____ _ _ _ __ __ _ _ _ | __ )(_)| || | \ \ / / _ _ __| |__ ___ _ __ | | (_) _ __ | _ \| || || | \ V / | | |/ __| '_ \ / _ \| '_ \ | | | || '_ \ | |_) | || || | | || |_| | (__| | | | __/| | | || |___| || | | | |____/|_||_||_| |_| \__,_|\___|_| |_|\___||_| |_||_____|_||_| |_|# Welcome to my terminal. Type 'help' for available commands.
bill ~ $ whoami
Bill Yuchen Lin
Member of Technical Staff @ xAI | Affiliate Asst. Prof @ UW
Working on RL for agentic coding models, long-horizon reasoning, and terminal-use agents at xAI. Broader interests include post-training & alignment of LLMs, reward modeling, evaluation, and synthetic data generation. Previously Research Scientist at Allen Institute for AI (AI2), working with Prof. Yejin Choi.
bill ~ $
# Type commands to explore, or show all
bill ~ $ cat experience.md
# Work Experience
| 2024 - Now | Member of Technical Staff, xAI |
| 2024 - Now | Affiliate Assistant Professor, University of Washington (ECE) |
| 2023 - 2024 | Research Scientist, Allen Institute for AI (AI2) |
| 2021 | Research Intern, Meta FAIR Lab — Host: Scott Yih |
| 2020 | Research Intern, Google AI — Host: William Cohen |
| 2019 | Research Intern, Google AI — Host: Sandeep Tata |
| 2017 - 2018 | Research Intern, Microsoft Research Asia |
# Education
| 2018 - 2022 | Ph.D. Computer Science, University of Southern California Advisor: Prof. Xiang Ren | Annenberg Fellowship |
| 2014 - 2018 | B.Sc. Computer Science (IEEE Honor Class), Shanghai Jiao Tong University Best Bachelor Thesis Award (Top 1%) |
bill ~ $ tree research/
research/
├── post-training/ # LLM alignment, RLHF, DPO
│ ├── reward-modeling
│ ├── synthetic-data-generation
│ └── personalized-rlhf
├── agents/ # AI agents & reasoning
│ ├── lumos-agent
│ └── swiftsage
├── evaluation/ # LLM benchmarks & metrics
│ ├── wildbench
│ ├── zeroeval
│ └── wildvision
├── multimodal/ # Vision-language models
│ └── wildvision-arena
└── commonsense/ # Knowledge & reasoning
├── riddlesense
└── llm-blender
5 directories, 10 files
bill ~ $ cat selected_projects.json
# Selected Projects
bill ~ $ grep -r "award" honors.log
# Awards & Honors
[Best Paper] CoRL 2024 LangRob Workshop
[Best Paper] TrustNLP @ NAACL 2021
[Best Paper Runner-Up] The Web Conference (WWW) 2020
[NeurIPS Spotlight x2] SwiftSage & FnF, NeurIPS 2023
[AI Rising Star] Baidu Scholar, 2021
[Best Thesis] Shanghai Jiao Tong University (Top 1%), 2018
[Fellowship] Annenberg Fellowship, USC, 2018
bill ~ $ cat service.yml
# Academic Service
senior_ac: ACL 2025
area_chair: ICLR 2025, ACL 2023, EMNLP 2023-2024
tutorials: ACL 2023, ACL 2022, WSDM 2023
workshops: FL4NLP@ACL22, CSRR@ACL22, CSKB@AKBC21, TamingLLM@SIGDIAL+INLG23
reviewer: ICML, NeurIPS, ICLR, ACL, EMNLP, NAACL, AAAI, TKDE, TMLR
bill ~ $ tail -15 news.log
# Recent News
2024-11-25 Joined xAI to work on post-training research for Grok.
2024-11-20 Invited talk at Stanford NLP Seminar. Moved to the Bay Area!
2024-11-01 Became Affiliate Asst. Prof at UW ECE.
2024-09-19 Released MagpieLM (4B & 8B), SOTA chat models with open alignment recipe.
2024-09-11 Released ZeroEval leaderboard for LLM reasoning.
2024-08-27 Released WildVision datasets: WV-Chat, WV-Battle, WV-Bench.
2024-08-19 Serving as Area Chair for ICLR 2025.
2024-06-29 Serving as Senior Area Chair for ACL 2025.
2024-05-08 Three ACL 2024 papers: Agent Lumos, ETO, SafeDecoding.
2024-03-08 Introducing WildBench! Dynamic LLM benchmark.
2024-01-16 ICLR 2024: "Unlocking Spell on Base LLMs: Rethinking Alignment via ICL".
2023-12-01 Released PairRM-0.4B reward model.
2023-09-21 Two NeurIPS 2023 Spotlight papers: SwiftSage & FnF.
2023-07-09 Co-presented ACL 2023 tutorial on Complex Reasoning in NL.