Multimodal Content Moderation

Latest papers

21 papers1 paper in the last four weeks, down 80% on the four weeks before. 0.0% of all new papers.

AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution
Oct 8, 2026AllSpark TeamMultimodal Content Moderation Reinforcement Learning
SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme Detection
Sep 12, 2026Hanling Wang, Chenlong Wei, Yingjuan Li +4Harmful Meme Detection Multimodal Content Moderation
University of California, San Diego · Xi’an Jiaotong-Liverpool University · University of Washington +2
Can Foundation Models Moderate Online Content? Evaluating Instruction- vs. Example-Driven Policy Operationalization
Sep 9, 2026Ayan Majumdar, Shounak Paul, Pushpdeep Singh +6VLM Evaluation LLM Prompting
MPI-SWS, Germany · Saarland University, Germany · INRIA, France
Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator
Aug 27, 2026Varun Singh, Anuj Doshi, Makesh Narsimhan Sreedhar +2Multimodal Content Moderation LLM Guardrails
NVIDIA Santa Clara, CA
The Temporal Moderation Gap: Text-to-Video Safety Filters Are Blind to Harm in Motion
Aug 19, 2026Yuxin Cao, Fusen Guo, Yuezhong Wu +2Video Content Moderation Multimodal Content Moderation
University of New South Wales Australia · Fuzhou University China
Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
Aug 18, 2026Hamidreza Saffari, Francesco PierriAlgorithmic Auditing Video Content Moderation
Politecnico di Milano
Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation
Jul 30, 2026Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2Multimodal Robustness Adversarial Attacks
Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg · Department of Mathematics, University of Padua, Padua, Italy
Shieldstral
Jul 28, 2026Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli +273Language Model Safety Evaluation Content Moderation
Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions
Jul 21, 2026Qianpu Chen, Derya SoydanerHate Speech Detection Multimodal Content Moderation
LIACS (Leiden Institute of Advanced Computer Science), Leiden University, Leiden, The Netherlands
Automatic Hard Example Synthesis with Multi-Level Agentic Data Curation
Jul 15, 2026Genglin Liu, Muye Zhang, Krishnamurthy Viswanathan +5Multimodal Robustness Adversarial Scenario Generation
1UCLA · *Work done as a student researcher at Google. · 2Google
Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine
Jul 1, 2026Jiaxian Lv, Shiyao Cui, Yingkang Wang +3Toxicity Detection Safety Filtering
The Conversational AI (CoAI) Group, DCST, Tsinghua University
UNIVID: Unified Vision-Language Model for Video Moderation
Jun 4, 2026Kejuan Yang, Yizhuo Zhang, Mingyuan Du +6Unified Multimodal Models VLM Adaptation
Bytedance
RuleSafe-VL: Evaluating Rule-Conditioned Decision Reasoning in Vision-Language Content Moderation
May 8, 2026Zhifeng Lu, Dianyuan Wang, Yuhu Shang +1VLM Evaluation Logical Reasoning
Beijing University of Posts and Telecommunications, Beijing, China
SenBen: Sensitive Scene Graphs for Explainable Content Moderation
Apr 9, 2026Fatih Cagatay Akyon, Alptekin TemizelContent Moderation Multimodal Content Moderation
Graduate School of Informatics, METU, Turkiye · Ultralytics, Inc., United States
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
Apr 8, 2026Zhiheng Li, Zongyang Ma, Yuntong Pan +8Multimodal Content Moderation Adversarial Attacks on VLMs
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information +4
Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems
Mar 31, 2026Zhiqian Zhang, Xu Zhao, Xiaoqing Xu +5Multimodal Content Moderation Multimodal Large Language Models
Computational Intelligence Dept, Hello Group Inc.
Beyond Hate: Differentiating Uncivil and Intolerant Speech in Multimodal Content Moderation
Mar 24, 2026Nils A. Herrmann, Tobias Eder, Jingyi He +1Multimodal Content Moderation Hate Speech Detection
Technical University of Munich
KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child Safety
Mar 17, 2026Viraj Panchal, Tanmay Talsaniya, Parag Patel +1Multimodal Content Moderation Content Moderation
KidsNanny Research Team, Vartit Technology Inc.
Tool-MCoT: Tool Augmented Multimodal Chain-of-Thought for Content Safety Moderation
Mar 15, 2026Shutong Zhang, Dylan Zhou, Yinxiao Liu +3Multimodal Content Moderation Content Moderation
Stanford University, USA · Google LLC, USA
BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards
Feb 20, 2026Yiran Yang, Zhaowei Liu, Yuan Yuan +10Video Content Moderation Content Moderation
1Kuaishou Technology · 2Beijing University of Posts and Telecommunications · 3Shandong University
PEST: Parameter Efficient Steering of Blackbox VLMs via Agentic Few-shot Alignment for Hateful Meme Moderation
Jan 8, 2026Naquee Rizwan, Subhankar Swain, Paramananda Bhaskar +3VLM Adaptation Hate Speech Detection
Indian Institute of Technology (IIT), Kharagpur · Simbian

Oct 8, 2026J/K move · Enter open · S save

AdaptEvo: Learning under Imperfect Supervision through Confidence-Adaptive Training with Knowledge Evolution

AllSpark Team

Multimodal Content Moderation Reinforcement Learning Self-Evolving Agents Rubric-Based RL Group Relative Policy Optimization

Open paper AskPDF arXiv

Rule-governed contextual decision tasks require models to apply specified rules to case-specific context and evidence. Written rules can leave gaps in decision guidance and process evaluation, while reference judgments vary in their support from the rules and evidence. To address these challenges, we introduce AdaptEvo, a framework for learning under imperfect supervision that couples confidence-adaptive policy optimization with evolving decision knowledge and evaluation rubrics. Its Training module uses Confidence-Adaptive GRPO (CA-GRPO) to balance outcome and process rewards according to reference confidence. Its Evolution module synthesizes reusable decision knowledge from recurring failures across training cases and refines process rubrics to detect overlooked errors. To support empirical evaluation, we construct an industrial multimodal content moderation dataset comprising a training set and In-Period and Out-of-Period test sets, with the latter collected under changed rules. Using Qwen3.6-35B-A3B, AdaptEvo achieves 61.9% exact-label accuracy and 72.2% binary decision accuracy on In-Period, exceeding GRPO by 7.5 and 3.7 percentage points, respectively. On Out-of-Period, the policy trained with CA-GRPO retains exact-label accuracy gains over the base model across evaluated checkpoints without injected decision knowledge, while GRPO declines with continued training. CA-GRPO also outperforms the tested fixed reward mixtures on both Out-of-Period metrics.