AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

CogniCred: A Dataset and Benchmark for Cognitive Credential Forgery Detection

Junchi Li, Jiasheng Sun, Weizhi Chen, Ziwei Wang, Sheng Zhou, Jiajun Bu, Chenfan Qu, Bohan Yu, Jian liu, Weiqiang Wang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: Interleaved image-text generation with MLLMs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
enable Thinking modeQwen3-VL-32B · CogniCredBench Contextual Reasoning (T1 closed-set)accuracy (%): 56.85 -> 85.80Improved
enable Thinking modeQwen3-VL-30B-A3B · CogniCredBench Contextual Reasoning (T1 closed-set)accuracy (%): 64.45 -> 75.25Improved
enable Thinking modeQwen3-VL-32B · CogniCredBench Visual Reasoning (T1 closed-set)accuracy (%): 39.54 -> 26.99Hurt
enable Thinking modeQwen3-VL-30B-A3B · CogniCredBench Visual Reasoning (T1 closed-set)accuracy (%): 26.56 -> 20.03Hurt
switch from closed-set classification (T1) to open-ended reasoning (T2)GLM-4.5V · CogniCredBench Visual Reasoningaccuracy (%): 32.61 -> 7.74Hurt
switch from closed-set classification (T1) to open-ended reasoning (T2)GLM-4.5V · CogniCredBench Format Complianceaccuracy (%): 29.48 -> 5.56Hurt
switch from closed-set classification (T1) to open-ended reasoning (T2)Gemini-3-Pro · CogniCredBench Visual Reasoningaccuracy (%): 65.09 -> 44.54Hurt
switch from closed-set classification (T1) to open-ended reasoning (T2)Qwen3-VL-32B-Instruct · CogniCredBench Visual Reasoningaccuracy (%): 39.54 -> 29.46Hurt
compare Gemini-3-Pro with GPT-4o as closed-source modelGPT-4o · CogniCredBench Visual Reasoning (T2 open-ended)accuracy (%): 44.54 -> 1.25Hurt
enable Thinking modeQwen3-VL-32B · CogniCredBench Format Compliance (T2 open-ended)accuracy (%): 36.53 -> 42.12Improved

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