Weijia Shi @ ICML
@WeijiaShi2
Followers
8K
Following
4K
Media
58
Statuses
1K
PhD student @uwnlp @allen_ai | Prev @MetaAI @CS_UCLA | 🏠 https://t.co/Q6Mzg8p3RR
Seattle, WA
Joined August 2019
Can data owners & LM developers collaborate to build a strong shared model while each retaining data control?. Introducing FlexOlmo💪, a mixture-of-experts LM enabling:.• Flexible training on your local data without sharing it.• Flexible inference to opt in/out your data
Introducing FlexOlmo, a new paradigm for language model training that enables the co-development of AI through data collaboration. 🧵
9
81
264
RT @pratyushmaini: At #ICML2025, I am super excited to introduce STAMP. This is a marriage b/w dataset inference & watermarking that finall….
0
13
0
RT @sarahwiegreffe: I am at #ICML2025! 🇨🇦🏞️.Catch me:. 1️⃣ Today at the @WiMLworkshop mentoring roundtables (1-2pm in W211-214). 2️⃣ Presen….
0
11
0
RT @XiaochuangHan: Check out our work led by @Cumquaaa on a hybrid autoregressive-diffusion architecture for image generation -- it flexibl….
0
6
0
RT @KempnerInst: If you can't make it to ICML and want to learn more about @du_yilun's work, check out the great talk he gave at the #Kempn….
0
9
0
RT @AkariAsai: I'll be hiring a couple of Ph.D. students at CMU (via LTI or MLD) in the upcoming cycle! .If you are interested in joining m….
0
13
0
RT @IanMagnusson: Come chat with us at our ICML poster tomorrow! .📈 Learn about the best ways to evaluate for base language model developme….
0
13
0
RT @RulinShao: Happy to share that ReasonIR is accepted by @COLM_conf! .Synthetic data & test-time scaling are powerful tools to enable new….
0
14
0
RT @PeterHndrsn: Check out our new blogpost and policy brief on our recently updated lab website! . ❓Are we actually capturing the bubble o….
0
11
0
RT @alisawuffles: SuperBPE is accepted to COLM (w/ three 9s)!🚀. We also wrote a blog w/ new results & suggestions after working with lots o….
0
24
0
RT @ShayneRedford: Copyrighted 🚧, private 🛑, and sensitive ☢️ data remain major challenges for AI. FlexOlmo introduces an architectural m….
0
6
0
RT @HannaHajishirzi: If you’re an organization with sensitive data but want to utilize state-of-the-art models, connect with our partnershi….
0
1
0
Going to #ICML2025 next week! Excited to chat about decentralized LM training, unified models, reasoning, and more. Please reach out if you like to meet up :).
9
4
136
RT @niloofar_mire: I'm gonna be at #ICML!. You can find me at the #Memorization workshop (MemFM co-organizer), the Technical #AI_Governance….
0
2
0
RT @mciccone_AI: Fantastic work from @allen_ai - asynchronous training of MoEs on private datasets and a domain-aware router. Akin to cros….
0
2
0
RT @shocheen: Check out our new paper, led by the amazing @orevaahia, on evaluating the reasoning abilities of audio LMs using brutally lon….
0
4
0
RT @ShirleyYXWu: Introducing 🔥Optimas🔥: The first unified framework to optimize compound AI systems composed of multiple components like tr….
0
34
0
RT @StellaLisy: FlexOlmo enables fine-grained data control on language models at test time through an anchor expert, such a cool work and g….
0
2
0
RT @notkevinfarhat: The bottleneck in AI isn't just compute - it's access to diverse, high-quality data, much of which is locked away due t….
0
46
0