Gemini-SQL2: Model, Harness, and System Design

Yanbang Wang, Qitian Wu, Sami Abu-el-Haija, Mohammadreza Pourreza, Michael Galkin, Hadi Hemmati, Hailong Li, Yeounoh Chung, Fatma Ozcan, Bryan Perozzi, Vahab Mirrokni

Preprint (under review) 2026

Gemini-SQL2 is currently the best coding LLM for text-to-SQL in the world. Gemini-SQL2 is Gemini 3.1 Pro post-trained and serves in a dedicated agentic harness. It currently ranks #1 on the BIRD leaderboard which is the de facto standard for text-to-SQL tasks.

[Google's Announcement] [VP's Repost] [BIRD Leaderboard]

Negative Sampling From the Ground Up

Yanbang Wang, Jon Kleinberg, Yanhong Wu

International Conference on Machine Learning (ICML) 2026

We revisit negative sampling for recommender systems from first principles and propose a redesign that improves recommendation quality.

[Paper]

Microstructures and Accuracy of Graph Recall by Large Language Models

Yanbang Wang, Hejie Cui, Jon Kleinberg

Neural Information Processing Systems (NeurIPS) 2025

The first systematic study of how LLMs memorizes structural information in text. We find LLMs often underperform and are biased towards certain error patterns, and that stronger models memorizes better when the structures are narrated in a domain-consistent style.

[Paper]

Network Recall by Large Language Models

Yanbang Wang, Hejie Cui, Jon Kleinberg

International Conference on Computational Social Science (IC2S2), Oral 2024

On the Relationship Between Relevance and Conflict in Online Social Link Recommendations

Yanbang Wang, Jon Kleinberg

International Conference on Computational Social Science (IC2S2) 2024

On the Relationship Between Relevance and Conflict in Online Social Link Recommendations

Yanbang Wang, Jon Kleinberg

Neural Information Processing Systems (NeurIPS) 2023

One of the first rigorous analyses of how link recommendations that boost engagement can also escalate conflict and polarization, using the Friedkin–Johnsen model of opinion dynamics.

[Paper]

Inductive Representation Learning in Temporal Networks via Causal Anonymous Walks

Yanbang Wang, Yen-Yu Chang, Yunyu Liu, Jure Leskovec, Pan Li

International Conference on Learning Representations (ICLR) 2021

Causal Anonymous Walks (CAWs) automatically retrieve temporal network motifs to represent network dynamics and use an anonymization strategy that keeps the method inductive, achieving SOTA on transductive and inductive temporal link prediction.

[Paper] [Project] [Code]

TEDIC: Neural Modeling of Behavioral Patterns in Dynamic Social Interaction Networks

Yanbang Wang, Pan Li, Chongyang Bai, Jure Leskovec

The Web Conference (WebConf) 2021

TEDIC learns representations on dynamic social interaction networks by diffusing node attributes over a network and its complement and applying temporal convolutions, outperforming prior methods across four social-character prediction tasks.

[Paper] [Project] [Talk]

Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning

Pan Li, Yanbang Wang, Hongwei Wang, Jure Leskovec

Neural Information Processing Systems (NeurIPS) 2020

Distance Encoding (DE) is a general class of structure-related features that provably gives GNNs more expressive power than the 1-Weisfeiler–Lehman test, distinguishing node sets in almost all regular graphs where traditional GNNs fail.

[Paper] [Project] [Code]

A Network-based Method for Estimating Potential for Career Advancement from Incomplete Data

Yanbang Wang, Bijia Chen, Cameron Campbell

Social Science History Association (SSHA) 2020

Generic Representation Learning for Dynamic Social Interaction

Yanbang Wang, Pan Li, Chongyang Bai, VS Subrahmanian, Jure Leskovec

KDD Workshop on Mining and Learning with Graphs (KDD-MLG) 2020

Transfer Learning using Representation Learning in Massive Open Online Courses

Mucong Ding, Yanbang Wang, Erik Hemberg, Una-May O'Reilly

International Conference on Learning Analytics & Knowledge (LAK) 2019

[Paper]