Pith. sign in

REVIEW 8 cited by

BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2507.14632 v4 pith:6ALDP3YF submitted 2025-07-19 cs.CV

BusterX++: Towards Unified Cross-Modal AI-Generated Content Detection and Explanation with MLLM

classification cs.CV
keywords imagevideocross-modalunifiedbusterxdetectionpolicyreasoning
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The rapid advancement of generative AI has substantially improved image and video synthesis, amplifying the risk of multimodal visual misinformation. Recent MLLMs have shown promise for transparent AI-generated content detection through reasoning and explanation, yet existing approaches largely treat image and video forensics as isolated tasks, leaving cross-modal synergies underexplored. To address this, we present \textbf{BusterX++}, a unified MLLM for joint image and video detection with interpretable reasoning. We also introduce \textbf{GenBuster-Bench++}, a meticulously curated, difficulty-aligned benchmark containing balanced image and video samples spanning recent generation models and diverse real-world scenarios. Using this controlled setting, we revisit the widely adopted $SFT \rightarrow RL$ post-training paradigm. Notably, our findings demonstrate that a single-stage, pure RL strategy driven strictly by sparse outcome rewards consistently matches or surpasses a strong SFT+RL baseline across both unified and single-modality settings. Our key insight reveals that SFT imposes lower policy entropy, which restricts the policy search space and dampens exploratory freedom. In contrast, single-stage pure RL maintains higher policy entropy throughout training, effectively unlocking the spontaneous emergence of cross-modal capability transfer between image and video forensics. Extensive experiments demonstrate that BusterX++ achieves state-of-the-art performance, highlighting the powerful potential of RL for unified cross-modal visual reasoning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Explainable Forensics of Manipulated Segments in Untrimmed Long Videos

    cs.CV 2026-06 unverdicted novelty 7.0

    Introduces TASLE benchmark and MSLoc baseline for temporal localization and explanation of manipulated segments in long videos.

  2. Dataset Biases and Shortcut Learning in Motion-Based AI-Generated Video Detection

    cs.CV 2026-07 unverdicted novelty 6.0

    Motion-based AI video detectors exploit motion biases in evaluation datasets and drop to near-random performance on rebalanced data, while frequency-based detectors remain robust.

  3. Artifact-Bench: Evaluating MLLMs on Detecting and Assessing the Artifacts of AI-Generated Videos

    cs.CV 2026-05 unverdicted novelty 6.0

    Artifact-Bench supplies a three-level artifact taxonomy and three evaluation tasks that show 19 MLLMs perform near or below random on AI-video realism detection and reasoning.

  4. DVAR: Adversarial Multi-Agent Debate for Video Authenticity Detection

    cs.CV 2026-04 unverdicted novelty 6.0

    DVAR turns video authenticity detection into an iterative debate between a generative hypothesis agent and a natural mechanism agent, resolved via minimum description length and a knowledge base for better generalizat...

  5. Skyra: AI-Generated Video Detection via Grounded Artifact Reasoning

    cs.CV 2025-12 unverdicted novelty 6.0

    Skyra is an MLLM that detects AI-generated videos by identifying and reasoning over grounded visual artifacts, supported by a new annotated dataset and benchmark.

  6. Video as Natural Augmentation: Towards Unified AI-Generated Image and Video Detection

    cs.CV 2026-05 unverdicted novelty 5.0

    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.

  7. FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection

    cs.CV 2026-05 unverdicted novelty 4.0

    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.

  8. Detecting AI-Generated Content on Social Media with Multi-modal Language Models

    cs.CL 2026-04 conditional novelty 4.0

    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.