Ang Lv

PhD student, Renmin University of China

Joined

September 2021

Names

Ang Lv (Preferred)

Emails

****@bupt.edu.cn (Confirmed)

****@ruc.edu.cn (Confirmed)

Personal Links

Career & Education History

PhD student

Renmin University of China (ruc.edu.cn)

2022 – 2027

Advisors, Relations & Conflicts

Coauthor

Jin Ma

2025 – Present

Coauthor

Ruobing Xie

2024 – Present

Coauthor

Xu Tan

2022 – 2025

Expertise

Foundation Model Architecture/Optimization

2024 – Present

Language Model

2021 – Present

Publications

Union-of-Experts: Experts in Mixture-of-Experts are Secretly Routers
Songhao Wu, Ang Lv, Ruobing Xie, Xingwu Sun, Di Wang, Rui Yan, Yankai Lin
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
Kaiyi Zhang, Ang Lv, Jinpeng Li, yongbo wang, Feng Wang, Haoyuan Hu, Rui Yan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
More Expressive Attention with Negative Weights
Ang Lv, Ruobing Xie, Shuaipeng Li, Jiayi Liao, Xingwu Sun, Zhanhui Kang, Di Wang, Rui Yan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
The Climb Carves Wisdom Deeper Than the Summit: On the Importance of Reasoning Patterns
Ang Lv, Ruobing Xie, Xingwu Sun, Zhanhui Kang, Rui Yan
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
Ang Lv, Jin Ma, Yiyuan Ma, Siyuan Qiao
- ICLR 2026 Oral
- Readers: Everyone
PolarQuant: Leveraging Polar Transformation for Key Cache Quantization and Decoding Acceleration
Songhao Wu, Ang Lv, xiao feng, Yufei zhang, Xun Zhang, Guojun Yin, Wei Lin, Rui Yan
- NeurIPS 2025 poster
- Readers: Everyone
Autonomy-of-Experts Models
Ang Lv, Ruobing Xie, Yining Qian, Songhao Wu, Xingwu Sun, Zhanhui Kang, Di Wang, Rui Yan
- ICML 2025 poster
- Readers: Everyone
GETMusic: Generating Music Tracks with a Unified Representation and Diffusion Framework
Ang Lv, Xu Tan, Peiling Lu, Wei Ye, Shikun Zhang, Jiang Bian, Ji-Rong Wen, Rui Yan
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead
Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, yongbo wang, Feng Wang, Jingtong Wu, xin lu, Rui Yan
- ICLR 2025 Conference Withdrawn Submission
- Readers: Everyone
PEAR: Position-Embedding-Agnostic Attention Re-weighting Enhances Retrieval-Augmented Generation with Zero Inference Overhead
Tao Tan, Yining Qian, Ang Lv, Hongzhan Lin, Songhao Wu, yongbo wang, Feng Wang, Jingtong Wu, xin lu, Rui Yan
- WWW 2025 Oral
- Readers: Everyone

View all 27 publications

Co-Authors

View all 65 co-authors