14 citations · 81 across the 23 of their papers we have counts for
23 papers
Apple Intelligence Foundation Language Models: Tech Report 2025
Ethan Li, Anders Boesen Lindbo Larsen, Chen Zhang +395
We introduce two multilingual, multimodal foundation language models that power Apple Intelligence features across Apple devices and services: i a 3B-parameter on-device model opti…
MR. Judge: Multimodal Reasoner as a Judge
Renjie Pi, Felix Bai, Qibin Chen +4
The paradigm of using Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) as evaluative judges has emerged as an effective approach in RLHF and inference-time…
Transfer learning in Scalable Graph Neural Network for Improved Physical Simulation
Siqi Shen, Yu Liu, Daniel Biggs +5
In recent years, Graph Neural Network (GNN) based models have shown promising results in simulating physics of complex systems. However, training dedicated graph network based phys…
Synth4Seg -- Learning Defect Data Synthesis for Defect Segmentation using Bi-level Optimization
Shancong Mou, Raviteja Vemulapalli, Shiyu Li +8
Defect segmentation is crucial for quality control in advanced manufacturing, yet data scarcity poses challenges for state-of-the-art supervised deep learning. Synthetic defect dat…
Smart Audit System Empowered by LLM
Xu Yao, Xiaoxu Wu, Xi Li +6
Manufacturing quality audits are pivotal for ensuring high product standards in mass production environments. Traditional auditing processes, however, are labor-intensive and relia…
TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
Aiwei Liu, Haoping Bai, Zhiyun Lu +9
Direct Preference Optimization (DPO) has been widely adopted for preference alignment of Large Language Models (LLMs) due to its simplicity and effectiveness. However, DPO is deriv…
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains
Guoli Yin, Haoping Bai, Shuang Ma +21
Recent advances in large language models (LLMs) have increased the demand for comprehensive benchmarks to evaluate their capabilities as human-like agents. Existing benchmarks, whi…
Apple Intelligence Foundation Language Models
Tom Gunter, Zirui Wang, Chong Wang +152
We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large serv…
A Survey of Multimodal Large Language Model from A Data-centric Perspective
Tianyi Bai, Hao Liang, Binwang Wan +12
Multimodal large language models (MLLMs) enhance the capabilities of standard large language models by integrating and processing data from multiple modalities, including text, vis…
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
Jingyuan Zhu, Shiyu Li, Yuxuan Liu +4
Modern diffusion-based image generative models have made significant progress and become promising to enrich training data for the object detection task. However, the generation qu…
Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation
Aiwei Liu, Haoping Bai, Zhiyun Lu +5
Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the re…
VeCLIP: Improving CLIP Training via Visual-enriched Captions
Zhengfeng Lai, Haotian Zhang, Bowen Zhang +9
Large-scale web-crawled datasets are fundamental for the success of pre-training vision-language models, such as CLIP. However, the inherent noise and potential irrelevance of web-…
VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON
Haoping Bai, Shancong Mou, Tatiana Likhomanenko +6
Despite progress in vision-based inspection algorithms, real-world industrial challenges -- specifically in data availability, quality, and complex production requirements -- often…
Efficient ConvBN Blocks for Transfer Learning and Beyond
Kaichao You, Guo Qin, Anchang Bao +4
Convolution-BatchNorm (ConvBN) blocks are integral components in various computer vision tasks and other domains. A ConvBN block can operate in three modes: Train, Eval, and Deploy…
RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection
Shancong Mou, Xiaoyi Gu, Meng Cao +4
Generative adversarial networks (GANs), trained on a large-scale image dataset, can be a good approximator of the natural image manifold. GAN-inversion, using a pre-trained generat…
DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
Xuan Zhang, Shiyu Li, Xi Li +3
Visual anomaly detection, an important problem in computer vision, is usually formulated as a one-class classification and segmentation task. The student-teacher (S-T) framework ha…
Synthetic Defect Generation for Display Front-of-Screen Quality Inspection: A Survey
Shancong Mou, Meng Cao, Zhendong Hong +3
Display front-of-screen (FOS) quality inspection is essential for the mass production of displays in the manufacturing process. However, the severe imbalanced data, especially the…
Information Gain Propagation: a new way to Graph Active Learning with Soft Labels
Wentao Zhang, Yexin Wang, Zhenbang You +5
Graph Neural Networks (GNNs) have achieved great success in various tasks, but their performance highly relies on a large number of labeled nodes, which typically requires consider…
PAEDID: Patch Autoencoder Based Deep Image Decomposition For Pixel-level Defective Region Segmentation
Shancong Mou, Meng Cao, Haoping Bai +3
Unsupervised pixel-level defective region segmentation is an important task in image-based anomaly detection for various industrial applications. The state-of-the-art methods have…
Self-supervised Semi-supervised Learning for Data Labeling and Quality Evaluation
Haoping Bai, Meng Cao, Ping Huang +1
As the adoption of deep learning techniques in industrial applications grows with increasing speed and scale, successful deployment of deep learning models often hinges on the avai…
RIM: Reliable Influence-based Active Learning on Graphs
Wentao Zhang, Yexin Wang, Zhenbang You +5
Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to…
BatchQuant: Quantized-for-all Architecture Search with Robust Quantizer
Haoping Bai, Meng Cao, Ping Huang +1
As the applications of deep learning models on edge devices increase at an accelerating pace, fast adaptation to various scenarios with varying resource constraints has become a cr…
Video Frame Interpolation via Structure-Motion based Iterative Fusion
Xi Li, Meng Cao, Yingying Tang +4
Video Frame Interpolation synthesizes non-existent images between adjacent frames, with the aim of providing a smooth and consistent visual experience. Two approaches for solving t…