Lightnews — Scholar-powered news

Reposted by Jacob Morrison

Kunal Jha @kjha02.bsky.social · 6d

Forget modeling every belief and goal! What if we represented people as following simple scripts instead (i.e "cross the crosswalk")?

Our new paper shows AI which models others’ minds as Python code 💻 can quickly and accurately predict human behavior!

shorturl.at/siUYI%F0%9F%...

3 14 36

Reposted by Jacob Morrison

Saumya Malik @saumyamalik.bsky.social · Jun 2

Thank you to co-authors @natolambert.bsky.social, @valentinapy.bsky.social, @jacobcares.bsky.social, Sander Land, @nlpnoah.bsky.social, @hanna-nlp.bsky.social!
Read more in the paper here (ArXiv soon!): github.com/allenai/rewa...
Dataset, leaderboard, and models here: huggingface.co/collections/...

Reward Bench 2 - a allenai Collection

Datasets, spaces, and models for Reward Bench 2 benchmark and paper!

huggingface.co

1 2

Reposted by Jacob Morrison

Ai2 @ai2.bsky.social · Jun 2

RewardBench 2 is here! We took a long time to learn from our first reward model evaluation tool to make one that is substantially harder and more correlated with both downstream RLHF and inference-time scaling.

The RewardBench 2 Leaderboard on HuggingFace.

1 8 20

Reposted by Jacob Morrison

Nathan Lambert @natolambert.bsky.social · Apr 29

Heading to NAACL? With "verification being the key to AI" you should go to the poster session Friday, 9-10:30am to chat with my star colleagues @valentinapy.bsky.social + @jacobcares.bsky.social about RewardBench (and really RewardBench 2, evaluation, and reward models in post-training).

2 14

Jacob Morrison @jacobcares.bsky.social · Apr 28

Valentina and I will be presenting RewardBench at NAACL! Come say hi at the poster session on Friday and we can chat about reward models, staying up for 30 hours straight to rapidly reset from Singapore time, and more 🏜️

Valentina Pyatkin @valentinapy.bsky.social · Apr 27

I'll be at #NAACL2025:

🖇️To present my paper "Superlatives in Context", showing how the interpretation of superlatives is very context dependent and often implicit, and how LLMs handle such semantic underspecification

🖇️And we will present RewardBench on Friday

Reach out if you want to chat!

3 5

Reposted by Jacob Morrison

Valentina Pyatkin @valentinapy.bsky.social · Apr 27

I'll be at #NAACL2025:

🖇️To present my paper "Superlatives in Context", showing how the interpretation of superlatives is very context dependent and often implicit, and how LLMs handle such semantic underspecification

🖇️And we will present RewardBench on Friday

Reach out if you want to chat!

1 5 28

Jacob Morrison @jacobcares.bsky.social · Apr 26

what a flattering picture lol

1 2

Jacob Morrison @jacobcares.bsky.social · Apr 23

📜Paper: arxiv.org/abs/2503.05804
✍️Thanks to my illustrious coauthors @clarana.bsky.social @jaredfern.bsky.social timdettmers.com @strubell.bsky.social @jessedodge.bsky.social, t'was a fun project 🌏

Holistically Evaluating the Environmental Impact of Creating Language Models

As the performance of artificial intelligence systems has dramatically increased, so too has the environmental impact of creating these systems. While many model developers release estimates of the po...

arxiv.org

4 9

Jacob Morrison @jacobcares.bsky.social · Apr 23

I'm in Singapore for @iclr-conf.bsky.social ! Come check out our spotlight paper on the environmental impact of training OLMo (link in next tweet) during the Saturday morning poster session from 10-12:30 -- happy to chat about this or anything else! DMs should be open, email works too

1 5 10

Reposted by Jacob Morrison

Ai2 @ai2.bsky.social · Mar 13

Announcing OLMo 2 32B: the first fully open model to beat GPT 3.5 & GPT-4o mini on a suite of popular, multi-skill benchmarks.

Comparable to best open-weight models, but a fraction of training compute. When you have a good recipe, ✨ magical things happen when you scale it up!

3 15 58

Reposted by Jacob Morrison

Cats of Yore @catsofyore.bsky.social · Feb 26

There are no proven benefits to raw feeding yet plenty of serious, well-documented risks. It has never been a good idea but ESPECIALLY NOW. washingtonstatestandard.com/briefs/two-w...

Two Washington cats infected with bird flu • Washington State Standard

Two domestic cats in Washington state have been infected with bird flu after eating raw pet food, according to the department of agriculture.

washingtonstatestandard.com

1 1.7K 6.8K

Jacob Morrison @jacobcares.bsky.social · Jan 30

also some other tülu contributors are on the market:
@ljvmiranda.bsky.social (ljvmiranda921.github.io) and Xinxi Lyu (alrope123.github.io) are also applying to phd programs, and @valentinapy.bsky.social (valentinapy.github.io) is on the faculty market, hire them all!!

1 1

Jacob Morrison @jacobcares.bsky.social · Jan 30

check out the updated paper here: arxiv.org/pdf/2411.15124 (with a beautiful new template!) and the model here: huggingface.co/allenai/Llam... and on the ai2 playground: playground.allenai.org

1

Jacob Morrison @jacobcares.bsky.social · Jan 30

big tülu is here! can't wait for everyone to try it, it's been a lot of fun seeing how RL performs at this scale thanks to @hamishivi.bsky.social
and @vwxyzjn.bsky.social, and preference data from @ljvmiranda.bsky.social

on an unrelated note, I'm applying to phd programs this year 👀

Ai2 @ai2.bsky.social · Jan 30

Here is Tülu 3 405B 🐫 our open-source post-training model that surpasses the performance of DeepSeek-V3! It demonstrates that our recipe, which includes RVLR scales to 405B - with performance on par with GPT-4o, & surpassing prior open-weight post-trained models of the same size including Llama 3.1.

1 4

Reposted by Jacob Morrison

Ai2 @ai2.bsky.social · Jan 30

Here is Tülu 3 405B 🐫 our open-source post-training model that surpasses the performance of DeepSeek-V3! It demonstrates that our recipe, which includes RVLR scales to 405B - with performance on par with GPT-4o, & surpassing prior open-weight post-trained models of the same size including Llama 3.1.

2 20 92

Reposted by Jacob Morrison

Hamish Ivison @hamishivi.bsky.social · Jan 8

Excited to see Tulu 3 sits in between Llama 3.1 and 3.3 instruct on the chatbot arena leaderboard right now!

Particularly happy it is top 20 for Math and Multi-turn prompts :)

All the details and data on how to train a model this good are right here: arxiv.org/abs/2411.15124

3 15

Reposted by Jacob Morrison

Nathan Lambert @natolambert.bsky.social · Jan 8

Very pleased to see Tulu 3 70B more or less tied with Llama 3.1 70B Instruct on style controlled ChatBotArena. The only model anywhere close to that with open code and data for post-training! Lots of stuff people can build on.

Next looking for OLMo 2 numbers.

3 24

Reposted by Jacob Morrison

Costa Huang @vwxyzjn.bsky.social · Jan 6

We released the OLMo 2 report! Ready for some more RL curves? 😏

This time, we applied RLVR iteratively! Our initial RLVR checkpoint on the RLVR dataset mix shows a low GSM8K score, so we did another RLVR on GSM8K only and another on MATH only 😆.

And it works! A thread 🧵 1/N

1 5 12

Reposted by Jacob Morrison

Kyle Lo @ COLM 2025 🍁 @kylelo.bsky.social · Jan 3

kicking off 2025 with our OLMo 2 tech report while payin homage to the sequelest of sequels 🫡

🚗 2 OLMo 2 Furious 🔥 is everythin we learned since OLMo 1, with deep dives into:

🚖 stable pretrain recipe
🚔 lr anneal 🤝 data curricula 🤝 soups
🚘 tulu post-train recipe
🚜 compute infra setup

👇🧵

2 17 69

Reposted by Jacob Morrison

Jiacheng Liu @liujch1998.bsky.social · Dec 9

Want to predict the task performance of LMs before pretraining them?

We develop task scaling laws and model ladders, which predict the accuracy on individual tasks by OLMo 2 7B & 13B models within 2 points of absolute error. The cost is 1% of the compute used to pretrain them.

2 14 33

Reposted by Jacob Morrison

derek guy @dieworkwear.bsky.social · Nov 27

Why is Tokyo so fashionable? Some theories. 🧵

Saagar Enjeti tweets: "Probably a cold take but IMO Tokyo is the male fashion capital of the world: whether it’s western wear, suits, street wear the aesthetic is refined to the highest possible level

From the salaryman to the rebel teen they are impeccably dressed

It also helps no one is fat"

220 1.7K 9K

Reposted by Jacob Morrison

Luca Soldaini 🎀 @soldaini.net · Nov 26

OLMo 2 is out 🥳 7B and 13B trained on 5T tokens, and meticulousy instruction tuned using Tulu 3 recipe.

Simply the best fully open models yet.

Really proud of the work & the amazing team at
@ai2.bsky.social

9 44 260

Jacob Morrison @jacobcares.bsky.social · Nov 26

🍲

1 2 17

Reposted by Jacob Morrison

Ai2 @ai2.bsky.social · Nov 26

Meet OLMo 2, the best fully open language model to date, including a family of 7B and 13B models trained up to 5T tokens. OLMo 2 outperforms other fully open models and competes with open-weight models like Llama 3.1 8B — As always, we released our data, code, recipes and more 🎁

The OLMo 2 models sit at the Pareto frontier of training FLOPs vs model average performance.

5 36 150

Jacob Morrison @jacobcares.bsky.social · Nov 21

Thanks Tyler, great to hear from you!!