Cover Image

LAVID: An Agentic LVLM Framework for Diffusion-Generated Video Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liu, Qingyuan, Tsai, Yun-Yun, Zha, Ruijian, Li, Victoria, Shi, Pengyuan, Mao, Chengzhi, Yang, Junfeng
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Turns Out I'm Not Real: Towards Robust Detection of AI-Generated Videos
by: Liu, Qingyuan, et al.
Published: (2024)

GDA: Generalized Diffusion for Robust Test-time Adaptation
by: Tsai, Yun-Yun, et al.
Published: (2024)

SHIELD: Suppressing Hallucinations In LVLM Encoders via Bias and Vulnerability Defense
by: Huang, Yiyang, et al.
Published: (2025)

Reasoning under Vision: Understanding Visual-Spatial Cognition in Vision-Language Models for CAPTCHA
by: Song, Python, et al.
Published: (2025)

AnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
by: Ahn, Sunghyun, et al.
Published: (2025)

ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models
by: Fang, Zixun, et al.
Published: (2025)

Robust and Annotation-Free Wound Segmentation on Noisy Real-World Pressure Ulcer Images: Towards Automated DESIGN-R\textsuperscript{\textregistered} Assessment
by: Tsai, Yun-Cheng
Published: (2025)

VanGogh: A Unified Multimodal Diffusion-based Framework for Video Colorization
by: Fang, Zixun, et al.
Published: (2025)

Multi-Level LVLM Guidance for Untrimmed Video Action Recognition
by: Peng, Liyang, et al.
Published: (2025)

LVLM-Composer's Explicit Planning for Image Generation
by: Ramsey, Spencer, et al.
Published: (2025)

MedM-VL: What Makes a Good Medical LVLM?
by: Shi, Yiming, et al.
Published: (2025)

DynamicRad: Content-Adaptive Sparse Attention for Long Video Diffusion
by: Long, Yongji, et al.
Published: (2026)

Generative Neural Video Compression via Video Diffusion Prior
by: Mao, Qi, et al.
Published: (2025)

Detecting AI-Generated Video via Frame Consistency
by: Ma, Long, et al.
Published: (2024)

Fighting Hallucinations with Counterfactuals: Diffusion-Guided Perturbations for LVLM Hallucination Suppression
by: Dastmalchi, Hamidreza, et al.
Published: (2026)

An Efficient Streaming Video Understanding Framework with Agentic Control
by: Liu, Jinming, et al.
Published: (2026)

Mitty: Diffusion-based Human-to-Robot Video Generation
by: Song, Yiren, et al.
Published: (2025)

ViViD: Video Virtual Try-on using Diffusion Models
by: Fang, Zixun, et al.
Published: (2024)

AdaIAT: Adaptively Increasing Attention to Generated Text to Alleviate Hallucinations in LVLM
by: Zhong, Li'an, et al.
Published: (2026)

EventMamba: Enhancing Spatio-Temporal Locality with State Space Models for Event-Based Video Reconstruction
by: Ge, Chengjie, et al.
Published: (2025)

NEWTON: Agentic Planning for Physically Grounded Video Generation
by: Feng, Yuxiang, et al.
Published: (2026)

VRMDiff: Text-Guided Video Referring Matting Generation of Diffusion
by: Yang, Lehan, et al.
Published: (2025)

VALD: Multi-Stage Vision Attack Detection for Efficient LVLM Defense
by: Kadvil, Nadav, et al.
Published: (2026)

Fooling the LVLM Judges: Visual Biases in LVLM-Based Evaluation
by: Hwang, Yerin, et al.
Published: (2025)

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision
by: Zhang, Chenshuang, et al.
Published: (2025)

Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception
by: Wu, Yuanchen, et al.
Published: (2025)

Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning
by: Wang, Yifan, et al.
Published: (2026)

SceneOrchestra: Efficient Agentic 3D Scene Synthesis via Full Tool-Call Trajectory Generation
by: He, Yun, et al.
Published: (2026)

ReManNet: A Riemannian Manifold Network for Monocular 3D Lane Detection
by: Hong, Chengzhi, et al.
Published: (2026)

ExpertGen: Training-Free Expert Guidance for Controllable Text-to-Face Generation
by: Shi, Liang, et al.
Published: (2025)

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
by: Song, Xiufeng, et al.
Published: (2024)

HERO: Human Reaction Generation from Videos
by: Yu, Chengjun, et al.
Published: (2025)

VideoMem: Enhancing Ultra-Long Video Understanding via Adaptive Memory Management
by: Jin, Hongbo, et al.
Published: (2025)

Before Forgetting, Learn to Remember: Revisiting Foundational Learning Failures in LVLM Unlearning Benchmarks
by: Kwon, JuneHyoung, et al.
Published: (2026)

Bridging Semantics and Geometry: A Decoupled LVLM-SAM Framework for Reasoning Segmentation in Optical Remote Sensing
by: Zhang, Xu, et al.
Published: (2025)

Unlocking Compositional Control: Self-Supervision for LVLM-Based Image Generation
by: Garcia, Fernando Gabriela, et al.
Published: (2025)

VT-LVLM-AR: A Video-Temporal Large Vision-Language Model Adapter for Fine-Grained Action Recognition in Long-Term Videos
by: Li, Kaining, et al.
Published: (2025)

Vision Remember: Recovering Visual Information in Efficient LVLM with Vision Feature Resampling
by: Feng, Ze, et al.
Published: (2025)

Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation
by: Li, Hang, et al.
Published: (2023)

Towards Better De-raining Generalization via Rainy Characteristics Memorization and Replay
by: Wang, Kunyu, et al.
Published: (2025)