Ruijun Huang

According to our database1, Ruijun Huang authored at least 9 papers between 2023 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
MeasHalu: Mitigation of Scientific Measurement Hallucinations for Large Language Models with Enhanced Reasoning.
CoRR, April, 2026

The Curse and Blessing of Mean Bias in FP4-Quantized LLM Training.
CoRR, March, 2026

Multi-Head Attention as a Source of Catastrophic Forgetting in MoE Transformers.
CoRR, February, 2026

SD-MoE: Spectral Decomposition for Effective Expert Specialization.
CoRR, February, 2026

Spectra: Rethinking Optimizers for LLMs Under Spectral Anisotropy.
CoRR, February, 2026

Dispelling the Curse of Singularities in Neural Network Optimizations.
CoRR, February, 2026

2025
Metis: Training LLMs with FP4 Quantization.
CoRR, September, 2025

Oracle-MoE: Locality-preserving Routing in the Oracle Space for Memory-constrained Large Language Model Inference.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2023
ML-Bench: Large Language Models Leverage Open-source Libraries for Machine Learning Tasks.
CoRR, 2023


  Loading...