Pith. sign in

Paper Citation Record · LEDGER

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE

As of 22 August 2026, this Paper Citation Record lists 93 of 93 outbound references and 1 inbound Pith citation observation for arXiv:2411.16856.

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

pith.paper-citation-record.v1
2411.16856 v3

Coverage vector

measured 93 of 93 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T12:52:10.504301Z

measured 94 of 94 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-21T06:32:19.484+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-05-21T14:48:21.787919Z

measured 1 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Reference resolution

93 of 93 outbound references displayed

  • verified exact0
  • verified fuzzy56
  • unresolved36
  • parse uncertain1
  • malformed identifier0
  • metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation b2a4df05-a876-4940-982b-184584b824ac · outbound

This paper cites GPT-4 Technical Report.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE GPT-4 Technical Report

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.084365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.084365Z digest=sha256:bf97f1e48e67f17b0d2423952e02ce2b718edb515ba21de8cf03720f24144f1d

Observation 8c4086a9-fbd9-4ef4-9b52-53b7bd4d1d21 · outbound

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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Flamingo: a visual language model for few-shot learning

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.089742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.089742Z digest=sha256:fac59e74a2a36a0fb5b8ca5a421eb69ab41049a4f758bdd9efe17a483fa96264

Observation e5f5b9ae-b026-429d-b1cf-e477c957156e · outbound

This paper cites Demystifying mmd gans.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Demystifying mmd gans

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.094793Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.094793Z digest=sha256:d84d5e40aae3623a1e5e0f27c505c15065d74e8b194165d654c6f7fdef2920ca

Observation df38ee96-2842-4930-a5d3-4feb28a9c736 · outbound

This paper cites Video generation models as world simulators.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Video generation models as world simulators

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.099617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.099617Z digest=sha256:a94303f700c3a4a50ec4aee0ddf59dc30b871ac90e2f431026230278c61c038f

Observation f884c0f6-02f5-406a-b35c-001fd00115e9 · outbound

This paper cites Lan- guage models are few-shot learners.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lan- guage models are few-shot learners

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.104973Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.104973Z digest=sha256:c1f1e6e351efa8c24874449d1a8303a54e3c0039a2bccfcd428928f4726aa6c9

Observation 3b334e59-2828-4a35-b637-51989331ffd5 · outbound

This paper cites ShapeNet: An Information-Rich 3D Model Repository.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE ShapeNet: An Information-Rich 3D Model Repository

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.109776Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.109776Z digest=sha256:149f5a93e0d5b699315f1f23471e4eca4acf8975dc1584ec94327cc2570e0823

Observation ddeb8333-e54e-42ea-80c0-a74877a506bc · outbound

This paper cites Maskgit: Masked generative image transformer.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Maskgit: Masked generative image transformer

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.114779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.114779Z digest=sha256:dd890d0a053ab6df9c2d31ac686c21a58541d09de22e040a345f4ca291b74c31

Observation 184058bf-2767-4e7a-a36e-aeec197f0482 · outbound

This paper cites Lara: Efficient large-baseline radiance fields.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lara: Efficient large-baseline radiance fields

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.119338Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.119338Z digest=sha256:38ee4c7a18a925ae7b30d72fe81f9979b66b18f472fafa5cb853b172f7686f64

Observation a34a7808-208e-441d-8c59-a5df9574e0ae · outbound

This paper cites Fan- tasia3d: Disentangling geometry and appearance for high- quality text-to-3d content creation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Fan- tasia3d: Disentangling geometry and appearance for high- quality text-to-3d content creation

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.124518Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.124518Z digest=sha256:6e30cfbc2203736e7dd914133b730fa4a4e7a598b9924a747efa02cda153198d

Observation 8eff5223-12e7-458b-bf06-b92f0982edee · outbound

This paper cites Comboverse: Compositional 3d assets creation using spatially-aware diffusion guidance.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Comboverse: Compositional 3d assets creation using spatially-aware diffusion guidance

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.129061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.129061Z digest=sha256:447e2aa1b375a1de124852a08cf75deab79614dbff0e1ac17abe3b61c6f376e5

Observation 717632a5-fac5-472f-aa8f-877600fbbe8b · outbound

This paper cites Meshanything: Artist- created mesh generation with autoregressive transformers.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Meshanything: Artist- created mesh generation with autoregressive transformers

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.134306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.134306Z digest=sha256:ba01014d0145acc50fc82fee1bb374f10c6e719ef6c1b955c188a13251f48e23

Observation 4a792050-dd0a-4f1f-865e-0224f030df8c · outbound

This paper cites Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.138746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.138746Z digest=sha256:af8ebe0a3e9aea7d33c333c5b9b2be6ec2fb329d43b5e00ad63cea58cf2020e5

Observation 83d55a0b-bab7-4463-8248-10cc1d91c3e9 · outbound

This paper cites Palm: Scaling language modeling with pathways.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Palm: Scaling language modeling with pathways

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.143385Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.143385Z digest=sha256:f88ed4a791f544ccadf698ee849a16ef94f42adb0ae097a581e4f4110e4109cb

Observation cb27c8d0-7c9d-4a11-a828-2c3e028c21eb · outbound

This paper cites Objaverse-xl: A universe of 10m+ 3d objects.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Objaverse-xl: A universe of 10m+ 3d objects

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.147883Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.147883Z digest=sha256:1cf0e4c632c417038f6d762110b5483f554c78fca62a5030a373952e05de57f5

Observation 3e8856e4-e1a5-4ecd-9e16-df802fdf20c3 · outbound

This paper cites Objaverse: A universe of annotated 3d objects.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Objaverse: A universe of annotated 3d objects

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.152354Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.152354Z digest=sha256:831cf327c6a4149aa4bb4432a83218ef289c1af8a1a7f038d7c1037e1f7ed75b

Observation 83534297-5288-4a3d-a4d6-5909c0e8c591 · outbound

This paper cites Palm- e: An embodied multimodal language model.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Palm- e: An embodied multimodal language model

Reference 16

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.684263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.156786Z digest=sha256:f9259605c718b61c1f5d65215d17d49c710e4e329d552a31d048fdedd6d2dbfc

Observation b154415c-54c7-44a0-a891-e0ca88c199d2 · outbound

This paper cites Taming transformers for high-resolution image synthesis.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Taming transformers for high-resolution image synthesis

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.161472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.161472Z digest=sha256:8a98fe634b3c3b434cc400d170304fdd9e985f1f5642ff4cc5e56674db9c7f7e

Observation d718883a-8478-4927-8f57-37d366037e8d · outbound

This paper cites Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.167237Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.167237Z digest=sha256:4aae4504ba83d8e9ece2ddd10c1803a6344c5e7b87088f725203453b33f19493

Observation 93153d77-a56d-4b25-8ba6-f69134e1b7a0 · outbound

This paper cites OpenLRM: Open-source large reconstruction models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE OpenLRM: Open-source large reconstruction models

Reference 19

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.660835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.172277Z digest=sha256:e262ae24f52b48b5531e341b14dadaeff9f4d05c5c5ae9e134d54f0999c94a8c

Observation 3cd612bb-cc44-4dd7-a04e-c3c1fb227622 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilib- rium.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Gans trained by a two time-scale update rule converge to a local nash equilib- rium

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.176860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.176860Z digest=sha256:82cc045aecf44a9055a9190c0f5290a87f2cd4c70ea2a1d286cb58f3d4c20662

Observation 83bdb322-003d-410b-8fea-bd9373a9e823 · outbound

This paper cites Classifier-free diffusion guidance.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Classifier-free diffusion guidance

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.181260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.181260Z digest=sha256:cd08fa877304484b7ec029381cb7c75a7301ed966159f371fff7136a8d4c5081

Observation 36b8f98f-24b5-4000-9d08-e51e92ef46ab · outbound

This paper cites Denoising diffu- sion probabilistic models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Denoising diffu- sion probabilistic models

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.185923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.185923Z digest=sha256:b35b1f633c875f864bda8caa3f394fca9d412aa8ccdb7a880d2f553e3f60a60d

Observation 79c6ec6d-3616-425a-bbad-a410c7927808 · outbound

This paper cites 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE 3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.190409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.190409Z digest=sha256:45bbbf1a142ff8e324bab44f9d8cfa6abd3b92ac16ee8a3717f2d72eced0ff23

Observation 21ead568-347e-494b-a0ac-b0e44806e213 · outbound

This paper cites 3d-llm: In- jecting the 3d world into large language models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE 3d-llm: In- jecting the 3d world into large language models

Reference 24

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.618201Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.195390Z digest=sha256:c6baf7ca935e4e0e07dc54c80ba8916f8e80143ee061f18a50d662b55faaecb1

Observation 5bff3f0c-8f8f-47fe-ba4d-657e9c54ad42 · outbound

This paper cites Lrm: Large reconstruction model for single image to 3d.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lrm: Large reconstruction model for single image to 3d

Reference 25

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.603468Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.199835Z digest=sha256:c66fc51b5baa04b4be63348f525a2f0f85704d9b19d911b5c33e624d5ff4e24f

Observation a986443c-a237-4e31-aec1-0414030b3afa · outbound

This paper cites 2d gaussian splatting for geometrically ac- curate radiance fields.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE 2d gaussian splatting for geometrically ac- curate radiance fields

Reference 26

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.588870Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.204127Z digest=sha256:657c5cf6e9c48d8a5a563715eb81cc68bcda48c2a5414e4684c51b38c16b3889

Observation 1de84dd7-41c9-4a7f-95ef-0f1efe65096c · outbound

This paper cites Shap-E: Generating Conditional 3D Implicit Functions.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Shap-E: Generating Conditional 3D Implicit Functions

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.208683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.208683Z digest=sha256:06b8146ae13a67a6ea87215c7d3a48237a55fb78f65c7727b5833cac1ff2b34c

Observation 6bf5d517-9a33-467a-9189-07787be4c080 · outbound

This paper cites Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Brown, Benjamin Chess, Rewon Child, Scott Gray, Alec Radford, Jeffrey Wu, and Dario Amodei

Reference 28

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.573772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.213565Z digest=sha256:6974b89bf44b2d3f2d3fbf719ac496aa9a8309578f0617480ec115d90906e00c

Observation d82dd398-3e3a-4244-bfc4-c2bb78827445 · outbound

This paper cites Musiq: Multi-scale image quality transformer.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Musiq: Multi-scale image quality transformer

Reference 29

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.558286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.218183Z digest=sha256:c86849247f3de1bd1a6b6a9c1e9bf6eec51ea794bc03134e9eca81a848926fd1

Observation 84d6e0a7-162f-4594-893a-f1a0a03f4782 · outbound

This paper cites Kingma and Max Welling.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Kingma and Max Welling

Reference 30

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.542881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.222597Z digest=sha256:d6c485b35902de79e503781208a0e2ff57563e568789baf6bbdfbfa67c67b250

Observation 181b492b-c64a-4e69-90a0-9d0d4ce2a62c · outbound

This paper cites Nerf-vae: A geometry aware 3d scene generative model.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Nerf-vae: A geometry aware 3d scene generative model

Reference 31

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.527816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.226855Z digest=sha256:34ed56320e484218ef71c6d3b0a58ae61b5843f805486f74f97eedd36b804811

Observation 22b3f0fa-a7ca-48ef-a3fc-bccd6703cdf7 · outbound

This paper cites Ln3diff: Scalable latent neural fields diffusion for speedy 3d generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Ln3diff: Scalable latent neural fields diffusion for speedy 3d generation

Reference 32

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.512855Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.231057Z digest=sha256:438535d1b644f109c4f98d37861522c5351007945fb91c35633f10078d02ffe9

Observation fbffe989-7344-4611-8b0a-7cd8a3bf9d2f · outbound

This paper cites Gaussiananything: Interactive point cloud latent dif- fusion for 3d generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Gaussiananything: Interactive point cloud latent dif- fusion for 3d generation

Reference 33

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.497786Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.235292Z digest=sha256:70bacef4ed621dbc2dc26b4be84c1cec4148507023f9e688258a589d34be62bb

Observation 27814b0d-7cac-45d9-9e86-c13f9bb2ff0b · outbound

This paper cites Autoregressive image generation using residual quantization.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Autoregressive image generation using residual quantization

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.240211Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.240211Z digest=sha256:6749a874af08f09290dbbb4019825fbb84cb732690c992e609b997302bfe40a9

Observation 04dc7fde-f63d-459e-92e9-b11b3ef14017 · outbound

This paper cites CraftsMan: High-fidelity mesh generation with 3D native generation and interactive geometry refiner.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE CraftsMan: High-fidelity mesh generation with 3D native generation and interactive geometry refiner

Reference 35

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.473350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.245097Z digest=sha256:0773c2aad1d9076b12e89f274897af40be700333b01d40a83d82f8cb9ef503d2

Observation 4e718b6e-cb74-4811-b9ef-9792feeede6a · outbound

This paper cites Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.249652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.249652Z digest=sha256:159e6f0a91c168a4e19e1f9f7990a7df0dc9d622aec03d3a2411892e4e3b400c

Observation 5a3db5ba-30c3-46c4-9604-9d0458f99b00 · outbound

This paper cites Visual instruction tuning.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Visual instruction tuning

Reference 37

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.458093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.254399Z digest=sha256:d1d31e9b7e4d426a686aaba852025782dfa723b103cd57353b77cfbc178fe65a

Observation e54ce1db-f26d-4554-b3ab-0f3c6fd6a12a · outbound

This paper cites One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimiza- tion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE One-2-3-45: Any single image to 3d mesh in 45 seconds without per-shape optimiza- tion

Reference 38

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.443893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.258753Z digest=sha256:71e6c32d7a3c070c5efc997499935eca67770088a7e0aa99cd8b1904b6bf2b5f

Observation cf297b72-e8f7-40f3-8983-f1a1067f77c1 · outbound

This paper cites Zero-1-to- 3: Zero-shot one image to 3d object.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Zero-1-to- 3: Zero-shot one image to 3d object

Reference 39

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.429464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.263015Z digest=sha256:dadb215d5ad6a3e1edbf31e58950a958c1306f6f13cfb699d38a4d69dbab035a

Observation d50b8a05-abde-4f19-aa22-9f6668fad508 · outbound

This paper cites Wonder3d: Sin- gle image to 3d using cross-domain diffusion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Wonder3d: Sin- gle image to 3d using cross-domain diffusion

Reference 40

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.414849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.267215Z digest=sha256:6594215fd942d53c4e02ad3f5a40a98e82fb86219552c2771d37b0ff7fb764ca

Observation 08d8f544-0920-4df0-8b45-229b557c645f · outbound

This paper cites Scalable 3d captioning with pretrained models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Scalable 3d captioning with pretrained models

Reference 41

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.400539Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.271394Z digest=sha256:ed25e8772ae4968f0a1c384fbbb922f56e2417dd094711d06fdc906396a6e179

Observation abf3f6b4-2824-4c8f-b435-f71e999c5eb3 · outbound

This paper cites View selec- tion for 3d captioning via diffusion ranking.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE View selec- tion for 3d captioning via diffusion ranking

Reference 42

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.386415Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.275802Z digest=sha256:303bdea0b973ca5496e00541c704bd6909805a0613ac0d8e2c3dff5ccc297d34

Observation 227ab008-0fa0-484c-aa81-4b0e5b2a84ea · outbound

This paper cites KOSMOS-2.5: A Multimodal Literate Model.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE KOSMOS-2.5: A Multimodal Literate Model

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.280261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.280261Z digest=sha256:17023fba30d142184add80f4c6e0693d521a27689165a9812cd6057a09a3172f

Observation 61a817c7-f2a2-4815-9f90-d634cbd7fff4 · outbound

This paper cites Nerf: Representing scenes as neural radiance fields for view syn- thesis.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Nerf: Representing scenes as neural radiance fields for view syn- thesis

Reference 44

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.371963Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.284950Z digest=sha256:65d70c40af48d131951553ef519ecae94df7e9e450922f3c1ed976147029339b

Observation 08c8c0b3-89f7-4349-8453-4b8c86293b06 · outbound

This paper cites Autosdf: Shape priors for 3d comple- tion, reconstruction and generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Autosdf: Shape priors for 3d comple- tion, reconstruction and generation

Reference 45

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.357222Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.289490Z digest=sha256:4693a25046da249262f149794b9c8aa3a1988cb92d531a70c6af51adcef25190

Observation 3cc9fa97-dc11-4ef5-af1a-14817b4e84bd · outbound

This paper cites Point-E: A System for Generating 3D Point Clouds from Complex Prompts.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Point-E: A System for Generating 3D Point Clouds from Complex Prompts

Reference 46

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.293892Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.293892Z digest=sha256:fb27a03bad4d8c20832e37c957ded3cbb292070dc416732a113722d58f634688

Observation 3372f6f5-95f2-4b1e-a396-fda875132564 · outbound

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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Dinov2: Learning robust visual features without supervision

Reference 47

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.342357Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.298697Z digest=sha256:cacc4eaefd1af4ea327441640b87c65d74bf40093410c81d9d215173b7d4f4f7

Observation c7ec7313-fb60-4e9f-986c-27154643d9d5 · outbound

This paper cites Training language models to follow instructions with human feedback.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Training language models to follow instructions with human feedback

Reference 48

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.327504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.303249Z digest=sha256:fcf0002e7a738913f260774a793d60fb67692ecd505dc1d63ec1531a146ca0f8

Observation 94b646af-38b1-4504-adf1-738999ce0ad1 · outbound

This paper cites Scalable diffusion mod- els with transformers.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Scalable diffusion mod- els with transformers

Reference 49

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.312867Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.307769Z digest=sha256:b9e52496c4a874aa3f1bbd798247fe240c756725e914268dd69fd1b8508ccf54

Observation 2f1aacc2-f2d0-41d3-9538-e3d5554644ad · outbound

This paper cites Dreamfusion: Text-to-3d using 2d diffusion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Dreamfusion: Text-to-3d using 2d diffusion

Reference 50

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.297932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.312138Z digest=sha256:1cade076edb4ac45b4e3b86b20bfe680ecf5ae5ec03a1760339b3cf6bbd799ec

Observation 796a8239-893d-4088-a8a6-e2019d5346b1 · outbound

This paper cites Shapellm: Universal 3d object understanding for embodied interaction.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Shapellm: Universal 3d object understanding for embodied interaction

Reference 51

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.283016Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.316867Z digest=sha256:b7704d10dbf528d1d472c5701d41dea37993314e96f4e6915b18f11c812449d0

Observation 567c8080-6bd6-45e9-bf39-32940f5fc96e · outbound

This paper cites Richdreamer: A generalizable normal-depth diffusion model for detail richness in text-to- 3d.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Richdreamer: A generalizable normal-depth diffusion model for detail richness in text-to- 3d

Reference 52

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.268213Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.321156Z digest=sha256:3d9b3577fb6d745bd44d5ec46372a674201b1dbf45f23550a8217ebea9385f2d

Observation c2cd2614-9ed9-47c4-a5be-c334fbf10bc3 · outbound

This paper cites Learn- ing transferable visual models from natural language super- vision.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Learn- ing transferable visual models from natural language super- vision

Reference 53

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.253444Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.325324Z digest=sha256:a3b4a4da6d21d3a6b32a38de7516fdeb05a10dba4889393e5acb4047db52f60b

Observation 20f051c1-874d-4cf9-82e5-a536a3c78d8c · outbound

This paper cites Zero-shot text-to-image generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Zero-shot text-to-image generation

Reference 54

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.238557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.329719Z digest=sha256:6793e0ab75022c984f1e480033acd46302ae5e196536adc5d2a896dd842428b0

Observation ac0b05aa-cd3b-4429-a435-bfabd014500c · outbound

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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE High-resolution image synthesis with latent diffusion models

Reference 55

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.223192Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.334678Z digest=sha256:a58871257eba5718d9860a273ceab8a7321c306338873bd65e11be77ad9ffd9f

Observation 3772de48-2a47-4b2b-b4ad-e00100368b5e · outbound

This paper cites Pixelcnn++: Improving the pixelcnn with dis- cretized logistic mixture likelihood and other modifications.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Pixelcnn++: Improving the pixelcnn with dis- cretized logistic mixture likelihood and other modifications

Reference 56

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.208265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.339224Z digest=sha256:d90b1179a2599a15520fd243afb7e5bee8d6d567eaa87bc689ee46cf8eee1e05

Observation 58f7e6d9-7e1b-44d9-a6ad-1ed8a8b43e61 · outbound

This paper cites Flexible isosurface extraction for gradient-based mesh optimization.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Flexible isosurface extraction for gradient-based mesh optimization

Reference 57

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.192186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.343727Z digest=sha256:0c9fc07b25cd42356a5bbcbede834c8e8b638ac844f0b09b84169c721a72ee3c

Observation 3b37534d-5ddd-42f6-ac33-d82dffeae3b7 · outbound

This paper cites Zero123++: a single image to consistent multi-view dif- fusion base model.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Zero123++: a single image to consistent multi-view dif- fusion base model

Reference 58

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.177336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.348218Z digest=sha256:04034440f2ec2fa6d5bb234473ecfd862418e0b318ca0346a1acec03fbf56fab

Observation be267b2b-3b1f-496d-9b4a-9a4ccc4dc7c4 · outbound

This paper cites Mvdream: Multi-view diffusion for 3d gen- eration.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Mvdream: Multi-view diffusion for 3d gen- eration

Reference 59

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.162340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.352745Z digest=sha256:610d413b188455ecbf96fb0ddd1b0ed6c38a925674efc3c477e2d2df5b886151

Observation 80e3a86d-f7eb-4ab9-8687-43cbec1eac1b · outbound

This paper cites Meshgpt: Generating triangle meshes with decoder-only transformers.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Meshgpt: Generating triangle meshes with decoder-only transformers

Reference 60

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.147220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.357307Z digest=sha256:dddbc2dc1a309bec3ced974d00e1cd80f219d7a2404795103b195375a939f781

Observation c663576f-1194-4c4d-a4a3-4819f0b16a4b · outbound

This paper cites Light field networks: Neural scene representations with single-evaluation rendering.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Light field networks: Neural scene representations with single-evaluation rendering

Reference 61

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.131501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.361853Z digest=sha256:e5099995c0c8cb98114a8c5d24df9f5e7a08206b51ee9f482491e39a59a82824

Observation 97ba22b4-e441-4f62-80bf-10b60d87018d · outbound

This paper cites Score-based generative modeling through stochastic differential equa- tions.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Score-based generative modeling through stochastic differential equa- tions

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.366352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.366352Z digest=sha256:6df3e5cb3bf640c716e16709030b397a21626f79b56b2a1e5585101671cea4ac

Observation 224e466d-c10e-445c-817f-5d8188c05ef5 · outbound

This paper cites Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.370840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.370840Z digest=sha256:f5493bc5cf5506956cd036e54b4a99cf803797a4e6cd8d405080917a6208b71e

Observation 1769e33d-a632-4ad3-a21e-6531e2ef35f7 · outbound

This paper cites Emu: Generative pretraining in multimodality.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Emu: Generative pretraining in multimodality

Reference 64

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.106128Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.375560Z digest=sha256:a499dc5425c0aca65e80cdd362033aa69d324e211219f1509a3b2ef8573bd2fe

Observation d228f497-3fc7-4005-b49f-e901727d11ee · outbound

This paper cites Splatter image: Ultra-fast single-view 3d recon- struction.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Splatter image: Ultra-fast single-view 3d recon- struction

Reference 65

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.091254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.379853Z digest=sha256:df69ee26acdb314f855ffe26af3462a2f0e876ea5e4ade5c82551db47e1ff94d

Observation a63fc588-d30e-4949-9916-bab4ce75b947 · outbound

This paper cites Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Make-it-3d: High-fidelity 3d creation from a single image with diffusion prior

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.384092Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.384092Z digest=sha256:1e1b748083485bcf80dd5446c1d4d6986df32611b7678efae8ad97c092d78abe

Observation fecfb698-b291-466e-9e08-fd82b0aec056 · outbound

This paper cites Lgm: Large multi-view gaus- sian model for high-resolution 3d content creation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lgm: Large multi-view gaus- sian model for high-resolution 3d content creation

Reference 67

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.066493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.388785Z digest=sha256:4eeaf590d2d25ffa643bc71a01ac9fd1def063477cfb9c1b9bcb554866cf1aaf

Observation ff91c9b5-1d4e-479b-9ec9-c7290ad391b4 · outbound

This paper cites Visual autoregressive modeling: Scalable image generation via next-scale prediction.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Visual autoregressive modeling: Scalable image generation via next-scale prediction

Reference 68

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.051889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.393225Z digest=sha256:6bfe668296627ce2db3f1fdcd6911962975ee0b7da75c2cc66ac2b2cb0d530d5

Observation 816442a4-3cdd-4ec8-a585-1c09b6a00ffc · outbound

This paper cites LLaMA: Open and Efficient Foundation Language Models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE LLaMA: Open and Efficient Foundation Language Models

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.402317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.402317Z digest=sha256:31e820ae1dfad1a44def309b1d684311a71a3ee79be5fd2d8b17655e49f4959e

Observation 4b267201-b8f4-4334-b540-8681a8d130c4 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.407101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.407101Z digest=sha256:d13f3bf424f72a6c6c7e15f6cbc429633a5e94e0c309c8ce3ede4ccfb68e35c9

Observation ba607be5-e79e-4c90-993e-4d829836b422 · outbound

This paper cites Lion: Latent point diffu- sion models for 3d shape generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Lion: Latent point diffu- sion models for 3d shape generation

Reference 71

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.022066Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.411761Z digest=sha256:6f4263078a23728d12ff527d0acbf421202f52739327d93a840a2e127386602f

Observation 6a826902-1301-4341-8879-43b6d004df67 · outbound

This paper cites Neural discrete representation learning.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Neural discrete representation learning

Reference 72

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:11.006542Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.416090Z digest=sha256:6925ad3677839d51e67580135babe47f2dda1ca0933a5ba956c674323f3cd1fc

Observation 4d3a26fb-8d3d-4ff7-acab-3a21fe65eff1 · outbound

This paper cites Rodin: A generative model for sculpting 3d digital avatars using diffusion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Rodin: A generative model for sculpting 3d digital avatars using diffusion

Reference 73

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.990378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.420602Z digest=sha256:0d4cbdbd383c9ec1b353980f7c943e2de0a6159f56fe30260a876e4f358b4020

Observation db1fc0c7-1445-4437-b2b6-9d62b50b19a8 · outbound

This paper cites Emu3: Next-Token Prediction is All You Need.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Emu3: Next-Token Prediction is All You Need

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.425149Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.425149Z digest=sha256:470b8c1f652521fa4d0b9a4b891829a9c611352b5e80b3cdde9720bdaa2472ba

Observation 05309087-c25b-430e-b3c0-c59489f30767 · outbound

This paper cites Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distilla- tion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distilla- tion

Reference 75

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.975676Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.429833Z digest=sha256:e956044beff372b436629997dcfdcd96c7d19d1a55f0f4b15d25cacc65156446

Observation 701c92f0-bc13-44ac-8a57-c377e6588531 · outbound

This paper cites Crm: Single image to 3d textured mesh with convo- lutional reconstruction model.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Crm: Single image to 3d textured mesh with convo- lutional reconstruction model

Reference 76

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.959484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.434286Z digest=sha256:14a86f0d915703d006ac84ecbf5ac59964d12ed9c29e4b9056a9f92ecfcdca58

Observation 78982d5a-598e-41fb-bfee-b6d6efe7193b · outbound

This paper cites Phidias: A gen- erative model for creating 3d content from text, image, and 3d conditions with reference-augmented diffusion.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Phidias: A gen- erative model for creating 3d content from text, image, and 3d conditions with reference-augmented diffusion

Reference 77

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.943707Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.438637Z digest=sha256:713b43b3d0c4c329c27704584d4ee005336f48e75f901ec558729b0b625082ad

Observation a6583e60-3763-424f-99e0-d0b6b08bac26 · outbound

This paper cites Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.442970Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.442970Z digest=sha256:cea376603510c8d656df3202581fa9d9534b650b7f2885ee64343a4801afb8a4

Observation 4d699d09-379b-43c4-9bdb-e4399817abd9 · outbound

This paper cites Multiview compres- sive coding for 3d reconstruction.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Multiview compres- sive coding for 3d reconstruction

Reference 79

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.928276Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.447766Z digest=sha256:b87f195fecce2451e2e8d331f9dfb087fba1e0496d42a03b08c53b75986e14a2

Observation 9d26c114-c46d-4507-ac0b-ef6fb07808fa · outbound

This paper cites Direct3d: Scal- able image-to-3d generation via 3d latent diffusion trans- former.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Direct3d: Scal- able image-to-3d generation via 3d latent diffusion trans- former

Reference 80

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.912941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.452097Z digest=sha256:ed89ad444e9e3f25bc7ea4f896ad278be9340655f83bfdb3edb0f921a01e88d3

Observation 4aaea32d-9c2e-48a4-ac9b-651ae9c7539c · outbound

This paper cites Latte3d: Large-scale amortized text-to-enhanced3d synthe- sis.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Latte3d: Large-scale amortized text-to-enhanced3d synthe- sis

Reference 81

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.897037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.456524Z digest=sha256:ac7a42d84615e3510777982f69873fc6fc7a7b266c47e2542912d888dfb02c21

Observation d7f248cd-c04c-459b-a3bc-a3b671bb05af · outbound

This paper cites InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.461037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.461037Z digest=sha256:8167f69220011796b90be978b0b7b38233fd500cf8121ca1184db8543b3ebefe

Observation 84455d40-91e0-4e4f-98dc-c6d2372321d2 · outbound

This paper cites Pointllm: Empowering large language models to understand point clouds.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Pointllm: Empowering large language models to understand point clouds

Reference 83

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.882030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.465511Z digest=sha256:217fd1ff7b2663df42e49ed62c7e212b4098f510f94814296d2ec4e7e23b86da

Observation 1a90409d-3647-47f8-aae7-c39f14720c11 · outbound

This paper cites Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Ulip: Learning a unified representation of language, images, and point clouds for 3d understanding

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.469877Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.469877Z digest=sha256:336c18b7f87327ff6618efc3e86b08ca06d23c250fc7f783eeb4907d02d2790c

Observation 3b67905f-e8e4-4a2f-b743-259b5a04c5ba · outbound

This paper cites Scaling autoregressive models for content-rich text-to-image generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Scaling autoregressive models for content-rich text-to-image generation

Reference 85

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.857578Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.474119Z digest=sha256:77cca791149be275a43fcef58024fbc14affe1bb0b555a828a5add23cd077b88

Observation ee76b518-11cd-480a-baf5-f0688ea3ccfd · outbound

This paper cites Language model beats diffusion-tokenizer is key to visual generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Language model beats diffusion-tokenizer is key to visual generation

Reference 86

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.842554Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.478339Z digest=sha256:b0c46eef47e1a8ebd4efa68f5be674489d476f2ba2f3d75f82dd4d9bc49fbec2

Observation 57331447-3d86-4891-b60a-9b540cf5a6cb · outbound

This paper cites An image is worth 32 tokens for reconstruction and generation.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE An image is worth 32 tokens for reconstruction and generation

Reference 87

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.827858Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.482482Z digest=sha256:b5d2df56221113be0cdd58b04533b5f9ee8dfca1ed4bb43b6130ca6cc6313b67

Observation 9de8e88f-e922-4e96-80e6-bd0eb7c5b7c9 · outbound

This paper cites Point-bert: Pre-training 3d point cloud transformers with masked point modeling.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Point-bert: Pre-training 3d point cloud transformers with masked point modeling

Reference 88

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.813443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.486667Z digest=sha256:5d63736ff40ab2d984e33c5fbe503b800cde1c3d5a2c5401c24f06b98e407bda

Observation c8946e61-1d34-480c-8688-d2a6a489a727 · outbound

This paper cites 3dshape2vecset: A 3d shape representation for neu- ral fields and generative diffusion models.ACM Transactions on Graphics (TOG), 42(4):1–16, 2023.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE 3dshape2vecset: A 3d shape representation for neu- ral fields and generative diffusion models.ACM Transactions on Graphics (TOG), 42(4):1–16, 2023

Reference 89

Resolution
unresolved
no resolver link, observed 2026-08-12T12:52:10.490938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T12:52:10.490938Z digest=sha256:e0990089221854ae0cd4dcc914c30f784a21b5cdfc3848716a3066df15943838

Observation 8e2e7596-eb7c-4c0a-80e4-e1a74289d56c · outbound

This paper cites Clay: A controllable large-scale generative model for creat- ing high-quality 3d assets.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Clay: A controllable large-scale generative model for creat- ing high-quality 3d assets

Reference 90

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.788673Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.495714Z digest=sha256:29edb3311a6445d2f4697a4e308f12ae3c73b503b68e31d400f319c6a89589c6

Observation 17f8524b-3f64-43b8-9b2d-4656f83fa133 · outbound

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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE The unreasonable effectiveness of deep features as a perceptual metric

Reference 91

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.773583Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.499987Z digest=sha256:906770fae0070d86cefdb8cf0641e676da5a827bdbdca523fdec0dc993075f51

Observation a44ad04c-6f0a-4da6-aab8-b1eebe377d5a · outbound

This paper cites Multi-HeadSelf Attention Multi-HeadCross Attention ×N Scale, Shift Layer Norm CLIPT Text Scale Scale ⊕ ⊕ (a) Transformer Block (Text condition) FFN𝛾!,𝛽!Scale, Shift 𝛼! Layer Norm𝛾.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Multi-HeadSelf Attention Multi-HeadCross Attention ×N Scale, Shift Layer Norm CLIPT Text Scale Scale ⊕ ⊕ (a) Transformer Block (Text condition) FFN𝛾!,𝛽!Scale, Shift 𝛼! Layer Norm𝛾

Reference 92

Resolution
verified fuzzy
raw_fallback, observed 2026-08-12T12:52:10.757885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.504301Z digest=sha256:b47afb84c001b45e379f3ea3b82158b740c54d9c899802a1b825210dcb0499fa

Observation 9cdeec13-9d32-4cab-975a-c39e131d86bd · outbound

This paper cites an unresolved cited work.

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE Unresolved cited work

Reference 2024

Resolution
parse uncertain
raw_fallback, observed 2026-08-12T12:52:11.037218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-08-12T12:52:10.397825Z digest=sha256:f21b4f0a0325b6c59e74a9829aedbfb1040adea7988c641b7db266a5fb763385

Pith citing papers

Observation 76acba24-64d5-4712-8ed8-482cebe95928 · inbound

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models cites this paper.

CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE

Reference 24

Resolution
verified exact
arxiv_id, observed 2026-05-21T14:50:14.784325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.

source=pdf_text observed=2026-05-21T14:48:21.787919Z digest=sha256:5ba11097a8ce7043165c2d05e27c7944de4ea80bfbbcda8e64569ef1c474718c