collaborators

7 papers

cs.CL2026

Refusing Intent, Not Form: Wrapper-Based Intent-Group Supervision for LLM Safety

Ping Wu, Haibo Tong, Feifei Zhao +7

Safety tuning can improve harmful refusal, but models may learn surface-form shortcuts: wrapped harmful prompts bypass safety, while similarly wrapped benign prompts are over-refus…

cs.AI2026

Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models

Jialin Wu, Wei Shi, Han Shen +5

Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textu…

cs.AI2026

Abstraction Generation for Generalized Planning with Pretrained Large Language Models

Zhenhe Cui, Huaxiang Xia, Hangjun Shen +3

Qualitative Numerical Planning (QNP) serves as an important abstraction model for generalized planning (GP), which aims to compute general plans that solve multiple instances at on…

cs.LG2026

On Entropy Control in LLM-RL Algorithms

Han Shen

For RL algorithms, appropriate entropy control is crucial to their effectiveness. To control the policy entropy, a commonly used method is entropy regularization, which is adopted…

cs.AI2026

Light Alignment Improves LLM Safety via Model Self-Reflection with a Single Neuron

Sicheng Shen, Mingyang Lv, Han Shen +7

The safety of large language models (LLMs) has increasingly emerged as a fundamental aspect of their development. Existing safety alignment for LLMs is predominantly achieved throu…

cs.CV2025

Kwai Keye-VL 1.5 Technical Report

Biao Yang, Bin Wen, Boyang Ding +58

In recent years, the development of Large Language Models (LLMs) has significantly advanced, extending their capabilities to multimodal tasks through Multimodal Large Language Mode…