Cover Image

AD-FM: Multimodal LLMs for Anomaly Detection via Multi-Stage Reasoning and Fine-Grained Reward Optimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liao, Jingyi, Su, Yongyi, Tu, Rong-Cheng, Jin, Zhao, Sun, Wenhao, Li, Yiting, Tao, Dacheng, Xu, Xun, Yang, Xulei
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

Robust Distribution Alignment for Industrial Anomaly Detection under Distribution Shift
by: Liao, Jingyi, et al.
Published: (2025)

Diffusion Model-Based Video Editing: A Survey
by: Sun, Wenhao, et al.
Published: (2024)

COFT-AD: COntrastive Fine-Tuning for Few-Shot Anomaly Detection
by: Liao, Jingyi, et al.
Published: (2024)

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration
by: Sun, Wenhao, et al.
Published: (2024)

Multi-View Industrial Anomaly Detection with Epipolar Constrained Cross-View Fusion
by: Liu, Yifan, et al.
Published: (2025)

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding
by: Jin, Zhao, et al.
Published: (2025)

SODA: Out-of-Distribution Detection in Domain-Shifted Point Clouds via Neighborhood Propagation
by: Goodge, Adam, et al.
Published: (2025)

SPAgent: Adaptive Task Decomposition and Model Selection for General Video Generation and Editing
by: Tu, Rong-Cheng, et al.
Published: (2024)

MLLM-Guided VLM Fine-Tuning with Joint Inference for Zero-Shot Composed Image Retrieval
by: Tu, Rong-Cheng, et al.
Published: (2025)

VORTA: Efficient Video Diffusion via Routing Sparse Attention
by: Sun, Wenhao, et al.
Published: (2025)

SPA-Cache: Singular Proxies for Adaptive Caching in Diffusion Language Models
by: Sun, Wenhao, et al.
Published: (2026)

Multimodal Reasoning Agent for Zero-Shot Composed Image Retrieval
by: Tu, Rong-Cheng, et al.
Published: (2025)

Skeleton2Stage: Reward-Guided Fine-Tuning for Physically Plausible Dance Generation
by: Jia, Jidong, et al.
Published: (2026)

Exploring Human-in-the-Loop Test-Time Adaptation by Synergizing Active Learning and Model Selection
by: Li, Yushu, et al.
Published: (2024)

SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
by: Jin, Weiyang, et al.
Published: (2025)

OmniAD: Detect and Understand Industrial Anomaly via Multimodal Reasoning
by: Zhao, Shifang, et al.
Published: (2025)

ToCoAD: Two-Stage Contrastive Learning for Industrial Anomaly Detection
by: Liang, Yun, et al.
Published: (2024)

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
by: Miao, Yuchun, et al.
Published: (2025)

Confidence as a Reward: Transforming LLMs into Reward Models
by: Du, He, et al.
Published: (2025)

ASPO: Adaptive Sentence-Level Preference Optimization for Fine-Grained Multimodal Reasoning
by: Wang, Yeyuan, et al.
Published: (2025)

AD-DINOv3: Enhancing DINOv3 for Zero-Shot Anomaly Detection with Anomaly-Aware Calibration
by: Yuan, Jingyi, et al.
Published: (2025)

Intra-Trajectory Consistency for Reward Modeling
by: Zhou, Chaoyang, et al.
Published: (2025)

Lightning Fast Caching-based Parallel Denoising Prediction for Accelerating Talking Head Generation
by: Long, Jianzhi, et al.
Published: (2025)

R1-ShareVL: Incentivizing Reasoning Capability of Multimodal Large Language Models via Share-GRPO
by: Yao, Huanjin, et al.
Published: (2025)

R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization
by: Zhang, Jingyi, et al.
Published: (2025)

Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
by: Zhang, Jiangning, et al.
Published: (2024)

OddGridBench: Exposing the Lack of Fine-Grained Visual Discrepancy Sensitivity in Multimodal Large Language Models
by: Weng, Tengjin, et al.
Published: (2026)

On the Adversarial Risk of Test Time Adaptation: An Investigation into Realistic Test-Time Data Poisoning
by: Su, Yongyi, et al.
Published: (2024)

SpatialThinker: Reinforcing 3D Reasoning in Multimodal LLMs via Spatial Rewards
by: Batra, Hunar, et al.
Published: (2025)

MCL-AD: Multimodal Collaboration Learning for Zero-Shot 3D Anomaly Detection
by: Li, Gang, et al.
Published: (2025)

Towards Real-World Test-Time Adaptation: Tri-Net Self-Training with Balanced Normalization
by: Su, Yongyi, et al.
Published: (2023)

UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation
by: Zhou, Yue, et al.
Published: (2025)

TeZO: Empowering the Low-Rankness on the Temporal Dimension in the Zeroth-Order Optimization for Fine-tuning LLMs
by: Sun, Yan, et al.
Published: (2025)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
by: Miao, Yuchun, et al.
Published: (2024)

AnomSeer: Reinforcing Multimodal LLMs to Reason for Time-Series Anomaly Detection
by: Zhang, Junru, et al.
Published: (2026)

Teaching LLMs to Abstain via Fine-Grained Semantic Confidence Reward
by: An, Hao, et al.
Published: (2025)

Boosting Fine-Grained Visual Anomaly Detection with Coarse-Knowledge-Aware Adversarial Learning
by: Fang, Qingqing, et al.
Published: (2024)

Fine-Grained Zero-Shot Learning: Advances, Challenges, and Prospects
by: Guo, Jingcai, et al.
Published: (2024)

Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks
by: Jin, Jing, et al.
Published: (2026)

Dissolving Is Amplifying: Towards Fine-Grained Anomaly Detection
by: Shi, Jian, et al.
Published: (2023)