need Bad Behavior Data From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-06-28T17:22:24.960996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 35950b30-a425-4cde-9359-48840d7643b1 · inbound

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring cites this paper.

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-07-02T02:56:29.043003Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26b762c2-5d3a-4258-bc31-2d7175a5612b · inbound

APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies cites this paper.

APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 59

Resolution: verified exact; arxiv_id, observed 2026-07-03T10:48:02.727730Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 41b0bc13-cd81-4e9c-8519-82d281cb7887 · inbound

DREAM-Chunk: Reactive Action Chunking with Latent World Model cites this paper.

DREAM-Chunk: Reactive Action Chunking with Latent World Model From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 36

Resolution: verified exact; arxiv_id, observed 2026-07-04T00:09:15.270179Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ec05cca0-bdac-44cb-bd0e-41436194c5f3 · inbound

Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation cites this paper.

Slow Brain, Fast Planner: Latency-Resilient VLM-Augmented Urban Navigation From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T04:09:33.934494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bb1f8008-4fff-4629-9b57-ac41cd6a5cee · inbound

Robot Critics that Sweat the Small Stuff cites this paper.

Robot Critics that Sweat the Small Stuff From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-07-04T06:39:37.258087Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f92489a7-9155-46f6-9020-878fce3872e4 · inbound

TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation cites this paper.

TEXEDO : Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T10:29:44.868915Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6617e871-9fb1-4b45-b2fe-ab32a93ca062 · inbound

Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure cites this paper.

Inference-Time Robot Behavior Steering through Physically-Aware Reconfiguration of Task-Structure From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:09:50.106851Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6d0e9dd3-8709-47ac-879a-b08065b458ee · inbound

DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning cites this paper.

DREAMSTEER: Latent World Models Can Steer VLA Policies During Deployment Without Any Finetuning From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-12T06:30:52.991927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.