Yuxuan Li

The paper proposes GeoMark, a geometry-aware localized watermarking framework that robustly protects Embedding-as-a-Service (EaaS) against model stealing and copyright infringement while preserving utility.

The paper introduces PhoneWorld, a scalable pipeline that automatically converts real-world GUI trajectories and screenshots into controllable, reproducible phone-use environments, significantly improving agent performance across multiple mobile benchmarks.

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, significantly boosting agent performance.

This paper proposes IOHMM-BO, a method using a high-order input-output hidden Markov model with Bayesian optimization for predictive dynamic power management in 5G NR user equipment, achieving 43% energy saving with low computational overhead.

This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (MultiTF). MBD-LMs improve inter-block parallelism and wall-clock acceleration.

This paper introduces DramaSR-532K, a large-scale benchmark for speaker recognition in long-form TV dramas, and proposes DramaSR-LRM, a robust approach for speaker recognition using a large reasoning model.