Xinyi Chen

PhD student at University of Amsterdam

[Xinyi Chen @xchen2023]

🎉😀 Excited to announce that our paper “What if Othello-Playing Language Models Could See?” is accepted at #EMNLP2025 Findings!
⭐️ We explore how multimodal training boosts sample efficiency & board-state understanding using Othello as a testbed.
🚀 Preprint coming soon!

[Xinyi Chen @xchen2023]

Big thanks to my wonderful collaborators: @yfyuan775,@jiaangli,@SergeBelongie,@mdr, Anders Søgaard!

[Xinyi Chen @xchen2023]

🎉😀 Excited to announce that our paper “What if Othello-Playing Language Models Could See?” is accepted at #EMNLP2025 Findings!
⭐️ We explore how multimodal training boosts sample efficiency & board-state understanding using Othello as a testbed.
🚀 Preprint coming soon!

[Xinyi Chen @xchen2023]

Many thanks to my collaborators: @yfyuan775, @jiaangli, @SergeBelongie, @mdr, Anders Søgaard!

[Xinyi Chen @xchen2023]

Excited to present at the #ICML2025 World Models Workshop!
📅 July 18, 15:45–17:00
🧠 What if Othello-Playing Language Models Could See?
We show that visual grounding improves prediction & internal structure.
♟️📷🧠

#ICML2025 #AI #LLMs

[Xinyi Chen @xchen2023]

Building effective agents \ Anthropic https://t.co/eO6AWyFkCb

[Xinyi Chen @xchen2023]

Wrapping up at #EMNLP2024 in Miami!🏝️ Many thanks for the attendees and their feedback in my poster session. Had a great time joining oral/poster sessions and meeting amazing people! So much to learn and share! Ending with the #UvA group photo to remember this amazing experience!

[Xinyi Chen @xchen2023]

Many thanks to my co-authors: @baohao_liao, @Jirui_Qi, Panagiotis Eustratiadis,@c_monz, @AriannaBisazza, @mdr

[Xinyi Chen @xchen2023]

🧠 Can LLMs actually reason? We have surprising observations on simple sequential reasoning tasks! Our paper in #EMNLP2024 Findings introduces the SIFo Benchmark—a tool testing LLMs' ability to follow & reason over multiple instructions. 📅 Join our poster on Nov 12, 16:00-17:30!

[Xinyi Chen @xchen2023]

📊 Our paper reveals that, while LLMs handle individual tasks, they struggle with reasoning over sequential instructions, highlighting a crucial gap in their robustness. 🚨
🔗 https://t.co/Avfm73fr6o

[Xinyi Chen @xchen2023]

Tomorrow (Friday, Dec 8), I will present my poster at #EMNLP2023 during the Language Grounding to Vision, Robotics and Beyond session in East Foyer from 11:00 - 12:30.  Feel free to swing by!

[Xinyi Chen @xchen2023]

🎉 Exciting News! Our paper "The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models" has been accepted at #EMNLP2023 Main Conference. Many thanks to my co-authors @sandropezzelle and @raquel_dmg.

#emnlp #NLP

[Xinyi Chen @xchen2023]

Good taste:
1. Smart enough: Good & innovative ideas instead of what everyone else is doing?
2. Good research: Not something A+B, but have them with good reasons.
3. Propose something with a reason but not simply trying something popular.

[Xinyi Chen @xchen2023]

Causal Inference in NLP: (review)https://t.co/K3dg77ix50.
Nice blog based on the above paper: https://t.co/5GiGejBWXP