Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining | Paper Citation Record

Observation 602fed6f-7d05-4df8-87ff-2c1d7997c77b · inbound

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer cites this paper.

Bag of Design Choices for Inference of High-Resolution Masked Generative Transformer Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:23:16.608097Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 75412ecb-9e26-49f5-adc9-a0033df6ccd8 · inbound

Continuous Speculative Decoding for Autoregressive Image Generation cites this paper.

Continuous Speculative Decoding for Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T18:38:40.166488Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ab9b0db-78f6-4386-8037-753973592291 · inbound

High-Resolution Image Synthesis via Next-Token Prediction cites this paper.

High-Resolution Image Synthesis via Next-Token Prediction Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-12T14:55:42.128419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE cites this paper.

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.

Observation 324b261a-1d65-47fa-9985-edba713facc7 · inbound

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient cites this paper.

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-12T12:06:01.000349Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10aaa647-03bb-4b2b-bdcc-5bfc0ec078e2 · inbound

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation cites this paper.

OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T11:10:54.689429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6577574b-44c9-47d8-a068-36bed90e6a6a · inbound

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

Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-12T10:35:22.651398Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3ca134d0-1df1-47ed-b85b-00d74882ee49 · inbound

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation cites this paper.

Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-12T04:50:49.145289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31cde6aa-6ae1-4f83-842c-bddaf0fc6804 · inbound

X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models cites this paper.

X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-12T00:56:59.639527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd2555aa-4a88-491b-aa82-b381cddce663 · inbound

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

TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-11T22:54:20.534492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62571cf7-2789-4a08-865d-877163f7177c · inbound

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance cites this paper.

ILLUME: Illuminating Your LLMs to See, Draw, and Self-Enhance Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-11T19:29:52.643443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dce2f0c-126c-4b86-92b1-74f7830d77bc · inbound

Doe-1: Closed-Loop Autonomous Driving with Large World Model cites this paper.

Doe-1: Closed-Loop Autonomous Driving with Large World Model Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-11T16:55:42.337407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5b47ab1-12f1-45d0-865a-28405a8645ea · inbound

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling cites this paper.

E-CAR: Efficient Continuous Autoregressive Image Generation via Multistage Modeling Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T12:28:54.819899Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d58b3ad1-85fe-452a-9860-ccbba45bc9f2 · inbound

Parallelized Autoregressive Visual Generation cites this paper.

Parallelized Autoregressive Visual Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-11T11:42:31.652085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 95406ae6-48ce-46d5-85ba-f8430b58703a · inbound

LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models cites this paper.

LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-08T15:46:22.091202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fbc2086-64f5-42a4-a939-35f47d22c474 · inbound

Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT cites this paper.

Lumina-Video: Efficient and Flexible Video Generation with Multi-scale Next-DiT Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-08T14:26:46.753819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e773658c-3710-4996-9cd0-ffd41c0fdb40 · inbound

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation cites this paper.

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T20:21:30.454426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d25135a-805d-4efd-97eb-8ddf379ddc46 · inbound

Personalized Text-to-Image Generation with Auto-Regressive Models cites this paper.

Personalized Text-to-Image Generation with Auto-Regressive Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:17:25.499383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 064ad557-cccb-4a1e-b1a5-6c67ea977343 · inbound

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens cites this paper.

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T11:48:03.314257Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e40635f-87ab-4833-a682-775729566e80 · inbound

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models cites this paper.

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-16T10:35:43.582377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26bc7693-c9e1-4dce-ab19-04882e189e26 · inbound

IA-T2I: Internet-Augmented Text-to-Image Generation cites this paper.

IA-T2I: Internet-Augmented Text-to-Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:17:26.115967Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70c81c4b-9bab-4fa5-a1e3-9800cc299360 · inbound

ChemMLLM: Chemical Multimodal Large Language Model cites this paper.

ChemMLLM: Chemical Multimodal Large Language Model Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T15:06:06.405683Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f04e4ae7-fcef-48e0-92e0-93a264e8f051 · inbound

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving cites this paper.

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-15T19:19:42.913849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 1adb9af2-121c-41eb-81d2-c622f8fed257 · inbound

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression cites this paper.

Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T14:16:15.891755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62cec599-c947-4a54-b4b7-ad3b636aa6b3 · inbound

StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation cites this paper.

StyleAR: Customizing Multimodal Autoregressive Model for Style-Aligned Text-to-Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T14:09:47.643689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

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

UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning cites this paper.

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 d6250347-bda3-4597-adbc-03089dc1fd81 · inbound

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

Muddit: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 13

Resolution: verified exact; arxiv_id, observed 2026-05-19T13:02:18.336941Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 49d3edac-ad4b-4652-88dc-a6fa4324f036 · inbound

Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation cites this paper.

Draw ALL Your Imagine: A Holistic Benchmark and Agent Framework for Complex Instruction-based Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:18:33.551160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 706012d4-a61f-401b-95a4-d33aad107f67 · inbound

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping cites this paper.

SkipVAR: Accelerating Visual Autoregressive Modeling via Adaptive Frequency-Aware Skipping Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T05:05:00.140921Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cce00cd-11e6-4d63-954a-b2f9934dd839 · inbound

RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought cites this paper.

RealSR-R1: Reinforcement Learning for Real-World Image Super-Resolution with Vision-Language Chain-of-Thought Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-05-19T08:33:02.136479Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5ea88251-6d04-4cff-842b-fd6359a7cac2 · inbound

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation cites this paper.

CycleVAR: Repurposing Autoregressive Model for Unsupervised One-Step Image Translation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:49:43.534834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d2bd89df-c72d-4e5d-8a5c-2f7b2e9f196a · inbound

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer cites this paper.

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T19:41:23.716761Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bc01014-fdca-4031-bfd8-854eff4a6a24 · inbound

Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation cites this paper.

Resurrect Mask AutoRegressive Modeling for Efficient and Scalable Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T16:37:35.505153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972c0fe8-36b9-454e-9097-5702aad21a43 · inbound

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling cites this paper.

Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 2014

Resolution: unresolved; no resolver link, observed 2026-08-15T18:22:42.168483Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59f2878a-3c54-45c2-be29-4e07cec1fb49 · inbound

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation cites this paper.

UNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T23:23:58.677295Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0905e324-4926-43f8-972c-984ff983303d · inbound

Exploring Autoregressive Vision Foundation Models for Image Compression cites this paper.

Exploring Autoregressive Vision Foundation Models for Image Compression Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-05T05:36:53.233971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a58b564-e316-4d5e-a931-3b5911feffed · inbound

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation cites this paper.

Speculative Coupled Decoding for Training-Free Lossless Acceleration of Autoregressive Visual Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-18T03:20:48.740044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 253ed8bd-367d-458c-8b6d-5b0899881c0e · inbound

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping cites this paper.

VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-17T21:35:17.580852Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 5d334b33-de6f-4a3d-a3ab-566b9c84a901 · inbound

dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models cites this paper.

dMLLM-TTS: Self-Verified and Efficient Test-Time Scaling for Diffusion Multi-Modal Large Language Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-16T20:38:24.554015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 68de935d-430c-48c8-b6cd-1b6821744d63 · inbound

SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation cites this paper.

SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-13T22:30:39.049531Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1849eba3-8fac-4819-b16b-f7b260442cf6 · inbound

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting cites this paper.

Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 19

Resolution: metadata mismatch; arxiv_id, observed 2026-05-14T22:08:04.950577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation d2a25238-8249-4e0f-a039-27e2163dfca9 · inbound

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation cites this paper.

MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-11T05:40:58.100853Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 47a61f61-ab51-416c-bde0-838e6bae69a0 · inbound

Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale cites this paper.

Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-10T10:14:10.770184Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a4c460ff-9f89-481a-b00c-da3616c772c1 · inbound

TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering cites this paper.

TextGround4M: A Prompt-Aligned Dataset for Layout-Aware Text Rendering Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 2

Resolution: metadata mismatch; arxiv_id, observed 2026-05-11T21:46:37.722392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 51cdcfe1-67c0-418a-9f68-24f7917fab1b · inbound

OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation cites this paper.

OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 46

Resolution: verified exact; arxiv_id, observed 2026-05-11T20:31:11.069089Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 12335dc9-37c8-408d-8b8d-b255ea492955 · inbound

CASCADE: Context-Aware Relaxation for Speculative Image Decoding cites this paper.

CASCADE: Context-Aware Relaxation for Speculative Image Decoding Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 28

Resolution: verified exact; arxiv_id, observed 2026-05-11T03:55:55.170887Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 6784e666-fbbb-45ff-a168-3c220c213ace · inbound

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation cites this paper.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-12T02:21:16.463596Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 23a5030c-42ef-4c75-8a0a-fd9a0293c645 · inbound

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation cites this paper.

FlashAR: Efficient Post-Training Acceleration for Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T06:02:23.659868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f8f0abe7-a300-4f66-ba5a-538d9d175aa8 · inbound

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving cites this paper.

DeepSight: Long-Horizon World Modeling via Latent States Prediction for End-to-End Autonomous Driving Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 125

Resolution: metadata mismatch; arxiv_id, observed 2026-05-12T06:31:26.229126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8389d4b9-e0ff-4288-9d2a-07a3b79fa962 · inbound

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution cites this paper.

Hierarchical Image Tokenization for Multi-Scale Image Super Resolution Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-06-30T21:15:04.280295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation ff6b55aa-22f3-4d85-86b6-41417a31e54b · inbound

Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation cites this paper.

Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 6

Resolution: verified exact; arxiv_id, observed 2026-06-28T22:42:46.717969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation e145c616-d838-4db0-907f-0ff8c6e91adf · inbound

Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs cites this paper.

Polaris: Scaling Up Instruction-Guided Image Generation Towards Millions of Personalized Style Needs Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 21

Resolution: metadata mismatch; arxiv_id, observed 2026-07-01T22:46:18.719326Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 01af4b66-d9ae-4ba2-83dc-32fef732688e · inbound

Parallel Jacobi Decoding for Fast Autoregressive Image Generation cites this paper.

Parallel Jacobi Decoding for Fast Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:26:57.136218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b02c2aed-bc8b-4cb6-afa6-d86d8910cb60 · inbound

Knowledge Distillation for Visual Autoregressive Models cites this paper.

Knowledge Distillation for Visual Autoregressive Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-07-02T12:36:56.883793Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2eb5c7f6-2ff7-426a-a41f-52ab3fd1cc5b · inbound

SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation cites this paper.

SSD: Spatially Speculative Decoding Accelerates Autoregressive Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 26

Resolution: verified exact; arxiv_id, observed 2026-07-04T03:49:30.630557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 30cbcc5d-0224-4654-a5f0-3a94e05ddaf5 · inbound

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation cites this paper.

From Open Loop to Closed Loop: A Test-Time Iterative Optimization Framework for Reference-Consistent Image Generation Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-11T15:05:11.166049Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d14b4f97-c2a7-4db3-acd5-ff77c4eea622 · inbound

Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models cites this paper.

Think, Plan, Paint: Layout-Aware Reasoning for Controllable Image Generation in Unified Models Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T21:07:59.570641Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4586da7-a100-48dc-81c0-b86d38c43ba2 · inbound

SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model cites this paper.

SynVAR: Synergizing Spatial and Semantic Alignment in Visual Autoregressive Model Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T00:44:45.940588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers