Pith. sign in

Paper Citation Record · LEDGER

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

As of 8 August 2026, this Paper Citation Record lists 100 of 145 outbound references and 0 inbound Pith citation observations for arXiv:2607.26991.

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

pith.paper-citation-record.v1
2607.26991 v2

Coverage vector

measured 100 of 145 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-01T10:23:22.546415Z

measured 100 of 100 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

100 of 145 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved99
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 82189999-d2a1-4aa9-8fbd-d1272d3f771b · outbound

This paper cites From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models From Intention to Execution: Probing the Generalization Boundaries of Vision-Language-Action Models

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.435458Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.435458Z digest=sha256:0ac64c094a84ce8f27218d495a94ac74a64e245be59e1f5ebdcfb4075a337272

Observation 4058a8c2-20b2-4552-ade8-5648240821b1 · outbound

This paper cites Interleave-VLA: Enhancing robot ma- nipulation with image-text interleaved instructions,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Interleave-VLA: Enhancing robot ma- nipulation with image-text interleaved instructions,

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.492884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.492884Z digest=sha256:3c8ae817664c13a75bdbcfdd361e23cef9741d03cf44811253f29d607c121c41

Observation 8d04be80-913f-4dae-84f5-6892ef26704b · outbound

This paper cites Openvla: An open-source vision-language-action model,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Openvla: An open-source vision-language-action model,

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.620644Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.620644Z digest=sha256:c05a258ce5021e40c8e13ba4760a00eb98b4889aeaad4a7ac8bbcf867a0e953d

Observation a5d449e5-326b-4bd5-9177-80821f0acfa3 · outbound

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

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.732230Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.732230Z digest=sha256:f1b09947834808b49c4b808826cc24e4e501a01049eb5225cbed2679864a405f

Observation 26ecde4f-a058-4467-b0bd-be50d94cfc35 · outbound

This paper cites π 0.5: a vision- language-action model with open-world generalization,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models π 0.5: a vision- language-action model with open-world generalization,

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.818099Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.818099Z digest=sha256:2280cd107f9251c1d67ff3800cac3c385e5d9b1c5cd192b2150a5b3abf27d9c5

Observation 836a3aa9-8e48-4ea9-b88b-f12df5d4f65f · outbound

This paper cites MolmoAct: Action Reasoning Models that can Reason in Space.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models MolmoAct: Action Reasoning Models that can Reason in Space

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.881598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.881598Z digest=sha256:bf3b3caec57456e5171f77dcba58326a91a3ffb371ed99a0c3c7024fd4fcdd6e

Observation 8f77e18b-c5c8-434c-84dd-e22b1dbc284c · outbound

This paper cites Open x-embodiment: Robotic learning datasets and rt-x models.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Open x-embodiment: Robotic learning datasets and rt-x models

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:13.955885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:13.955885Z digest=sha256:2a7cde5e7ac9ef9fe6ce737b90d849d36a26c5b9f56a267b330d3c90a7602b76

Observation 8247ecf9-282f-4cea-99d9-e682e690fe3f · outbound

This paper cites GRAPE: Generalizing Robot Policy via Preference Alignment.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models GRAPE: Generalizing Robot Policy via Preference Alignment

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.040221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.040221Z digest=sha256:7e0de2bfb72e98f0a2e18c46fe886b82d1eb9c69efa94f8f87a4705fc184478f

Observation 8b64a5cd-3678-4ceb-89c0-ba09c37d333d · outbound

This paper cites Robotic control via embodied chain-of-thought reasoning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Robotic control via embodied chain-of-thought reasoning,

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.126447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.126447Z digest=sha256:75464d74e0d35ede93dc08fa3307255fc33483bab569157ab783a7d5dfd8ade8

Observation 2fa1ccc3-685b-4333-af6d-97b64a207dbd · outbound

This paper cites Fast ecot: Efficient embodied chain-of-thought via thoughts reuse,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Fast ecot: Efficient embodied chain-of-thought via thoughts reuse,

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.218154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.218154Z digest=sha256:b5f781fa3d3a8929ca0c29d48eba5dc5e10559b53189624072eaf3b9cf0cd1d2

Observation 8c34d8a8-1442-4862-80f1-30b347952d6b · outbound

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

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Steering your generalists: Improving robotic foundation models via value guidance,

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.314459Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.314459Z digest=sha256:015333d11b9855c67749c859fc10ee2aa03f9e1564d437cd28af7d37aa9a1480

Observation 2abd730c-9928-476c-aa25-ece195e49fc4 · outbound

This paper cites Robomonkey: Scaling test-time sampling and verifi- cation for vision-language-action models,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Robomonkey: Scaling test-time sampling and verifi- cation for vision-language-action models,

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.407718Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.407718Z digest=sha256:abc675ae1e7090602b7e6d188310714d4b6f7a9fb95d5684b7baad4bce2fc19e

Observation 24177c57-d34b-4b97-ab02-764330135832 · outbound

This paper cites Scaling verification can be more effective than scaling policy learning for vision-language-action alignment,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Scaling verification can be more effective than scaling policy learning for vision-language-action alignment,

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.511876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.511876Z digest=sha256:adbeed270e703db0a5b37a8147a1597694e30b8b824e47dd567d3ef82b5253f7

Observation 38b13b1a-62e6-4e76-bf34-5a8351475e0f · outbound

This paper cites From foresight to fore- thought: Vlm-in-the-loop policy steering via latent alignment,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models From foresight to fore- thought: Vlm-in-the-loop policy steering via latent alignment,

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.605511Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.605511Z digest=sha256:5891c4a60216fed8be8d8e2374d765fbaa532411047f84b3709427541277698c

Observation fa7863d8-ce58-4de8-ab0c-6e13f8cb9783 · outbound

This paper cites Do what you say: Steering vision-language-action models via runtime reasoning-action alignment verification,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Do what you say: Steering vision-language-action models via runtime reasoning-action alignment verification,

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.697591Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.697591Z digest=sha256:cfe01e7a43cecf4eb87824b39ab1cf39088258bdb846f46a628f0e13d7c592e0

Observation cfeeb6de-fdc0-442d-8e48-6232de845942 · outbound

This paper cites Dynaguide: Steering diffusion policies with active dynamic guidance,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Dynaguide: Steering diffusion policies with active dynamic guidance,

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.792815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.792815Z digest=sha256:f0de32b7db960503c02232448631bb4f0781ffa5e4009aab9b32b3f24fb66831

Observation 17a3eb91-e3b8-4596-9db3-5df5637da133 · outbound

This paper cites VLS: Steering pretrained robot policies via vision-language models,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models VLS: Steering pretrained robot policies via vision-language models,

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.869132Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.869132Z digest=sha256:3d4a5772ea59844331345688532d58f9d26a9b6a770830c902d15ab3f81e0ff0

Observation 3ceff9a1-5900-42a1-b5ae-7869d131bc48 · outbound

This paper cites Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:14.938409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:14.938409Z digest=sha256:3cd3b4edf878b6437d803943b99a8f8db0984c445aad486360f47cc9dd55a0c7

Observation 915828f1-0902-45cf-b36a-ba3f53163dce · outbound

This paper cites Compose your policies! improving diffusion-based or flow-based robot policies via test-time distribution- level composition,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Compose your policies! improving diffusion-based or flow-based robot policies via test-time distribution- level composition,

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.033215Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.033215Z digest=sha256:28936d9b7f820b59a2afe735fbd9b3efcb2425c8d1bfeb6851178b87980e213b

Observation 5d98c612-a7d0-4b30-8fe9-52d1eac505f2 · outbound

This paper cites Safe: Multitask failure detection for vision-language-action models,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Safe: Multitask failure detection for vision-language-action models,

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.125967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.125967Z digest=sha256:5100023d1a7a198c08235446e364583d5191c9008733ca7311cf1f90043daa42

Observation 8a620c79-e51d-40df-b3f6-860cbe107bfe · outbound

This paper cites Evaluating Real-World Robot Manipulation Policies in Simulation.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Evaluating Real-World Robot Manipulation Policies in Simulation

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.210833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.210833Z digest=sha256:f0854c6d8ca420215a8469c8c81250a6490f3b72e7b84a320409e7462d0280a7

Observation 8e8fd429-779b-492c-a9b7-cb4accc96e0f · outbound

This paper cites Polaris: Scalable real-to-sim evaluations for generalist robot policies,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Polaris: Scalable real-to-sim evaluations for generalist robot policies,

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.286564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.286564Z digest=sha256:8557951962d440b1bcfa94100a45ed1ebdbfd41984e12964a4fca798ea28b352

Observation e13195e9-186c-476a-850e-4225a93e5ac1 · outbound

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

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models $\pi^{*}_{0.6}$: a VLA That Learns From Experience

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.337472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.337472Z digest=sha256:740e14b1b1bf28138407a922678b79dbd38bd2071c1834088503a22267ed0c12

Observation 4f6bdf98-badb-4894-b743-112ebdf6bb6a · outbound

This paper cites SimpleVLA-RL: Scaling VLA training via reinforcement learning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models SimpleVLA-RL: Scaling VLA training via reinforcement learning,

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.417435Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.417435Z digest=sha256:da47e9f6c8ee547a96b25499cdc5a653c085a5729c6ae4fd8dc166eacf1943ab

Observation 207cf4cb-6321-426a-a817-a9615cb056b3 · outbound

This paper cites Conrft: A reinforced fine-tuning method for vla models via consistency policy,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Conrft: A reinforced fine-tuning method for vla models via consistency policy,

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.508623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.508623Z digest=sha256:27452d3266d967fa4fe0edd6bae1d2ef29585ede882966b7a461cf7fedf59ffe

Observation 49350aa3-aa90-4f42-a1b9-204ee52fbbc3 · outbound

This paper cites Policy decorator: Model-agnostic online refinement for large policy model,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Policy decorator: Model-agnostic online refinement for large policy model,

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.618052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.618052Z digest=sha256:9f83bf87dcaca3b332a2ba50b9809b696bf1fe3c6e472870e61e5b9873855634

Observation 5bf7d3ac-a881-4c33-a488-a00f148adfc0 · outbound

This paper cites Self-improving vision-language-action models with data generation via residual RL,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Self-improving vision-language-action models with data generation via residual RL,

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.692751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.692751Z digest=sha256:afc32950ddb3ff40f28858f411f99502d8db77ca078bf4016dac8dcf68e89b44

Observation 1d6071e7-ceab-4e17-b42f-6d3f1996cdec · outbound

This paper cites Steering your diffusion policy with latent space reinforcement learning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Steering your diffusion policy with latent space reinforcement learning,

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.749064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.749064Z digest=sha256:9c152b262cd404f571a663b79916179c201514af13543d24e72ccf0174e9924f

Observation 0e1362db-aeea-44bd-9b26-8c1c4a8479de · outbound

This paper cites RL Token: Bootstrapping Online RL with Vision-Language-Action Models.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models RL Token: Bootstrapping Online RL with Vision-Language-Action Models

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.805915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.805915Z digest=sha256:a4b72390358dcd4b4d4ba473e633ef8f3d7fc1e3e9c74052ac38a3c45406bf0b

Observation 9171437d-0dea-4e0e-b5ba-fa55e7d57e0d · outbound

This paper cites OnetwoVLA: A unified vision-language-action model with adaptive reasoning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models OnetwoVLA: A unified vision-language-action model with adaptive reasoning,

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.869557Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.869557Z digest=sha256:cbbf32060a363af8fc55244070b6ec7c6c4e596311d5f88c33e0494b564889c6

Observation 6333fa52-f636-4d23-813d-3c410867247c · outbound

This paper cites Recurrent-depth vla: Implicit test-time compute scaling of vision-language-action models via latent iterative reasoning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Recurrent-depth vla: Implicit test-time compute scaling of vision-language-action models via latent iterative reasoning,

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.921754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.921754Z digest=sha256:ebb132e1bf30478cf418806c7b7e0c9b7335b650600402502632f800cef9aad8

Observation c788c747-a420-4035-84fc-9fe037a81601 · outbound

This paper cites VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:15.979649Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:15.979649Z digest=sha256:0940538ea250752de838502783919c1f53fb95879205b77a8505dedcaf2337f9

Observation 1bc2efdc-0710-4644-9269-31cc5f73f224 · outbound

This paper cites Scale: Self-uncertainty conditioned adaptive looking and execution for vision- language-action models,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Scale: Self-uncertainty conditioned adaptive looking and execution for vision- language-action models,

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.027697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.027697Z digest=sha256:11f828922b6096527ecfff23f838982aa6ccf8c0dcbf7937c068481322842e05

Observation e01631d8-3810-48af-827b-0de4b259d73a · outbound

This paper cites Diffusion models beat GANs on image synthesis,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Diffusion models beat GANs on image synthesis,

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.079243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.079243Z digest=sha256:b67033208f402dccdcdb504a302fb002a523e29a0afa05cdf0e2609d4bc12de1

Observation 83dcab72-84e2-4488-afda-73d946d6210a · outbound

This paper cites Tree-guided diffusion planner,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Tree-guided diffusion planner,

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.142731Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.142731Z digest=sha256:a91d5ea4d0f6ac17bafec908eacd1f55cc7263db91fa64bf820eb0c44b402978

Observation aa55a7d3-da41-4efa-8fc0-24e71f3ea53a · outbound

This paper cites Bridgedata v2: A dataset for robot learning at scale,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Bridgedata v2: A dataset for robot learning at scale,

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.215444Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.215444Z digest=sha256:ec98f38de3cd69ffaf2fb7afd5efae64edc1072c42dcacb045dee27c9e0ceec3

Observation 3fa36e8c-f983-40f1-95ef-4ccf1eefefaf · outbound

This paper cites Q-learning with adjoint matching,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Q-learning with adjoint matching,

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.280145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.280145Z digest=sha256:e5d41d4e0f53f30b5ea192ccff4d78c2ab0d8bab0e69a6a4e629706c0f86418b

Observation f20e95fa-ae97-4ff2-9098-c94021ffafe4 · outbound

This paper cites Droid: A large-scale in-the-wild robot manipulation dataset,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Droid: A large-scale in-the-wild robot manipulation dataset,

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.322982Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.322982Z digest=sha256:d950d75338c0002951826580a31a9b28b6fad3483043fc8fcf3df4fce5997920

Observation ece1d371-fefd-4e55-917b-4bb59d3f7dde · outbound

This paper cites Flow q-learning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Flow q-learning,

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.373443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.373443Z digest=sha256:6af3a1d6f71a43fcfa7a217e216457babe1db8b2483040bbaca9ad63fa69d610

Observation db41bc28-2948-473d-96b4-28dfbdace6cf · outbound

This paper cites Conservative q-learning for offline reinforcement learning,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Conservative q-learning for offline reinforcement learning,

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.413313Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.413313Z digest=sha256:0e847a14e8558fa3d0ae3a60104e7ddc1294d1059b8826bc1544d9c949e84296

Observation e11dd19a-af92-43ff-9f1f-d7154a4e67ac · outbound

This paper cites Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Can We Detect Failures Without Failure Data? Uncertainty-Aware Runtime Failure Detection for Imitation Learning Policies

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.470353Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.470353Z digest=sha256:fe9b517cd54ee6cbfc8cdc6b9da3ae2158928eff6198f2b548634cb19aaf4413

Observation 91018a86-7d02-4932-b3bb-b735a798e16a · outbound

This paper cites Embodied Red Teaming for Auditing Robotic Foundation Models.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Embodied Red Teaming for Auditing Robotic Foundation Models

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.532893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.532893Z digest=sha256:a503706c379ef66e103c22005e67a2801bf1b44dfb28077157c111200a3af7a2

Observation 7a205f8a-8c8e-49f5-8f28-71951d52cc3e · outbound

This paper cites OGBench: Bench- marking offline goal-conditioned RL,.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models OGBench: Bench- marking offline goal-conditioned RL,

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.592086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.592086Z digest=sha256:f1cf29777ecdeba36595a1c6a84cab12af84942473fa2041f26cf42844e63336

Observation d2dbeff4-8c9f-42e8-b956-28d37b90d3c0 · outbound

This paper cites Continued on next page 19 TABLE IX LANGUAGEINSTRUCTIONSREPHRASES(CONTINUED FROM PREVIOUS PAGE).

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Continued on next page 19 TABLE IX LANGUAGEINSTRUCTIONSREPHRASES(CONTINUED FROM PREVIOUS PAGE)

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:16.999044Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:16.999044Z digest=sha256:0f9e38b4f24218fb278c4e58466a2d5cb4ea6fee74ac3ba0b720fab32bff73c9

Observation 026edf7b-258d-40e9-8722-7120c0b36a6b · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.062377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.062377Z digest=sha256:357233bc76d0695866f3ed57d33c50fe1f16f0f346caf2046e1bc6d5222166a9

Observation f6b92b59-37dc-49da-a6b5-b232d7eb6bc0 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.563954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.563954Z digest=sha256:16cde39425fecd9987a699ef031fb0ceb634a7eab2e391afd95ef777d4b699da

Observation 45411861-9b51-4343-a6f9-cde6954eff54 · outbound

This paper cites Stack Cubes (SIMPLER) Stack the green block on the yellow block.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Stack Cubes (SIMPLER) Stack the green block on the yellow block

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.663291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.663291Z digest=sha256:500141f75ee1b285e5ba4c19aed1ff9c30ed2604baf908e386e4a10df1301410

Observation c021fd19-f3bb-4de4-a0eb-a1a77647b544 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.714772Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.714772Z digest=sha256:fb2d3edb7e396fc7ca23e6056ad0469d30946ded4232930ef6a3b8f77a39d048

Observation 5e812c8c-c2c4-4228-b429-2d679a8c61cc · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.790917Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.790917Z digest=sha256:d8744f203fa6b8e97d3b1399ef172257c2e754a637f5d240fa7d84fb14b95ff5

Observation d744e415-e37c-4d53-a231-083d660a245d · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.832452Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.832452Z digest=sha256:735972a53e3bbd30154acbada434ef991cda58ce638ed7c19a9afd19c52f7063

Observation 340745dd-6b87-4076-846a-86dbed13ca33 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:17.883906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:17.883906Z digest=sha256:2f5de53406f25b2deffb3a53a278669451cb139144727ea5ee3272d7d328f133

Observation 96791625-f56a-4aab-86b3-a53a3fb9c428 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.006692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.006692Z digest=sha256:91906b37c4e0e1a3572c5fd0dbcdad9a64ffde5048e6d7f20bf0e950b33f4f67

Observation e3d16601-ffe9-4f26-a867-ba93653ee71c · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.062391Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.062391Z digest=sha256:b6063e75e6b7c65f6be0ef4467b1dafafd8a8d9ffdbb149c50cfa953b0b6bb1a

Observation dbb14d00-bb74-4292-8da7-2ddca360b88f · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.114528Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.114528Z digest=sha256:6078c276b2b2c8550cf221020067b9ef87c5b06d8a8fe04931c8f95e0366d9b8

Observation 09eadde3-4cba-42b9-8c72-cd68485f434e · outbound

This paper cites Eggplant in Basket (SIMPLER) Put eggplant into yellow basket.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Eggplant in Basket (SIMPLER) Put eggplant into yellow basket

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.177799Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.177799Z digest=sha256:4f48bb8c2871b976ad3f26d9a559a98477578ec86346a65f37f770d12b254001

Observation de19a3b3-4078-461b-b257-ef3db3377a7f · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.215730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.215730Z digest=sha256:b8234ab7af578dad8820e0d0e1939dfcb3f65618337922b32e5c9f00f1a844b5

Observation 251c7197-76db-4895-bfe0-687fcfabc634 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.265103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.265103Z digest=sha256:1e8ee2d59702e1c1fe58978369688690c37dcf7df21aa0c1f884189be9e61b10

Observation ccbfe763-d46a-4b59-b8fa-8ed50fa9ee1b · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.320046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.320046Z digest=sha256:d77980002ae213e1b2afd866fd8edc60aa65c8de17a01f9c7930bec790d904a5

Observation ece91bfd-5463-428d-b280-941636eef344 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.379107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.379107Z digest=sha256:866ffece8e5e8cdb8f56de5158c18018fd48cac58cc5018f9245098fc61e1f96

Observation 93acb861-1793-4ce8-b8b5-3e8edf90d965 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.491832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.491832Z digest=sha256:23e2d6a3c702fd9077531a8f9312422e3eecb11d08c5df3f6076030ffcf7da02

Observation da656ec7-3130-46b8-af68-7d4987e894cc · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.557785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.557785Z digest=sha256:7c1a25d4f07434631a5b33b766d2341c829f1d40195041da85fbb1315b77f7ca

Observation 336407d0-f3ab-40a5-829c-d3a32284c279 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.620792Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.620792Z digest=sha256:35d5c97b1ececda266f504a7803b122520dbacc16e77a9784b2c0bb4c525c51c

Observation 12d63119-9cd6-45ae-9273-7b456e3d8ee8 · outbound

This paper cites Orange Juice on Plate (SIMPLER) Put orange juice on plate.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Orange Juice on Plate (SIMPLER) Put orange juice on plate

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.703396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.703396Z digest=sha256:7521fa47e06468094315063d52c65e95cedb3c5ff4d4058839a5e8122982fdec

Observation c119ea1b-4265-4b6f-a906-3c3ecbac3609 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.770604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.770604Z digest=sha256:32df5e4ffb32b1ad84c55320aba3bd6769786f8aa482e077a7e420b65afd8645

Observation 30e1990a-4a3f-412d-9540-f0ad7fc2b75b · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.846143Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.846143Z digest=sha256:59442bdc969ddd099d56f4e2ff4a22fff75a0feb3815d4e520b2a28f6b6a01a8

Observation 3b4b4133-1b74-4486-add6-8745382d1259 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:18.966008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:18.966008Z digest=sha256:a54880983d571163615e72674eabc5c4dc85298bcfdb3431dcc0ae5c31b858d3

Observation dcba702e-68cb-45d5-9240-cd6f422fcd53 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.112850Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.112850Z digest=sha256:223bd5aea392b993c2c4caf99214d027643a52d1206452bdc528e1ae674b143f

Observation 9cffd2b4-7922-421c-a1d2-d5c597ee76a2 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.237382Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.237382Z digest=sha256:0f73f5b0ae70479c2c0c0c7d1ea42bbd80bcef82d916000e4b77d49f8a13a8ea

Observation 5aaf8e5a-841b-442b-a691-9867f3f3e6b5 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.364076Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.364076Z digest=sha256:8c85ff0de565c941dbcb8b08e10fb6c6010e4b5c9335bd2f4cfab6c3cbb310c3

Observation b14d1703-9284-4db9-bee8-c494cac8088a · outbound

This paper cites Spoon on Towel (Google) (SIMPLER) Put the spoon on the towel google.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Spoon on Towel (Google) (SIMPLER) Put the spoon on the towel google

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.492236Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.492236Z digest=sha256:956e1f3323f2e64c2923cfe901ab1187af6a8c978d55dba3b60211dc44ae21d0

Observation 67103780-10d5-4295-b42b-d11ff9fea364 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.634507Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.634507Z digest=sha256:6ea8c4b5ae55b497ea1899879e557850086fdb579aa9ed9c8c29f06008c1c86f

Observation e5cd675b-401c-49c4-9be4-27cfed98acee · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.750758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.750758Z digest=sha256:5522ed2ffd39dcf116d17aa1cedae3ecc9614b8d395a57203da5f45d3671fa68

Observation fe83d52c-3d7f-4254-b59b-110d713abff7 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.866588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.866588Z digest=sha256:c4681603d6086a03ad37be25002b8f6914098d970e36ea97e07043e8d1f37ef1

Observation f15bb228-0af1-43d9-b64a-5a8ad9b20e04 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:19.981726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:19.981726Z digest=sha256:0d6c451c689aaac5b5a52bc6aefb23171ba50b368e8af1fb8535add7a79bd120

Observation 689f1b12-2129-48dd-b2f4-13043c28555d · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.096440Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.096440Z digest=sha256:3eca4cceaf24c8215c4d64cb143062ba934aebcdb93d43ea1fc10cbb3690f2cb

Observation 0ce87732-d2b6-4e4c-b9d4-2c4fdd4cabfd · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 88

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.208506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.208506Z digest=sha256:4eb9977e9f42833e046cb17669b61cec11002452f1ccdb0cc38a9d9a03d48fc0

Observation db9ccfa6-c986-4ad8-9d71-aaeda05f7b7c · outbound

This paper cites Toy Dinosaur on Towel (SIMPLER) Put the toy dinosaur on the towel.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Toy Dinosaur on Towel (SIMPLER) Put the toy dinosaur on the towel

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.317398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.317398Z digest=sha256:31a8a139435aab8696da2282260553dc125faa9e86202495b31ebb8edf8665c0

Observation 5c2a3019-eebc-4e34-9ab2-2248e377e9f2 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 90

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.423981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.423981Z digest=sha256:afe31942c9d8d8e017907f899b1c5f4c49c9509369eb74b8d5e7ed14dbfa7553

Observation afd4d84e-624d-4ae2-949d-5641c0589eb4 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 91

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.544621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.544621Z digest=sha256:0d9a8385fc19461ae95975ee1e5fc4cbfd07320ba0b44fb3be865e4d7200703a

Observation 556990df-6497-4b66-8464-02efe9743cbf · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 92

Resolution
parse uncertain
no resolver link, observed 2026-08-01T10:23:20.641990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.641990Z digest=sha256:c0d44505f75152890220b0303e52708f0172ef4502f406d4f317bbb4d7108d6c

Observation c27ff3ce-bda0-401f-b4ae-00c757c906fc · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 93

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.740790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.740790Z digest=sha256:f0f745066ca52d640d913b03296eb9ccaffa2ec760fcdcfadbb39f2d6a2f21f0

Observation 3b853103-2b3f-4851-8dd6-a2118daabed7 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 94

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.861030Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.861030Z digest=sha256:51514b8fa3927c80274bb16cfb9d2031da93c2f32afe64335c138efff55cfcde

Observation 2f8aa4f4-b613-4a73-9e41-52ca58737958 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 95

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:20.957873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:20.957873Z digest=sha256:f130f8e300e5e65f9e873895ff3a361eb267497d87a3f528c1ea614b9f0d0f41

Observation e918508e-e656-4fd3-8317-7f6b588feb5d · outbound

This paper cites Tape Measure in Basket (SIMPLER) Put tape measure into yellow basket.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Tape Measure in Basket (SIMPLER) Put tape measure into yellow basket

Reference 96

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.086090Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.086090Z digest=sha256:4afe2bd76128d9a768394c4f4c7cfe219b70b1c85f0be4d989687ad4c7db3212

Observation 5b740f6e-b5be-4340-bec9-b2e00cd79562 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 97

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.194399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.194399Z digest=sha256:6e816150dd0c225dfc18df2269940d5841976b735387983d47fad3cef40583fa

Observation d91999a3-4c2c-4441-a83d-2b9a2f98eac1 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 98

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.313613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.313613Z digest=sha256:2d6380078d0b38552dc5b043a2717f89bb86d16cdfc4dde6ac4e356f6ec22bc5

Observation 894f4e51-9769-498d-991d-f0ee9ece1658 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 99

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.415872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.415872Z digest=sha256:7082db99f6cf072a3ddadb3b782cfdb788faf004571e13d14f38efe78b9f7914

Observation 8f498697-bf6c-4e24-a324-537fea6c667e · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 100

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.532286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.532286Z digest=sha256:ae317bd5aa4fdfe7f727a1ebb6ca3544dde1f9805aebaf33b86b909c2f84dd02

Observation e60a3612-4ade-4d71-8513-ee29ff76ce5a · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 101

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.619286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.619286Z digest=sha256:d95dc50594f67806a4a36ded2d935052f675e83a7103f9b6f9ea6f4200fe1de1

Observation 134b3c02-dcf8-449b-8a99-204868406b84 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 102

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.709015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.709015Z digest=sha256:440c5e447f3661635ff4d43d176e3c8893f697c7106eda29b0b30635e8bed1e6

Observation d2008f78-3d6e-4ce5-803a-1630c93436bc · outbound

This paper cites Continued on next page 20 TABLE IX LANGUAGEINSTRUCTIONSREPHRASES(CONTINUED FROM PREVIOUS PAGE).

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Continued on next page 20 TABLE IX LANGUAGEINSTRUCTIONSREPHRASES(CONTINUED FROM PREVIOUS PAGE)

Reference 103

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.815758Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.815758Z digest=sha256:cc3c80f5845f55f503491b8a1bbf970fd6a3ce10e3b00942ce8e71718ecd9089

Observation c0924578-ab81-4222-9e3a-3769765beaff · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 104

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:21.924963Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:21.924963Z digest=sha256:da852d5230263feac51cb748e5fdeeafa2bfa61d660926a4ad3aac0c8af8a256

Observation 09340f14-c14f-4457-bdb8-a8de0257143f · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 105

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.008419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.008419Z digest=sha256:a262c5b4b973313bd90c7f56cff4d83dbad3953fdc9c9598a37c08081397226a

Observation f3c67ee5-eee2-4102-9c9b-aa4f34e1e5fd · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 106

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.085585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.085585Z digest=sha256:8e4998d1e38be37578ee9ae7bfcdb0f6a3784b69eb06e110f33e419e64d3bf79

Observation 07ca74ee-b0cb-4f52-b187-cf596fbf824a · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 107

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.177392Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.177392Z digest=sha256:31a3f2a214adedd515a50d3f82e52a33353915116a9c79105f12203b3c30f471

Observation 3b49baf8-ed4c-4aa8-9f62-c97c0c3eaadf · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 108

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.277613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.277613Z digest=sha256:5361c9cadd3e773cbd753c3ad834e5015bef4ebd4c0704c037ab2e516e23b0f2

Observation d9e1b330-b07e-4385-891e-5f0a08ca0485 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 109

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.343463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.343463Z digest=sha256:d442d43ef6a05365c8d52e55f132b94feea81fea4b3c390d2895133781b95879

Observation ec4741ae-3599-4fff-8f48-288bb6d39bdb · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 110

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.408398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.408398Z digest=sha256:225feb443a08d346bde1a9d34a673c4d62c55c1bea7bb7adaa02e574cd7837ba

Observation 337717c4-b7d0-4876-901e-cbefe32beefd · outbound

This paper cites Tape into Container (PolaRiS) Put the tape into the container.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Tape into Container (PolaRiS) Put the tape into the container

Reference 111

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.478879Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.478879Z digest=sha256:1ed61e17d7a99b7cef56fa7cb8f1d02ae7b20e8764f0f28f3814c91abea71b4e

Observation de0e8dc0-be9b-4958-9979-f741e8493580 · outbound

This paper cites an unresolved cited work.

RL$^2$-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models Unresolved cited work

Reference 112

Resolution
unresolved
no resolver link, observed 2026-08-01T10:23:22.546415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-01T10:23:22.546415Z digest=sha256:c4adb9893e732f0f0eda344b71eb6b3e787c124c530d0781155f9221eb0bb91e

Pith citing papers

No inbound Pith citation observations are available.