17 papers
Agentic Tool-Augmented Reasoning for Explainable Image Forgery Detection
Zhiya Tan, Jing Huang, Changtao Miao +5
Conventional image forgery detection methods produce binary scores or pixel-level masks without interpretable evidence, while recent multimodal large language model (MLLM)-based ap…
PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents
Junchi Chen, Changtao Miao, Yuxiao Xiang +9
Embodied task planners may produce multi-step plans whose subtask dependencies and interactions with the environment create physical risks during execution. Yet existing safeguards…
Open-AoE: An Open Egocentric Manipulation Dataset and Toolchain for Embodied Learning
Zishuo Li, Bowen Yang, Changtao Miao +29
Egocentric videos of human manipulation provide scalable supervision for embodied intelligence, yet existing resources rarely combine low-cost continuous capture, manipulation-leve…
DT-Guard: Intent-Driven Reasoning-Active Training for Reasoning-Free LLM Safety Guardrail
He Liu, Changtao Miao, Xinjie Yang +12
Large language models deployed in open-world applications require safety guardrails that are both robust to complex risks and efficient enough for low-latency runtime moderation. E…
Visual-Seeker: Towards Visual-Native Multimodal Agentic Search via Active Visual Reasoning
Zhengbo Zhang, Changtao Miao, Jinbo Su +10
Multimodal large language models (MLLMs) have demonstrated impressive capabilities in many visual tasks, but they often struggle with factual grounding when confronted with complex…
The Courtroom Trial of Pixels: Robust Image Manipulation Localization via Adversarial Evidence and Reinforcement Learning Judgment
Songlin Li, Zhiqing Guo, Kebin Chen +6
Although some existing image manipulation localization (IML) methods incorporate authenticity-related supervision, this information is typically utilized merely as an auxiliary tra…
VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing Agents
Zhengbo Zhang, Jinbo Su, Zhaowen Zhou +14
The rapid advancement of Multimodal Large Language Models (MLLMs) has enabled browsing agents to acquire and reason over multimodal information in the real world. But existing benc…
AoE: Always-on Egocentric Human Video Collection for Embodied AI
Bowen Yang, Zishuo Li, Yang Sun +15
Embodied foundation models require large-scale, high-quality real-world interaction data for pre-training and scaling. However, existing data collection methods suffer from high in…
Beyond Next-Token Alignment: Distilling Multimodal Large Language Models via Token Interactions
Lin Chen, Xiaoke Zhao, Kun Ding +9
Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation…
LogicLens: Visual-Logical Co-Reasoning for Text-Centric Forgery Analysis
Fanwei Zeng, Changtao Miao, Jing Huang +7
Sophisticated text-centric forgeries, fueled by rapid AIGC advancements, pose a significant threat to societal security and information authenticity. Current methods for text-centr…
ViRC: Enhancing Visual Interleaved Mathematical CoT with Reason Chunking
Lihong Wang, Liangqi Li, Weiwei Feng +6
CoT has significantly enhanced the reasoning ability of LLMs while it faces challenges when extended to multimodal domains, particularly in mathematical tasks. Existing MLLMs typic…
MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection
Mengxue Hu, Yunfeng Diao, Changtao Miao +7
The rapid advancement of AI-generated multimodal video-audio content has raised significant concerns regarding information security and content authenticity. Existing synthetic vid…
EIRES:Training-free AI-Generated Image Detection via Edit-Induced Reconstruction Error Shift
Wan Jiang, Jing Yan, Xiaojing Chen +4
Diffusion models have recently achieved remarkable photorealism, making it increasingly difficult to distinguish real images from generated ones, raising significant privacy and se…
MFFI: Multi-Dimensional Face Forgery Image Dataset for Real-World Scenarios
Changtao Miao, Yi Zhang, Man Luo +9
Rapid advances in Artificial Intelligence Generated Content (AIGC) have enabled increasingly sophisticated face forgeries, posing a significant threat to social security. However,…
DDL: A Large-Scale Dataset for Deepfake Detection and Localization in Diversified Real-World Scenarios
Changtao Miao, Yi Zhang, Weize Gao +11
Recent advances in AIGC have exacerbated the misuse of malicious deepfake content, making the development of reliable deepfake detection methods an essential means to address this…
SUEDE:Shared Unified Experts for Physical-Digital Face Attack Detection Enhancement
Zuying Xie, Changtao Miao, Ajian Liu +4
Face recognition systems are vulnerable to physical attacks (e.g., printed photos) and digital threats (e.g., DeepFake), which are currently being studied as independent visual tas…
Vulnerabilities in AI-generated Image Detection: The Challenge of Adversarial Attacks
Yunfeng Diao, Naixin Zhai, Changtao Miao +4
Recent advancements in image synthesis, particularly with the advent of GAN and Diffusion models, have amplified public concerns regarding the dissemination of disinformation. To a…