VictoriaLinML's profile picture. MTS @thinkymachines | MoMa/MoT🖼 • RA-DIT🔍 • Llama4🦙
Ex: @AIatMeta, @SFResearch • PhD @uwcse 
📜 http://threads.net/@v.linspiration 🌴 Bay Area

Victoria X Lin

@VictoriaLinML

MTS @thinkymachines | MoMa/MoT🖼 • RA-DIT🔍 • Llama4🦙 Ex: @AIatMeta, @SFResearch • PhD @uwcse 📜 http://threads.net/@v.linspiration 🌴 Bay Area

Pinned

1/n Introducing MoMa 🖼, our new sparse early-fusion architecture for mixed-modal language modeling that significantly boosts pre-training efficiency 🚀 (arxiv.org/pdf/2407.21770). MoMa employs a mixture-of-expert (MoE) framework with modality-specific expert groups. Given any…

VictoriaLinML's tweet image. 1/n Introducing MoMa 🖼, our new sparse early-fusion architecture for mixed-modal language modeling that significantly boosts pre-training efficiency 🚀 (arxiv.org/pdf/2407.21770).
MoMa employs a mixture-of-expert (MoE) framework with modality-specific expert groups. Given any…

Victoria X Lin reposted

Think about this talk a lot. There was a time when people were bullish on "feed all the modalities to the LLM," but it didn't really pan out as I would have expected. The discrete / continuous divide remains a interesting challenge in deep learning.


🤞🤞

Congrats on the move. The "kind, world-class team" part is often underestimated in these announcements. Technical ambition is common enough in AI right now.. but building something genuinely novel requires a team culture that can sustain deep collaboration without burning out.…



Very interesting read ☕ When poking different frontier models (e.g., GPT-5 vs Gemini), I’ve often noticed surprising similarity on non-STEM questions. This paper carefully quantified the “inter-model homogeneity” as part of their study — both in terms of embedding similarity and…

⚠️Different models. Same thoughts.⚠️ Today’s AI models converge into an 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐇𝐢𝐯𝐞𝐦𝐢𝐧𝐝 🐝, a striking case of mode collapse that persists even across heterogeneous ensembles. Our #neurips2025 𝐃&𝐁 𝐎𝐫𝐚𝐥 𝐩𝐚𝐩𝐞𝐫 (✨𝐭𝐨𝐩 𝟎.𝟑𝟓%✨) dives deep into…

liweijianglw's tweet image. ⚠️Different models. Same thoughts.⚠️

Today’s AI models converge into an 𝐀𝐫𝐭𝐢𝐟𝐢𝐜𝐢𝐚𝐥 𝐇𝐢𝐯𝐞𝐦𝐢𝐧𝐝 🐝, a striking case of mode collapse that persists even across heterogeneous ensembles.

Our #neurips2025 𝐃&𝐁 𝐎𝐫𝐚𝐥 𝐩𝐚𝐩𝐞𝐫 (✨𝐭𝐨𝐩 𝟎.𝟑𝟓%✨) dives deep into…


Victoria X Lin reposted

Today we’re announcing research and teaching grants for Tinker: credits for scholars and students to fine-tune and experiment with open-weight LLMs. Read more and apply at: thinkingmachines.ai/blog/tinker-re…


Victoria X Lin reposted

I'm recruiting PhD students! I'm interested in: 1. Understanding how LLMs 'see' the world (ex: LMs can't see conspicious omissions, see AbsenceBench) 2. How can we make things with LLMs that have never been made before? (ex: Communnication Games, see 📌) 3. See my other posts :)


Victoria X Lin reposted

Several of my team members + myself are impacted by this layoff today. Welcome to connect :)


Victoria X Lin reposted

This is an excellent history of LLMs, doesn't miss seminal papers I know. Reminds you we're standing on the shoulders of giants, and giants are still being born today. gregorygundersen.com/blog/2025/10/0…


Victoria X Lin reposted

Luke Zettlemoyer (@LukeZettlemoyer) plenary talk on scalable architectures for multimodal language modeling #COLM2025 Chameleon: autoregressive multimodal language models -- treat image as tokens -- works but harder to scale -- modality gap seems to be a big problem…

sivareddyg's tweet image. Luke Zettlemoyer (@LukeZettlemoyer)  plenary talk on scalable architectures for multimodal language modeling #COLM2025

Chameleon: autoregressive multimodal language models
-- treat image as tokens
-- works but harder to scale
-- modality gap seems to be a big problem…
sivareddyg's tweet image. Luke Zettlemoyer (@LukeZettlemoyer)  plenary talk on scalable architectures for multimodal language modeling #COLM2025

Chameleon: autoregressive multimodal language models
-- treat image as tokens
-- works but harder to scale
-- modality gap seems to be a big problem…
sivareddyg's tweet image. Luke Zettlemoyer (@LukeZettlemoyer)  plenary talk on scalable architectures for multimodal language modeling #COLM2025

Chameleon: autoregressive multimodal language models
-- treat image as tokens
-- works but harder to scale
-- modality gap seems to be a big problem…
sivareddyg's tweet image. Luke Zettlemoyer (@LukeZettlemoyer)  plenary talk on scalable architectures for multimodal language modeling #COLM2025

Chameleon: autoregressive multimodal language models
-- treat image as tokens
-- works but harder to scale
-- modality gap seems to be a big problem…

Victoria X Lin reposted

Tinker provides an abstraction layer that is the right one for post-training R&D -- it's the infrastructure I've always wanted. I'm excited to see what people build with it. "Civilization advances by extending the number of important operations which we can perform without…

Introducing Tinker: a flexible API for fine-tuning language models. Write training loops in Python on your laptop; we'll run them on distributed GPUs. Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…

thinkymachines's tweet image. Introducing Tinker: a flexible API for fine-tuning language models.

Write training loops in Python on your laptop; we'll run them on distributed GPUs.

Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…


Victoria X Lin reposted

Tinker brings tools similar to the ones we use internally to the community. It provides a clean, transparent, abstraction that lets researchers write expressive experiments and training pipelines, while we manage the complexities of distributed training and sampling. We hope…

Introducing Tinker: a flexible API for fine-tuning language models. Write training loops in Python on your laptop; we'll run them on distributed GPUs. Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…

thinkymachines's tweet image. Introducing Tinker: a flexible API for fine-tuning language models.

Write training loops in Python on your laptop; we'll run them on distributed GPUs.

Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…


Victoria X Lin reposted

Introducing Tinker: a flexible API for fine-tuning language models. Write training loops in Python on your laptop; we'll run them on distributed GPUs. Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…

thinkymachines's tweet image. Introducing Tinker: a flexible API for fine-tuning language models.

Write training loops in Python on your laptop; we'll run them on distributed GPUs.

Private beta starts today. We can't wait to see what researchers and developers build with cutting-edge open models!…

Victoria X Lin reposted

LoRA makes fine-tuning more accessible, but it's unclear how it compares to full fine-tuning. We find that the performance often matches closely---more often than you might expect. In our latest Connectionism post, we share our experimental results and recommendations for LoRA.…

thinkymachines's tweet image. LoRA makes fine-tuning more accessible, but it's unclear how it compares to full fine-tuning. We find that the performance often matches closely---more often than you might expect. In our latest Connectionism post, we share our experimental results and recommendations for LoRA.…

Victoria X Lin reposted

...is today a good day for new paper posts? 🤖Learning to Reason for Factuality 🤖 📝: arxiv.org/abs/2508.05618 - New reward func for GRPO training of long CoTs for *factuality* - Design stops reward hacking by favoring precision, detail AND quality - Improves base model across…

jaseweston's tweet image. ...is today a good day for new paper posts? 
🤖Learning to Reason for Factuality 🤖
📝: arxiv.org/abs/2508.05618
- New reward func for GRPO training of long CoTs for *factuality*
- Design stops reward hacking by favoring precision, detail AND quality
- Improves base model across…

Victoria X Lin reposted

Happy to share that ReasonIR is accepted by @COLM_conf! Synthetic data & test-time scaling are powerful tools to enable new capabilities for challenging tasks. I’m impressed by how quickly smaller retrievers and better rerankers have been developed with ReasonIR data! #COLM2025

Meet ReasonIR-8B✨the first retriever specifically trained for reasoning tasks! Our challenging synthetic training data unlocks SOTA scores on reasoning IR and RAG benchmarks. ReasonIR-8B ranks 1st on BRIGHT and outperforms search engine and retriever baselines on MMLU and GPQA🔥

RulinShao's tweet image. Meet ReasonIR-8B✨the first retriever specifically trained for reasoning tasks! Our challenging synthetic training data unlocks SOTA scores on reasoning IR and RAG benchmarks. ReasonIR-8B ranks 1st on BRIGHT and outperforms search engine and retriever baselines on MMLU and GPQA🔥


Victoria X Lin reposted

Some updates 🚨 I finished my Ph.D at @uwcse in June 2025! After a year at AI2 as a Research Scientist, I am joining CMU @LTIatCMU & @mldcmu (courtesy) as an Assistant Professor in Fall 2026. The journey, acknowledgments & recruiting in 🧵

AkariAsai's tweet image. Some updates 🚨
I finished my Ph.D at @uwcse in June 2025!
After a year at AI2 as a Research Scientist, I am joining CMU @LTIatCMU & @mldcmu (courtesy) as an Assistant Professor in Fall 2026.
The journey, acknowledgments & recruiting in 🧵
AkariAsai's tweet image. Some updates 🚨
I finished my Ph.D at @uwcse in June 2025!
After a year at AI2 as a Research Scientist, I am joining CMU @LTIatCMU & @mldcmu (courtesy) as an Assistant Professor in Fall 2026.
The journey, acknowledgments & recruiting in 🧵

Gorgeous building! Just learned that both the CDIS building at UW–Madison and the Bill & Melinda Gates Center at U Washington are by the same architects — @LMNArchitects. 🏨 UW-Madison: lmnarchitects.com/project/comput… 🏨 U Washington: lmnarchitects.com/project/bill-m…

lmnarchitects.com

Bill & Melinda Gates Center for Computer Science & Engineering University of Washington - LMN...

-2789

My students called the new CDIS building “state-of-the-art”. I thought they were exaggerating. Today I moved in and saw it for myself. Wow. Photos cannot capture the beauty of the design.

SharonYixuanLi's tweet image. My students called the new CDIS building “state-of-the-art”. I thought they were exaggerating.

Today I moved in and saw it for myself. Wow. Photos cannot capture the beauty of the design.
SharonYixuanLi's tweet image. My students called the new CDIS building “state-of-the-art”. I thought they were exaggerating.

Today I moved in and saw it for myself. Wow. Photos cannot capture the beauty of the design.
SharonYixuanLi's tweet image. My students called the new CDIS building “state-of-the-art”. I thought they were exaggerating.

Today I moved in and saw it for myself. Wow. Photos cannot capture the beauty of the design.
SharonYixuanLi's tweet image. My students called the new CDIS building “state-of-the-art”. I thought they were exaggerating.

Today I moved in and saw it for myself. Wow. Photos cannot capture the beauty of the design.


Victoria X Lin reposted

OK, @sarawiltberger and I are experimenting with a small, project-based mentorship program designed for the age of AI. We’re looking for resourceful self-starters—from early high school to early-career professionals—who want to prove their abilities through hard work. You don’t…

I've been reflecting deeply on how the rapid AI revolution is reshaping education, employment, and entrepreneurship. I want to help ambitious, talented individuals—whether high schoolers, PhDs, skilled professionals, or entrepreneurs outside AI—to thrive during this transition.…



Loading...

Something went wrong.


Something went wrong.