Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers | Paper Citation Record

Observation ed5fd672-e20c-400b-b421-ef3dd71676cc · outbound

This paper cites Krea 2.https://www.krea.ai/blog/krea-2-technical-report, 2026.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Krea 2.https://www.krea.ai/blog/krea-2-technical-report, 2026

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:52.799777Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00275228-a364-4051-9e69-bf4a7045e746 · outbound

This paper cites Qwen3-VL Technical Report.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Qwen3-VL Technical Report

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:52.918201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3aae196b-5f7c-41b3-9161-e033d66ac249 · outbound

This paper cites Qwen2.5-VL Technical Report.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Qwen2.5-VL Technical Report

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.011945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c258eae7-a2a5-4276-9a6c-8c293a3dc5a9 · outbound

This paper cites All are worth words: A vit backbone for diffusion models.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers All are worth words: A vit backbone for diffusion models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.103906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7547b882-7e87-414b-a744-2b31eeb8251d · outbound

This paper cites Why do LLMs attend to the first token?.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Why do LLMs attend to the first token?

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.224227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation def04688-54ab-4390-a77a-09fd2f1a4675 · outbound

This paper cites Pixart-σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Pixart-σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.497214Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f7afd5c-4ddd-4287-84fd-4dcf90f6cc52 · outbound

This paper cites Revealing the attention floating mechanism in masked diffusion models.arXiv preprint arXiv:2601.07894, 2026.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Revealing the attention floating mechanism in masked diffusion models.arXiv preprint arXiv:2601.07894, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.591968Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d05e40a0-274c-4cf7-a23c-5e4e3f987189 · outbound

This paper cites Vision transformers need registers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Vision transformers need registers

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.651927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55ebf71c-fcbf-41d6-bb2b-7ce7e0204c2d · outbound

This paper cites Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Diffusion models beat gans on image synthesis.Advances in neural information processing systems, 34:8780–8794, 2021

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.710242Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 972615ac-f152-47c6-bda1-362ee94d5cb8 · outbound

This paper cites Scaling rectified flow transformers for high-resolution image synthesis.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Scaling rectified flow transformers for high-resolution image synthesis

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.769965Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 36f981b6-bb10-4ddd-81f4-3ea6dfe240cb · outbound

This paper cites MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:53.938768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8af1125a-2db2-4d65-b4fe-e7547c9015fa · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.Advances in Neural Information Processing Systems, 36:52132–52152, 2023.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Geneval: An object-focused framework for evaluating text-to-image alignment.Advances in Neural Information Processing Systems, 36:52132–52152, 2023

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.101515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf9b2b1d-7f8f-4f8d-a451-0908b085667d · outbound

This paper cites When attention sink emerges in language models: An empirical view.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers When attention sink emerges in language models: An empirical view

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.232383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1c2eb649-ccb4-42b1-a613-5a0adcff069e · outbound

This paper cites ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.283706Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b07286-5e14-4493-8628-f916b0686bc3 · outbound

This paper cites Classifier-Free Diffusion Guidance.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Classifier-Free Diffusion Guidance

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.344837Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47de641d-9517-43a0-a468-e2d695216dc7 · outbound

This paper cites Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Denoising diffusion probabilistic models.Advances in neural information processing systems, 33:6840–6851, 2020

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.409820Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b7b2e25-e437-4429-a7e1-a39d13a30ae5 · outbound

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

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.469069Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74f9ee19-b2c6-4420-a524-ae5ff5ffe928 · outbound

This paper cites Diffusion transformers use sink registers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Diffusion transformers use sink registers

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.511807Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9fdeb14-72e5-4e36-ba7e-c387fd53d6c6 · outbound

This paper cites Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515, 2024.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Minference 1.0: Accelerating pre-filling for long-context llms via dynamic sparse attention.Advances in Neural Information Processing Systems, 37:52481–52515, 2024

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.571160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9133c5f7-b234-4653-b523-6150df645b5a · outbound

This paper cites Vision transformers don’t need trained registers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Vision transformers don’t need trained registers

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.638521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5b66a19-8b7a-43b8-b13f-0909d0cc1a4a · outbound

This paper cites See What You Are Told: Visual Attention Sink in Large Multimodal Models.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers See What You Are Told: Visual Attention Sink in Large Multimodal Models

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.711000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c37f7209-7b1d-4eb1-bfc1-d9fc7964b08e · outbound

This paper cites Flux.https://github.com/black-forest-labs/flux, 2024.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Flux.https://github.com/black-forest-labs/flux, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.786395Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 964c0d47-ff42-4f60-8204-97f31703bdb7 · outbound

This paper cites FLUX.2.https://bfl.ai/blog/flux-2, 2025.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers FLUX.2.https://bfl.ai/blog/flux-2, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.841306Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a9ea87f-7eb1-43c0-bf44-e36ff981c03c · outbound

This paper cites Remarkable robustness of llms: Stages of inference? Advances in Neural Information Processing Systems, 38:130050–130083, 2026.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Remarkable robustness of llms: Stages of inference? Advances in Neural Information Processing Systems, 38:130050–130083, 2026

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.889184Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04cc3de6-669c-4141-a719-37c79c982594 · outbound

This paper cites FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:54.951687Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bcbbeca9-3a29-42a9-878e-b11c0b38861e · outbound

This paper cites Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.041601Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74e748d0-5c55-4e63-85e4-65ebde2136a8 · outbound

This paper cites Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970, 2024.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Snapkv: Llm knows what you are looking for before generation.Advances in Neural Information Processing Systems, 37:22947–22970, 2024

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.133494Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82787b11-7954-4c20-b39a-38a28326eaad · outbound

This paper cites Flow Matching for Generative Modeling.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Flow Matching for Generative Modeling

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.212873Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d26d798-fda6-4528-b34f-1e777e879fa6 · outbound

This paper cites Step1X-Edit: A Practical Framework for General Image Editing.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Step1X-Edit: A Practical Framework for General Image Editing

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.306981Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 15d6635e-f971-460d-b56f-74ef53175989 · outbound

This paper cites Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time.Advances in Neural Information Processing Systems, 36:52342–52364, 2023.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time.Advances in Neural Information Processing Systems, 36:52342–52364, 2023

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.414673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a6a16b-11aa-49fc-a8f8-3a47fa8f8107 · outbound

This paper cites Rethinking cross-modal interaction in multimodal diffusion transformers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Rethinking cross-modal interaction in multimodal diffusion transformers

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.546543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 528b5a11-d8fe-4503-b45c-ffce51ca280d · outbound

This paper cites Hpsv3: Towards wide-spectrum human preference score.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Hpsv3: Towards wide-spectrum human preference score

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.731288Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6e6fa3b4-2147-4948-9cb2-504a577b5930 · outbound

This paper cites DiffSynth-Studio.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers DiffSynth-Studio

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.863673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64c79edb-1053-4b91-8866-5c9f94021bd3 · outbound

This paper cites Improved denoising diffusion probabilistic models.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Improved denoising diffusion probabilistic models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:55.958079Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73431231-0fab-4778-860a-afe8d9cb81a6 · outbound

This paper cites Scalable diffusion models with transformers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Scalable diffusion models with transformers

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.157834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 18a4fc37-b5c2-47e4-b27e-b68477a11a57 · outbound

This paper cites Sdxl: Improving latent diffusion models for high-resolution image synthesis.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Sdxl: Improving latent diffusion models for high-resolution image synthesis

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.295492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a73e2805-7315-47ff-95fd-a527cb241849 · outbound

This paper cites Attention sinks and compression valleys in llms are two sides of the same coin.arXiv preprint arXiv:2510.06477, 2025.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Attention sinks and compression valleys in llms are two sides of the same coin.arXiv preprint arXiv:2510.06477, 2025

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.408302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70a6a3a3-274f-46a6-a6cd-9fbfb14cb64f · outbound

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

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Learning transferable visual models from natural language supervision

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.577719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 237c1009-8b9c-4561-a86a-f8d5b0fcf5e1 · outbound

This paper cites Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Exploring the limits of transfer learning with a unified text-to-text transformer.Journal of machine learning research, 21(140):1–67, 2020

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.693770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c2dca0f-d5bb-4976-9705-f0b4612addae · outbound

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

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers High-resolution image synthesis with latent diffusion models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.803780Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1f499106-9519-4fd2-89be-36d0be2bf6fa · outbound

This paper cites Attention sinks in diffusion language models.arXiv preprint arXiv:2510.15731, 2025.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Attention sinks in diffusion language models.arXiv preprint arXiv:2510.15731, 2025

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.887020Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44e36ff8-25f4-4c97-a5a4-d75688bb3575 · outbound

This paper cites Exploring multimodal diffusion transformers for enhanced prompt-based image editing.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Exploring multimodal diffusion transformers for enhanced prompt-based image editing

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:56.978686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19630ee3-7318-44bd-b0cc-a31e23d98af6 · outbound

This paper cites DINOv3.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers DINOv3

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.055084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2861eaf-dc50-4a82-bdc2-3b0c42dc245c · outbound

This paper cites Denoising Diffusion Implicit Models.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Denoising Diffusion Implicit Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.150126Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a502d2f-89d3-437e-8512-13cb6c9718e1 · outbound

This paper cites Score-Based Generative Modeling through Stochastic Differential Equations.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Score-Based Generative Modeling through Stochastic Differential Equations

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.209122Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fad91a25-f3de-4c12-8649-8e19869de2a2 · outbound

This paper cites Registers Matter for Pixel-Space Diffusion Transformers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Registers Matter for Pixel-Space Diffusion Transformers

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.302343Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f39f12d3-f021-4699-939d-3efa67c21e5e · outbound

This paper cites Massive Activations in Large Language Models.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Massive Activations in Large Language Models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.390684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 11ea65a6-6a70-41a1-90b6-c941b52139c7 · outbound

This paper cites Razorattention: Efficient kv cache compression through retrieval heads.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Razorattention: Efficient kv cache compression through retrieval heads

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.480162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20a28329-c971-418d-8512-f362a78b0b91 · outbound

This paper cites Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.560088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13c1d7ff-e5a2-4799-b431-504114993ff2 · outbound

This paper cites Qwen-Image-2512-Turbo-LoRA-2-Steps.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Qwen-Image-2512-Turbo-LoRA-2-Steps

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.631075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 924779ec-1970-4f3a-8fea-1e1009829c00 · outbound

This paper cites Fasa: Frequency-aware sparse attention.arXiv preprint arXiv:2602.03152, 2026.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Fasa: Frequency-aware sparse attention.arXiv preprint arXiv:2602.03152, 2026

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.731544Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f3048d-5100-4a41-838e-d1c77988c5e8 · outbound

This paper cites Qwen-Image Technical Report.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Qwen-Image Technical Report

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.808405Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc0064a2-54e5-4e0f-a0f0-2ef7f616a75d · outbound

This paper cites Attention Sinks in Diffusion Transformers: A Causal Analysis.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Attention Sinks in Diffusion Transformers: A Causal Analysis

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.876482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d5b18ea-6a8f-47d9-921a-35c8ab42c2ef · outbound

This paper cites Efficient streaming language models with attention sinks.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Efficient streaming language models with attention sinks

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:57.941108Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d7a165d-24fc-476a-a30e-80f5e4f0c854 · outbound

This paper cites Duoattention: Efficient long-context llm inference with retrieval and streaming heads.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Duoattention: Efficient long-context llm inference with retrieval and streaming heads

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.000723Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17693f33-97a7-4bda-abb6-2113260ceaf7 · outbound

This paper cites Rethinking Cross-Layer Information Routing in Diffusion Transformers.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Rethinking Cross-Layer Information Routing in Diffusion Transformers

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.077386Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0695804-9f58-40ad-879c-bffcaf33df39 · outbound

This paper cites On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers On the Nature of Attention Sink that Shapes Decoding Strategy in Omni-LLMs

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.191704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 187948a6-f9bc-4db3-80fd-a16f6f262228 · outbound

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

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers The unreasonable effectiveness of deep features as a perceptual metric

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.287501Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 976841c5-3d91-40dd-bb1f-3ed1fb9d7e6b · outbound

This paper cites H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36:34661–34710, 2023

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.362255Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1d17a784-04ab-4b32-8988-f90cbf5718cb · outbound

This paper cites Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps.

Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-01T13:25:58.421803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers