collaborators

6 papers

cs.CL2026

Position Encoding in Transformers: From Absolute and Relative Methods to Rotary Position Embeddings and Long-Context Scaling

Jiguo Li

Self-attention models content-dependent interactions between tokens but does not by itself encode token order. Position encoding addresses this limitation by introducing absolute c…

cs.CL2026

The Evolution of Mixture-of-Experts Architectures in Large Language Models: Routing, Topology, Load Balancing, and Expert Parallelism

Jiguo Li

Mixture-of-Experts models increase parameter capacity while keeping the computation activated by each token bounded, but their architectural evolution cannot be explained by a chro…

cs.LG2026

GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

Jiaying Zhang, Lei Shi, Jiguo Li +4

Reinforcement Learning with Verifiable Rewards (RLVR) is a key paradigm for improving large-scale reasoning models. Unlike supervised fine-tuning (SFT), RLVR exhibits distinct opti…

cs.CL2026

MUSE: Multi-Domain Chinese User Simulation via Self-Evolving Profiles and Rubric-Guided Alignment

Zihao Liu, Hantao Zhou, Jiguo Li +5

User simulators are essential for the scalable training and evaluation of interactive AI systems. However, existing approaches often rely on shallow user profiling, struggle to mai…

cs.AI2026

Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments

Qinglong Shi, Donghai Wang, Hantao Zhou +5

Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders t…

cs.AI2025

VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of Xbench's Professional-Aligned Series

Pengyu Xu, Shijia Li, Ao Sun +15

We propose OutboundEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound calling scenarios. Unlike existing methods that…