Search Results - "Lin, Junyang"

A Gesture Air-Writing Tracking Method that uses 24 GHz SIMO Radar SoC by Wang, Pengcheng, Lin, Junyang, Wang, Fuyue, Xiu, Jianping, Lin, Yue, Yan, Na, Xu, Hongtao

“…Gesture air-writing is an advanced nontouching interaction method that replaces traditional typewriter keyboards, touch screens and other input devices. Due to…”
Get full text

Immunogenicity of Varicella Zoster Virus DNA Vaccines Encoding Glycoprotein E and Immediate Early Protein 63 in Mice by Liu, Jie, Lin, Junyang, Cai, Linjun, Sun, Jie, Ding, Xue, Wang, Cenrong, Wu, Yanchun, Gao, Xiaoling, Su, Weiheng, Jiang, Chunlai

“…Herpes zoster (HZ) is caused by the reactivation of latent varicella-zoster virus (VZV) from the sensory ganglia due to aging or immunosuppression…”
Get full text

Nomogram for predicting the overall survival and cancer-specific survival of patients with intraductal carcinoma of the prostate by Cui, Yongqiang, Lin, Junyang, Sun, Dingqi, Zhang, Hui, Diao, Tongxiang, Fu, Qiang

“…Purpose Intraductal carcinoma of the prostate (IDC-P) is a histological subtype that differs from conventional acinar adenocarcinoma in terms of its origin,…”
Get full text

Connecting Language and Vision for Natural Language-Based Vehicle Retrieval by Bai, Shuai, Zheng, Zhedong, Wang, Xiaohan, Lin, Junyang, Zhang, Zhu, Zhou, Chang, Yang, Hongxia, Yang, Yi

“…Vehicle search is one basic task for the efficient traffic management in terms of the AI City. Most existing prac-tices focus on the image-based vehicle…”
Get full text

Future-Prediction-Based Model for Neural Machine Translation by Wei, Bingzhen, Lin, Junyang

“…We propose a novel model for Neural Machine Translation (NMT). Different from the conventional method, our model can predict the future text length and words…”
Get full text

Rethinking Data Selection at Scale: Random Selection is Almost All You Need by Xia, Tingyu, Yu, Bowen, Dang, Kai, Yang, An, Wu, Yuan, Tian, Yuan, Chang, Yi, Lin, Junyang

“…Supervised fine-tuning (SFT) is crucial for aligning Large Language Models (LLMs) with human instructions. The primary goal during SFT is to select a small yet…”
Get full text

Rotated Runtime Smooth: Training-Free Activation Smoother for accurate INT4 inference by Yi, Ke, Liu, Zengke, Zhang, Jianwei, Li, Chengyuan, Zhang, Tong, Lin, Junyang, Zhou, Jingren

“…Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial…”
Get full text

Analyzing and Mitigating Inconsistency in Discrete Audio Tokens for Neural Codec Language Models by Liu, Wenrui, Guo, Zhifang, Xu, Jin, Lv, Yuanjun, Chu, Yunfei, Zhao, Zhou, Lin, Junyang

“…Building upon advancements in Large Language Models (LLMs), the field of audio processing has seen increased interest in training audio generation tasks with…”
Get full text

SongTrans: An unified song transcription and alignment method for lyrics and notes by Wu, Siwei, He, Jinzheng, Yuan, Ruibin, Wei, Haojie, Wei, Xipin, Lin, Chenghua, Xu, Jin, Lin, Junyang

“…The quantity of processed data is crucial for advancing the field of singing voice synthesis. While there are tools available for lyric or note transcription…”
Get full text

Synthesizing Text-to-SQL Data from Weak and Strong LLMs by Yang, Jiaxi, Hui, Binyuan, Yang, Min, Yang, Jian, Lin, Junyang, Zhou, Chang

“…The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to-SQL tasks. In this paper, we introduce a…”
Get full text

Can Large Language Models Always Solve Easy Problems if They Can Solve Harder Ones? by Yang, Zhe, Zhang, Yichang, Liu, Tianyu, Yang, Jian, Lin, Junyang, Zhou, Chang, Sui, Zhifang

“…Large language models (LLMs) have demonstrated impressive capabilities, but still suffer from inconsistency issues (e.g. LLMs can react differently to…”
Get full text

An Image is Worth 1/2 Tokens After Layer 2: Plug-and-Play Inference Acceleration for Large Vision-Language Models by Chen, Liang, Zhao, Haozhe, Liu, Tianyu, Bai, Shuai, Lin, Junyang, Zhou, Chang, Chang, Baobao

“…In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5,…”
Get full text

P-MMEval: A Parallel Multilingual Multitask Benchmark for Consistent Evaluation of LLMs by Zhang, Yidan, Deng, Boyi, Wan, Yu, Yang, Baosong, Wei, Haoran, Huang, Fei, Yu, Bowen, Lin, Junyang, Zhou, Jingren

“…Recent advancements in large language models (LLMs) showcase varied multilingual capabilities across tasks like translation, code generation, and reasoning…”
Get full text

Language Models can Self-Lengthen to Generate Long Texts by Quan, Shanghaoran, Tang, Tianyi, Yu, Bowen, Yang, An, Liu, Dayiheng, Gao, Bofei, Tu, Jianhong, Zhang, Yichang, Zhou, Jingren, Lin, Junyang

“…Recent advancements in Large Language Models (LLMs) have significantly enhanced their ability to process long contexts, yet a notable gap remains in generating…”
Get full text

Modality Competition: What Makes Joint Training of Multi-modal Network Fail in Deep Learning? (Provably) by Huang, Yu, Lin, Junyang, Zhou, Chang, Yang, Hongxia, Huang, Longbo

“…Despite the remarkable success of deep multi-modal learning in practice, it has not been well-explained in theory. Recently, it has been observed that the best…”
Get full text

Aligning CodeLLMs with Direct Preference Optimization by Miao, Yibo, Gao, Bofei, Quan, Shanghaoran, Lin, Junyang, Zan, Daoguang, Liu, Jiaheng, Yang, Jian, Liu, Tianyu, Deng, Zhijie

“…The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention…”
Get full text

Aligning Large Language Models via Self-Steering Optimization by Xiang, Hao, Yu, Bowen, Lin, Hongyu, Lu, Keming, Lu, Yaojie, Han, Xianpei, Sun, Le, Zhou, Jingren, Lin, Junyang

“…Automated alignment develops alignment systems with minimal human intervention. The key to automated alignment lies in providing learnable and accurate…”
Get full text

A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegrained Image Generation by Chen, Liang, Tan, Sinan, Cai, Zefan, Xie, Weichu, Zhao, Haozhe, Zhang, Yichi, Lin, Junyang, Bai, Jinze, Liu, Tianyu, Chang, Baobao

“…This work tackles the information loss bottleneck of vector-quantization (VQ) autoregressive image generation by introducing a novel model architecture called…”
Get full text

Routing to the Expert: Efficient Reward-guided Ensemble of Large Language Models by Lu, Keming, Yuan, Hongyi, Lin, Runji, Lin, Junyang, Yuan, Zheng, Zhou, Chang, Zhou, Jingren

“…The complementary potential of Large Language Models (LLM) assumes off-the-shelf LLMs have heterogeneous expertise in a wide range of domains and tasks so that…”
Get full text

Self-Evolved Diverse Data Sampling for Efficient Instruction Tuning by Wu, Shengguang, Lu, Keming, Xu, Benfeng, Lin, Junyang, Su, Qi, Zhou, Chang

“…Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer…”
Get full text