activity
20232026
most citedMIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense

2 citations · 4 across the 12 of their papers we have counts for

collaborators

12 papers

cs.LG2026

Weak Ties, Strong Signals: Efficient Training Data Detection in Diffusion LLMs via Independent Token Sampling

Hongyao Yu, Tianqu Zhuang, Ziyuan Xu +4

Diffusion large language models (dLLMs) offer a compelling alternative to autoregressive models, yet they may expose sensitive training data during denoising. Detecting such usage…

cs.CV2026

Beyond Illumination: A Conditional Mutual Information-Guided Network for Low-Light Image Enhancement

Ya-nan Guan, Shaonan Zhang, Tao Dai +5

Low-light image enhancement (LLIE) seeks to restore structural fidelity, natural color rendition, and proper exposure from images captured under inadequate lighting conditions. Rec…

cs.CV2026

NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)

Ya-nan Guan, Shaonan Zhang, Hang Guo +55

In this paper, we present a comprehensive overview of the NTIRE 2026 3rd Restore Any Image Model (RAIM) challenge, with a specific focus on Track 3: AI Flash Portrait. Despite sign…

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.CL2026

Towards Distillation-Resistant Large Language Models: An Information-Theoretic Perspective

Hao Fang, Tianyi Zhang, Tianqu Zhuang +6

Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can still exploit their outputs to extr…

cs.LG2025

Large Foundation Model for Ads Recommendation

Shangyu Zhang, Shijie Quan, Zhongren Wang +30

Online advertising relies on accurate recommendation models, with recent advances using pre-trained large-scale foundation models (LFMs) to capture users' general interests across…