6 papers
Learning from a Thoughtful Teacher: Adaptive On-Policy Self-Distillation for Mathematical Reasoning
Jiacheng Du, Weiwei Xie, Tianyi Du +3
On-policy self-distillation (OPSD) trains a question-only student with token-level feedback from a teacher given training-only privileged information (PI). OPSD therefore provides…
MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps
Sujin Chen, Lijun Li, Tianyi Du +1
LLM-powered GUI agents that autonomously operate smartphones are rapidly transitioning from research prototypes to early real-world deployment. However, because these agents routin…
DeepSafe-SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring
Chunxiao Li, Yuan Xiong, Lijun Li +4
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely…
DeepSight: An All-in-One LM Safety Toolkit
Bo Zhang, Jiaxuan Guo, Lijun Li +17
As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) s…
Improving Latent Reasoning in LLMs via Soft Concept Mixing
Kang Wang, Xiangyu Duan, Tianyi Du
Unlike human reasoning in abstract conceptual spaces, large language models (LLMs) typically reason by generating discrete tokens, which potentially limit their expressive power. T…
The Plot Twist: Jailbreaking Unified Multimodal Models with a Three-Act NarrativeAttack
Shaoxiong Guo, Tianyi Du, Lijun Li +3
Unified Multimodal Understanding and Generation Models (UMMs) increasingly combine visual understanding and image generation within a single interactive workflow, making generated…