Jingxuan Fan

Orcid: 0009-0007-9645-3539

According to our database1, Jingxuan Fan authored at least 13 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Scaling Reward Modeling without Human Supervision.
CoRR, March, 2026

Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers.
CoRR, January, 2026

ENCORE: Entropy-guided Reward Composition for Multi-head Safety Reward Models.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Closing the Data-Efficiency Gap Between Autoregressive and Masked Diffusion LLMs.
CoRR, October, 2025

User-Assistant Bias in LLMs.
CoRR, August, 2025

Multi-head Reward Aggregation Guided by Entropy.
CoRR, March, 2025

Data-adaptive Safety Rules for Training Reward Models.
CoRR, January, 2025

RuleAdapter: Dynamic Rules for training Safety Reward Models in RLHF.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics.
Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024
Intrusion Detection in IIoT: A Federated Approach Using TCN-GRU and Lookahead Optimization.
Proceedings of the 2024 14th International Conference on Communication and Network Security, 2024

Real-Time Secure Video Streaming System Based on FPGA and CUDA Technology.
Proceedings of the 2024 14th International Conference on Communication and Network Security, 2024

A Lightweight PUF-Based Authentication Protocol for M2M Communications in Industrial IoT.
Proceedings of the 2024 14th International Conference on Communication and Network Security, 2024

2022
Joint Semantic Segmentation and Object Detection Based on Relational Mask R-CNN.
Proceedings of the Intelligent Computing Theories and Application, 2022


  Loading...