SL
Shih-Yang Liu
cs.AIcs.CLcs.LGcs.ARcs.CVcs.NEeess.IV
On Valency
published · living versionsW_xgra3rkn·v1 · currentpublished
You don't need long context
with Peter Belcak, Saurav Muralidharan, Jindong Jiang, Yonggan Fu +7
1 version
Preprints & journals
15 papers in the corpus · 2023–2026When Do We Need On-Policy Distillation? Distilling on Offline Student Rollouts Is Often Better2610.11291v1 · Siyan Zhao, Yonggan Fu, Jindong Jiang et al.2026 · 0 citationsarXiv
31.1 A 14.08-to-135.69Token/s ReRAM-on-Logic Stacked Outlier-Free Large-Language-Model Accelerator with Block-Clustered Weight-Compression and Adaptive Parallel-Speculative-Decoding2605.09375v1 · Pingcheng Dong, Yonghao Tan, Xuejiao Liu et al.2026 · 1 citationarXiv
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization2601.05242v1 · Shih-Yang Liu, Xin Dong, Ximing Lu et al.2026 · 0 citationsarXiv
A 28nm 0.22{\mu}J/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation2512.17555v2 · Pingcheng Dong, Yonghao Tan, Xuejiao Liu et al.2025 · 11 citations2025 IEEE International Solid-State Circuits Conference (ISSCC), vol. 68, pp. 01-03, 2025
DLER: Doing Length pEnalty Right - Incentivizing More Intelligence per Token via Reinforcement Learning2510.15110v1 · Shih-Yang Liu, Xin Dong, Ximing Lu et al.2025 · 0 citationsarXiv
APSQ: Additive Partial Sum Quantization with Algorithm-Hardware Co-Design2505.03748v1 · Yonghao Tan, Pingcheng Dong, Yongkun Wu et al.2025 · 1 citationarXiv
Hymba: A Hybrid-head Architecture for Small Language Models2411.13676v1 · Xin Dong, Yonggan Fu, Shizhe Diao et al.2024 · 2 citationsarXiv
EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation2410.21271v6 · Shih-Yang Liu, Maksim Khadkevich, Nai Chit Fung et al.2024 · 0 citationsarXiv
RoLoRA: Fine-tuning Rotated Outlier-free LLMs for Effective Weight-Activation Quantization2407.08044v2 · Xijie Huang, Zechun Liu, Shih-Yang Liu et al.2024 · 7 citationsarXiv
Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers2403.19591v2 · Pingcheng Dong, Yonghao Tan, Dong Zhang et al.2024 · 13 citationsarXiv
DoRA: Weight-Decomposed Low-Rank Adaptation2402.09353v6 · Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin et al.2024 · 74 citationsarXiv
CMOSE: Comprehensive Multi-Modality Online Student Engagement Dataset with High-Quality Labels2312.09066v2 · Chi-hsuan Wu, Shih-yang Liu, Xijie Huang et al.2023 · 12 citationsarXiv
LLM-FP4: 4-Bit Floating-Point Quantized Transformers2310.16836v1 · Shih-yang Liu, Zechun Liu, Xijie Huang et al.2023 · 50 citationsProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Efficient and Robust Quantization-aware Training via Adaptive Coreset Selection2306.07215v3 · Xijie Huang, Zechun Liu, Shih-Yang Liu et al.2023 · 8 citationsarXiv
Oscillation-free Quantization for Low-bit Vision Transformers2302.02210v3 · Shih-Yang Liu, Zechun Liu, Kwang-Ting Cheng2023 · 8 citationsICML 2023
Career total: 23 works. 15 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.