IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI | Paper Citation Record

Observation 9b581b68-ccdd-45de-b531-0391d1bd19c7 · inbound

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations cites this paper.

Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 93

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T18:38:11.313568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 91ebf4bc-00de-4437-80f8-de0c067b9d74 · inbound

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions cites this paper.

UniVLA: Learning to Act Anywhere with Task-centric Latent Actions IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-12T15:28:06.967896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 87d28d03-a0ad-4bca-a374-5a7b333b7764 · inbound

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning cites this paper.

CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T14:56:33.139916Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6d8aa1ed-3ea4-4adc-9999-2e46881603c9 · inbound

WorldEval: World Model as Real-World Robot Policies Evaluator cites this paper.

WorldEval: World Model as Real-World Robot Policies Evaluator IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T14:25:41.835024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 794491b1-9a61-44bd-8399-e6d5650962a6 · inbound

Playing with Transformer at 30+ FPS via Next-Frame Diffusion cites this paper.

Playing with Transformer at 30+ FPS via Next-Frame Diffusion IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T11:49:42.207829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cbd0345-3ac5-4cbe-85e4-6bda7755a4c8 · inbound

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation cites this paper.

GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-25T07:50:29.231047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3827fc8f-d211-4da5-b32d-9e48b3d2b97c · inbound

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers cites this paper.

VQ-VLA: Improving Vision-Language-Action Models via Scaling Vector-Quantized Action Tokenizers IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:07:22.759775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 368c1dee-66e7-4e08-a7c8-d6b3dfddfcbb · inbound

Is Diversity All You Need for Scalable Robotic Manipulation? cites this paper.

Is Diversity All You Need for Scalable Robotic Manipulation? IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T19:17:10.758757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd2ef776-c9c6-459e-ad1a-8a7c1a38296a · inbound

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models cites this paper.

villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 9

Resolution: metadata mismatch; arxiv_id, observed 2026-05-15T21:52:02.980898Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 6efd5a22-aa1e-4ed5-92a7-f8b23806f8cd · inbound

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation cites this paper.

PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video Generation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T13:24:44.036005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30b947d9-96c0-4a33-b2c0-49c890709df5 · inbound

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos cites this paper.

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-16T17:02:34.146487Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ad1e5935-e2cc-422b-9efb-6a396a4b0f5c · inbound

UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models cites this paper.

UniLACT: Depth-Aware RGB Latent Action Learning for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-15T20:20:17.665714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 64c0227a-a4b0-48ff-b393-3a78a56503d8 · inbound

Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training cites this paper.

Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-05-11T14:36:07.668999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ba7bbf18-1bc3-4ac1-84f5-bfff8fdfe94b · inbound

GazeVLA: Learning Human Intention for Robotic Manipulation cites this paper.

GazeVLA: Learning Human Intention for Robotic Manipulation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T19:36:12.527612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 46bce8bf-d9c5-4aaa-aebb-c581e90d3716 · inbound

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation cites this paper.

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-11T22:26:11.673687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8de5b719-e340-4891-9f79-461ecb42440f · inbound

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation cites this paper.

Learning Human-Intention Priors from Large-Scale Human Demonstrations for Robotic Manipulation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 32

Resolution: verified exact; arxiv_id, observed 2026-05-22T11:21:29.238755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 965afae3-47c1-41c4-a357-a712ee39d9ae · inbound

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models cites this paper.

From Pixels to Tokens: A Systematic Study of Latent Action Supervision for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T17:16:09.928505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 7331027b-87d9-40cd-9f0f-fd2ab52caec9 · inbound

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts cites this paper.

VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T20:26:10.252214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5594f8e5-fee1-41e7-86b4-ce891a6aa4e8 · inbound

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models cites this paper.

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-12T06:26:27.062999Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation bf2bea7b-7d9b-48df-aab2-66738c7dc589 · inbound

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models cites this paper.

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-14T21:17:59.505091Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3efa652d-3532-4adf-8404-f23d6b9d4d17 · inbound

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

RotVLA: Rotational Latent Action for Vision-Language-Action Model IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-14T17:49:23.120637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ec9a79a5-9e97-473b-bd2c-63a9685361e0 · inbound

DiLA: Disentangled Latent Action World Models cites this paper.

DiLA: Disentangled Latent Action World Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 5

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T19:38:56.388138Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3163ce5d-1ad9-47d0-966b-5d5c7d73387d · inbound

Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model cites this paper.

Structure Abstraction and Generalization in a Hippocampal-Entorhinal Inspired World Model IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 3

Resolution: malformed identifier; arxiv_id, observed 2026-05-19T19:37:43.756786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation e9adc3f5-8256-4c5d-b50d-54b231aa71d3 · inbound

UAM: A Dual-Stream Perspective on Forgetting in VLA Training cites this paper.

UAM: A Dual-Stream Perspective on Forgetting in VLA Training IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:28:55.099978Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 32c9b733-a34b-4e5d-bc26-1b09967633af · inbound

Why Latent Actions Fail, and How to Prevent It cites this paper.

Why Latent Actions Fail, and How to Prevent It IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-21T08:34:05.330376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 172dd323-3d20-42be-9cab-eb70a0bdf684 · inbound

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data cites this paper.

From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-06-30T18:55:00.167016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8344fbfe-375e-40f9-94ba-00c48daaa38b · inbound

CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization cites this paper.

CLAW: Learning Continuous Latent Action World Models via Adversarial Latent Regularization IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-02T03:36:29.583480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 5c0ca728-7f52-46cb-9560-31f73155c281 · inbound

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

LARA: Latent Action Representation Alignment for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T16:47:09.499733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 77d76d54-83c7-4ceb-9f3a-5e1da62f7a68 · inbound

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

LARA: Latent Action Representation Alignment for Vision-Language-Action Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T08:35:34.492973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 92fadd4d-7535-4bbc-a91d-d257a94dbd83 · inbound

Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos cites this paper.

Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-03T23:39:04.235028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f2cded77-958a-4ab6-a065-0eeb889d2748 · inbound

Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos cites this paper.

Motion-Focused Latent Action Enables Cross-Embodiment VLA Training from Human EgoVideos IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-03T23:49:01.900671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c276495b-7d4f-4f51-a882-7d22f3eeb120 · inbound

Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models cites this paper.

Imitation from Heterogeneous Demonstrations using Grounded Latent-Action World Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-07-04T06:49:38.568483Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation ef32b57f-519a-4253-b24c-a2b511622482 · inbound

Learning Action Priors for Cross-embodiment Robot Manipulation cites this paper.

Learning Action Priors for Cross-embodiment Robot Manipulation IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 61

Resolution: verified exact; arxiv_id, observed 2026-07-04T21:00:09.785386Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation db4fb4c8-8d36-4d37-864c-cb06c02743e2 · inbound

Causally Debiased Latent Action Model for Embodied Action Conditioned World Models cites this paper.

Causally Debiased Latent Action Model for Embodied Action Conditioned World Models IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-13T04:50:59.096166Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d99e890-b6a8-4652-bca8-e6f8c2abf07d · inbound

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control cites this paper.

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T11:27:05.835624Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1756cd0f-e81c-4df8-a802-d10edc9e8d97 · inbound

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control cites this paper.

Enfold: Folding World Model Imagination into Predictive Representations for Ultra-Efficient Embodied Control IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T03:23:48.964275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58573bcf-2373-411b-884b-74b3d872dc1c · inbound

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow cites this paper.

ShadowDancer: Teaching Video World Models Any Action by Learning Unified Dynamics Representations from a Video and Its Shadow IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T09:42:43.644737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 720ef27e-345d-4bce-b680-ae4155102304 · inbound

Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer cites this paper.

Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 216

Resolution: unresolved; no resolver link, observed 2026-07-31T08:51:28.134244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc6f7df7-6c3e-44a2-8987-523be07b7926 · inbound

Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer cites this paper.

Hand-Object Interaction in the Age of Large Foundation Models:Reconstruction, Generation, and Embodied Transfer IGOR: Image-GOal Representations are the Atomic Control Units for Foundation Models in Embodied AI

Reference 197

Resolution: unresolved; no resolver link, observed 2026-08-04T01:23:09.888871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers