Song Jiang

songjiang (at) meta (dot) com

About Me

• I'm a research engineer at FAIR, Meta.

• Currently I'm working on LLM Reasoning / Planning.

• I received my Ph.D. from UCLA. My advisor was Prof. Yizhou Sun.

Publication

2024

• NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
  

  • Weizhe Yuan, Jane Yu, Song Jiang, Karthik Padthe, Yang Li, Dong Wang, Ilia Kulikov, Kyunghyun Cho, Yuandong Tian, Jason Weston, Xian Li
    

  • Preprint 2025
    

  • [Paper] [Dataset (Huggingface)]
    

• Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning
  

  • Song Jiang, Da Ju, Andrew Cohen, Sasha Mitts, Aaron Foss, Justine T Kao, Xian Li, Yuandong Tian
    

  • Preprint 2024
    

  • [Paper]
    

• To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning
  

  • Da Ju, Song Jiang, Andrew Cohen, Aaron Foss, Sasha Mitts, Arman Zharmagambetov, Brandon Amos, Xian Li, Justine T Kao, Maryam Fazel-Zarandi, Yuandong Tian
    

  • EMNLP Demo Track 2024, Miami, FL
    

  • [Paper]

• FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion
  

  • Fred Xu, Song Jiang, Zijie Huang, Xiao Luo, Shichang Zhang, Yuanzhou Chen, Yizhou Sun
    

  • ACL-Findings 2024, Bangkok, Thailand
    

  • [Paper]

• ResPrompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models
  

  • Song Jiang, Zahra Shakeri, Aaron Chan, Maziar Sanjabi, Hamed Firooz, Yinglong Xia, Bugra Akyildiz, Yizhou Sun, Jinchao Li, Qifan Wang, Asli Celikyilmaz
    

  • NAACL 2024, Mexico City, Mexico
    

  • [Paper]

• LLM-Rec: Personalized Recommendation via Prompting Large Language Models
  

  • Hanjia Lyu, Song Jiang, Hanqing Zeng, Qifan Wang, Si Zhang, Ren Chen, Chris Leung, Jiajie Tang, Yinglong Xia, Jiebo Luo
    

  • NAACL 2024 - Findings, Mexico City, Mexico
    

  • [Paper]

• On the Equivalence of Graph Convolution and Mixup
  

  • Xiaotian Han, Hanqing Zeng, Yu Chen, Shaoliang Nie, Jingzhou Liu, Kanika Narang, Zahra Shakeri, Karthik Abinav Sankararaman, Song Jiang, Madian Khabsa, Qifan Wang, Xia Hu
    

  • TMLR 2024
    

  • [Paper]

2023

• CARE: Modeling Interacting Dynamics Under Temporal Distribution Shift
  

  • Xiao Luo, Haixin Wang, Zijie Huang, Huiyu Jiang, Abhijeet Sadashiv Gangan, Song Jiang, Yizhou Sun
    

  • NeurIPS 2023, New Orleans, LA
    

  • [Paper]

• CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems
  

  • Song Jiang, Zijie Huang, Xiao Luo and Yizhou Sun
    

  • KDD 2023, Long Beach, CA
    

  • [Paper] [Code]

• A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings
  

  • Song Jiang, Qiyue Yao, Qifan Wang and Yizhou Sun
    

  • WWW 2023, Austin, TX
    

  • Best Student Paper Award
    

  • [Paper] [Code]

• A Primer on Deep Learning for Causal Inference
  

  • Bernard Koch, Tim Sainburg, Pablo Geraldo, Song Jiang, Yizhou Sun, and Jacob Gates Foster
    

  • Sociological Methods & Research (Journal) 2023
    

  • [Paper]

2022

• Estimating Causal Effects on Networked Observational Data via Representation Learning
  

  • Song Jiang and Yizhou Sun
    

  • CIKM 2022, Atlanta, GA
    

  • [Paper] [Code]

• Bridging Self-Attention and Time Series Decomposition for Periodic Forecasting
  

  • Song Jiang, Tahin Syed, Xuan Zhu, Joshua Levy, Boris Aronchik and Yizhou Sun
    

  • CIKM 2022, Atlanta, GA
    

  • [Paper] [Code]

• Unit Selection: Learning Benefit Function from Finite Population Data
  

  • Ang Li, Song Jiang, Yizhou Sun and Judea Pearl
    

  • NeurIPS 2022 Workshop on Causality for Real-world Impact
    

  • [Paper]

2021

• HINTS: Citation Time Series Prediction for New Publications via Dynamic Heterogeneous Information Network Embedding
  

  • Song Jiang, Bernard Koch and Yizhou Sun
    

  • WWW 2021, virtual
    

  • [Paper] [Code]

2019

• Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
  

  • Difan Zou, Ziniu Hu, Yewen Wang, Song Jiang, Yizhou Sun and Quanquan Gu
    

  • NeurIPS 2019, Vancouver, Canada
    

  • [Paper]

Work Experience

• FAIR, Meta, Research Engineer,  2024 - Now
  

Services

• Reviewer: ICLR, ICML, NeurIPS, KDD, WWW, ARR

  
  

Template from link