RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
Loki: A comprehensive synthetic data de- tection benchmark using large multimodal models
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
dataset 1
citation-polarity summary
roles
dataset 1polarities
background 1representative citing papers
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
SalArt-VQA benchmark shows that high image-level artifact detection accuracy in VLMs does not imply correct localization, grounding, or evidence-supported defect descriptions.
Social gaze consistency between interacting people is proposed as a new semantic cue orthogonal to low-level artifacts for detecting AI-generated images, with reported accuracy gains on vision and vision-language models.
A unified synthetic data generation pipeline produces unlimited annotated multimodal video data across multiple tasks, enabling models trained mostly on synthetic data to generalize effectively to real-world video understanding benchmarks.
VINA trains a single detector on images plus video frames using a cross-modal supervised contrastive objective, yielding bidirectional gains and SOTA results on 14 image, video, and in-the-wild 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.
A 3B-parameter vision-language model trained on continuously curated social media data detects AI-generated content with state-of-the-art accuracy on benchmarks and shows positive engagement effects in production deployment.
citing papers explorer
-
RobustSora: De-Watermarked Benchmark for Robust AI-Generated Video Detection
RobustSora benchmark demonstrates that current AI video detectors rely heavily on visible watermarks, with average accuracy drops of 6.6 percentage points when watermarks are erased and increased false alarms when watermarks are spoofed onto real videos.
-
VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?
VideoASMR-Bench shows state-of-the-art VLMs fail to reliably detect AI-generated ASMR videos from real ones, though humans can still identify the fakes relatively easily.
-
Toward Generalizable Forgery Detection and Reasoning
FakeReasoning is an MLLM-based framework for unified forgery detection and reasoning on AI-generated images, supported by the new MMFR-Dataset of 120K images and 378K annotations across 10 generators.
-
SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated Images
SalArt-VQA benchmark shows that high image-level artifact detection accuracy in VLMs does not imply correct localization, grounding, or evidence-supported defect descriptions.
-
When Eyes Betray AI: Social Gaze Consistency as a Semantic Cue for AI-Generated Image Detection
Social gaze consistency between interacting people is proposed as a new semantic cue orthogonal to low-level artifacts for detecting AI-generated images, with reported accuracy gains on vision and vision-language models.
-
All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding
A unified synthetic data generation pipeline produces unlimited annotated multimodal video data across multiple tasks, enabling models trained mostly on synthetic data to generalize effectively to real-world video understanding benchmarks.
-
Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection
VINA trains a single detector on images plus video frames using a cross-modal supervised contrastive objective, yielding bidirectional gains and SOTA results on 14 image, video, and in-the-wild 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.
-
Detecting AI-Generated Content on Social Media with Multi-modal Language Models
A 3B-parameter vision-language model trained on continuously curated social media data detects AI-generated content with state-of-the-art accuracy on benchmarks and shows positive engagement effects in production deployment.