Generative recommendation models based on autoregressive decoding have been adopted as alternatives to classical ranking-based systems. While their modeling flexibility has been widely studied, their resilience to data poisoning remains largely unexplored. In this work, we ask: how susceptible are generative recommende...
Zhuo-Xuan Zhang, Jinhao Duan, Xin-Yu Zhao et al.· 0 citations
Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to correct an agent, but whether it can guide these decisions remains unclear. We steer agent trajectories separately at every non-terminal step with each of four mechanisms and...
Han Li, Jinhao Duan, Guan-Hua Zhu et al.· 0 citations
This work proposes Multi-Scale Autoencoder with Cross-Scale Attention for TSAD (MSCAD), a simple yet powerful semi-supervised TSAD framework founded on parallel autoencoder branches corresponding to different patch sizes.
Jia-Heng Guo, H. Zhang, Yu-Chao Huang et al.· 0 citations
This work proposes ARIA (autoencoder-gated inference-time unlearning), a test-time unlearning method that leaves model weights intact and gates access to unwanted knowledge only when generation enters a forget-related state and introduces three post-unlearning adversarial attacks targeting weight-space and decoding-spa...
Ping-Zhi Li, Jinhao Duan, Vaishnav Tadiparthi et al.· 0 citations
The proposed Stochastic Meta-Unlearning (SMU), a bilevel framework that uses VLM-level feedback to learn an unlearning-ready initialization, suggests that VLM-level feedback can make language-backbone unlearning more reliable and more transferable for VLMs.
Zijie Liu, Jinhao Duan, Gaowen Liu et al.· arXiv.org· 0 citations
The results show that reliable tabular LLM unlearning depends not only on the forgetting objective, but also on how retain constraints are constructed, which shows that reliable tabular LLM unlearning depends not only on the forgetting objective, but also on how retain constraints are constructed.
Zi-Jie Liu, Jinhao Duan, Bing-Qi Shang et al.· 0 citations
DrugReason is proposed, a multi-view reasoning framework that integrates grounded KG reasoning with LLM-generated mechanistic inference for drug repurposing and achieves competitive or superior results compared with graph-based alternatives, while providing interpretable routing-based predictions.
Zi-Jie Liu, Hong-Xuan Li, Zhen Tan et al.· 0 citations
HarnessRisk, a lifecycle oriented benchmark that organizes agent harness safety into six operational phases including Harness Configuration, Capability Extension, Runtime Operation, State Persistence, Action Control, and Incident Recovery, finds that explicit risk recognition does not reliably lead to safe action as so...
Ya Bai, Jinhao Duan, Jie Peng et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
