activity
20242026
collaborators

14 papers

cs.CV2026

Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization

Hao Fang, Jinyu Li, Jiawei Kong +4

While multimodal reasoning models (MLRMs) have exhibited impressive capabilities, they remain prone to hallucinations, and effective solutions are still underexplored. In this pape…

cs.CV2026

Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization

Hao Fang, Wenbo Yu, Bin Chen +4

Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning, allowing multiple clients to collaboratively train a global model…

cs.CV2026

Looking Back and Forth: Cross-Image Attention Calibration and Attentive Preference Learning for Multi-Image Hallucination Mitigation

Xiaochen Yang, Hao Fang, Jiawei Kong +3

Although large vision-language models (LVLMs) have demonstrated remarkable capabilities, they are prone to hallucinations in multi-image tasks. We attribute this issue to limitatio…

cs.CV2025

Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization

Yixiang Qiu, Yanhan Liu, Hongyao Yu +4

The growing complexity of Deep Neural Networks (DNNs) has led to the adoption of Split Inference (SI), a collaborative paradigm that partitions computation between edge devices and…

cs.CV2025

ICAS: Detecting Training Data from Autoregressive Image Generative Models

Hongyao Yu, Yixiang Qiu, Yiheng Yang +6

Autoregressive image generation has witnessed rapid advancements, with prominent models such as scale-wise visual auto-regression pushing the boundaries of visual synthesis. Howeve…

cs.CL2025

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

Hao Fang, Changle Zhou, Jiawei Kong +3

Large Vision-Language Models (LVLMs) are susceptible to hallucinations, where generated responses seem semantically plausible yet exhibit little or no relevance to the input image.…