PL
Pengzhang Liu
cs.AIcs.CVcs.LG
On Valency
published · living versionsW_5n5rdpjf·v1 · currentpublished
Advancement or Acceleration? How Data Curation Improves LLM Training
with Jiaxing Wang, Zicheng Zhang, Deping Xiang, Jin Xu +3
1 version
W_petey6wk·v1published
Preprints & journals
15 papers in the corpus · 2022–2026JD Oxygen AI Item Center (Oxygen AIIC) V1: An Industrial-Scale LLM/VLM-Centric Solution for Item Understanding, Management, and Applications2606.28070v2 · Oxygen AIIC, Chan Long, Chao Liu et al.2026 · 0 citationsarXiv
BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training2606.18650v1 · Jiaxing Wang, Deping Xiang, Jin Xu et al.2026 · 0 citationsarXiv
The Hidden Power of Scaling Factor in LoRA Optimization2606.12883v1 · Zicheng Zhang, Haoran Li, Jiaxing Wang et al.2026 · 0 citationsarXiv
TANDEM: Bi-Level Data Mixture Optimization with Twin Networks2606.04401v1 · Jiaxing Wang, Deping Xiang, Jin Xu et al.2026 · 0 citationsarXiv
Spectral Disentanglement and Enhancement: A Dual-domain Contrastive Framework for Representation Learning2602.09066v1 · Jinjin Guo, Yexin Li, Zhichao Huang et al.2026 · 0 citationsarXiv
FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learning2511.20997v1 · Jiaoyang Li, Jun Fang, Tianhao Gao et al.2025 · 0 citationsarXiv
Temporal Modeling With Frozen Vision-Language Foundation Models for Parameter-Efficient Text-Video Retrieval.40924521 · Shen, Leqi, Hao, Tianxiang, He, Tao et al.2025 · 3 citationsIEEE transactions on neural networks and learning systems. 2025;36(10):17527-17540
The Primacy of Magnitude in Low-Rank Adaptation2507.06558v2 · Zicheng Zhang, Haoran Li, Yifeng Zhang et al.2025 · 0 citationsNeurIPS 2025
DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval2506.08887v1 · Leqi Shen, Guoqiang Gong, Tianxiang Hao et al.2025 · 8 citationsarXiv
FastVID: Dynamic Density Pruning for Fast Video Large Language Models2503.11187v3 · Leqi Shen, Guoqiang Gong, Tao He et al.2025 · 7 citationsarXiv
LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs2503.11205v1 · Leqi Shen, Tao He, Guoqiang Gong et al.2025 · 0 citationsarXiv
DAR-Prompt: Dynamic Regulation in Prompt Tuning for Multi-Label Zero-Shot Learning.41182924 · Liang, Yiwen, Chen, Hui, Lin, Zijia et al.2025 · 1 citationIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2025;34:7697-7711
TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval2409.01156v2 · Leqi Shen, Tianxiang Hao, Tao He et al.2024 · 0 citationsarXiv
Exploring Structured Semantic Prior for Multi Label Recognition with Incomplete Labels2303.13223v5 · Zixuan Ding, Ao Wang, Hui Chen et al.2023 · 43 citationsIEEE/CVF Conference on Computer Vision and Pattern Recognition 2023
Prompt Tuning with Soft Context Sharing for Vision-Language Models2208.13474v2 · Kun Ding, Ying Wang, Pengzhang Liu et al.2022 · 20 citationsarXiv
Career total: 35 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.