Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models | Paper Citation Record

Observation 168c138b-5b28-48a2-9e18-51b61348cba2 · outbound

This paper cites RT-1: Robotics transformer for real-world control at scale,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models RT-1: Robotics transformer for real-world control at scale,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.433041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d41ccb1-28fa-4344-8721-eb0f3c1270f8 · outbound

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

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models OpenVLA: An open-source vision-language-action model,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.498298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4340d76-8cb1-40bd-9926-c82e604cc9ac · outbound

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

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.563364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15d08ad3-b1d1-4906-bbc5-4ace3c238c75 · outbound

This paper cites RT-2: Vision-language-action models transfer web knowledge to robotic control,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models RT-2: Vision-language-action models transfer web knowledge to robotic control,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.631505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b41b2c2-a51e-4c51-959b-28a852d27df9 · outbound

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

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models π 0.5: A vision-language-action model with open-world generalization,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.689972Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05b9df07-540b-435f-9d44-3ad02a2d2a90 · outbound

This paper cites FAST: Efficient Action Tokenization for Vision-Language-Action Models.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models FAST: Efficient Action Tokenization for Vision-Language-Action Models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.776432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77c6d70d-6cb4-45f1-ba0e-04c1d9600072 · outbound

This paper cites VQ-VLA: Improving vision-language-action models via scaling vector-quantized action tokenizers,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models VQ-VLA: Improving vision-language-action models via scaling vector-quantized action tokenizers,

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.861393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1533588-0a9b-4320-a324-d7079b8c57bb · outbound

This paper cites Latent action pretraining from videos,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Latent action pretraining from videos,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:29.942388Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 476587b7-83dd-4d1d-9db3-723908f040ae · outbound

This paper cites Learning to act anywhere with task-centric latent actions,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Learning to act anywhere with task-centric latent actions,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.060679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3014be4-9765-487d-8d81-2ee225112ea3 · outbound

This paper cites RotVLA: Rotational Latent Action for Vision-Language-Action Model.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models RotVLA: Rotational Latent Action for Vision-Language-Action Model

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.181563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef5d9e8a-f341-4bfa-91ca-2e9dbd3a5b62 · outbound

This paper cites Learning transferable visual models from natural language supervision,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Learning transferable visual models from natural language supervision,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.319349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a7b6a1c-7f0c-4f82-805e-08098bf12975 · outbound

This paper cites Align before fuse: Vision and language representation learning with momentum distillation,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Align before fuse: Vision and language representation learning with momentum distillation,

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.461696Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e83d065-144b-446d-aecb-f7e79013b687 · outbound

This paper cites BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.599740Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9de61cc-a106-44b7-9630-e6e93b987c5e · outbound

This paper cites Visual instruction tuning,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Visual instruction tuning,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.685381Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed05aa5d-8654-43c9-8fe2-d5c4f95ef435 · outbound

This paper cites Perceiver: General perception with iterative attention,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Perceiver: General perception with iterative attention,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.777303Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7716786-d9b1-4637-94f3-fc2a37d4d9fe · outbound

This paper cites Flamingo: A visual language model for few-shot learning,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Flamingo: A visual language model for few-shot learning,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.870154Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 923415a7-9bd2-49a4-88fe-a6d3bd47c635 · outbound

This paper cites BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:30.960688Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c49c74d-9986-4f96-b0a7-db0f3047c11a · outbound

This paper cites InstructBLIP: Towards general-purpose vision-language models with instruction tuning,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models InstructBLIP: Towards general-purpose vision-language models with instruction tuning,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.053667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9637b991-567d-4564-8175-23d732540a7d · outbound

This paper cites VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.166730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ead814d6-4973-4ae1-9688-f1eda41eb078 · outbound

This paper cites DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.269443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 074e1e22-2d11-4cd4-b40b-49822b0b9199 · outbound

This paper cites HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action Model

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.334140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0bcd7638-d956-4d7a-9b0c-18e40d3d4ef2 · outbound

This paper cites LARA: Latent Action Representation Alignment for Vision-Language-Action Models.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models LARA: Latent Action Representation Alignment for Vision-Language-Action Models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.411913Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56aa65d7-e7da-4bf5-a083-24c74d54eef3 · outbound

This paper cites Making Foresight Actionable: Repurposing Representation Alignment in World Action Models.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Making Foresight Actionable: Repurposing Representation Alignment in World Action Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.476784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a87a132-008f-48dd-9d21-a3f5767226a7 · outbound

This paper cites A formal basis for the heuristic determination of minimum cost paths,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models A formal basis for the heuristic determination of minimum cost paths,

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.541114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cec96d1-84a1-4269-8b49-73017f76d0ec · outbound

This paper cites The dynamic window approach to collision avoidance,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models The dynamic window approach to collision avoidance,

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.602905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7acdcb17-7df6-4517-bd60-2c2202c9e3e3 · outbound

This paper cites ViKiNG: Vision-based kilometer-scale navigation with geographic hints,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models ViKiNG: Vision-based kilometer-scale navigation with geographic hints,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.688754Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 45b6e0e3-aa74-46fc-a565-6864dce056a6 · outbound

This paper cites GNM: A general navigation model to drive any robot,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models GNM: A general navigation model to drive any robot,

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.745987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 60b2c79c-6854-4342-9f7e-59017e491a0f · outbound

This paper cites ViNT: A foundation model for visual navigation,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models ViNT: A foundation model for visual navigation,

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.799338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a20c86d-0c4d-4318-afe6-1498b8d62cc5 · outbound

This paper cites NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.849984Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0e19cde-c6eb-4aca-8ce8-022e72b98cc1 · outbound

This paper cites LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models LM-Nav: Robotic navigation with large pre-trained models of language, vision, and action,

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.928705Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3517109-29f0-42f2-8a4e-e7f4e012a460 · outbound

This paper cites NaVid: Video-based vlm plans the next step for vision- and-language navigation,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models NaVid: Video-based vlm plans the next step for vision- and-language navigation,

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:31.989633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 641a3b0e-511b-44fb-a13e-ee9f7b980fa6 · outbound

This paper cites Uni-NaVid: A video-based vision-language-action model for unifying embodied navigation tasks,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Uni-NaVid: A video-based vision-language-action model for unifying embodied navigation tasks,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.050463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8c0ee6e-9933-4b35-9cf4-7dee1f335325 · outbound

This paper cites Embodied navigation foundation model,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Embodied navigation foundation model,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.102790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d593800d-480f-4f4d-b9fd-8912113eed2b · outbound

This paper cites Navigation world models,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Navigation world models,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.173003Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42860d4a-8a13-45c9-adb6-3eccb20c7d28 · outbound

This paper cites Habitat: A platform for embodied ai research,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Habitat: A platform for embodied ai research,

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.225527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ed974af-8670-469b-bac0-d40b8af23c2b · outbound

This paper cites ObjectNav revisited: On evaluation of embodied agents navigating to objects,.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models ObjectNav revisited: On evaluation of embodied agents navigating to objects,

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.327882Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d62678d-e558-41a8-b12a-c0ee58e35ac4 · outbound

This paper cites an unresolved cited work.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Unresolved cited work

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.403060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10b45c3a-54d0-4c01-9a52-5529cd98d10e · outbound

This paper cites In the main training setup, this parsing uses thespecial-token branchexclusively.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models In the main training setup, this parsing uses thespecial-token branchexclusively

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.482082Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 308a49be-7698-4501-bf4d-2d46507a8aa4 · outbound

This paper cites an unresolved cited work.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Unresolved cited work

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.565185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd1d99b8-d009-4994-9894-fb5cacfddc32 · outbound

This paper cites make a left turn.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models make a left turn

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.642066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 49c84480-0031-416f-b8f9-295d3eb852dc · outbound

This paper cites Thedirect-fusion baselineuses the minimal shared-context interface described in Sec.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Thedirect-fusion baselineuses the minimal shared-context interface described in Sec

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.746572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c118e976-ecdd-4dfc-83a7-1c27e862da10 · outbound

This paper cites These set- tings differ in which parts of the inherited multimodal pathway are exposed to action-loss gradients.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models These set- tings differ in which parts of the inherited multimodal pathway are exposed to action-loss gradients

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.820960Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7554865d-e876-417b-9474-1fda0ca23fbb · outbound

This paper cites an unresolved cited work.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Unresolved cited work

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.876278Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 520758be-a9a1-48c8-bd17-3eb81162391c · outbound

This paper cites Token-wise rewriting and rewriting-subspace analyses examine how strongly the inherited pathway is rewritten and whether that rewriting is broad or targeted.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Token-wise rewriting and rewriting-subspace analyses examine how strongly the inherited pathway is rewritten and whether that rewriting is broad or targeted

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:32.984898Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1fc04309-d7d6-4a5f-ab9e-e3044dfd14de · outbound

This paper cites These statistics are supporting measurements: they are not intended to replace the token-level visualizations in Sec.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models These statistics are supporting measurements: they are not intended to replace the token-level visualizations in Sec

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.064517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f877ce6-2ddb-4ece-971e-ff9a85ac6098 · outbound

This paper cites We partition tokens into boundary, control, spatial, and other groups, and report each group’s share of the total rewriting budget in Table VIII.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models We partition tokens into boundary, control, spatial, and other groups, and report each group’s share of the total rewriting budget in Table VIII

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.108432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a284d3e-0b81-4b44-bc9d-dee06831325f · outbound

This paper cites We next ask whether this selectivity is also reflected in how rewritten dimensions are organized.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models We next ask whether this selectivity is also reflected in how rewritten dimensions are organized

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.159920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3a8b086-09c5-4be3-ad73-9e8c228cfc88 · outbound

This paper cites an unresolved cited work.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Unresolved cited work

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.236218Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 71385eb9-5416-4727-a888-a2b4a0614e02 · outbound

This paper cites These statistics provide additional views of how closely an action-loss-exposed atten- tion map remains aligned with its action-update-blocked refer- ence.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models These statistics provide additional views of how closely an action-loss-exposed atten- tion map remains aligned with its action-update-blocked refer- ence

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.281574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6701a273-65d1-432f-8b5c-3b6f98e49d3a · outbound

This paper cites 18 provides complementary distributional views of attention stability across the full set of phrase-level comparisons.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models 18 provides complementary distributional views of attention stability across the full set of phrase-level comparisons

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.348531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6967e63-079c-47b5-b8e4-eb3ea5aecc2d · outbound

This paper cites an unresolved cited work.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models Unresolved cited work

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.434174Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4f04fbf-6567-4331-8616-3e12c1f68dd2 · outbound

This paper cites 20 shows that the all-head average can hide substantial head-level heterogeneity.

Action QFormer: Structured Representation Shaping under Action Supervision in Vision-Language-Action Models 20 shows that the all-head average can hide substantial head-level heterogeneity

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T01:34:33.493545Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers