Paper Citation Record · LEDGER

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

As of 6 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 17 inbound Pith citation observations for arXiv:2604.24763.

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

pith.paper-citation-record.v1
2604.24763 v2

Coverage vector

measured 58 of 58 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-20T23:41:25.275207Z

measured 75 of 75 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-06T06:34:29.942622+00:00

measured 17 of 17 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T11:55:27.994286Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-07-10T13:37:06.881254Z

Reference resolution

58 of 58 outbound references displayed

verified exact54
verified fuzzy1
unresolved0
parse uncertain0
malformed identifier0
metadata mismatch3

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation f10e9c16-da04-44bd-a042-8b7609c692a2 · outbound

This paper cites Ming-flash-omni: A sparse, unified architecture for multimodal perception and generation.arXiv preprint arXiv:2510.24821.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Ming-flash-omni: A sparse, unified architecture for multimodal perception and generation.arXiv preprint arXiv:2510.24821

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.165136Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aa21ed8b-d792-4f37-8981-a01aba58df48 · outbound

This paper cites LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training

Reference 2

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.182896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation bbb8a7cf-805c-42e0-ab18-994621a85522 · outbound

This paper cites VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-07-14T02:20:26.920520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d4a23b81-b675-474e-9942-5ea3b1ebd1f7 · outbound

This paper cites Qwen Technical Report.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Qwen Technical Report

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T23:43:51.123112Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 003d9e10-1d2d-4967-ac36-9fab5437f7a8 · outbound

This paper cites Qwen3-VL Technical Report.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Qwen3-VL Technical Report

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.224063Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 72626697-3026-439a-bd03-6981120e3144 · outbound

This paper cites Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Bie, T., Cao, M., Chen, K., Du, L., Gong, M., Gong, Z., Gu, Y ., Hu, J., Huang, Z., Lan, Z., et al

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-20T23:43:51.088011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a95c9959-6841-4ac8-b32b-bcfbbdf71840 · outbound

This paper cites Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.133147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 34dbc408-464e-4870-a933-076b1d57bfd0 · outbound

This paper cites BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.126327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 02e8942e-6abf-4af7-a3b9-2e719e2aa46e · outbound

This paper cites PixelFlow: Pixel-Space Generative Models with Flow.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation PixelFlow: Pixel-Space Generative Models with Flow

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.084701Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 43c9d681-bb25-43b8-b687-61e13146f13c · outbound

This paper cites Emu3.5: Native Multimodal Models are World Learners.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Emu3.5: Native Multimodal Models are World Learners

Reference 10

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.071493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 72fdccde-a861-4c3e-9420-90339c50ded2 · outbound

This paper cites Emerging Properties in Unified Multimodal Pretraining.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Emerging Properties in Unified Multimodal Pretraining

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.115609Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 721f847d-105d-4625-abbd-92c9c73210f1 · outbound

This paper cites From pixels to words–towards native vision-language primitives at scale.arXiv preprint arXiv:2510.14979, 2025a.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation From pixels to words–towards native vision-language primitives at scale.arXiv preprint arXiv:2510.14979, 2025a

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.063724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1683cb3c-e9e0-4994-9a8a-409e6b24e763 · outbound

This paper cites Unified Autoregressive Visual Generation and Understanding with Continuous Tokens.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Unified Autoregressive Visual Generation and Understanding with Continuous Tokens

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.078460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a2363116-a38e-4124-9544-8abb6ebdbed1 · outbound

This paper cites X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again

Reference 14

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.185958Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 47986ce8-2cf0-4917-ad52-e37215bcd7c2 · outbound

This paper cites The Llama 3 Herd of Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation The Llama 3 Herd of Models

Reference 15

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.198204Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d48b7176-f7d3-438e-aec4-f7d2d4da5b79 · outbound

This paper cites Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.091129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f1b3d296-1dcc-417c-9045-60c6cfc9b2d4 · outbound

This paper cites Uni-x: Mitigating modality conflict with a two-end- separated architecture for unified multimodal models.arXiv preprint arXiv:2509.24365.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Uni-x: Mitigating modality conflict with a two-end- separated architecture for unified multimodal models.arXiv preprint arXiv:2509.24365

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.059913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dd250552-955d-4a8b-a4a5-47a1ff54fc22 · outbound

This paper cites Emma: Efficient multimodal understanding, generation, and editing with a unified architecture.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Emma: Efficient multimodal understanding, generation, and editing with a unified architecture

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.204198Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 05581f8c-820e-4922-8863-1bbc53f66c78 · outbound

This paper cites ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.081493Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 86b12f4f-653a-482f-b4f1-a599f959860e · outbound

This paper cites Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Ming-univision: Joint image understanding and generation with a unified continuous tokenizer.arXiv preprint arXiv:2510.06590, 2025a

Reference 20

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.221343Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ba1c9eb7-70df-43e6-8237-b274202c8ade · outbound

This paper cites LLaVA-OneVision: Easy Visual Task Transfer.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation LLaVA-OneVision: Easy Visual Task Transfer

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.201029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b8e1917f-cc1f-4dec-b203-0b3bf18af1c9 · outbound

This paper cites Back to Basics: Let Denoising Generative Models Denoise.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Back to Basics: Let Denoising Generative Models Denoise

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.230376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d3a281b8-a4c6-4ec7-9e22-7b5e6f809ea1 · outbound

This paper cites VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.161913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a5036c6b-1a90-4e68-a26d-226ec35f09c4 · outbound

This paper cites UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.215328Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6fa77aed-f707-4f87-9e84-f8485345517d · outbound

This paper cites Tuna: Taming unified visual representations for native unified multimodal models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Tuna: Taming unified visual representations for native unified multimodal models

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.207144Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e885048b-1347-4ffe-96a9-dcf1154235a3 · outbound

This paper cites Decoupled Weight Decay Regularization.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Decoupled Weight Decay Regularization

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.209927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f82ec47e-2cdb-4108-8ad9-40949b9471f4 · outbound

This paper cites Unitok: A unified tokenizer for visual generation and understanding.arXiv preprint arXiv:2502.20321, 2025a.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Unitok: A unified tokenizer for visual generation and understanding.arXiv preprint arXiv:2502.20321, 2025a

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.094637Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c41ea23d-ac1f-4cae-bca3-3a3b1838ce8d · outbound

This paper cites Does understanding inform generation in unified multimodal models? from analysis to path forward.arXiv preprint arXiv:2511.20561.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Does understanding inform generation in unified multimodal models? from analysis to path forward.arXiv preprint arXiv:2511.20561

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.098439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cee7d3ff-0c0d-4d00-bf20-3d8ed4726065 · outbound

This paper cites Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, and Tali Dekel.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Roni Paiss, Ariel Ephrat, Omer Tov, Shiran Zada, Inbar Mosseri, Michal Irani, and Tali Dekel

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T23:43:51.767832Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d46546bf-b744-497b-9b7a-abbb50206e52 · outbound

This paper cites Histream: Efficient high-resolution video generation via redundancy-eliminated streaming.arXiv preprint arXiv:2512.21338.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Histream: Efficient high-resolution video generation via redundancy-eliminated streaming.arXiv preprint arXiv:2512.21338

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.158464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 542a1cf9-2fe7-4fa3-a9b7-0c64c5f89c55 · outbound

This paper cites Mammothmoda2: A unified ar-diffusion framework for multimodal understanding and generation.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Mammothmoda2: A unified ar-diffusion framework for multimodal understanding and generation

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.115596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7b303691-2cef-4775-90ec-5adcbc8b568d · outbound

This paper cites Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.168069Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f466b11f-5c7c-44ea-9f02-f15502eb6161 · outbound

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

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.180253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation d467844e-d54c-44a3-bdc1-36a6dbb2340a · outbound

This paper cites Unilip: Adapting clip for unified multimodal understanding, generation and editing.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Unilip: Adapting clip for unified multimodal understanding, generation and editing

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.108996Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a446c5a9-1e2f-4cf8-b6dc-531f51947ee5 · outbound

This paper cites Chameleon: Mixed-Modal Early-Fusion Foundation Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.177504Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0454ea17-2581-470b-a4cf-6ed4919cf638 · outbound

This paper cites LongCat-Image Technical Report.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation LongCat-Image Technical Report

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.192137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7768f308-46d6-429a-84bb-f3be31651339 · outbound

This paper cites Internvl-u: Democratizing unified multimodal models for understanding, reasoning, generation and editing.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Internvl-u: Democratizing unified multimodal models for understanding, reasoning, generation and editing

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.052384Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2f5c6bb5-4b09-495a-979c-3596d0ab9730 · outbound

This paper cites Beyond language modeling: An exploration of multimodal pretraining.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Beyond language modeling: An exploration of multimodal pretraining

Reference 38

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.218228Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9f938dcc-30c8-454c-a350-3808e2b5e8b5 · outbound

This paper cites SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features

Reference 39

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.119286Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 4fdd0d68-d172-4b47-aca6-75aba365f915 · outbound

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

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Wan: Open and Advanced Large-Scale Video Generative Models

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.136076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ed7f43f2-3360-479d-bc81-2260ec90bc9f · outbound

This paper cites Ovis-U1 Technical Report.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Ovis-U1 Technical Report

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.147802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 334ecb48-2067-4346-91be-f1a6d78d489f · outbound

This paper cites UniVideo: Unified Understanding, Generation, and Editing for Videos.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation UniVideo: Unified Understanding, Generation, and Editing for Videos

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-07-07T03:17:13.018030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 89c604ab-8f2a-4aab-8fee-696b595a2204 · outbound

This paper cites Qwen-Image Technical Report.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Qwen-Image Technical Report

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.101640Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 921dab5b-a36c-4778-adfb-20bfbf7fbcb0 · outbound

This paper cites OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.195508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 5c35c0d9-e5c1-416d-b475-ff16dc69a0a5 · outbound

This paper cites Reconstruction Alignment Improves Unified Multimodal Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Reconstruction Alignment Improves Unified Multimodal Models

Reference 45

Resolution: metadata mismatch; arxiv_id, observed 2026-06-26T02:15:36.738364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 2d4ec96d-b77a-4d76-ac64-d13e0329d4fb · outbound

This paper cites Show-o2: Improved Native Unified Multimodal Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Show-o2: Improved Native Unified Multimodal Models

Reference 46

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.113006Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a0811705-ddff-44b3-bd81-7a3f14c18916 · outbound

This paper cites VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models

Reference 47

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.138864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 9e3482fc-0701-46c0-8218-8693526b6cbe · outbound

This paper cites MMaDA: Multimodal Large Diffusion Language Models.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation MMaDA: Multimodal Large Diffusion Language Models

Reference 48

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.129679Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1dd6f632-2917-4b90-9e78-3438c90654cb · outbound

This paper cites ImgEdit: A Unified Image Editing Dataset and Benchmark.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation ImgEdit: A Unified Image Editing Dataset and Benchmark

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.154165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e54215e6-0e04-43d0-937d-becee4f02a46 · outbound

This paper cites Llada-o: An effective and length-adaptive omni diffusion model.arXiv preprint arXiv:2603.01068.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Llada-o: An effective and length-adaptive omni diffusion model.arXiv preprint arXiv:2603.01068

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.189154Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 0d4639ad-a10a-4ed7-bc50-b533bc33d46a · outbound

This paper cites Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.150877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1a465710-521a-472a-8533-a8a4f9e8c82f · outbound

This paper cites MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.111865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation cf1e5e24-eef8-46fd-9f45-268c9e4766cd · outbound

This paper cites PixelDiT: Pixel Diffusion Transformers for Image Generation.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation PixelDiT: Pixel Diffusion Transformers for Image Generation

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.212501Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation dce48e95-9d8f-475e-95de-a077b01672f5 · outbound

This paper cites Uniflow: A unified pixel flow tokenizer for visual understanding and generation.arXiv preprint arXiv:2510.10575.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Uniflow: A unified pixel flow tokenizer for visual understanding and generation.arXiv preprint arXiv:2510.10575

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.144460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 6e715181-b3df-4444-bf5c-054d92fbe1bd · outbound

This paper cites Penguin-vl: Exploring the efficiency limits of vlm with llm-based vision encoders.arXiv preprint arXiv:2603.06569, 2026a.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Penguin-vl: Exploring the efficiency limits of vlm with llm-based vision encoders.arXiv preprint arXiv:2603.06569, 2026a

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.122848Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation a4cd0c68-afba-4977-9d8b-f5f60c3df444 · outbound

This paper cites Diffusion Transformers with Representation Autoencoders.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Diffusion Transformers with Representation Autoencoders

Reference 56

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.141634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8c462b17-eef0-4708-bb87-b3f03c431587 · outbound

This paper cites Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-20T23:43:51.227568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation c276a854-1ceb-4b4a-9443-5f50ba344815 · outbound

This paper cites Scaling zero-shot reference-to-video generation.arXiv preprint arXiv:2512.06905.

Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation Scaling zero-shot reference-to-video generation.arXiv preprint arXiv:2512.06905

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-20T23:43:51.174771Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Pith citing papers

Observation 5cd4c18f-214b-4a12-8456-b454291dc81c · inbound

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation cites this paper.

STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-05-11T02:45:57.023589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 79cb73b9-d6e8-4043-be91-48f40f65f8aa · inbound

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm cites this paper.

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-05-13T06:07:22.907523Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation f919d687-9f33-4bbc-91b7-f97d15e76730 · inbound

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm cites this paper.

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-01T14:05:46.658675Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 7e87a0de-826d-44e1-b9fd-4df531930344 · inbound

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture cites this paper.

SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-unify Architecture Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 85

Resolution: verified exact; local_arxiv, observed 2026-05-13T05:17:18.656071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation eecd669e-9280-4a33-9e24-cb7ad660f112 · inbound

Lance: Unified Multimodal Modeling by Multi-Task Synergy cites this paper.

Lance: Unified Multimodal Modeling by Multi-Task Synergy Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 78

Resolution: verified exact; local_arxiv, observed 2026-05-20T11:48:14.832936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 1841f1f9-3efe-45ae-ad77-4ed7a70d1b87 · inbound

Lance: Unified Multimodal Modeling by Multi-Task Synergy cites this paper.

Lance: Unified Multimodal Modeling by Multi-Task Synergy Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 79

Resolution: verified exact; local_arxiv, observed 2026-05-21T07:59:50.672370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation ecb394ca-831f-4321-9ff1-79a7ca9d4c73 · inbound

Toward Native Multimodal Modeling: A Roadmap cites this paper.

Toward Native Multimodal Modeling: A Roadmap Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-06-29T23:04:01.807470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation aaae50c0-09d6-4294-91d0-c03f773b6f88 · inbound

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning cites this paper.

How and What to Imagine? Visual Thinking in Unified Multimodal Models for Cross-View Spatial Reasoning Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-29T18:23:50.680893Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 057076fe-1fe7-45c2-b07d-830f1064b729 · inbound

Representation Forcing for Bottleneck-Free Unified Multimodal Models cites this paper.

Representation Forcing for Bottleneck-Free Unified Multimodal Models Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-07-01T19:16:00.974604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 3fd2ec9a-f921-45db-a224-2f68be5cd6e7 · inbound

Representation Forcing for Bottleneck-Free Unified Multimodal Models cites this paper.

Representation Forcing for Bottleneck-Free Unified Multimodal Models Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-12T15:31:57.426559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce8add9b-090a-4cf1-9c68-236101331b6c · inbound

LLM can Read Spectrogram: Encoder-free Speech-Language Modeling cites this paper.

LLM can Read Spectrogram: Encoder-free Speech-Language Modeling Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-03T03:47:35.738546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation b55fc75b-67a4-49dd-a29b-6a47fc00ccde · inbound

LLM can Read Spectrogram: Encoder-free Speech-Language Modeling cites this paper.

LLM can Read Spectrogram: Encoder-free Speech-Language Modeling Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-03T23:59:06.141726Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 8c24bcf8-cb8a-4126-9c27-970d8c9c3642 · inbound

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation cites this paper.

IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 25

Resolution: metadata mismatch; local_arxiv, observed 2026-07-04T16:39:58.204439Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 08c59d78-89a3-47f3-89a3-027c525b7e77 · inbound

GEAR: Guided End-to-End AutoRegression for Image Synthesis cites this paper.

GEAR: Guided End-to-End AutoRegression for Image Synthesis Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-01T10:35:42.603436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation 10f0d88f-3a7f-4a92-9a22-8170a221360b · inbound

APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts cites this paper.

APIVOT: Adaptive Planning with Interleaved Vision-Language Thoughts Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-07-10T13:37:06.882491Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.

Observation e72af9cb-8b76-4ba0-9cf0-57fbbfa3ebad · inbound

STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs cites this paper.

STBridge: Shared-Target Alignment for Bridging Understanding and Generation in UMMs Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T18:56:57.561814Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 376e13c2-d6df-4e2b-b34a-86dc7b3a7e44 · inbound

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes cites this paper.

Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-06T11:55:27.994286Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.