Genta Winata

AI Researcher @CapitalOne AIF. Ex @TechAtBloomberg @BigScienceW @SFResearch @hkust. Working on multilingual and LLM #NLProc.

[Genta Winata @gentaiscool]

@lawrenceztang what is your MMR?

[M. Rifqi Farhansyah @rifqifrhnsyah]

🥳 Happy to share that PingPong has been accepted to EMNLP 2026 - Main Conference!

Special thanks to all of my collaborators: @hanifmz07, @faridlazuarda, Maryam**, @Shmuhammadd, @nedjmaou, @sathready, @ponguru, @KodaliPrashant, Sunayana**, @gentaiscool, @AyuP_AI, @AlhamFikri

[Genta Winata @gentaiscool]

@IkhlasulHanif0 congrats

[Genta Winata @gentaiscool]

@pywirrarika @akkikiki lol

[Genta Winata @gentaiscool]

@mohitban47 I didn’t find this spot yesterday

[Genta Winata @gentaiscool]

@jiaxin_pei I am around

[Mohit Bansal @mohitban47]

-- Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection (Oral)

@niu_tianyi , @cyjustinchen , @gentaiscool , Shi-Xiong Zhang, Supriyo Chakraborty, Sambit Sahu, @zhan1624 , @EliasEskin

https://t.co/yUlyUyZYLf

#ACL2026 Harbor D: Session 17: Oral Session G: Tues. July 7, 11:00-12:30 PT

https://t.co/i74tqh1lkw

[Elias Stengel-Eskin @EliasEskin]

2/ #ACL2026 Tues. July 7, 11:00-12:30
Harbor D: Session 17: Oral Session G

Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection

@niu_tianyi, @cyjustinchen, @gentaiscool, Shi-Xiong Zhang, Supriyo Chakraborty, Sambit Sahu, @zhan1624, @mohitban47

https://t.co/9sTqOZdJFg

https://t.co/fF7Ov0dTax

[Genta Winata @gentaiscool]

@pywirrarika @AmericasNLP I am attending ACL too :)

[Elias Stengel-Eskin @EliasEskin]

🚨 Excited to announce that RGD has been accepted to #ACL2026 Main!

Routing with Generated Data (RGD) is a new LLM routing paradigm where routers estimate skills of models using generated data, without ground-truth labels.

We further introduce CASCAL, a new router for RGD that discovers niche skills via consensus voting + hierarchical clustering, with no ground truth needed.

🧵👇

[Alham Fikri Aji @AlhamFikri]

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:

📜https://t.co/UfXwf9DepP
🤗https://t.co/8J9L8zrjZ5

Amazing work by @patrickamadeus_ and colleagues!

[Genta Winata @gentaiscool]

Happy to have my first Nature paper. Thank you @CAIS for the collaboration https://t.co/OGDsDfoQ5x

[Center for AI Safety @CAIS]

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.

[Center for AI Safety @CAIS]

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.

[Elias Stengel-Eskin @EliasEskin]

📢 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.

[Genta Winata @gentaiscool]

@quarbby Me too

[Genta Winata @gentaiscool]

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

[Genta Winata @gentaiscool]

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

[Genta Winata @gentaiscool]

@prajdabre @osanseviero We need IndicGPT @prajdabre

[Genta Winata @gentaiscool]

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