collaborators

6 papers

cs.AI2026

Your Probabilistic JEPA Is Secretly a Hidden Markov Model: A State-Space Interpretation of Joint-Embedding Predictive Learning

Yongchao Huang

A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations, propagation through a Markov transition, and emission back to observation sp…

cs.CL2026

How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel

Chang Liu, Chaoyang Ning, Dayi Jiang +32

Traditional industrial agents rely on modular pipelines, including Router, Retriever, Planner, Executor, Responder, Reviewer, and other components. These systems often fracture int…

cs.CY2026

LSSF: Safety Alignment for Large Language Models through Low-Rank Safety Subspace Fusion

Guanghao Zhou, Panjia Qiu, Cen Chen +4

The safety mechanisms of large language models (LLMs) exhibit notable fragility, as even fine-tuning on datasets without harmful content may still undermine their safety capabiliti…

cs.AI2025

Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary

Licheng Pan, Yongqi Tong, Xin Zhang +3

Large language models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they often refuse to answer legitimate queries--a phenomenon known as overr…

cs.CL2025

REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective

Zhihao Xu, Yongqi Tong, Xin Zhang +2

Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e.g., helpfulness) frequently compromises oth…

cs.CR2025

CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models

Guanghao Zhou, Panjia Qiu, Mingyuan Fan +4

Despite explicit alignment efforts for large language models (LLMs), they can still be exploited to trigger unintended behaviors, a phenomenon known as "jailbreaking." Current jail…