Paper Citation Record · LEDGER

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

As of 7 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 7 inbound Pith citation observations for arXiv:2505.23380.

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

pith.paper-citation-record.v1
2505.23380 v1

Coverage vector

measured 51 of 51 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:53:27.275816Z

measured 58 of 58 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-07T06:34:17.273281+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-04T22:36:08.089323Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-04T13:39:51.505020Z

Reference resolution

51 of 51 outbound references displayed

verified exact1
verified fuzzy6
unresolved44
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation aec5fbc9-7aeb-4bbe-a4ec-b481b7096a02 · outbound

This paper cites Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.247048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58bb2215-a757-4c2a-965b-9064c404f0fa · outbound

This paper cites Gemini: A Family of Highly Capable Multimodal Models.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Gemini: A Family of Highly Capable Multimodal Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.392275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b548974f-40f1-47cd-8543-216fa5d1fe4e · outbound

This paper cites Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.498548Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de27a906-4d36-4c4a-a3db-7a66dbc3c57d · outbound

This paper cites SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.647902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5188efac-6b8d-4830-88d7-73269d8607d5 · outbound

This paper cites MMDetection: Open MMLab Detection Toolbox and Benchmark.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning MMDetection: Open MMLab Detection Toolbox and Benchmark

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.803824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 451f3035-a90e-470e-9aec-921385dd5ba2 · outbound

This paper cites Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:21.903111Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20b0f5b4-8f58-44e8-a842-3f91de0cca06 · outbound

This paper cites Schwing, Alexander Kirillov, and Rohit Girdhar.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Schwing, Alexander Kirillov, and Rohit Girdhar

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:30.932772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dd42ec44-cf96-4338-868e-c364240aa56b · outbound

This paper cites Baldridge, Roopal Garg, Peter Anderson, Ranjay Krishna, Mohit Bansal, Jordi Pont-Tuset, and Su Wang.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Baldridge, Roopal Garg, Peter Anderson, Ranjay Krishna, Mohit Bansal, Jordi Pont-Tuset, and Su Wang

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:30.653559Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 9dc2eece-21b3-4a7d-a269-9cd6afc167cb · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:22.203748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9db14ca-f33c-4c9c-a4ac-1bcc3f660906 · outbound

This paper cites DreamLLM: Synergistic multimodal comprehension and creation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning DreamLLM: Synergistic multimodal comprehension and creation

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:22.295884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8db548b-d4fe-41f3-a841-c5bd44d5cf05 · outbound

This paper cites An image is worth 16x16 words: Transformers for image recognition at scale.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning An image is worth 16x16 words: Transformers for image recognition at scale

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:30.410352Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation ba29a64c-395e-4fe1-afd7-b2d004a890d3 · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Taming transformers for high-resolution image synthesis

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:30.134836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 66ebf948-5046-4075-86b9-878955536ed3 · outbound

This paper cites SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:22.622402Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 018ec1df-5998-4250-a5a9-2177b76fca32 · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Geneval: An object-focused framework for evaluating text-to-image alignment

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:22.801107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e8053ea-4c2d-445e-aebf-e7b2b1ee8a09 · outbound

This paper cites Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:22.895103Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b0265b6-958f-4093-95cd-96faa8adc758 · outbound

This paper cites OpenAI o1 System Card.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning OpenAI o1 System Card

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.010341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 668be6c0-d07f-4c16-b854-b3f4c42bb6ef · outbound

This paper cites Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.148041Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c634cf9-a721-40d5-8aac-613f2429c5f9 · outbound

This paper cites Imagine while Reasoning in Space: Multimodal Visualization-of-Thought.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Imagine while Reasoning in Space: Multimodal Visualization-of-Thought

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.280824Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4fa1d2f-af8a-4a60-aea4-08ba69542773 · outbound

This paper cites SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning SynerGen-VL: Towards Synergistic Image Understanding and Generation with Vision Experts and Token Folding

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.378411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 43be3b75-d5fa-411d-a840-991ebc006b4b · outbound

This paper cites OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning OmniFlow: Any-to-Any Generation with Multi-Modal Rectified Flows

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.481480Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e9ad2e1-f710-4333-9696-fce27c100765 · outbound

This paper cites Evaluating object hallucination in large vision-language models.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Evaluating object hallucination in large vision-language models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:29.928449Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation fc666632-e083-4888-866b-1ae50628efdb · outbound

This paper cites Textbooks Are All You Need II: phi-1.5 technical report.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Textbooks Are All You Need II: phi-1.5 technical report

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.636560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c72fe73b-cab8-499d-8243-8f62cb7fce89 · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.757213Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51de8089-3bda-4734-b1ce-cfd61af89862 · outbound

This paper cites World model on million-length video and language with ringattention.arXiv preprint, 2024.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning World model on million-length video and language with ringattention.arXiv preprint, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:23.884539Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2e40da-f413-46e3-91e8-cafa6f0483eb · outbound

This paper cites Llava-next: Improved reasoning, ocr, and world knowledge, 2024.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Llava-next: Improved reasoning, ocr, and world knowledge, 2024

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:24.079598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd8acce9-ac40-4322-a4be-1e017b220653 · outbound

This paper cites Visual instruction tuning.NeurIPS, 36, 2024.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Visual instruction tuning.NeurIPS, 36, 2024

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:24.253921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7a0385d-c4bf-4561-aeb5-f7d4665e6dd0 · outbound

This paper cites JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:24.426795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abbcd6f8-fb9e-4226-bd62-53b52b9d3f5c · outbound

This paper cites UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:24.588515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ed1468c-7cf9-4a0c-b1c7-8dcfafffb433 · outbound

This paper cites TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:24.689189Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7ab2202-5522-41f1-b062-d5223aef3e5a · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Learning transferable visual models from natural language supervision

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:53:29.228511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation dc850bae-8438-49fc-b1eb-d0faf2e5271d · outbound

This paper cites Manning, Stefano Ermon, and Chelsea Finn.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Manning, Stefano Ermon, and Chelsea Finn

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.018029Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 971cb1b3-6d1f-49e9-bc2e-e50d243c1c7d · outbound

This paper cites Proximal Policy Optimization Algorithms.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Proximal Policy Optimization Algorithms

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.202348Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62ac2f3a-ce0f-4374-8b79-36b0b4b1a2de · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.336876Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05dac12b-2ec1-4114-b49e-baa9bdda25cf · outbound

This paper cites LMFusion: Adapting Pretrained Language Models for Multimodal Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning LMFusion: Adapting Pretrained Language Models for Multimodal Generation

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.463377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b70c008-595a-485d-b86a-263d5d806029 · outbound

This paper cites Journeydb: A benchmark for generative image understanding.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Journeydb: A benchmark for generative image understanding

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.595623Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16b7d5a9-ffd4-40e9-a283-5569a2b83d4b · outbound

This paper cites Emu: Generative pretraining in multimodality.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Emu: Generative pretraining in multimodality

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.723242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2a227863-0077-490b-81b3-7e8ae235e776 · outbound

This paper cites Any-to-any generation via composable diffusion.NeurIPS, 36, 2024.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Any-to-any generation via composable diffusion.NeurIPS, 36, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.798707Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation de4c8042-f473-4ec0-be7e-fa036b0c4a4a · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Chameleon: Mixed-Modal Early-Fusion Foundation Models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.864139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc8082fa-ff6c-40a4-86de-58673450e2ed · outbound

This paper cites MetaMorph: Multimodal Understanding and Generation via Instruction Tuning.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:25.933048Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9438d87-f325-472f-852a-a530122fe4ab · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning LLaMA: Open and Efficient Foundation Language Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.025472Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbde4961-f1a8-460f-a1a2-23d466d71dd6 · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Emu3: Next-Token Prediction is All You Need

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.121878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b1f686e-b87c-4b9a-a8fa-b6dced2d1622 · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.245919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e308dcb7-501d-44bf-9a0f-d4708432b45f · outbound

This paper cites Liquid: Language Models are Scalable and Unified Multi-modal Generators.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Liquid: Language Models are Scalable and Unified Multi-modal Generators

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.366317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 727c3c1d-52ce-4d27-bf43-8b46fbc2fb7f · outbound

This paper cites NExT-GPT: Any-to-Any Multimodal LLM.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning NExT-GPT: Any-to-Any Multimodal LLM

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.460651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd41ded9-b835-43de-a77e-0011efa915fc · outbound

This paper cites VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.558833Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c66c372-c2ee-43d4-9d91-34869edf7d61 · outbound

This paper cites Show-o: One Single Transformer to Unify Multimodal Understanding and Generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Show-o: One Single Transformer to Unify Multimodal Understanding and Generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.689185Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17d2601d-6d50-4659-876f-f6998775a666 · outbound

This paper cites Qwen2.5-1M Technical Report.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Qwen2.5-1M Technical Report

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.847399Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 34296fd0-0dcc-4c8b-b655-9991d86c2266 · outbound

This paper cites Hermesflow: Seamlessly closing the gap in multimodal understanding and generation.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Hermesflow: Seamlessly closing the gap in multimodal understanding and generation

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:26.974393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 598112ee-2156-417e-9f68-063ebb26669d · outbound

This paper cites MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning MMMU: A massive multi-discipline multimodal understanding and reasoning benchmark for expert AGI

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:27.100136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1266f9e7-3c5b-4c78-baf3-94b4c1da3891 · outbound

This paper cites DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles.

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning DoraCycle: Domain-Oriented Adaptation of Unified Generative Model in Multimodal Cycles

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:53:27.611095Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation b7ac9371-df22-4361-af2c-b5731326aa0e · outbound

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-07T12:53:27.275816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation c63afbc4-b1d7-43af-ba5c-dc92b302b53b · inbound

Reconstruction Alignment Improves Unified Multimodal Models cites this paper.

Reconstruction Alignment Improves Unified Multimodal Models UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T22:36:08.089323Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1b38343b-63f0-4da6-9d9e-c2958e2738fb · inbound

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models cites this paper.

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T09:54:26.172394Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f65b3710-3e23-49d2-92cc-c271d97ff38f · inbound

LatentUMM: Dual Latent Alignment for Unified Multimodal Models cites this paper.

LatentUMM: Dual Latent Alignment for Unified Multimodal Models UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-20T12:43:17.438705Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation d3fe3d45-ba2a-4eb6-98ba-c8dccb1f69d1 · inbound

Toward Native Multimodal Modeling: A Roadmap cites this paper.

Toward Native Multimodal Modeling: A Roadmap UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 195

Resolution: verified exact; arxiv_id, observed 2026-06-29T23:04:01.711658Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation a4bd0c27-f7ff-4223-9366-d8b551a7fab2 · inbound

Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards cites this paper.

Ask, Solve, Generate: Self-Evolving Unified Multimodal Understanding and Generation via Self-Consistency Rewards UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-07-04T13:39:51.506849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.

Observation 75fc4684-086d-4358-8cb7-ba8102369c62 · inbound

Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning cites this paper.

Model Guides You How to Draw: Adaptive Visual Gating for Unified Multimodal Reasoning UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-14T01:07:06.861298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2b02145-2d74-4af7-b2cf-57e6af75cced · 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 UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T18:56:58.185926Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.