Jin Ma

Researcher, ByteDance Inc.

Joined

May 2025

Names

Jin Ma (Preferred)

Emails

****@foxmail.com (Confirmed)

****@bytedance.com (Confirmed)

Personal Links

Google Scholar

Career & Education History

Researcher

ByteDance Inc. (bytedance.com)

2022 – Present

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats
Mengzhao Chen, Meng Wu, Hui Jin, Zhihang Yuan, Jing Liu, Chaoyi Zhang, Yunshui Li, Jie Huang, Jin Ma, Zeyue Xue, Zhiheng Liu, Xingyan Bin, Ping Luo
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Scaling Law for Quantization-Aware Training
Mengzhao Chen, Chaoyi Zhang, Jing Liu, Yutao Zeng, Zeyue Xue, Zhiheng Liu, Yunshui Li, Jin Ma, Jie Huang, zhou Xun, Ping Luo
- Submitted to ICLR 2026
- 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
GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models
Chen Zheng, Yuhang Cai, Deyi Liu, Jin Ma, Yiyuan Ma, Yuan Yang, Jing Liu, Yutao Zeng, Xun Zhou, Siyuan Qiao
- Submitted to ICLR 2026
- Readers: Everyone
HSA: Head-wise Sparse Attention for Efficient and Accurate Long-context Inference
Jing Liu, Jianqiao Lu, Yao Luo, Yuan Yang, Chen Zheng, Deyi Liu, Mengzhao Chen, Chaoyi Zhang, Yunshui Li, Jin Ma, Yutao Zeng, Ya Wang, Hongmin chen, Ziqiang Pei, Fan Xia, Tianqi Zhang, Xiaoying Jia, Yiyuan Ma, Siyuan Qiao
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Model Merging in Pre-training of Large Language Models
Yunshui Li, Yiyuan Ma, Shen Yan, Chaoyi Zhang, Jing Liu, Jianqiao Lu, Ziwen Xu, Mengzhao Chen, Minrui Wang, Shiyi Zhan, Jin Ma, Xunhao Lai, Yao Luo, Xingyan Bin, Hongbin Ren, Mingji Han, Wenhao Hao, Bairen Yi, LingJun Liu, Bole Ma et al. (4 additional authors not shown)
- NeurIPS 2025 poster
- Readers: Everyone

Co-Authors

View all 43 co-authors

Jin Ma

Names

Emails

Personal Links

Career & Education History

Advisors, Relations & Conflicts

Expertise

Publications

INT v.s. FP: A Comprehensive Study of Fine-Grained Low-bit Quantization Formats

Scaling Law for Quantization-Aware Training

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss

GatePro: Parameter-Free Expert Selection Optimization for Mixture-of-Experts Models

HSA: Head-wise Sparse Attention for Efficient and Accurate Long-context Inference

Model Merging in Pre-training of Large Language Models

Co-Authors