@robinomial Profile picture

Robin Jia

@robinomial

Assistant Professor @CSatUSC | Previously Visiting Researcher @facebookai | Stanford CS PhD @StanfordNLP

Similar User
Yejin Choi photo

@YejinChoinka

Sewon Min photo

@sewon__min

Hanna Hajishirzi photo

@HannaHajishirzi

Sean (Xiang) Ren photo

@xiangrenNLP

Mohit Bansal photo

@mohitban47

Kai-Wei Chang photo

@kaiwei_chang

Maarten Sap (he/him) photo

@MaartenSap

Luke Zettlemoyer photo

@LukeZettlemoyer

Yu Su ✈️ #NeurIPS2024 photo

@ysu_nlp

Wei Xu photo

@cocoweixu

UW NLP photo

@uwnlp

Roy Schwartz photo

@royschwartzNLP

Mohit Iyyer photo

@MohitIyyer

Violet Peng photo

@VioletNPeng

Swabha Swayamdipta ✈️ EMNLP'24 🏖️ photo

@swabhz

Robin Jia Reposted

Any questions on generalisation that you feel need discussing? As them at one of our exciting invited talks by @najoungkim, @kylelostat and @sameer_), or share them so we can ask them at the @GenBench panel!


I’ll be on the GenBench panel this afternoon at 4pm! Please send in your questions!

Any questions on generalisation that you feel need discussing? As them at one of our exciting invited talks by @najoungkim, @kylelostat and @sameer_), or share them so we can ask them at the @GenBench panel!



Robin Jia Reposted

Not EMNLP'd out yet? Join the @GenBench workshop on generalisation in NLP today! 🤩 genbench.org/workshop/ Location: Brickell


Robin Jia Reposted

Come say hi! #EMNL2024 this week, featuring research by @CSatUSC researchers @swabhz @robinomial @_jessethomason_ @xiangrenNLP @jaspreetranjit_ and more!✨ @USCViterbi @USCAdvComputing

Welcome reception is in full swing at #EMNLP2024

Tweet Image 1


Robin Jia Reposted

My "looking for a postdoc" stickers and I are in Miami for #EMNLP2024! 🤩 Do you have/know of a postdoc for summer/autumn '25 related to interpretability, figlang and/or memorisation (vs generalisation)? Reach out! Looking forward to #GenBench2024 on Saturday and the many many...

Tweet Image 1

Robin Jia Reposted

How can LLMs 🤖 find all 𝙚𝙨𝙨𝙚𝙣𝙩𝙞𝙖𝙡 facts to write about a topic? 🤔 In our work, we leverage the planning capabilities of LLMs to guide retrieval of fine-grained facts for improved grounding of response. See our #EMNLP2024 paper: aclanthology.org/2024.emnlp-mai… [1/N]


Robin Jia Reposted

Drop by our poster tomorrow!! @emnlpmeeting #EMNLP2024 Nov 12 (Tue) at 11:00-12:30 Session: 02 Sub-session: Generation Looking forward to chatting with everyone!

How can LLMs 🤖 find all 𝙚𝙨𝙨𝙚𝙣𝙩𝙞𝙖𝙡 facts to write about a topic? 🤔 In our work, we leverage the planning capabilities of LLMs to guide retrieval of fine-grained facts for improved grounding of response. See our #EMNLP2024 paper: aclanthology.org/2024.emnlp-mai… [1/N]



Robin Jia Reposted

I will be presenting our LLM Interp. paper at #EMNLP2024 in Miami! 🗞️When Parts are Greater Than Sums: Individual LLM Components Can Outperform Full Models 🗓️Nov 12 Tue 14:00-15:30 (Jasmine) terarachang.github.io/projects/llm-d…


Robin Jia Reposted

In Miami for #EMNLP2024! Come check out our findings poster, Weak-to-Strong Reasoning, on Wednesday at 10:30am. Super excited for my first in-person conference. Looking forward to connecting and chatting about reasoning, hallucination, self-correction, and all things LLMs! 🌴🌴

Tweet Image 1

Robin Jia Reposted

Super excited about our new workshop on LLM memorization at ACL '25! Stay tuned :)

Our new workshop on Large Language Model Memorization will debut at ACL 2025 🎉 See you in Vienna!!



Robin Jia Reposted

Thrilled about the fact that L2M2 got accepted as a #ACL2025 workshop!! Stay tuned for more info & I hope to see you in Vienna 🥳

🎉 Happy to announce that the L2M2 workshop has been accepted at @aclmeeting! #NLProc #ACL2025 More details will follow soon. Stay tuned and spread the word! 📣



Our new workshop on Large Language Model Memorization will debut at ACL 2025 🎉 See you in Vienna!!

🎉 Happy to announce that the L2M2 workshop has been accepted at @aclmeeting! #NLProc #ACL2025 More details will follow soon. Stay tuned and spread the word! 📣



Robin Jia Reposted

Join us at USC's Thomas Lord Department of Computer Science! We’re hiring associate and full professors in all areas of computer science. Apply now: cs.usc.edu/about/open-fac… Please share with you communities! @USCViterbi @USCAdvComputing

Tweet Image 1

Robin Jia Reposted

For this week’s NLP Seminar, we are thrilled to host @jieyuzhao11 to talk about Building Accountable NLP Models for Social Good! When: 10/24 Thurs 11am PT Non-Stanford affiliates registration form (closed at 9am PT on the talk day): forms.gle/JbuJ1DiUuQp1sX…

Tweet Image 1

Robin Jia Reposted

Thanks for sharing our latest work on token-level reward models (TLDR) for multimodal models. Paper is out here: arxiv.org/abs/2410.04734

Tweet Image 1

Token-Level Detective Reward (TLDR) model instead of giving one score for the whole text provides fine-grained feedback on each token level for Large Vision LMs (VLMs). This development by @AIatMeta and @USC enhances error diagnosis and self-correction. Let's see how it works:

Tweet Image 1
Tweet Image 2


Robin Jia Reposted

Token-Level Detective Reward (TLDR) model instead of giving one score for the whole text provides fine-grained feedback on each token level for Large Vision LMs (VLMs). This development by @AIatMeta and @USC enhances error diagnosis and self-correction. Let's see how it works:

Tweet Image 1
Tweet Image 2

Loading...

Something went wrong.


Something went wrong.