ReAlign distills LLM-generated reasoning texts into a lightweight AIGI forgery detector via contrastive image-text alignment to improve generalization on complex forgeries.
Seeing before reasoning: A unified frame- work for generalizable and explainable fake image detection
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
NormGuard adds a training-time hinge penalty on velocity norm inflation in flow-matching RL to improve MLLM-judged image quality and forensic realism while preserving reward across multiple setups.
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.
citing papers explorer
-
ReAlign: Generalizable Image Forgery Detection via Reasoning-Aligned Representation
ReAlign distills LLM-generated reasoning texts into a lightweight AIGI forgery detector via contrastive image-text alignment to improve generalization on complex forgeries.
-
NormGuard: Reward-Preserving Norm Constraints in Flow-Matching Reinforcement Learning
NormGuard adds a training-time hinge penalty on velocity norm inflation in flow-matching RL to improve MLLM-judged image quality and forensic realism while preserving reward across multiple setups.
-
Venus-DeFakerOne: Unified Fake Image Detection & Localization
DeFakerOne is a unified foundation model for joint image-level fake image detection and pixel-level localization that reports SOTA results on 39 detection and 9 localization benchmarks.
-
FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
FakeVLM-R1 combines GRPO reinforcement learning with critical-thinking CoT and a physics-annotated FakeClue++ dataset to reach claimed SOTA synthetic image detection while reducing over-rejection of real images.