Jian Yang
6 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
AgentVisor is a novel defense framework that uses semantic virtualization, inspired by OS principles, to significantly reduce LLM agent vulnerability to prompt injection while maintaining high utility.
MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.
The paper proposes RoRo, a rubric-guided process reward framework that improves stepwise model routing by evaluating the quality of intermediate reasoning steps, leading to better performance and cost trade-offs.
The paper proposes a dual-interventional framework to characterize how linguistic structures and contextual cues influence LLMs' spatial reasoning for navigation, finding that topological information is crucial, while semantic details can be unreliable.
The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small set of paired anchors.
The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.
Papers
Preserving Data Privacy in Learning Causal Structure with Fully Homomorphic Encryption
The paper proposes a novel method using fully homomorphic encryption (FHE) to learn causal structures while preserving data privacy, achieving high consistency and practical efficiency.