ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation | Paper Citation Record

Observation f803b111-71a9-4599-b87d-11ec18beebbb · outbound

This paper cites Qwen2.5-VL Technical Report.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Qwen2.5-VL Technical Report

Reference 1

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.068936Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation eed5aa38-4179-43f9-97f2-8da97b63ade5 · outbound

This paper cites End-to-end reconstruction- classification learning for face forgery detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation End-to-end reconstruction- classification learning for face forgery detection

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.848714Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0ce9e2a2-54a8-4ba1-95fa-32db96567533 · outbound

This paper cites AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation AntifakePrompt: Prompt-Tuned Vision-Language Models are Fake Image Detectors

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.048010Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9c1db3ce-a314-437f-9d58-61fca94baa63 · outbound

This paper cites ShareGPT4V: Improving Large Multi-Modal Models with Better Captions.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation ShareGPT4V: Improving Large Multi-Modal Models with Better Captions

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.117577Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e91fbefa-dd5c-4d29-8872-112e7f539547 · outbound

This paper cites R1-v: Reinforcing super generalization ability in vision- language models with less than $3.https://github.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation R1-v: Reinforcing super generalization ability in vision- language models with less than $3.https://github

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.813076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7c050c8f-2150-43dc-98a2-400f9598f754 · outbound

This paper cites SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.034411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d787e753-5945-46fb-9898-b19059b94534 · outbound

This paper cites Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.002040Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5263e2d5-839a-4a03-9f82-6a5ba3da73bc · outbound

This paper cites Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Instructblip: Towards general-purpose vision- language models with instruction tuning.Advances in neural information processing systems, 36:49250–49267

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.851743Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c55e4733-d669-45e2-8d38-ee00f1bba24e · outbound

This paper cites Forensichub: A unified benchmark & codebase for all- domain fake image detection and localization.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Forensichub: A unified benchmark & codebase for all- domain fake image detection and localization

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.106488Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 073060fa-738a-4b0a-8605-ab2e383e1e91 · outbound

This paper cites Leveraging fre- quency analysis for deep fake image recognition.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Leveraging fre- quency analysis for deep fake image recognition

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.804076Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 13530593-1c07-41d2-8e6a-9e0a5fd84796 · outbound

This paper cites Seedream 3.0 Technical Report.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Seedream 3.0 Technical Report

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.113345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 833af666-209e-4621-a445-216a69f5d782 · outbound

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

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.030413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2dc373d2-2d4b-4630-be5a-16e49b65f3f8 · outbound

This paper cites UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation UniShield: An Adaptive Multi-Agent Framework for Unified Forgery Image Detection and Localization

Reference 13

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.082196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 61795daf-cd4a-452a-8083-d53a8798aa16 · outbound

This paper cites Mm-iml: Multi- modal image forgery detection and localization.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Mm-iml: Multi- modal image forgery detection and localization

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.807691Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cbb21a22-74c1-4f6f-9424-0b29f7641549 · outbound

This paper cites Sida: Social media image deepfake detection, localization and explanation with large multimodal model.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Sida: Social media image deepfake detection, localization and explanation with large multimodal model

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.789775Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fc7b5fb6-c8ea-4a83-a14f-8b29cddc0183 · outbound

This paper cites So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation So-Fake: Benchmarking and Explaining Social Media Image Forgery Detection

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-08-03T03:15:17.929242Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b56f2be3-17a9-40e5-9161-6339ad7dedfc · outbound

This paper cites Scaling up visual and vision-language representa- tion learning with noisy text supervision.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Scaling up visual and vision-language representa- tion learning with noisy text supervision

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.800593Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d81c33fc-560b-489f-80b9-085b9cdd2071 · outbound

This paper cites Fusing global and local features for gen- eralized ai-synthesized image detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Fusing global and local features for gen- eralized ai-synthesized image detection

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.797202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 197a5f44-c06d-4407-a057-47ff97d27492 · outbound

This paper cites LEGION: Learning to Ground and Explain for Synthetic Image Detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation LEGION: Learning to Ground and Explain for Synthetic Image Detection

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.098569Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7eb7c440-26d5-45f7-b4e7-7765be90b92f · outbound

This paper cites Leveraging rep- resentations from intermediate encoder-blocks for synthetic image detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Leveraging rep- resentations from intermediate encoder-blocks for synthetic image detection

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.793835Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0096f7b3-72f2-4eb2-ac44-d13229dc2805 · outbound

This paper cites Contextual integrity in LLMs via reasoning and reinforcement learning.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Contextual integrity in LLMs via reasoning and reinforcement learning

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.790210Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e88d5f3f-8a49-476a-bea1-059b0bf6ba7b · outbound

This paper cites Freqblender: Enhancing deepfake detec- tion by blending frequency knowledge.Advances in Neural Information Processing Systems, 37:44965–44988.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Freqblender: Enhancing deepfake detec- tion by blending frequency knowledge.Advances in Neural Information Processing Systems, 37:44965–44988

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.800333Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 65096daf-fda3-476e-8071-a073ba7dac00 · outbound

This paper cites Lion-fs: Fast & slow video-language thinker as on- line video assistant.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Lion-fs: Fast & slow video-language thinker as on- line video assistant

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.810794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a9a7f130-d237-4dcf-85b7-cbe551a54134 · outbound

This paper cites Ultrare: Enhancing receraser for recommendation unlearn- ing via error decomposition.Advances in Neural Informa- tion Processing Systems, 36:12611–12625.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Ultrare: Enhancing receraser for recommendation unlearn- ing via error decomposition.Advances in Neural Informa- tion Processing Systems, 36:12611–12625

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.782038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2db22f06-1556-4974-8e8e-22baf1896ab5 · outbound

This paper cites Texture, shape and order matter: A new transformer design for sequential deepfake detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Texture, shape and order matter: A new transformer design for sequential deepfake detection

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.814293Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f4f6c878-f5b1-4c5c-8c11-e0e1e4218a0b · outbound

This paper cites Multi-objective unlearning in recommender systems via preference guided pareto exploration.IEEE Transactions on Services Computing.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Multi-objective unlearning in recommender systems via preference guided pareto exploration.IEEE Transactions on Services Computing

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.810143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation acc3fe8d-c4ea-4e31-a701-b7a7780b847c · outbound

This paper cites Seeing before reasoning: A unified frame- work for generalizable and explainable fake image detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Seeing before reasoning: A unified frame- work for generalizable and explainable fake image detection

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.056825Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1054fbbb-4ccb-48a3-a983-396a37090539 · outbound

This paper cites Detecting generated images by real images.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Detecting generated images by real images

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.774387Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 52861259-77db-4f28-98b8-553b7e5742ca · outbound

This paper cites Visual instruction tuning.Advances in neural information processing systems, 36.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Visual instruction tuning.Advances in neural information processing systems, 36

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.824719Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 17a3787f-7382-4504-9b39-605bf551cac8 · outbound

This paper cites ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation ForgeryGPT: A Multimodal LLM for Interpretable Image Forgery Detection and Localization

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.045644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 33171a3b-3812-4942-a17a-a638fc022da4 · outbound

This paper cites Forgery-aware adaptive learning with vision transformer for generalized face forgery detection.IEEE Transactions on Circuits and Systems for Video Technology.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Forgery-aware adaptive learning with vision transformer for generalized face forgery detection.IEEE Transactions on Circuits and Systems for Video Technology

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.821589Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3ec81407-9ac8-44c8-b568-6a430956944b · outbound

This paper cites Lareˆ 2: Latent reconstruction error based method for diffusion-generated image detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Lareˆ 2: Latent reconstruction error based method for diffusion-generated image detection

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.806897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 67a09bfa-29c4-4068-8d0f-fa0183d1583f · outbound

This paper cites IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation IML-ViT: Benchmarking Image Manipulation Localization by Vision Transformer

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.079649Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fd356217-59d5-4f2b-908f-db35f79a1840 · outbound

This paper cites Visualizing data using t-sne.Journal of machine learning research, 9 (Nov):2579–2605.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Visualizing data using t-sne.Journal of machine learning research, 9 (Nov):2579–2605

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.767782Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ba6f1b83-31a9-4d1f-b8a9-e22c5e4fa5dc · outbound

This paper cites Towards uni- versal fake image detectors that generalize across generative models.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Towards uni- versal fake image detectors that generalize across generative models

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.817670Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5eebd474-e56b-4b90-afee-d9045d574366 · outbound

This paper cites GPT-4 Technical Report.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation GPT-4 Technical Report

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.074411Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4977479b-5ba4-47ce-a02f-5947cab40b62 · outbound

This paper cites TextSleuth: Towards Explainable Tampered Text Detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation TextSleuth: Towards Explainable Tampered Text Detection

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.052380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 726accdf-3b51-4ab5-a620-4e606980b5f6 · outbound

This paper cites Learning transferable visual models from natural language supervi- sion.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Learning transferable visual models from natural language supervi- sion

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.764143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a7623b80-6609-46e8-9b3f-a8a2d599f15a · outbound

This paper cites A ro- bust approach to multimodal deepfake detection.Journal of Imaging, 9(6):122.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation A ro- bust approach to multimodal deepfake detection.Journal of Imaging, 9(6):122

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.761186Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 7e87d582-0a49-4d6a-aea9-3fba665ba953 · outbound

This paper cites Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural in- formation processing systems, 35:25278–25294.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural in- formation processing systems, 35:25278–25294

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.754071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e0f8ecf4-68d3-45a7-baa9-88106c6b4874 · outbound

This paper cites VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation VLM-R1: A Stable and Generalizable R1-style Large Vision-Language Model

Reference 41

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.052215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 755eb098-1518-46ee-9fcf-08bbbc8dc341 · outbound

This paper cites Ai-enhanced disaster risk prediction with explainable shap analysis: A multi-class classification approach using xgboost.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Ai-enhanced disaster risk prediction with explainable shap analysis: A multi-class classification approach using xgboost

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.751029Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 19202b76-91d5-4faa-a99f-ac8ef9490d5a · outbound

This paper cites Learning on gradients: Generalized arti- facts representation for gan-generated images detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Learning on gradients: Generalized arti- facts representation for gan-generated images detection

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.828666Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation d6471fbf-2b25-4bb4-81ee-9e059b50f1be · outbound

This paper cites Rethinking the up-sampling op- erations in cnn-based generative network for generalizable deepfake detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Rethinking the up-sampling op- erations in cnn-based generative network for generalizable deepfake detection

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.855469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 57ede332-523b-4eb9-bfb8-d9487a35d1cf · outbound

This paper cites C2p-clip: Inject- ing category common prompt in clip to enhance generaliza- tion in deepfake detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation C2p-clip: Inject- ing category common prompt in clip to enhance generaliza- tion in deepfake detection

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.835174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 8b297201-2d68-464a-afe2-28488465b533 · outbound

This paper cites Hunyuanimage 2.1: An efficient diffusion model for high-resolution (2k) text-to-image gener- ation.https://github.com/Tencent-Hunyuan/ HunyuanImage-2.1.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Hunyuanimage 2.1: An efficient diffusion model for high-resolution (2k) text-to-image gener- ation.https://github.com/Tencent-Hunyuan/ HunyuanImage-2.1

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.831445Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 987628ba-b3ed-4778-9b9f-35615ade224d · outbound

This paper cites Cnn-generated images are sur- prisingly easy to spot...for now.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Cnn-generated images are sur- prisingly easy to spot...for now

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.831681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ef75055-9bee-49f5-be83-5dfed2594984 · outbound

This paper cites Cnn-generated images are surprisingly easy to spot.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Cnn-generated images are surprisingly easy to spot

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.741627Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9c1b0082-8641-4ef4-bc02-35cd3ddda452 · outbound

This paper cites Opensdi: Spotting diffusion-generated images in the open world.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Opensdi: Spotting diffusion-generated images in the open world

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.738660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 3d2d6107-df11-41fa-94cf-0f2b7e0f63e3 · outbound

This paper cites Dire for diffusion-generated image detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Dire for diffusion-generated image detection

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.821051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9d149797-d783-4e36-a772-da581a012cbc · outbound

This paper cites Qwen-Image Technical Report.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Qwen-Image Technical Report

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-05-20T19:33:42.088441Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cabb1c3c-f8d7-4822-98cf-d9752be835d5 · outbound

This paper cites Reversible primitive–composition align- ment for continual vision–language learning.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Reversible primitive–composition align- ment for continual vision–language learning

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.731740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation dd693f90-f719-475e-ba24-482def0fea04 · outbound

This paper cites Confusion-resistant federated learn- ing via diffusion-based data harmonization on non-iid data.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Confusion-resistant federated learn- ing via diffusion-based data harmonization on non-iid data

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.842104Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4941acab-6d59-4977-abf7-17f097880f5a · outbound

This paper cites Fakeshield: Explainable image forgery detection and localization via multi-modal large lan- guage models.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Fakeshield: Explainable image forgery detection and localization via multi-modal large lan- guage models

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.824477Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f2bb66ec-9329-46d7-a9f6-cbec5e698501 · outbound

This paper cites Avatarshield: Visual reinforcement learning for human-centric video forgery detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Avatarshield: Visual reinforcement learning for human-centric video forgery detection

Reference 55

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.070774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5ea45011-a048-4dde-b61d-deaecf2d8cfc · outbound

This paper cites A Sanity Check for AI-generated Image Detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation A Sanity Check for AI-generated Image Detection

Reference 56

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.092997Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 68959c1e-67bd-45e3-a9dc-fd42dda2abd1 · outbound

This paper cites Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning

Reference 57

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.096932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ee81ce55-0365-471e-9c99-7c0c34538f11 · outbound

This paper cites All patches matter, more patches better: Enhance ai-generated image detection via panoptic patch learning.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation All patches matter, more patches better: Enhance ai-generated image detection via panoptic patch learning

Reference 58

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.086868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fa0095ea-9dea-43b6-afe1-7f3b7bdb560d · outbound

This paper cites Swift sampler: Efficient learning of sampler by 10 parameters.Advances in Neural Information Processing Systems, 37:59030–59053.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Swift sampler: Efficient learning of sampler by 10 parameters.Advances in Neural Information Processing Systems, 37:59030–59053

Reference 59

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.724269Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e5d8df1d-dcc1-4fb9-bf64-0315eeb2db7b · outbound

This paper cites Depthssc: Monocular 3d semantic scene com- pletion via depth-spatial alignment and voxel adaptation.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Depthssc: Monocular 3d semantic scene com- pletion via depth-spatial alignment and voxel adaptation

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.720993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 18e9cfd6-3a42-460b-9988-00e2ec8696a2 · outbound

This paper cites Identifying money laundering risks in digital as- set transactions based on ai algorithms.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Identifying money laundering risks in digital as- set transactions based on ai algorithms

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.838895Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6ee8595f-62fb-42ba-a7f7-f21fee816675 · outbound

This paper cites Janusvln: Decoupling semantics and spatiality with dual implicit memory for vision-language navigation.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Janusvln: Decoupling semantics and spatiality with dual implicit memory for vision-language navigation

Reference 62

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.026733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a7347bff-5be9-45c8-917b-e5b1173ce71f · outbound

This paper cites Strfilter: Multi-modal medical image fusion via structure-oriented adaptive filter- ing.Information Fusion, page 103888.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Strfilter: Multi-modal medical image fusion via structure-oriented adaptive filter- ing.Information Fusion, page 103888

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.717038Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b30d0188-2582-4d4b-b381-687e81c6754d · outbound

This paper cites Molebridge: Synthetic space projecting with discrete markov bridges.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Molebridge: Synthetic space projecting with discrete markov bridges

Reference 64

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.834926Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 42073d99-9afb-4ee2-b3e2-36a7b5bc6700 · outbound

This paper cites Exploit your la- tents: Coarse-grained protein backmapping with latent dif- fusion models.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Exploit your la- tents: Coarse-grained protein backmapping with latent dif- fusion models

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.709967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 772ab67e-427d-4e2d-b302-144bf840835f · outbound

This paper cites Badwindtunnel: Defending backdoor in high-noise simulated training with confidence variance.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Badwindtunnel: Defending backdoor in high-noise simulated training with confidence variance

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.848485Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 967e3bd6-c554-4337-b537-8a8eb559f5f7 · outbound

This paper cites Editguard: Versatile image watermarking for tamper localization and copyright protection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Editguard: Versatile image watermarking for tamper localization and copyright protection

Reference 67

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.851979Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a8bbf8c0-618d-4502-af1d-a33ce9ad0c3d · outbound

This paper cites Omniguard: Hy- brid manipulation localization via augmented versatile deep image watermarking.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Omniguard: Hy- brid manipulation localization via augmented versatile deep image watermarking

Reference 68

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.841907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9ccab993-5c56-4f10-b3ac-8ca0a840aeb7 · outbound

This paper cites Vq-insight: Teaching vlms for ai-generated video quality understanding via progressive visual reinforce- ment learning.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Vq-insight: Teaching vlms for ai-generated video quality understanding via progressive visual reinforce- ment learning

Reference 69

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.838526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation be177ff7-f67e-4293-8191-a9da0633a42d · outbound

This paper cites Reasoning as representation: Rethinking visual reinforcement learning in image quality assessment.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Reasoning as representation: Rethinking visual reinforcement learning in image quality assessment

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.845239Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fce7264b-dc48-49b0-9451-ac5185319697 · outbound

This paper cites PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.111014Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 6478b6b5-c323-497e-871b-1e821f66a9df · outbound

This paper cites Rich and poor texture contrast: A simple yet effective ap- proach for ai-generated image detection.CoRR.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation Rich and poor texture contrast: A simple yet effective ap- proach for ai-generated image detection.CoRR

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-20T19:33:42.845470Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 352d11e6-59ea-4abc-95b4-a13070f211d5 · outbound

This paper cites AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models.

ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation AIGI-Holmes: Towards Explainable and Generalizable AI-Generated Image Detection via Multimodal Large Language Models

Reference 73

Resolution: verified exact; arxiv_id, observed 2026-05-20T19:33:42.103759Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers