58 citations · 123 across the 15 of their papers we have counts for
15 papers
When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy
Xiaofeng Tan, Jun Liu, Bin-Bin Gao +5
RLHF is widely used to align flow-matching text-to-image models with human preferences, but often leads to severe diversity collapse after fine-tuning. In RL, diversity is often as…
AnomalyClaw: A Universal Visual Anomaly Detection Agent via Tool-Grounded Refutation
Xi Jiang, Yinjie Zhao, Zesheng Yang +1
Visual anomaly detection (VAD) is crucial in many real-world fields, such as industrial inspection, medical imaging, infrastructure monitoring, and remote sensing. However, the spe…
When Rewards Disagree: Reward Weighting for Token-Efficient Video Reasoning
Zinuo Li, Yongxin Guo, Jun Liu +7
Human perception interprets video dynamics by constructing structured mental representations of entities, actions, and temporal boundaries before engaging in high-level reasoning.…
AD-Copilot: A Vision-Language Assistant for Industrial Anomaly Detection via Visual In-context Comparison
Xi Jiang, Yue Guo, Jian Li +7
Multimodal Large Language Models (MLLMs) have achieved impressive success in natural visual understanding, yet they consistently underperform in industrial anomaly detection (IAD).…
Mastering Negation: Boosting Grounding Models via Grouped Opposition-Based Learning
Zesheng Yang, Xi Jiang, Bingzhang Hu +4
Current vision-language detection and grounding models predominantly focus on prompts with positive semantics and often struggle to accurately interpret and ground complex expressi…
ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning
Xiaofeng Tan, Jun Liu, Yuanting Fan +7
Reinforcement Fine-Tuning (RFT) on flow-based models is crucial for preference alignment. However, they often introduce visual hallucinations like over-optimized details and semant…
UniPCB: A Unified Vision-Language Benchmark for Open-Ended PCB Quality Inspection
Fuxiang Sun, Xi Jiang, Jiansheng Wu +3
Multimodal Large Language Models (MLLMs) show promise for general industrial quality inspection, but fall short in complex scenarios, such as Printed Circuit Board (PCB) inspection…
SoftPatch+: Fully Unsupervised Anomaly Classification and Segmentation
Chengjie Wang, Xi Jiang, Bin-Bin Gao +4
Although mainstream unsupervised anomaly detection (AD) (including image-level classification and pixel-level segmentation)algorithms perform well in academic datasets, their perfo…
CAR: Controllable Autoregressive Modeling for Visual Generation
Ziyu Yao, Jialin Li, Yifeng Zhou +6
Controllable generation, which enables fine-grained control over generated outputs, has emerged as a critical focus in visual generative models. Currently, there are two primary te…
MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection
Xi Jiang, Jian Li, Hanqiu Deng +6
In the field of industrial inspection, Multimodal Large Language Models (MLLMs) have a high potential to renew the paradigms in practical applications due to their robust language…
Tuning-Free Adaptive Style Incorporation for Structure-Consistent Text-Driven Style Transfer
Yanqi Ge, Jiaqi Liu, Qingnan Fan +6
In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while…
SoftPatch: Unsupervised Anomaly Detection with Noisy Data
Xi Jiang, Ying Chen, Qiang Nie +6
Although mainstream unsupervised anomaly detection (AD) algorithms perform well in academic datasets, their performance is limited in practical application due to the ideal experim…
Toward Multi-class Anomaly Detection: Exploring Class-aware Unified Model against Inter-class Interference
Xi Jiang, Ying Chen, Qiang Nie +4
In the context of high usability in single-class anomaly detection models, recent academic research has become concerned about the more complex multi-class anomaly detection. Altho…
Tuning-Free Image Customization with Image and Text Guidance
Pengzhi Li, Qiang Nie, Ying Chen +7
Despite significant advancements in image customization with diffusion models, current methods still have several limitations: 1) unintended changes in non-target areas when regene…
A Bayesian Federated Learning Framework with Online Laplace Approximation
Liangxi Liu, Xi Jiang, Feng Zheng +4
Federated learning (FL) allows multiple clients to collaboratively learn a globally shared model through cycles of model aggregation and local model training, without the need to s…