AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

FakeWorld 1.0: An Omni-modal Benchmark for Fake Media and Content

Yifeng Gao, Yifan Ding, Li Wang, Feida Huang, Ye Sun, Yixu Wang, Xin Wang, Yutao Wu, Hanxun Huang, Yunhao Feng, Yingshui Tan, Xingjun Ma and 1 more

ICML 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Introduces FakeWorld 1.0, an omni-modal benchmark that unifies media authenticity and content veracity to evaluate detection of fake media and content.

Problem

Existing research treats media authenticity (real vs. machine-generated) and content veracity (semantic consistency and factual correctness) as separate problems, overlooking how real-world deception combines both.

Approach

A benchmark that jointly evaluates media authenticity and content veracity across multiple modalities, rather than along two separate axes.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add explicit thinking (ablation)Qwen3-VL-235B-A22B · FakeWorld media authenticity (overall)accuracy (%): 57.08 -> 71.52Improved
add explicit thinking (ablation)Qwen3-VL-8B · FakeWorld media authenticity (overall)accuracy (%): 65.13 -> 55.60Hurt
add explicit thinking (ablation)Qwen3-VL-2B · FakeWorld media authenticity (overall)accuracy (%): 50.08 -> 37.79Hurt
add explicit thinking (ablation)Qwen3-VL-32B · FakeWorld media authenticity (overall)accuracy (%): 63.90 -> 66.86Improved
add explicit thinking (ablation)Qwen3-Omni-30B-A3b · FakeWorld media authenticity (overall)accuracy (%): 61.17 -> 50.15Hurt
add explicit thinking (ablation)Qwen3-VL-32B · FakeWorld fact verificationaccuracy (%): 65.35 -> 72.78Improved
add explicit thinking (ablation)Qwen3-VL-235B-A22B · FakeWorld cross-modal consistency (overall)accuracy (%): 71.71 -> 75.01Improved
increase model size from Qwen3-VL-2B to 235BQwen3-VL · FakeWorld media authenticity (overall)accuracy (%): 50.08 -> 57.08Improved
relax web search budget (ablation)Gemini 3 Pro · FakeWorld fact verificationaccuracy (%): 0.75 -> 1.27Improved
use decomposed OmniCheck workflow instead of single pass (ablation)GPT-5.2 and Gemini 3 Pro · FakeWorldaccuracy (%)Improved
use decomposed OmniCheck workflow instead of single pass (ablation)Qwen3-VL-235B-Thinking · FakeWorldaccuracy (%)Hurt
train detector jointly on all modalities instead of per modality (ablation)LoRA Detector · FakeWorld image and video detectionaccuracy (%)Improved

Experimental setup

Benchmarks: FakeWorld 1.0

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy