Leonardo Neves

Leonardo Neves

Auto-generated profile, based on publicly available information

Leonardo Neves

Snap Inc., Santa Monica, USA

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 November 2025
Verified
Conference Paper
Open access
CJClark Mingxuan Ju
Clark Mingxuan Ju
LCLiam Collins
Liam Collins
LNLeonardo Neves
Leonardo Neves
BKBhuvesh Kumar
Bhuvesh Kumar
LWLouis Yufeng Wang
Louis Yufeng Wang
NSNeil Shah
Neil Shah

3 August 2025
Verified
Conference Paper
Open access
CJClark Mingxuan Ju
Clark Mingxuan Ju
LNLeonardo Neves
Leonardo Neves
BKBhuvesh Kumar
Bhuvesh Kumar
LCLiam Collins
Liam Collins
TZTong Zhao
Tong Zhao
NSNeil Shah
Neil Shah

13 July 2025
Verified
Conference Paper
Open access
CJClark Mingxuan Ju
Clark Mingxuan Ju
LNLeonardo Neves
Leonardo Neves
BKBhuvesh Kumar
Bhuvesh Kumar
LCLiam Collins
Liam Collins
TZTong Zhao
Tong Zhao
NSNeil Shah
Neil Shah

22 April 2025
Verified
Conference Paper
Open access
XWXinyi Wu
Xinyi Wu
DLDonald Loveland
Donald Loveland
RCRunjin Chen
Runjin Chen
YLYozen Liu
Yozen Liu
XCXin Chen
Xin Chen
TZTong Zhao
Tong Zhao

10 July 2024
Verified
Conference Paper
Open access
QFQixiang Fang
Qixiang Fang
ZZZhihan Zhou
Zhihan Zhou
FBFrancesco Barbieri
Francesco Barbieri
YLYozen Liu
Yozen Liu
LNLeonardo Neves
Leonardo Neves
RDRon Dotsch
Ron Dotsch
Learning general-purpose user representations based on user behavioral logs is an increasingly popular user modeling approach. It benefits from easily available, privacy-friendly yet expressive data, and does not require extensive re-tuning of the upstream user model for different downstream tasks. While this approach has shown promise in search engines and e-commerce applications, its fit for instant messaging platforms, a cornerstone of modern digital communication, remains largely uncharted. We explore this research gap using Snapchat data as a case study. Specifically, we implement a Transformer-based user model with customized training objectives and show that the model can produce high-quality user representations across a broad range of evaluation tasks, among which we introduce three new downstream tasks that concern pivotal topics in user research: user safety, engagement and churn. We also tackle the challenge of efficient extrapolation of long sequences at inference time, by applying a novel positional encoding method.

19 July 2026
Verified
Conference Paper
Open access
CJClark Mingxuan Ju
Clark Mingxuan Ju
TZTong Zhao
Tong Zhao
LNLeonardo Neves
Leonardo Neves
LCLiam Collins
Liam Collins
BKBhuvesh Kumar
Bhuvesh Kumar
NSNeil Shah
Neil Shah
Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within training data, such that RecSys models can extrapolate during the inference and personalize the prediction based on users' behavioral histories. Recently, Semantic IDs (SIDs) have become a trending paradigm for RecSys. In comparison to the conventional atomic ID, an SID is an ordered list of codes, derived from tokenizers such as residual quantization, applied to semantic representations commonly extracted from foundation models or collaborative signals. SIDs have drastically smaller cardinality than the atomic counterpart, and induce semantic clustering in the ID space. At Snapchat, we apply SIDs as auxiliary features for ranking models, and also explore SIDs as additional retrieval sources in different ML applications. In this paper, we discuss practical technical challenges we encountered while applying SIDs, experiments we have conducted, and design choices we have iterated to mitigate these challenges. Backed by promising offline results on both internal data and academic benchmarks as well as online A/B studies, SID variants have been launched in multiple production models with positive metrics impact.