T2I-ConBench: Text-to-Image Benchmark for Continual Post-training | Paper Citation Record

Observation d23fab2d-abc6-47a1-b8b3-f6ce19f4cdb5 · outbound

This paper cites Denton, Seyed Kam- yar Seyed Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Denton, Seyed Kam- yar Seyed Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.451397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3174e729-9c2e-4178-b654-a243587e74ef · outbound

This paper cites High-resolution image synthesis with latent diffusion models.CVPR, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training High-resolution image synthesis with latent diffusion models.CVPR, 2022

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.225332Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 18a859ee-763e-4961-862d-6f69615eabe4 · outbound

This paper cites SDXL: improving latent diffusion models for high-resolution image synthesis.ICLR, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training SDXL: improving latent diffusion models for high-resolution image synthesis.ICLR, 2024

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:10.052350Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8660f1ac-1583-4092-8e17-03544e1cf11b · outbound

This paper cites Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.788926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 51df0d5d-8c5b-48f3-ae32-9a7a6d160fcc · outbound

This paper cites Pixart- Σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.ECCV, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Pixart- Σ: Weak-to-strong training of diffusion transformer for 4k text-to-image generation.ECCV, 2024

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.605079Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1204c36d-b25a-4ec3-b6dd-64d560252d46 · outbound

This paper cites A survey on personalized content synthesis with diffusion models.arXiv preprint arXiv:2405.05538, 2025.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A survey on personalized content synthesis with diffusion models.arXiv preprint arXiv:2405.05538, 2025

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:52.031267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e67113ad-e4c6-4abf-ae6a-1ec712148110 · outbound

This paper cites Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation.CVPR, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Dream- booth: Fine tuning text-to-image diffusion models for subject-driven generation.CVPR, 2023

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.325186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f62206f5-d5d4-4dba-b22f-cfaa5f4a7b71 · outbound

This paper cites Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Prompt to Polyp: Medical Text-Conditioned Image Synthesis with Diffusion Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:52.343614Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 70af777a-88be-4473-aef1-0bf49e0cccae · outbound

This paper cites Customizing text-to-image diffusion with object viewpoint control.SIGGRAPH Asia, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Customizing text-to-image diffusion with object viewpoint control.SIGGRAPH Asia, 2024

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:09.114093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 04db9b2b-35b7-4b2f-ae13-644731d47b1b · outbound

This paper cites Diffusion based augmenta- tion for captioning and retrieval in cultural heritage.ICCV (Workshops), 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Diffusion based augmenta- tion for captioning and retrieval in cultural heritage.ICCV (Workshops), 2023

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:08.852828Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 797ef686-d5e5-47ae-a984-0ef6433a30c1 · outbound

This paper cites Parameter-efficient transfer learning for NLP.ICML, 2019.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Parameter-efficient transfer learning for NLP.ICML, 2019

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:08.542457Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d7e051f0-fd1d-481d-b3a9-d0143fe6eedd · outbound

This paper cites an unresolved cited work.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:56:08.299598Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 203a61d0-7a10-4e40-acd9-9e05459748bb · outbound

This paper cites Towards a unified view of parameter-efficient transfer learning.ICLR, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Towards a unified view of parameter-efficient transfer learning.ICLR, 2022

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:08.080248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b0ad766b-96a0-4900-9632-ae40ff9cd1b9 · outbound

This paper cites Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities.NPJ Computational Materials, 2025.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities.NPJ Computational Materials, 2025

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:07.950358Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 20273b34-90d6-41dd-8c3a-7d7ceb5ab7e1 · outbound

This paper cites Continual diffusion: Continual customization of text-to-image diffusion with c-lora.Trans.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Continual diffusion: Continual customization of text-to-image diffusion with c-lora.Trans

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:07.820304Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 173bc682-3ef1-4664-8d37-e0861e1a3fca · outbound

This paper cites Continual training of language models for few-shot learning.EMNLP, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Continual training of language models for few-shot learning.EMNLP, 2022

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:07.579488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c7d5854b-3eeb-4e0c-9d2a-834a0c23b205 · outbound

This paper cites Continual pre-training of language models.ICLR, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Continual pre-training of language models.ICLR, 2023

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:07.438455Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65cc2fbb-c8e9-4cbb-bf6d-415de74a2568 · outbound

This paper cites an unresolved cited work.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Unresolved cited work

Reference 18

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:56:07.284173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 08ed5c58-1740-4f6c-80fb-d10a82d5712d · outbound

This paper cites Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.Psychological Review, 1990.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Connectionist models of recognition memory: constraints imposed by learning and forgetting functions.Psychological Review, 1990

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:07.113214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5db969ee-bc6f-4a89-91de-6d711c4d6e19 · outbound

This paper cites A comprehensive survey of continual learning: Theory, method and application.IEEE Trans.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A comprehensive survey of continual learning: Theory, method and application.IEEE Trans

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.979547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a210583-9fe8-4f7c-9f49-7084d8350af5 · outbound

This paper cites On Tiny Episodic Memories in Continual Learning.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training On Tiny Episodic Memories in Continual Learning

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:54.153379Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 186b16d5-54ac-46cc-aeb6-da1a12a46152 · outbound

This paper cites Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.884315Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 19c9bca7-ef7b-46e5-ac57-348212fe775b · outbound

This paper cites Continual learning through synaptic intelligence.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Continual learning through synaptic intelligence

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.784506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ec1c5489-2ffa-44b6-abb0-c0e325919784 · outbound

This paper cites HFT: Half Fine-Tuning for Large Language Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training HFT: Half Fine-Tuning for Large Language Models

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:56:01.233917Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7f2d6a24-a591-4565-bdfa-43056489a3a4 · outbound

This paper cites Mofo: Momentum-filtered optimizer for mitigating forgetting in llm fine-tuning.arXiv preprint arXiv:2407.20999, 2025.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Mofo: Momentum-filtered optimizer for mitigating forgetting in llm fine-tuning.arXiv preprint arXiv:2407.20999, 2025

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:54.564679Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 545850d2-c155-4d66-b91d-d078b2b5be0b · outbound

This paper cites Continual Learning of Large Language Models: A Comprehensive Survey.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Continual Learning of Large Language Models: A Comprehensive Survey

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:54.664729Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c99c9ed8-f4b3-44b9-b189-617ee7da8129 · outbound

This paper cites TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:54.752131Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 361e7f10-369e-445b-9629-743c15d2a499 · outbound

This paper cites Dick, and Hidenori Tanaka.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Dick, and Hidenori Tanaka

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.612763Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4821700b-3221-4c3d-90ef-21acc3e8f15f · outbound

This paper cites Are transformers able to reason by connecting separated knowledge in training data?arXiv preprint arXiv:2501.15857, 2025.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Are transformers able to reason by connecting separated knowledge in training data?arXiv preprint arXiv:2501.15857, 2025

Reference 29

Resolution: verified exact; raw_fallback, observed 2026-08-07T14:56:00.875443Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 62728e44-29f5-4164-a77e-2742d98220e6 · outbound

This paper cites DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training DomainStudio: Fine-Tuning Diffusion Models for Domain-Driven Image Generation using Limited Data

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:54.983757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad4620b4-725f-4116-9270-0144fc422330 · outbound

This paper cites Diffusion models beat gans on image synthesis.NeurIPS, 2021.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Diffusion models beat gans on image synthesis.NeurIPS, 2021

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.414806Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 000eaafb-19b1-4c42-875d-2a29e066a897 · outbound

This paper cites T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation.NeurIPS, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation.NeurIPS, 2023

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.286548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9d260cc7-5d04-4174-a1ff-0f5448c7bb52 · outbound

This paper cites Geneval: An object-focused framework for evaluating text-to-image alignment.NeurIPS, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Geneval: An object-focused framework for evaluating text-to-image alignment.NeurIPS, 2023

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:06.027799Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6d8d0bdf-9d60-4941-9007-689761b6ae77 · outbound

This paper cites Dreambench++: A human-aligned benchmark for personalized image generation.ICLR, 2025.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Dreambench++: A human-aligned benchmark for personalized image generation.ICLR, 2025

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:05.876577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 85fb8854-68f7-477e-8750-389b0b445d93 · outbound

This paper cites an unresolved cited work.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Unresolved cited work

Reference 35

Resolution: unresolved; raw_fallback, observed 2026-08-07T14:56:05.621265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1513644e-1c6e-4ec1-bdd0-d819d3ada8f8 · outbound

This paper cites Synthetic data protection: Towards a paradigm change in data regulation?Big Data Soc., 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Synthetic data protection: Towards a paradigm change in data regulation?Big Data Soc., 2024

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:05.398259Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 76e9d30c-7d5c-4843-8645-3dac7c7c8cb5 · outbound

This paper cites Gans trained by a two time-scale update rule converge to a local nash equilibrium.NIPS, 2017.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Gans trained by a two time-scale update rule converge to a local nash equilibrium.NIPS, 2017

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:05.212148Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d05114d9-89ac-46bc-a50d-30b0030a0b4c · outbound

This paper cites Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and C

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:05.011450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 380a9616-e18a-472a-be36-ed890e532933 · outbound

This paper cites A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:55.660939Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaec64d7-927b-435a-a8a9-a0f65bc980e6 · outbound

This paper cites Minigpt-4: Enhancing vision-language understanding with advanced large language models.ICLR, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Minigpt-4: Enhancing vision-language understanding with advanced large language models.ICLR, 2024

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:04.802881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 59926ea7-b4d5-41d8-a191-fa194fd091f7 · outbound

This paper cites Robust visual question answering: Datasets, methods, and future challenges.IEEE Trans.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Robust visual question answering: Datasets, methods, and future challenges.IEEE Trans

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:04.520446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation bddb4821-2d73-4d01-93e8-a3b2897ba1df · outbound

This paper cites Human preference score: Better aligning text-to-image models with human preference.ICCV, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Human preference score: Better aligning text-to-image models with human preference.ICCV, 2023

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:04.288634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f02fd237-be6d-4468-a3e5-f4d405a9cb4c · outbound

This paper cites A theory for knowledge transfer in continual learning.CoLLAs, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A theory for knowledge transfer in continual learning.CoLLAs, 2022

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:04.098593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 20591492-0095-479d-b3b5-9a2cff205e84 · outbound

This paper cites Is multi-task learning an upper bound for continual learning?ICASSP, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Is multi-task learning an upper bound for continual learning?ICASSP, 2023

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:04.002864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f096873e-93e4-49bb-88d5-179778eee440 · outbound

This paper cites SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:56.304312Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41223eae-84fe-4858-b359-6799d27d0706 · outbound

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

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:56.404533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6c159a8-ed32-4b4c-a0ef-f78fea04467a · outbound

This paper cites A statistical theory of regularization-based continual learning.ICML, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A statistical theory of regularization-based continual learning.ICML, 2024

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.862024Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 79cb6f1d-f567-4b8f-a3ce-074943793bd6 · outbound

This paper cites Approximate fisher information matrix to characterise the training of deep neural networks.IEEE Trans.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Approximate fisher information matrix to characterise the training of deep neural networks.IEEE Trans

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.733323Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e4690716-9cd4-407c-9f58-686bca19fe1a · outbound

This paper cites BERT: pre-training of deep bidirectional transformers for language understanding.NAACL-HLT, 2019.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training BERT: pre-training of deep bidirectional transformers for language understanding.NAACL-HLT, 2019

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.617050Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dc34078c-c284-4710-bd3d-88decc521aa2 · outbound

This paper cites Orthogonal subspace learning for language model continual learning.EMNLP, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Orthogonal subspace learning for language model continual learning.EMNLP, 2023

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.453360Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation d173c5f5-dc6e-4ec7-a750-cb45bf0de7ab · outbound

This paper cites Sutherland.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Sutherland

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.306570Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4751c03e-4852-4d28-ae0b-0b6cf8299b16 · outbound

This paper cites LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training LoRanPAC: Low-rank Random Features and Pre-trained Models for Bridging Theory and Practice in Continual Learning

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:56.858393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4feba1f3-fd7f-4a8b-b979-c09ec413a74a · outbound

This paper cites Create your world: Lifelong text-to-image diffusion.IEEE Trans.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Create your world: Lifelong text-to-image diffusion.IEEE Trans

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.194563Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 65cffd4e-310a-4597-8452-78c3530817f4 · outbound

This paper cites Progressive Compositionality in Text-to-Image Generative Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Progressive Compositionality in Text-to-Image Generative Models

Reference 54

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:56:00.580119Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e5795070-caca-4424-b3f2-f0e30768f368 · outbound

This paper cites Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:57.193568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93e6205a-ce89-4085-8d55-6a02a9a8db53 · outbound

This paper cites U-net: Convolutional networks for biomedical image segmentation.MICCAI, 2015.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training U-net: Convolutional networks for biomedical image segmentation.MICCAI, 2015

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:03.036965Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation abe635c4-395a-4254-9cd9-8fd9e9a24186 · outbound

This paper cites Learning transferable visual models from natural language supervision.ICML, 2021.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Learning transferable visual models from natural language supervision.ICML, 2021

Reference 57

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.925943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 8c5846e6-16ad-4093-ae14-24dc7a801559 · outbound

This paper cites Improving image captioning with better use of captions.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Improving image captioning with better use of captions

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.781614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c396b7a4-0876-4115-a01a-434955f1c288 · outbound

This paper cites Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:57.615254Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26c47138-98a0-4539-a7bc-ed3b37c287de · outbound

This paper cites Identity Encoder for Personalized Diffusion.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Identity Encoder for Personalized Diffusion

Reference 60

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:56:00.382547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 148f1bdc-9f15-49b3-bda3-7a37b137f8ab · outbound

This paper cites Prompt-to- prompt image editing with cross attention control.ICLR, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Prompt-to- prompt image editing with cross attention control.ICLR, 2022

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.658634Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation aec9f678-4e23-42ab-9cb6-f750344a45bd · outbound

This paper cites Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Diffuse-UDA: Addressing Unsupervised Domain Adaptation in Medical Image Segmentation with Appearance and Structure Aligned Diffusion Models

Reference 62

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:56:00.206036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 73d02449-732d-4cdd-be17-597e7ef674f0 · outbound

This paper cites Diffboost: Enhancing medical image segmentation via text-guided diffusion model.IEEE Transactions on Medical Imaging, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Diffboost: Enhancing medical image segmentation via text-guided diffusion model.IEEE Transactions on Medical Imaging, 2024

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.481446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation dd1a52c2-82d4-4827-ad77-2727bf025231 · outbound

This paper cites Diffportrait3d: Controllable diffusion for zero-shot portrait view synthesis.CVPR, 2024.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Diffportrait3d: Controllable diffusion for zero-shot portrait view synthesis.CVPR, 2024

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.373784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 20084761-37c5-427b-91d4-b3346620be5f · outbound

This paper cites Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Towards High-Fidelity 3D Portrait Generation with Rich Details by Cross-View Prior-Aware Diffusion

Reference 65

Resolution: verified exact; local_arxiv, observed 2026-08-07T14:56:00.083520Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1949151f-277f-4b49-88c0-3d7e6ed9c1a0 · outbound

This paper cites A Note on the Inception Score.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training A Note on the Inception Score

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:58.393757Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e739c3e5-5862-48e3-973b-f5ef1c9854e7 · outbound

This paper cites Rethinking the inception architecture for computer vision.CVPR, 2016.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Rethinking the inception architecture for computer vision.CVPR, 2016

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.257577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6ed43eed-1b59-4073-bece-503dbbb05975 · outbound

This paper cites Efros, Eli Shechtman, and Oliver Wang.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Efros, Eli Shechtman, and Oliver Wang

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:02.129482Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2c6e5f04-5d01-4f3a-83e7-c3f939092d41 · outbound

This paper cites Emerging properties in self-supervised vision transformers.ICCV, 2021.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Emerging properties in self-supervised vision transformers.ICCV, 2021

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:01.990027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 10d05be9-749f-4ea1-ba86-ef8fe8009100 · outbound

This paper cites Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.ICML, 2022.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation.ICML, 2022

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:01.828516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation af00fe6c-ad4f-42f1-a4c8-7853dd2c0a11 · outbound

This paper cites Imagereward: Learning and evaluating human preferences for text-to-image generation.NeurIPS, 2023.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Imagereward: Learning and evaluating human preferences for text-to-image generation.NeurIPS, 2023

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:01.654289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 547e8f05-0e97-403a-8a92-94de89e4a92b · outbound

This paper cites CLoG: Benchmarking Continual Learning of Image Generation Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training CLoG: Benchmarking Continual Learning of Image Generation Models

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:58.931222Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc794c2a-1090-458f-8f31-9925d481eee4 · outbound

This paper cites DeepSeek-V3 Technical Report.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training DeepSeek-V3 Technical Report

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.037860Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f4949118-8bc3-42e1-8e38-a6bc94b423b7 · outbound

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

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.082383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 74cb58b1-0377-442b-8756-2d682f9ae20e · outbound

This paper cites Qwen2.5 Technical Report.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Qwen2.5 Technical Report

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.179186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61b360f0-ea25-4bb4-a401-d2d259f58d2c · outbound

This paper cites The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision).

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.290217Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b058e921-b167-4e20-980e-3ac2278c6f46 · outbound

This paper cites Kingma and Jimmy Ba.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Kingma and Jimmy Ba

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T14:56:01.466920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation cd6ba267-fb86-4c85-b355-b7f53185af27 · outbound

This paper cites ZeRO: Memory Optimizations Toward Training Trillion Parameter Models.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training ZeRO: Memory Optimizations Toward Training Trillion Parameter Models

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.441095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 039c1cd3-c8dd-4572-a342-66740d4a06d2 · outbound

This paper cites Decoupled weight decay regularization.ICLR, 2019.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training Decoupled weight decay regularization.ICLR, 2019

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-07T14:55:59.520935Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a7249be-c7cc-42c2-a2f4-c03b4ca4b1ad · outbound

This paper cites item customization.

T2I-ConBench: Text-to-Image Benchmark for Continual Post-training item customization

Reference 80

Resolution: verified exact; raw_fallback, observed 2026-08-07T14:55:59.807812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers