Genta Winata

⭐️We're thrilled to share that our paper WorldCuisines has been selected for the Best Theme Paper Award at NAACL 2025 @naaclmeeting! 🎉 A huge thank you to the reviewers and area chair for this incredible recognition — we’re truly honored. Massive gratitude to all our amazing co-authors for the countless hours, late nights, and deep discussions that went into creating this high-quality dataset. 2025.naacl.org/blog/best-pape… We can't wait to present next week at NAACL! Catch us at our poster session (Wednesday, April 30) and Best Paper Award Session (Friday, May 2) for our oral presentation. Check out the paper and project here: 🌐 worldcuisines.github.io Contributors: @fredyhudi, @patrickamadeus_, @davidanugraha, @rifkiaputri, @zzeet, @ubaidalih, @auliaadilaa, @adamnohejl, @JunhoMyung00211, @aliceoh, @AnarSnowball, @faridlazuarda, @jcblaisecruz, @nedjmaou, @jodieyzhou, @AboladeDaud, @prajdabre1, @holylovenia, @SCahyawijaya, @bryanwilie92, @mrpeerat, @farizikhwantri, @gkuwanto, @llamagrp, @mv_zhukova, @EmmanueleChers1, @AlhamFikri, @davlanade, @tarowatanabe, @OptionsGod_lgd,@AyuP_AI, and many others who are not on X. Acknowledgments: @nayeon7lee, @Wenliang_Dai, @pascalefung who helped and provided us insightful suggestions. #nlproc #naacl2025 #worldcuisines

VLMs can easily get distracted by unrelated cultural cues. Happy to present our work on this soon at #CVPR2026🥳 Working on multilingual VLMs? Consider using our benchmark: 📜arxiv.org/pdf/2511.17004 🤗huggingface.co/datasets/patri… Amazing work by @patrickamadeus_ and colleagues!

Happy to have my first Nature paper. Thank you @CAIS for the collaboration nature.com/articles/s4158…

Last week, Humanity’s Last Exam was published in @Nature. In just over a year, model scores on HLE have risen from under 5% to nearly 40%. Thank you to @scale_AI and the 1000+ HLE co-authors for helping policymakers and the public track these rapid advances in AI capabilities.

📢 Introducing Routing with Generated Data (RGD), a new setting for annotation-free LLM routing. We study how routers can be trained without any ground-truth labels. We also introduce CASCAL, a novel label-free LLM router that identifies niche skills using consensus-voting and hierarchical clustering. ➡️ Most LLM routers assume access to labeled, in-domain data to estimate model skills (query-answer routers). However, user distributions are unknown and labels are expensive or unavailable, highlighting the need for routers that work without labels. ➡️ We introduce Routing with Generated Data (RGD): routers are trained only on Q&A data generated from task descriptions, without human annotation. We experiment with various LLM generators of different strengths (Gemini-2.5-Flash, Qwen-3-32B, Exaone-3.5-7.8B). ➡️ CASCAL outperforms other query-answer and query-only routers across diverse datasets (MMLU-Pro, SuperGPQA, MedMCQA, BigBench Extra Hard), and is more robust to weaker generators.

@quarbby Me too

On this day, I finally got myself Premium as a Christmas present. Finally in the cool kids club 😀

@haryoaw Happened to me as well in neurips. They got poster, we got nothing

It's interesting that in the conference, I met someone who had presented a paper that had the same idea (different execution) as ours. Ours led to a finding, and theirs led to an oral presentation. 😭

@haryoaw Try kfc and mcd in India. I heard it is good

My friend ordered and ate fish and chips in India out of lots of Indian food choices.

@prajdabre @osanseviero We need IndicGPT @prajdabre

Very excited to release our ongoing work on IndicBERT-V3! Some key points: 1. Long context 2. Various model sizes 3. SOTA performance on bitext mining and RAG on our internal evaluations 4. Multilingual Indic support Go wild! cc @osanseviero for visibility, since we used Gemma. @anoopk

@IkhlasulHanif0 @WenhuChen 10k is all my citations till 2025 lol

@WenhuChen Insane

Surpassed 10K citations in a single year! 🥳

@WenhuChen GOAT!!!

💡Have you ever wondered whether vision–language models can be easily tricked by adding landmarks or flags to an image? In the spirit of the holidays🎄, we show that VLMs can indeed be easily confused like "Confused Tourists" ✈️: their performance drops significantly when such image perturbations are applied. 🔎 Check out "VLMs are Confused Tourists" ✈️ here arxiv.org/pdf/2511.17004 #vision #nlproc #robustness

@IkhlasulHanif0 x = San Diego (ACL) y = South Korea (ICML) 😀

Prof: "what are your plans on winter break?" Stud: "Oh I plan to go to x, y, z, ..." Prof: "Oh I mean in terms of research" aint noway

@IkhlasulHanif0 @patrickamadeus_ spend some real money

@patrickamadeus_ How to buy patrick

I WANT THIS PLEASE 😭😭

Craving holiday-themed paper? Say less🎄 Turns out, Vision Language Models are Confused Tourists ✈️😵‍💫 We show that adversarially induced cultural scenes significantly impair VLM cultural comprehension and trigger potential bias #NLProc #multimodal #robustness /thread 🧵(1/8)

@cneuralnetwork Sadly not joining aacl in person

anyone wanna catch dinner with me tomorrow in Mumbai pls dm

@IkhlasulHanif0 @UKPLab Winter is coming

Will be visiting @UKPLab on 10 jan yay

@IkhlasulHanif0 @UKPLab Wow nice