Jing-Wei Zhang

Discourse-guided multi-view adaptive fusion for multimodal emotion recognition in conversation

LA-CPD: Local-Evidence-Aware Change-Point Detection for Human-LLM Authorship Segmentation

LA-CPD is proposed, a structured method that transforms noisy sentence-level score sequences into coherent authorship segments and outperforms WCP+AIC, increasing sentence-level accuracy from 0.747 to 0.796 while improving boundary localization and LLM-span delineation.

C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text

Large Language Models (LLMs) increasingly participate in writing by modifying or extending human drafts, causing machine involvement to vary in both form and extent. Yet most Machine-Generated Text (MGT) detectors are evaluated only on fully human-written versus fully AI-generated text. Because human--AI collaboration...

Trajectory-Guided Forget-Recover Network for Continual LLM Unlearning

The Trajectory-guided Forget-Recover Network (TFR-Net) is proposed, which separates persistent target-related channels from transient hotspots and suppresses only the persistent ones, and achieves a more favorable trade-off between unlearning effectiveness and retained utility than representative baselines.