Scholar
Song Jiang
Google Scholar ID: SjbhMQEAAAAJ
FAIR, Meta
Machine learning
Reinforcement Learning
Language Models
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
950
H-index
13
i10-index
14
Publications
20
Co-authors
13
list available
Contact
Twitter
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
1 items
Examining Reasoning LLMs-as-Judges in Non-Verifiable LLM Post-Training
2026
Cited
0
Resume (English only)
Academic Achievements
NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions (Preprint 2025)
Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning (Preprint 2024)
To the Globe (TTG): Towards Language-Driven Guaranteed Travel Planning (EMNLP Demo Track 2024, Miami, FL)
FUSE: Measure-Theoretic Compact Fuzzy Set Representation for Taxonomy Expansion (ACL-Findings 2024, Bangkok, Thailand)
ResPrompt: Residual Connection Prompting Advances Multi-Step Reasoning in Large Language Models (NAACL 2024, Mexico City, Mexico)
LLM-Rec: Personalized Recommendation via Prompting Large Language Models (NAACL 2024 - Findings, Mexico City, Mexico)
On the Equivalence of Graph Convolution and Mixup (TMLR 2024)
CARE: Modeling Interacting Dynamics Under Temporal Distribution Shift (NeurIPS 2023, New Orleans, LA)
CF-GODE: Continuous-Time Causal Inference for Multi-Agent Dynamical Systems (KDD 2023, Long Beach, CA) - Best Student Paper Award
A Single Vector Is Not Enough: Taxonomy Expansion via Box Embeddings (WWW 2023, Austin, TX) - Best Student Paper Award
A Primer on Deep Learning for Causal Inference (Sociological Methods & Research, 2023)
Estimating Causal Effects on Networked Observational Data via Representation Learning (CIKM 2022, Atlanta, GA)
Bridging Self-Attention and Time Series Decomposition for Periodic Forecasting (CIKM 2022, Atlanta, GA)
Unit Selection: Learning Benefit Function from Finite Population Data (NeurIPS 2022 Workshop on Causality for Real-world Impact)
HINTS: Citation Time Series Prediction for New Publications via Dynamic Heterogeneous Information Network Embedding (WWW 2021, virtual)
Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks (NeurIPS 2019, Vancouver, Canada)
Research Experience
Research Engineer at FAIR, Meta, 2024 - Present
Education
Ph.D. from UCLA, advised by Prof. Yizhou Sun.
Background
Research Engineer at FAIR, Meta. Currently working on LLM Reasoning / Planning.
Miscellany
Reviewer: ICLR, ICML, NeurIPS, KDD, WWW, ARR
Co-authors
13 total
Yizhou Sun
Professor, Computer Science, UCLA
Qifan Wang
Research Scientist, Meta AI
Yuandong Tian
Research Scientist, Meta AI (FAIR)
Xian Li
FAIR, Meta
Xiao Luo
University of Wisconsin–Madison
Zijie Huang
Google Deepmind
Jason Weston
Meta
Judea Pearl
Professor of Computer Science, University of California, Los Angeles
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up