49 citations · 171 across the 43 of their papers we have counts for
44 papers
Bilinear maximal functions associated with some degenerate surfaces on the Heisenberg group
Sayan Bagchi, Rahul Garg, Surya Kanta Rana
Motivated by the works of Lee--Shuin and Borges--Foster on the Euclidean space, in this article we consider bilinear averages on the Heisenberg group corresponding t…
EStream: Fast and Memory-Efficient MoE Prefill through Expert Virtualization on Mobile NPUs
Junming Zhang, Zhenzhe Zheng, Fan Wu +2
Mobile vendors and application developers increasingly deploy LLMs on smartphones for diverse prefill-only services. Yet current systems rely mainly on dense models whose regular c…
An Efficient and Privacy-Preserving Architecture for Cross-Institutional Collaborative RAG
Chenxin Mao, Shangyu Liu, Zhenzhe Zheng +3
Retrieval-Augmented Generation (RAG) empowers LLMs with external knowledge, making cross-institutional domain-specific knowledge base integration a highly promising deployment para…
Optimizing Feature Extraction for On-device Model Inference with User Behavior Sequences
Chen Gong, Zhenzhe Zheng, Yiliu Chen +3
Machine learning models are widely integrated into modern mobile apps to analyze user behaviors and deliver personalized services. Ensuring low-latency on-device model execution is…
Guiding the Recommender: Information-Aware Auto-Bidding for Content Promotion
Yumou Liu, Zhenzhe Zheng, Jiang Rong +3
Modern content platforms offer paid promotion to mitigate cold start by allocating exposure via auctions. Our empirical analysis reveals a counterintuitive flaw in this paradigm: w…
Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs
Wei Zhou, Jun Zhou, Haoyu Wang +16
Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them, which is essential for a wide range of data-centric app…
TTF: A Trapezoidal Temporal Fusion Framework for LTV Forecasting in Douyin
Yibing Wan, Zhengxiong Guan, Chaoli Zhang +5
In the user growth scenario, Internet companies invest heavily in paid acquisition channels to acquire new users. But sustainable growth depends on acquired users' generating lifet…
Optimizing Storage Overhead of User Behavior Log for ML-embedded Mobile Apps
Chen Gong, Yan Zhuang, Zhenzhe Zheng +4
Machine learning (ML) models are increasingly integrated into modern mobile apps to enable personalized and intelligent services. These models typically rely on rich input features…
TSRec: Enhancing Repeat-Aware Recommendation from a Temporal-Sequential Perspective
Shigang Quan, Shui Liu, Zhenzhe Zheng +1
Repeat consumption, such as repurchasing items and relistening songs, is a common scenario in daily life. To model repeat consumption, the repeat-aware recommendation has been prop…
MERIT: A Merchant Incentive Ranking Model for Hotel Search & Ranking
Shigang Quan, Hailong Tan, Shui Liu +5
Online Travel Platforms (OTPs) have been working on improving their hotel Search & Ranking (S&R) systems that facilitate efficient matching between consumers and hotels. Existing O…
A Two-Stage Data Selection Framework for Data-Efficient Model Training on Edge Devices
Chen Gong, Rui Xing, Zhenzhe Zheng +1
The demand for machine learning (ML) model training on edge devices is escalating due to data privacy and personalized service needs. However, we observe that current on-device mod…
HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmark
Jianqing Zhang, Xinghao Wu, Yanbing Zhou +7
As AI evolves, collaboration among heterogeneous models helps overcome data scarcity by enabling knowledge transfer across institutions and devices. Traditional Federated Learning…
Efficient Distributed Retrieval-Augmented Generation for Enhancing Language Model Performance
Shangyu Liu, Zhenzhe Zheng, Xiaoyao Huang +3
Small language models (SLMs) support efficient deployments on resource-constrained edge devices, but their limited capacity compromises inference performance. Retrieval-augmented g…
Ten Challenging Problems in Federated Foundation Models
Tao Fan, Hanlin Gu, Xuemei Cao +30
Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of fed…
AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference
Zhuomin He, Yizhen Yao, Pengfei Zuo +4
Long-context large language models (LLMs) inference is increasingly critical, motivating a number of studies devoted to alleviating the substantial storage and computational costs…
Contextual Generative Auction with Permutation-level Externalities for Online Advertising
Ruitao Zhu, Yangsu Liu, Dagui Chen +7
Online advertising has become a core revenue driver for the internet industry, with ad auctions playing a crucial role in ensuring platform revenue and advertiser incentives. Tradi…
Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning
Chen Gong, Zhenzhe Zheng, Fan Wu +2
In modern mobile applications, users frequently encounter various new contexts, necessitating on-device continual learning (CL) to ensure consistent model performance. While existi…
MEBS: Multi-task End-to-end Bid Shading for Multi-slot Display Advertising
Zhen Gong, Lvyin Niu, Yang Zhao +9
Online bidding and auction are crucial aspects of the online advertising industry. Conventionally, there is only one slot for ad display and most current studies focus on it. Nowad…
Trajectory-wise Iterative Reinforcement Learning Framework for Auto-bidding
Haoming Li, Yusen Huo, Shuai Dou +5
In online advertising, advertisers participate in ad auctions to acquire ad opportunities, often by utilizing auto-bidding tools provided by demand-side platforms (DSPs). The curre…
ECLM: Efficient Edge-Cloud Collaborative Learning with Continuous Environment Adaptation
Yan Zhuang, Zhenzhe Zheng, Yunfeng Shao +3
Pervasive mobile AI applications primarily employ one of the two learning paradigms: cloud-based learning (with powerful large models) or on-device learning (with lightweight small…
Auction Design for Bidders with Ex Post ROI Constraints
Hongtao Lv, Xiaohui Bei, Zhenzhe Zheng +1
Motivated by practical constraints in online advertising, we investigate single-parameter auction design for bidders with constraints on their Return On Investment (ROI) -- a targe…
Truthful Auctions for Automated Bidding in Online Advertising
Yidan Xing, Zhilin Zhang, Zhenzhe Zheng +4
Automated bidding, an emerging intelligent decision making paradigm powered by machine learning, has become popular in online advertising. Advertisers in automated bidding evaluate…
Utility Maximizer or Value Maximizer: Mechanism Design for Mixed Bidders in Online Advertising
Hongtao Lv, Zhilin Zhang, Zhenzhe Zheng +5
Digital advertising constitutes one of the main revenue sources for online platforms. In recent years, some advertisers tend to adopt auto-bidding tools to facilitate advertising p…
Learning Optimal Deterministic Auctions with Correlated Valuation Distributions
Da Huo, Zhilin Zhang, Zhenzhe Zheng +3
In mechanism design, it is challenging to design the optimal auction with correlated values in general settings. Although value distribution can be further exploited to improve rev…