iiinova — where your digital self keeps evolving

Yifei Yuan @yfyuan01.bsky.social · 21/04/2026

Excited to be heading to ICLR Rio 🇧🇷 this week to present two of my latest papers (1main+1workshop)! • Paper 1: 𝗥𝗔𝗩𝗘𝗡𝗘𝗔: 𝗔 𝗕𝗲𝗻𝗰𝗵𝗺𝗮𝗿𝗸 𝗳𝗼𝗿 𝗠𝘂𝗹𝘁𝗶𝗺𝗼𝗱𝗮𝗹 𝗥𝗲𝘁𝗿𝗶𝗲𝘃𝗮𝗹-𝗔𝘂𝗴𝗺𝗲𝗻𝘁𝗲𝗱 𝗩𝗶𝘀𝘂𝗮𝗹 𝗖𝘂𝗹𝘁𝘂𝗿𝗲 𝗨𝗻𝗱𝗲𝗿𝘀𝘁𝗮𝗻𝗱𝗶𝗻𝗴 • Paper 2: 𝐂𝐀𝐍 𝐒𝐌𝐀𝐋𝐋 𝐀𝐆𝐄𝐍𝐓𝐒 𝐂𝐎𝐋𝐋𝐀𝐁𝐎𝐑𝐀𝐓𝐄 𝐓𝐎 𝐁𝐄𝐀𝐓 𝐀 𝐒𝐈𝐍𝐆𝐋𝐄 𝐋𝐀𝐑𝐆𝐄 𝐋𝐀𝐍𝐆𝐔𝐀𝐆𝐄 𝐌𝐎𝐃𝐄𝐋? #ICLR #AgenticAI

020

Reposted by Yifei Yuan

Jiaang Li @jiaangli.bsky.social · 17/04/2026

🙏 Huge thanks to all collaborators @yfyuan01.bsky.social, @wenyan62.bsky.social, @aliannejadi.bsky.social, @danielhers.bsky.social, Anders Søgaard, Ivan Vulić, Wenxuan Zhang, Paul Liang, Yang Deng, @serge.belongie.com

021

Reposted by Yifei Yuan

ECIR 2026 @ecir2026.eu · 08/01/2026

ECIR is pleased to offer Student Support Grants . Applicants must be full-time students. Priority consideration will be given to students with accepted papers and demonstrated financial need. To apply👉 Please complete the form docs.google.com/forms/d/e/1F... before January 24.

docs.google.com

ECIR 2026 Student Travel Grant Application Form

135

Reposted by Yifei Yuan

ECIR 2026 @ecir2026.eu · 11/12/2025

🎖️ Call for Nominations – The Keith van Rijsbergen (KvR) Award 2026 Read more about the award, nomination process, and find the form to submit your nominations here: lnkd.in/emecdsXm #ECIR2026 #InformationRetrieval #Awards #ResearchExcellence ecir2026.eu/calls/keith-...

ecir2026.eu

Keith van Rijsbergen Award

keith van rijsbergen award

045

Yifei Yuan @yfyuan01.bsky.social · 15/09/2025

Are you looking to gain experience in reviewing scientific papers? Do you know someone who can be an excellent reviewer? #ECIR26 invites you to nominate yourself or others to join the Program Committee (PC) for the short paper track. Apply👉: forms.gle/LsvXHWEa859v...

forms.gle

011

Yifei Yuan @yfyuan01.bsky.social · 13/07/2025

Please feel free to reach out and chat with Xinyi on 18 July, Vancouver at #ICML2025 👀

000

Yifei Yuan @yfyuan01.bsky.social · 13/07/2025

Thrilled to be presenting our tutorial with Zahra Abbasiantaeb, @aliannejadi.bsky.social, Yang Deng at #SIGIR2025! 🧠 Query Understanding in LLM-based Conversational Information Seeking 🗓️ 14:00-17:30, 13 July 📍 CARRARESI, Padova Congress Center 🔗 Learn more: sigirusertutorial.github.io

030

Reposted by Yifei Yuan

Jiaang Li @jiaangli.bsky.social · 23/05/2025

🚀New Preprint🚀 Can Multimodal Retrieval Enhance Cultural Awareness in Vision-Language Models? Excited to introduce RAVENEA, a new benchmark aimed at evaluating cultural understanding in VLMs through RAG. arxiv.org/abs/2505.14462 More details:👇

1177

Yifei Yuan @yfyuan01.bsky.social · 21/04/2025

I won’t be attending #ICLR in person this year😢. But feel free to check our paper ‘Revisiting the Othello World Model Hypothesis’ with Anders Søgaard, accepted at ICLR world models workshop! Paper link arxiv.org/abs/2503.04421

arxiv.org

Revisiting the Othello World Model Hypothesis

Li et al. (2023) used the Othello board game as a test case for the ability of GPT-2 to induce world models, and were followed up by Nanda et al. (2023b). We briefly discuss the original experiments, ...

012

Reposted by Yifei Yuan

Chris Potts @cgpotts.bsky.social · 13/01/2025

I've posted the practice run of my LSA keynote. My core claim is that LLMs can be useful tools for doing close linguistic analysis. I illustrate with a detailed case study, drawing on corpus evidence, targeted syntactic evaluations, and causal intervention-based analyses: youtu.be/DBorepHuKDM

youtu.be

Finding linguistic structure in large language models

YouTube video by Chris Potts

17420

Yifei Yuan @yfyuan01.bsky.social · 14/12/2024

I feel extremely upset and offended by this. How can we expect LLMs to generate unbiased, toxic-free content when AI professors make racist remarks during an AI Ethics talk? And some people think we’re overreacting and it’s no big deal? There’s so much more work to be done.

0110

Reposted by Yifei Yuan

Bradley Love @profdata.bsky.social · 27/11/2024

"Large language models surpass human experts in predicting neuroscience results" w @ken-lxl.bsky.social and braingpt.org. LLMs integrate a noisy yet interrelated scientific literature to forecast outcomes. nature.com/articles/s41... 1/8

19279109

Reposted by Yifei Yuan

Jiaang Li @jiaangli.bsky.social · 19/11/2024

🤔Do Vision and Language Models Share Concepts? 🚀 We present an empirical evaluation and find that language models partially converge towards representations isomorphic to those of vision models. #EMNLP 📃 direct.mit.edu/tacl/article...

2267