Pith. sign in

Paper Citation Record · LEDGER

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks

As of 4 August 2026, this Paper Citation Record lists 88 of 88 outbound references and 0 inbound Pith citation observations for arXiv:2605.19957.

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

pith.paper-citation-record.v1
2605.19957 v1

Coverage vector

measured 88 of 88 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T06:36:47.265734Z

measured 88 of 88 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-04T06:34:03.388597+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

88 of 88 outbound references displayed

  • verified exact30
  • verified fuzzy54
  • unresolved2
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d23c753b-cdce-448d-a8e4-94eeba67f2e8 · outbound

This paper cites Recurrent world models facilitate policy evolution.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Recurrent world models facilitate policy evolution

Reference 1

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.124193Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:87f43cd04efc8ceddefa25bb918b6e940f0723764b900abc199650fb0a67b47b

Observation 2d40781f-3811-4a5d-8bb2-85ab4639f22b · outbound

This paper cites Mastering diverse control tasks through world models.Nature.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Mastering diverse control tasks through world models.Nature

Reference 2

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.069651Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:595ca8dc1966cce6b717599e8f3ac95d26f528fefd1eb0a66a86968b393245d4

Observation a19a8bc7-52fd-4e8d-979d-580fe3f41671 · outbound

This paper cites Causal World Modeling for Robot Control.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Causal World Modeling for Robot Control

Reference 3

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.663060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:f71a020abcc9a80efd086994c394f0387b6ec6f3928ae7f159c894a94fda22a6

Observation e50022bd-9fd3-4a0e-8d35-ab29e06f4077 · outbound

This paper cites Dreamgen: Unlocking generalization in robot learning through video world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Dreamgen: Unlocking generalization in robot learning through video world models

Reference 4

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.105628Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:dad75115e23b92936ed4477ec6199841f598d9650999e808fc1a6b9418cc2154

Observation 4fec8993-9ba9-4ba9-beb1-3056287a71b6 · outbound

This paper cites Learning interactive real-world simulators.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Learning interactive real-world simulators

Reference 5

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.085133Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:c77cf56eb8166bca905c4361e32d55c10a8f7fb3e2bbb96054cfa74b1550666d

Observation 88af185b-db97-43d5-bcf2-b02558e2d1d0 · outbound

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

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Daydreamer: World models for physical robot learning

Reference 6

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.081111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:16dd54779c39ae5ea7a5f3650fd0ef14b2c87e0152c25bc16b88a1eadf7763ac

Observation e68e723c-611d-4897-ada7-25313369798a · outbound

This paper cites FLARE: Robot learning with implicit world modeling.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks FLARE: Robot learning with implicit world modeling

Reference 7

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.083148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:fa5b97e13ad4660976a77070e7540ca6a2ac75047c339ca70edc1d392cb3d49a

Observation c3edb3b3-3906-4360-9aa7-05aee0fa6873 · outbound

This paper cites Cosmos policy: Fine-tuning video models for visuomotor control and planning.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Cosmos policy: Fine-tuning video models for visuomotor control and planning

Reference 8

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.093210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:a9bb76fe7228ccd294540279c302a248f179e8ada88079ece92a0387cc44abc5

Observation 029dbabd-7274-4677-9563-6a95f0db90b0 · outbound

This paper cites World Action Models are Zero-shot Policies.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks World Action Models are Zero-shot Policies

Reference 9

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.656748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:329a8662ae1005583a4021c236f3a65b235bebf0bf7174106b485a1832bc2556

Observation bd0dd0f5-a2ec-4d24-adfa-6ed73e6c79fa · outbound

This paper cites Any-point trajectory modeling for policy learning.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Any-point trajectory modeling for policy learning

Reference 10

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.015519Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:a8987b50ac9fedb52c3ce4378b3812dc7a2d9fbe3ef402fea482d8deb083bfe1

Observation 90fbc7a4-0442-44db-97ee-ea967c87c4e8 · outbound

This paper cites Cosmos World Foundation Model Platform for Physical AI.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Cosmos World Foundation Model Platform for Physical AI

Reference 11

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.620538Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:2308f02722f4100eab816fb437293f19a320f0def615f05934f1057b6e346dc8

Observation 2d959405-5891-4b63-899e-9b1337ae3a52 · outbound

This paper cites World Simulation with Video Foundation Models for Physical AI.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks World Simulation with Video Foundation Models for Physical AI

Reference 12

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.636274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:f73c22199b60ba1bf74fa3aba36bd8d4d42a729089832343f25797c9466b8a4f

Observation 21c5e0a8-0bcc-4da0-b7d2-7e502ad2b871 · outbound

This paper cites Owl-1: Omni World Model for Consistent Long Video Generation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Owl-1: Omni World Model for Consistent Long Video Generation

Reference 13

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.639325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:aece12b1b75eb6f1bd4f47ad75920dde977dfed7855ffda556f567ad104e52ad

Observation 20ecf15f-869d-4e95-a0e5-4cbfbbdf1532 · outbound

This paper cites WORLDMEM: Long-term consistent world simulation with memory.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks WORLDMEM: Long-term consistent world simulation with memory

Reference 14

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.089300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:5685f27673a25d48b8c9022a9651346f79d0ed5b9e2d8b3fce4551f3b45c2625

Observation a385e63b-5e4a-4a73-ac23-a22cd4f65d40 · outbound

This paper cites StableWorld: Towards stable and consistent long interactive video generation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks StableWorld: Towards stable and consistent long interactive video generation

Reference 15

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.643124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:53a1e9ce6eb278910be92b36f148ccf50f08dcf6960e69eadb374dbfacef2908

Observation 6d6451ef-6616-4439-a051-bed2ba05603a · outbound

This paper cites Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Reference 16

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.617521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:153b76c1e57901f513a901c4b52a238a79921906c9b079d569c358414bd82968

Observation fc68e76a-2e74-4fd7-bc25-524d03b57261 · outbound

This paper cites Genie: Generative interactive environments.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Genie: Generative interactive environments

Reference 17

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.077280Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:bc1abf2522c99f485324785052f4fdecbc5f755c515920334d540522ceb35ddf

Observation b780648a-8ab4-4cc5-9f84-3f796ba9b936 · outbound

This paper cites Robodreamer: Learning composi- tional world models for robot imagination.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Robodreamer: Learning composi- tional world models for robot imagination

Reference 18

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.079252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:5633c18f7abbaa8a23d3e4ee3e32a2cb007e542dca0aee86cb0ffee34e197a6c

Observation dbb33114-2c13-4fb6-a20f-41cc8b4f0cb2 · outbound

This paper cites Pan: Aworldmodelforgeneral,interactable,andlong-horizonworldsimulation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Pan: Aworldmodelforgeneral,interactable,andlong-horizonworldsimulation

Reference 19

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.611622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:01ba473be4c412a3d23559bbe93549b6cb0c3c11eea941abecce95171f9548e0

Observation 87c69eab-da7f-4b2d-b24a-70f905cb4727 · outbound

This paper cites Tesseract: Learning 4d embodied world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Tesseract: Learning 4d embodied world models

Reference 20

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.052481Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:ac6e4b38c7e13fde635f170db6362b03ccf59b38df351b7a9a53bc354964fa46

Observation dcad6c66-b089-485c-9bd5-78b4cf20a784 · outbound

This paper cites Learning world models for interactive video generation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Learning world models for interactive video generation

Reference 21

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.063497Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:9ceea087586f4f75aab67ae32c82c26560ab714d280975a433ffa08b15579aea

Observation e2f9a099-f213-48aa-86b8-d810da47aa21 · outbound

This paper cites VideoREPA: Learning physics for video generation through relational alignment with foundation models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks VideoREPA: Learning physics for video generation through relational alignment with foundation models

Reference 22

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.067821Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:06aa04a7cf5a7a2fede647c82ef95025b74c639591e8e2a60fee72da5b345621

Observation b96bff0c-b4b9-40e3-94f8-c913459d7555 · outbound

This paper cites A path towards autonomous machine intelligence.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks A path towards autonomous machine intelligence

Reference 23

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.048206Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:0b2d9f1ea6b8b99a1961dd3287005c175f32c6fc3ca6a032a0501226794b61c2

Observation 250b4241-be2e-418a-9eea-5ff991bce0dc · outbound

This paper cites V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Reference 24

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.598866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:d07b759487a0e276d67e0b785d4bc83e29084f385ccd473178bb54e938838599

Observation 41ac6e0c-c15b-4e39-8241-8dfb5e62e3c6 · outbound

This paper cites Gem: A generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Gem: A generalizable ego-vision multimodal world model for fine-grained ego-motion, object dynamics, and scene composition control

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.071676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:76eac7ea4527b9e9c05411d3dd36372c3e473674971d99a575210822b0a453ae

Observation 9d8b8d26-fe06-4e07-843b-01bb8721f668 · outbound

This paper cites Longscape: Advancing long-horizon embodied world models with context-aware moe.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Longscape: Advancing long-horizon embodied world models with context-aware moe

Reference 26

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.650405Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:3dd52a26db97478b663b8f6666a23bbd9e64cbc78b2e7911fadae1d776795ded

Observation 264d2cc0-417e-42b6-a2e1-3f6e9cefbc8d · outbound

This paper cites Dexterous world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Dexterous world models

Reference 27

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.046110Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:bdaec6b9208dc9c216b86771a0c108ea6aa0943c1d36b81e2a726fbb02a3229e

Observation 9495982d-a414-438f-9932-cd16b56f8c47 · outbound

This paper cites Towards long-horizon vision- language navigation: Platform, benchmark and method.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Towards long-horizon vision- language navigation: Platform, benchmark and method

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.037306Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:7939d51d881d82844516c4289e30c4d6ca0e2a9f597ed694e714582ccef68a66

Observation 0dcd6740-9f27-4cb7-8f23-991e792d77a1 · outbound

This paper cites Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Mobility VLA: Multimodal instruction navigation with long-context VLMs and topological graphs

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.065740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:6061a82047dd2d5390800ce6906177dbd8e049a3825fb765aa060d3e65550f2e

Observation e0014e4d-784b-4eae-a2e7-9b392ba35f2c · outbound

This paper cites MoManipVLA: Transferring vision-language- action models for general mobile manipulation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks MoManipVLA: Transferring vision-language- action models for general mobile manipulation

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.061305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:d5b14f9c5f8f2541f8c8d5a5e8b182457e811d6bf82b803e57fa160c531102fb

Observation f249b379-e18e-4948-9898-9b2525340e98 · outbound

This paper cites MAGI-1: Autoregressive Video Generation at Scale.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks MAGI-1: Autoregressive Video Generation at Scale

Reference 31

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.633588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:ecafb6c7a03dd7acf0f2212a756e07f456b6664105400f864bac928e34402a6c

Observation 5e928f8b-cbb3-4057-b48d-75fd9d2b7fc7 · outbound

This paper cites Diffusion forcing: Next-token prediction meets full-sequence diffusion.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Diffusion forcing: Next-token prediction meets full-sequence diffusion

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.054475Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:24995c36fc3073c032bf57932b86b7f75695d2dfd09dbce0734d968d02acf002

Observation 07986733-7800-4209-a755-4c26760777ad · outbound

This paper cites Rolling forcing: Autoregressive long video diffusion in real time.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Rolling forcing: Autoregressive long video diffusion in real time

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.022848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:9545c5ec3f56d78b01a964d3c7ffd4c17d61e6b3334ae9868e1c25a6c55a1019

Observation cc428f4a-770c-4798-bf5a-8680af789ed3 · outbound

This paper cites Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion

Reference 34

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.579396Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:ef31b0c02eb1c37fb823a16c84659341b46a56bac72fada67405568aa1c8edfc

Observation f43758bd-fc96-410e-9b16-15baf678398d · outbound

This paper cites Infinity-RoPE: Action-controllable infinite video generation emerges from autoregressive self- rollout.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Infinity-RoPE: Action-controllable infinite video generation emerges from autoregressive self- rollout

Reference 35

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.592162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:adcdc5c9f151f151c8f9f82f78ac2f1026997cbde73b7190bba9c64c985934bd

Observation b69cf3f4-55e6-47b7-8d59-e6fd8ec84820 · outbound

This paper cites VBench++: Comprehensive and versatile benchmark suite for video generative models.IEEE TPAMI.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks VBench++: Comprehensive and versatile benchmark suite for video generative models.IEEE TPAMI

Reference 36

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.032708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:1811056f0210b351eb3bf29ab134b74352b9dc96c4815caa1d1c0796428425db

Observation 7a125abd-43c8-43f2-81e9-7c6fe25480c9 · outbound

This paper cites Worldmodelbench: Judging video generation models as world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Worldmodelbench: Judging video generation models as world models

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.034921Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:1db3a866b3cbb307253b91ee271d9e71835c639b0cdcece54c3501b904f099fd

Observation 7a9948fa-6688-4c38-b4ea-80ef9ebc17ab · outbound

This paper cites Rethinking video generation model for the embodied world.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Rethinking video generation model for the embodied world

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.024797Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:05c197055bff7ec9128f4025e31996b4c7425d1975552cdbf9a8f05b6362b8b5

Observation 650f7cdb-a335-475f-92b3-f4c4f1c74031 · outbound

This paper cites Worldarena: A unified benchmark for evaluating perception and functional utility of embodied world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Worldarena: A unified benchmark for evaluating perception and functional utility of embodied world models

Reference 39

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.624156Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:aaf2dd110fc67e299cc512d571120903408f70480a7619390704dc8d0b00e5d0

Observation b6f35a44-9285-40ce-925c-c4d76b4ccd43 · outbound

This paper cites BEHA VIOR-1K: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks BEHA VIOR-1K: A benchmark for embodied ai with 1,000 everyday activities and realistic simulation

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.128594Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:5b0e8b2c2e02e0a69d0117d45497382ab323c0d94b729c93fad6ac5b796957ee

Observation 9e52fcb1-3816-454c-be5d-e62fe9c1c83b · outbound

This paper cites Dream to control: Learning behaviors by latent imagination.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Dream to control: Learning behaviors by latent imagination

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.017505Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:888ab4130a3492149250c493f2a179241351cdeffd493ffe5924936964f23c9a

Observation 77d65a72-9a60-4ca4-a25d-b5ed72313029 · outbound

This paper cites Denoising diffusion probabilistic models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Denoising diffusion probabilistic models

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.027066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:7ea451d681eb883dd8752fa56ff3d5f8074c3e9aa4baa121bdb1e516f6702d05

Observation 2e435714-e872-4ea0-8cc0-c2ee22d11a82 · outbound

This paper cites High-resolution image synthesis with latent diffusion models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks High-resolution image synthesis with latent diffusion models

Reference 43

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.043741Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:b6e6e50f526cd0454d2a8bb0dcc6bd58aade91a2abfe5c27dab5313e9657be4a

Observation 7b01c368-bd60-4353-a179-74cb4c728ce6 · outbound

This paper cites Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models

Reference 44

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.605058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:bf0889b05c3a943315b65c9c951ca94d2ec067726e03a750b79429a4a1ddffba

Observation a0eee9b6-9c45-4144-af6b-d3c08d9894b7 · outbound

This paper cites Wan: Open and Advanced Large-Scale Video Generative Models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Wan: Open and Advanced Large-Scale Video Generative Models

Reference 45

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.595178Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:232fa3215bb5b15ea70f2f508fe7350f8f577324df52551f465b270fb071528f

Observation 05cdecc4-9d59-4db6-8dff-b00a0755b3c3 · outbound

This paper cites CogVideoX: Text-to-video diffusion models with an expert transformer.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks CogVideoX: Text-to-video diffusion models with an expert transformer

Reference 46

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.039479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:d1d544773c6e0a579bcc27eb5a7bd3c63423a342a7fb093632d9158e11491a8e

Observation 9333ada2-8197-409a-94bb-f38d5f18315a · outbound

This paper cites Genie 2: A large-scale foundation world model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Genie 2: A large-scale foundation world model

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.041459Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:952d2a70447f5d753e3106019b4604b2bdd17a3cce9e82a3f5ef7118c56125fc

Observation 8590ecf6-e335-4f7a-a36f-2692929b8c26 · outbound

This paper cites Open-Sora: Democratizing Efficient Video Production for All.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Open-Sora: Democratizing Efficient Video Production for All

Reference 48

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.588638Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:609a452fcd5891ea91981bcd0d6df6ea569f4c70d4cb8b0112dafdf16e4775b2

Observation a52923ff-473c-43e3-a569-798cccba3f77 · outbound

This paper cites Vid2World: Crafting video diffusion models to interactive world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Vid2World: Crafting video diffusion models to interactive world models

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.050356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:b67e300864b23fe32bac5fef829885396f0a26a0f25e36fdd080a797bcb7fd19

Observation a99eb45f-bcb2-456d-9d55-eecaf3de33e5 · outbound

This paper cites Matrix-game 2.0: An open-source real-time and streaming interactive world model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Matrix-game 2.0: An open-source real-time and streaming interactive world model

Reference 50

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.585462Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:56c116959117b8a96dad1c853487901b591797b85cce201b32555c04233938ab

Observation 3c00d4b8-ac54-4f30-a893-1e1d42e88f95 · outbound

This paper cites HunyuanVideo: A Systematic Framework For Large Video Generative Models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks HunyuanVideo: A Systematic Framework For Large Video Generative Models

Reference 51

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.608300Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:3fb60972bb992f7ecc46c5bf6bdcacf73e3c727336569f9c46dd846881b1cfe3

Observation 4a075017-1cac-4903-8322-389a10c74f2b · outbound

This paper cites MotionCtrl: A unified and flexible motion controller for video generation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks MotionCtrl: A unified and flexible motion controller for video generation

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.130819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:29ccd36aa79b3f1d3d904780df20240d26320c332e6ebea1bec78f45b596d5af

Observation 6875d7f4-aabb-441e-861b-7dd8163b309b · outbound

This paper cites FloVD: Optical flow meets video diffusion model for enhanced camera-controlled video synthesis.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks FloVD: Optical flow meets video diffusion model for enhanced camera-controlled video synthesis

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.028889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:2f657aeff2abea454d09685781ab6aea4e208830bdd3636aa8b08c88ea9eb15f

Observation a462c287-0dd4-4127-8011-b708f81d0f4d · outbound

This paper cites Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories

Reference 54

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.630553Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:38516c11ce16e6a27f3cb06a38e653cef5b24b547baf70f19c570a46b89d54ac

Observation 9aeab5b2-58cc-4dcd-a3a4-f2d45f4a22e4 · outbound

This paper cites Motion attribution for video generation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Motion attribution for video generation

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.132548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:05feb3de68366f62bdfd0e8952766090669faa9650c30f3035926c2a03db9d67

Observation 768c3ed4-d20e-482b-a5a7-92962342cc1f · outbound

This paper cites The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Reference 56

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.666168Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:b14a679d986c8810d026e395bd7fa49610bb48ffdae098f00e122fe23a2f3172

Observation ce034579-582b-41e2-b65f-c1529d605b92 · outbound

This paper cites Yume: An Interactive World Generation Model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Yume: An Interactive World Generation Model

Reference 57

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.659767Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:26e8dbb66c05c04415b4c9c633a7331cc5dfc045c40d40b0ca63d5a8ee29749a

Observation 1be52e9e-1cd8-4b21-8f1e-37cd4967bd1b · outbound

This paper cites Live: Long-horizon interactive video world modeling.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Live: Long-horizon interactive video world modeling

Reference 58

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.646637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:3295d2049ecdcb35d1b16bef89e947557512e941501ebdbe499e6f5b6680b0c7

Observation dab48ae7-fe7a-4bbc-aee1-b42bcdb04826 · outbound

This paper cites Roboscape: Physics-informed embodied world model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Roboscape: Physics-informed embodied world model

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.120274Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:f1c67b35d0feb4665e0d878cd5aef1929a5473f4d4c34aada575f32a8f61e1a5

Observation ecc6f345-d336-4135-9d91-2486bf166b4f · outbound

This paper cites BridgeData V2: A dataset for robot learning at scale.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks BridgeData V2: A dataset for robot learning at scale

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.122135Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:98713e7dc12df3819d2991b560fac5f19bccd3052fc9c2ce1a9d6f315dea00f3

Observation 1bc5e16b-2395-465a-a878-d878d7a7d086 · outbound

This paper cites Astra: Toward general-purpose mobile robots via hierarchical multimodal learning.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Astra: Toward general-purpose mobile robots via hierarchical multimodal learning

Reference 61

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.627585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:1b644aeb9701c772e0937d1c082bb24090fe91cea969ce6cf4af63d19e4e5bc3

Observation c01da346-445a-4a12-9499-612fe71dc20e · outbound

This paper cites Motus: A Unified Latent Action World Model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Motus: A Unified Latent Action World Model

Reference 62

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.653566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:f3b3049d89fdba34f2df31b9363bab04d55ccb87deefb922262f294109c57fbf

Observation 27ec94b9-7fcf-40f8-845d-d740c94d1aa2 · outbound

This paper cites Large Video Planner Enables Generalizable Robot Control.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Large Video Planner Enables Generalizable Robot Control

Reference 63

Resolution
metadata mismatch
local_arxiv, observed 2026-05-20T06:38:05.602010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:e6260cacc56961a840bd7e858fe4bf66583d24fb72873257c499123501dccd28

Observation 19f18501-5b31-466b-9f0d-e30fb9db3006 · outbound

This paper cites Wow: Towards a world omniscient world model through embodied interaction.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Wow: Towards a world omniscient world model through embodied interaction

Reference 64

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.575833Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:14d1f8bf760190cb5eab7618d8798a6cbdfd410a1bfeb94daaf781bfe3948571

Observation 88fd9be5-b288-4f83-a5aa-8208b30e0103 · outbound

This paper cites Ctrl-world: A controllable generative world model for robot manipulation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Ctrl-world: A controllable generative world model for robot manipulation

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.019348Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:b174988f4503270f73c3079887c2eb68af7a344b0e7ec0f540e1a813a2ec5c02

Observation 062436eb-72d1-4301-95ad-814e195db16f · outbound

This paper cites Vla-jepa: Enhancing vision-language-action model with latent world model.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Vla-jepa: Enhancing vision-language-action model with latent world model

Reference 66

Resolution
verified exact
arxiv_id, observed 2026-05-20T06:38:05.572447Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:93d4d344f55b85b825901937ec3e52644306fa94b3112f845ca9d3b98a8b5b74

Observation 000dd9da-a886-49db-8fb4-7585e1037e6c · outbound

This paper cites JanusVLN: Decoupling semantics and spatiality with dual implicit memory for vision-language navigation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks JanusVLN: Decoupling semantics and spatiality with dual implicit memory for vision-language navigation

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.101438Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:22efa08cb71a28347b6e46e504e02a8bf70437cb82cfed95402a39998616558f

Observation 5bc90833-8b69-42ca-92cb-c8340c869449 · outbound

This paper cites 4D-VLA: Spatiotemporal vision-language-action pretraining with cross-scene calibration.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks 4D-VLA: Spatiotemporal vision-language-action pretraining with cross-scene calibration

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.057098Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:3fb17e37895e2f2b6947ab88a1dc1f6b49b853eef962bbcc111f0c339a1a3d27

Observation a6b25baa-8594-4ac2-a42e-1f28f20022d7 · outbound

This paper cites Unified world models: Coupling video and action diffusion for pretraining on large robotic datasets.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Unified world models: Coupling video and action diffusion for pretraining on large robotic datasets

Reference 69

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.059186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:48dea445eb14c733052892febdb09679faa6731b3a25cdaf0ad68f596289eda6

Observation cfc137aa-6d99-4a85-8623-d97149cb48f1 · outbound

This paper cites Iso-Dream: Isolating and leveraging noncontrollable visual dynamics in world models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Iso-Dream: Isolating and leveraging noncontrollable visual dynamics in world models

Reference 70

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.074180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:85669ce8f400f32d9d5481be23930a9683570c946316ac627fe000c9c15c9f9f

Observation cfce3eab-fa01-4b49-8a2d-14e3471d8d41 · outbound

This paper cites Qwen3-VL Technical Report.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Qwen3-VL Technical Report

Reference 71

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.582461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:b8bd91e470d52b8547f0c515311f92fac20effe80f8bb07e4fcfd80525f4c999

Observation d7e177ee-f076-4bdd-93d0-75583cd815d7 · outbound

This paper cites Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.JMLR.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity.JMLR

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.103323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:d4695eb959d6cc71cde2cfbbc2596025c58cfdae8cd20adfd21a789633a21e83

Observation c87a9151-46f4-43aa-861d-4bbf330ddea8 · outbound

This paper cites Mixtral of Experts.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Mixtral of Experts

Reference 73

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.614210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:e5eb47a6982bc0efc2802768b6b750e001172a36ec86cbaf521f8952c68d7cb8

Observation 9ce97c76-52c2-4ba0-bf8c-82eca7851f7e · outbound

This paper cites Vision transformers for dense prediction.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Vision transformers for dense prediction

Reference 74

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.030905Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:967b33f5037463bf48aa3ed124036146b098887222eda468472f82caa6edb1ab

Observation 7f9dd8d0-d465-43f9-ad34-92638104f418 · outbound

This paper cites an unresolved cited work.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Unresolved cited work

Reference 75

Resolution
unresolved
raw_fallback, observed 2026-05-20T06:38:06.021083Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:db3144b38b7887dab4aedc699c4d045bfadf6a481c24dc5c2944d445a77eb5f2

Observation 0019201d-93ab-4fbc-a79b-c5a43f2d0909 · outbound

This paper cites Dice loss for data-imbalanced NLP tasks.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Dice loss for data-imbalanced NLP tasks

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.095105Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:e0fc4fff28437dd13c491f4c5341693ee44298024635f5406b38633ad066eebb

Observation 65ed45e4-f996-4f87-9576-2e2077bf6292 · outbound

This paper cites VBench: Comprehensive benchmark suite for video generative models.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks VBench: Comprehensive benchmark suite for video generative models

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.099579Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:00c6ddd0c696a569618255c37292e654a4f730caa56030bc33b35890dc9295fc

Observation 69412894-ea02-48f8-8557-4a4b19f957fa · outbound

This paper cites VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness

Reference 78

Resolution
verified exact
local_arxiv, observed 2026-05-20T06:38:05.568899Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:4a17217fe299cd12ef2a3a7e9dd8ba2d511fc22c301231bf441f2b27ee08b3ff

Observation 97d00d15-2004-40e7-9a3a-73190508928c · outbound

This paper cites IRASim: A fine-grained world model for robot manipulation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks IRASim: A fine-grained world model for robot manipulation

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.087503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:25062f135ee40633999bfe6dbe58e8413d7df34e55fceef2d3cfdd599251db32

Observation 870007e3-881a-4a5e-815d-99202fb2623f · outbound

This paper cites Raft: Recurrent all-pairs field transforms for optical flow.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Raft: Recurrent all-pairs field transforms for optical flow

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.091334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:6ffc337335e22d54c595df71ff5951e190a60b0192ea0ab17d4e41b4be6f2827

Observation 7ccc4138-74e3-46ff-86e2-378aeb91a7ec · outbound

This paper cites The unreasonable effectiveness of deep features as a perceptual metric.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks The unreasonable effectiveness of deep features as a perceptual metric

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.097523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:5d44d6cf1e058b3806c012ffbe9e2b07e78a9af8230a31674570dede7caee392

Observation 0857f8a8-d4aa-4261-882a-940e3861312c · outbound

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

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Learning transferable visual models from natural language supervision

Reference 82

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.126676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:a8a6c7b4a4628ca6efdc3dc7127058aa194e4b44d20b17e2cec9eebf6db24a0c

Observation dc3a594d-2110-48dd-919e-bbf8dcea8742 · outbound

This paper cites Scalable diffusion models with transformers.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Scalable diffusion models with transformers

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.114171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:d126dce68b7dc33ef97880735350f32c33f8f690126f015295ded4a6bb4b0f51

Observation e24b3160-f17f-4259-ac48-51ae621a0c1e · outbound

This paper cites Learning phrase representations using rnn encoder–decoder for statistical machine translation.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Learning phrase representations using rnn encoder–decoder for statistical machine translation

Reference 84

Resolution
malformed identifier
raw_fallback, observed 2026-05-20T06:38:06.116554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:3ae1982a59a501cfee9d0fdc42bcb0e4dde44babdfa8c5c9a9a7f3949c1c0ae1

Observation 4ca12977-1c74-4bac-ab4f-8802a1cd8664 · outbound

This paper cites lower-left and lower-right of frame.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks lower-left and lower-right of frame

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.111900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:eda68e2bfd9d1cd12495abf6e99bac3c182080d01bd99b3718173087cad19c2c

Observation 795eaa33-9323-44a7-8d5a-ba4313681d80 · outbound

This paper cites an unresolved cited work.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks Unresolved cited work

Reference 86

Resolution
unresolved
raw_fallback, observed 2026-05-20T06:38:06.107584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:cfe3cf2feacdd5d55c312399fbee0b52b9a6754f8ffc3a89fb444587a24bf023

Observation a8dba1e3-0c4e-41c7-9021-5fe43613c0a2 · outbound

This paper cites clip 3 of 5, 60% through this action.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks clip 3 of 5, 60% through this action

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.109779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:0dbd75c1c4067977d47f3b2194be761c7bc6c290af31a71754412caa98e8294c

Observation 4e4fbcb5-a54b-4019-bf7d-2fabe11987f5 · outbound

This paper cites forward”, “left.

World-Ego Modeling for Long-Horizon Evolution in Hybrid Embodied Tasks forward”, “left

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-05-20T06:38:06.118433Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

source=pdf_text observed=2026-05-20T06:36:47.265734Z digest=sha256:786c43e52f1cbaba0c554e74fb0f0bdc6b2f32653b3f82242a14310050594f18

Pith citing papers

No inbound Pith citation observations are available.