activity
20242026
most citedAn overview of domain-specific foundation model: key technologies, applications and challenges

18 citations · 63 across the 27 of their papers we have counts for

collaborators
Showing cs.LGShow all

10 papers · 1 filter

cs.LG2026

Low-Interaction-Rank Learning: Unifying Multiplicative Dual-Encoder Heads

Zijian Zhao, Sen Li

A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings. This architecture has been developed inde…

cs.LG2026

Is Per-Agent Policy Composition Safe? Rethinking Successor-Feature Transfer in Cooperative Multi-Agent Reinforcement Learning

Zijian Zhao, Sen Li

Many reinforcement learning systems, from fleet management to traffic signal control, must serve an objective that changes dynamically after deployment, and retraining a policy for…

cs.LG2026

Bridging MARL to SARL: An Order-Independent Multi-Agent Transformer via Latent Consensus

Zijian Zhao, Jing Gao, Sen Li

Cooperative multi-agent reinforcement learning (MARL) is widely used to address large joint observation and action spaces by decomposing a centralized control problem into multiple…

cs.LG2026

Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

Chuxue Cao, Jinluan Yang, Haoran Li +8

Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic system…

cs.LG2025

AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt

Zijian Zhao, Yitong Shang, Sen Li

Accurate traffic prediction is essential for Intelligent Transportation Systems, including ride-hailing, urban road planning, and vehicle fleet management. However, due to signific…

cs.LG2025

Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?

Zijian Zhao, Sen Li

On-demand ride-sharing platforms, such as Uber and Lyft, face the intricate real-time challenge of bundling and matching passengers-each with distinct origins and destinations-to a…

cs.LG2025

Automatic Stage Lighting Control: Is it a Rule-Driven Process or Generative Task?

Zijian Zhao, Dian Jin, Zijing Zhou +1

Stage lighting is a vital component in live music performances, shaping an engaging experience for both musicians and audiences. In recent years, Automatic Stage Lighting Control (…

cs.LG2025

Label Unbalance in High-frequency Trading

Zijian Zhao, Xuming Zhang, Jiayu Wen +2

In financial trading, return prediction is one of the foundation for a successful trading system. By the fast development of the deep learning in various areas such as graphical pr…

cs.LG2024★ 3 cited

CSI-BERT2: A BERT-inspired Framework for Efficient CSI Prediction and Classification in Wireless Communication and Sensing

Zijian Zhao, Fanyi Meng, Zhonghao Lyu +3

Channel state information (CSI) is a fundamental component in both wireless communication and sensing systems, enabling critical functions such as radio resource optimization and e…

cs.LG2024★ 15 cited

Finding the Missing Data: A BERT-inspired Approach Against Package Loss in Wireless Sensing

Zijian Zhao, Tingwei Chen, Fanyi Meng +3

Despite the development of various deep learning methods for Wi-Fi sensing, package loss often results in noncontinuous estimation of the Channel State Information (CSI), which neg…