Get started
Author

Bei Liu

DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration
2025 · Tianteng Gu, Bei Liu, et al. · neural information processing systems · 1
DesireKV: Decoupling Sensitivity and Importance for Reasoning-Aware KV Cache Compression
2026 · Pengyu Cheng, Jiacheng Wang, et al. · Proceedings of the AAAI Conference on Artificial Intelligence
Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs
2026 · Binxing Xu, Hao Gu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training–Inference Mismatch
2026 · Hao Gu, Hao Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models
2026 · Tianle Chen, Pengyu Cheng, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 6
Citation count: 1
H-index: 1
I10-index:
Year
Topic
Type