Publications (27)
The NANOGrav 15-year Data Set: Observations and Timing of 68 Millisecond Pulsars
Gabriella Agazie, Md Faisal Alam, Akash Anumarlapudi +97
We present observations and timing analyses of 68 millisecond pulsars (MSPs) comprising the 15-year data set of the North American Nanohertz Observatory for Gravitational Waves (NA…
Bag of Tricks for Optimizing Transformer Efficiency
Ye Lin, Yanyang Li, Tong Xiao +1
Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But…
JEPA-VLA: Video Predictive Embedding is Needed for VLA Models
Shangchen Miao, Ningya Feng, Jialong Wu +4
Recent vision-language-action (VLA) models built upon pretrained vision-language models (VLMs) have achieved significant improvements in robotic manipulation. However, current VLAs…
Defect-engineered graphene for bulk supercapacitors with high energy and power densities
Jingyi Zhu, Anthony S. Childress, Mehmet Karakaya +4
The development of high-energy and high-power density supercapacitors (SCs) is critical for enabling next-generation energy storage applications. Nanocarbons are excellent SC elect…
Orthogonal greedy algorithm for linear operator learning with shallow neural network
Ye Lin, Jiwei Jia, Young Ju Lee +1
Greedy algorithms, particularly the orthogonal greedy algorithm (OGA), have proven effective in training shallow neural networks for fitting functions and solving partial different…
MobileNMT: Enabling Translation in 15MB and 30ms
Ye Lin, Xiaohui Wang, Zhexi Zhang +3
Deploying NMT models on mobile devices is essential for privacy, low latency, and offline scenarios. For high model capacity, NMT models are rather large. Running these models on d…
CECILIA: The Mass-Metallicity Relation of Low-Mass Galaxies at Cosmic Noon
Menelaos Raptis, Gwen C. Rudie, Ryan F. Trainor +9
A galaxy's metallicity and its relation to stellar mass encode the history of gas accretion, star formation, and outflows within cosmic ecosystems. We present new constraints on th…
Understanding Parameter Sharing in Transformers
Ye Lin, Mingxuan Wang, Zhexi Zhang +3
Parameter sharing has proven to be a parameter-efficient approach. Previous work on Transformers has focused on sharing parameters in different layers, which can improve the perfor…
CSRN: Collaborative Sequential Recommendation Networks for News Retrieval
Bing Bai, Guanhua Zhang, Ye Lin +3
Nowadays, news apps have taken over the popularity of paper-based media, providing a great opportunity for personalization. Recurrent Neural Network (RNN)-based sequential recommen…
Unsupervised Many-to-Many Image-to-Image Translation Across Multiple Domains
Ye Lin, Keren Fu, Shenggui Ling +1
Unsupervised multi-domain image-to-image translation aims to synthesis images among multiple domains without labeled data, which is more general and complicated than one-to-one ima…
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning
ByteDance Seed, :, Jiaze Chen +267
We introduce Seed1.5-Thinking, capable of reasoning through thinking before responding, resulting in improved performance on a wide range of benchmarks. Seed1.5-Thinking achieves 8…
The NiuTrans System for the WMT21 Efficiency Task
Chenglong Wang, Chi Hu, Yongyu Mu +8
This paper describes the NiuTrans system for the WMT21 translation efficiency task (http://statmt.org/wmt21/efficiency-task.html). Following last year's work, we explore various te…
Green Multigrid Network
Ye Lin, Young Ju Lee, Jiwei Jia
GreenLearning networks (GL) directly learn Green's function in physical space, making them an interpretable model for capturing unknown solution operators of partial differential e…
RcAE: Recursive Reconstruction Framework for Unsupervised Industrial Anomaly Detection
Rongcheng Wu, Hao Zhu, Shiying Zhang +9
Unsupervised industrial anomaly detection requires accurately identifying defects without labeled data. Traditional autoencoder-based methods often struggle with incomplete anomaly…
Simultaneous Localization and Parameter Estimation for Single Particle Tracking via Sigma Points based EM
Ye Lin, Sean B. Andersson
Single Particle Tracking (SPT) is a powerful class of tools for analyzing the dynamics of individual biological macromolecules moving inside living cells. The acquired data is typi…
Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Ye Lin, Yanyang Li, Ziyang Wang +4
Knowledge distillation has been proven to be effective in model acceleration and compression. It allows a small network to learn to generalize in the same way as a large network. R…
A Scheduling Framework for Efficient MoE Inference on Edge GPU-NDP Systems
Qi Wu, Chao Fang, Jiayuan Chen +5
Mixture-of-Experts (MoE) models facilitate edge deployment by decoupling model capacity from active computation, yet their large memory footprint drives the need for GPU systems wi…
An Efficient Transformer Decoder with Compressed Sub-layers
Yanyang Li, Ye Lin, Tong Xiao +1
The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises t…
A Simple and Effective Approach to Robust Unsupervised Bilingual Dictionary Induction
Yanyang Li, Yingfeng Luo, Ye Lin +5
Unsupervised Bilingual Dictionary Induction methods based on the initialization and the self-learning have achieved great success in similar language pairs, e.g., English-Spanish.…
The NiuTrans System for WNGT 2020 Efficiency Task
Chi Hu, Bei Li, Ye Lin +5
This paper describes the submissions of the NiuTrans Team to the WNGT 2020 Efficiency Shared Task. We focus on the efficient implementation of deep Transformer models \cite{wang-et…
Multi-Path Transformer is Better: A Case Study on Neural Machine Translation
Ye Lin, Shuhan Zhou, Yanyang Li +3
For years the model performance in machine learning obeyed a power-law relationship with the model size. For the consideration of parameter efficiency, recent studies focus on incr…
The environment of barred galaxies in the low-redshift Universe
Ye Lin, Bernardo Cervantes Sodi, Cheng Li +2
We present a study of the environment of barred galaxies using a volume-limited sample of over 30,000 galaxies drawn from the Sloan Digital Sky Survey. We use four different statis…
General-Purpose User Embeddings based on Mobile App Usage
Junqi Zhang, Bing Bai, Ye Lin +3
In this paper, we report our recent practice at Tencent for user modeling based on mobile app usage. User behaviors on mobile app usage, including retention, installation, and unin…
CD-PIM: A High-Bandwidth and Compute-Efficient LPDDR5-Based PIM for Low-Batch LLM Acceleration on Edge-Device
Ye Lin, Chao Fang, Xiaoyong Song +4
Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) o…
Boundary neuron method for solving partial differential equations
Ye Lin, Wentao Liu, Young Ju Lee +1
We propose a boundary neuron method with random features (BNM-RF) for solving partial differential equations. The method approximates the unknown boundary function by a shallow net…
NoTVLA: Semantics-Preserving Robot Adaptation via Narrative Action Interfaces
Zheng Huang, Mingyu Liu, Xiaoyi Lin +9
Vision-Language-Action (VLA) models represent a pivotal advance in embodied intelligence, yet they confront critical barriers to real-world deployment, most notably catastrophic fo…
Towards Fully 8-bit Integer Inference for the Transformer Model
Ye Lin, Yanyang Li, Tengbo Liu +3
8-bit integer inference, as a promising direction in reducing both the latency and storage of deep neural networks, has made great progress recently. On the other hand, previous sy…