Scholar
Tianlu Wang
Google Scholar ID: inzQqX8AAAAJ
Research Scientist at Meta AI (FAIR team)
Citations & Impact
Citations
10,338
H-index
26
i10-index
33
Publications
20
Co-authors
6
list available
Contact
Publications
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Jointly Reinforcing Diversity and Quality in Language Model Generations
- ASTRO: Teaching Language Models to Reason by Reflecting and Backtracking In-Context
- J1: Incentivizing thinking in llm-as-a-judge via reinforcement learning
- Multi-Token Attention (COLM 2025)
- Learning to plan & reason for evaluation with thinking-llm-as-a-judge (ICML 2025)
- Self-taught evaluators
- Contextual Position Encoding: Learning to Count What's Important
- Chameleon: Mixed-modal early-fusion foundation models
- Shepherd: A critic for language model generation
- Efficient tool use with chain-of-abstraction reasoning (COLING 2025)
- Understanding in-context learning via supportive pretraining data (ACL 2023)
- OPT: Open Pre-trained Transformer Language Models
- Few-shot Learning with Multilingual Language Models (EMNLP 2022)
- Identifying and mitigating spurious correlations for improving robustness in NLP models (NAACL 2022 Findings)
- VisualNews : Benchmark and Challenges in Entity-aware Image Captioning (EMNLP 2021)
- General Multi-label Image Classification with Transformers (CVPR 2021)
- CAT-Gen: Improving Robustness in NLP Models via Controlled Adversarial Text Generation
Research Experience
- Serves as a research scientist at Meta AI, FAIR team, focusing on post-training of large language models.
Education
- Ph.D. in Computer Science from the University of Virginia, advised by Prof. Vicente Ordóñez Román; Bachelor's degree in Computer Science from Zhejiang University, China.
Background
- Currently a research scientist at Meta AI, FAIR team, working on large language model post-training.
