Ai2

non-profit

Verified

https://allenai.org/

AI & ML interests

Building breatkthrough AI to solve the world's biggest problems.

Recent Activity

abhishekraok new activity 1 day ago

allenai/Dolci-Think-SFT-Clean-v2:Drop 63 residual identity-leak rows (2,050,318 rows)

roTripathi new activity 3 days ago

allenai/toyblocks-data:updated dataset card safety disclosure

roTripathi new activity 3 days ago

allenai/maniflow-tb:Adding model card safety disclosure

View all activity

Papers

Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

View all Papers

Articles

ToyBlocks: A controlled world for robot learning and evaluation

StateBench: Testing how language models track state changes over long documents

Can we trust LLMs to judge whether a research idea is novel?

LitPivot: Developing research ideas through dynamic contextualization within the literature landscape

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

FairStress: A deeper evaluation of fairness in LLM decision-making

HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost

Impactful scheduling for GPU clusters

Open-sourcing AstaBrief, the fast report-generation model in Asta

Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs

BenchMIRT: What are LLM benchmarks actually measuring?

Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis

TutorMoments: Do AI tutors know when to help and when to hold back?

The OlmoEarth Platform: Geospatial inference at planetary scale

What building Shippy taught us about building agents

DiScoFormer: One transformer for density and score, across distributions

Which tokens does a hybrid model predict better?

MolmoMotion: Language-guided 3D motion forecasting

olmo-eval: An evaluation workbench for the model development loop

OlmoEarth v1.1: A more efficient family of Earth observation models

EMO: Pretraining mixture of experts for emergent modularity

View all articles

in allenai/Dolci-Think-SFT-Clean-v2 1 day ago

Drop 63 residual identity-leak rows (2,050,318 rows)

#1 opened 1 day ago by

in allenai/toyblocks-data 3 days ago

updated dataset card safety disclosure

#1 opened 3 days ago by

in allenai/maniflow-tb 3 days ago

Adding model card safety disclosure

#1 opened 3 days ago by

in allenai/Molmo2-4B-tb 3 days ago

added license detail to model card description

#3 opened 3 days ago by

Revised model card safety disclosure

#2 opened 3 days ago by

Add ToyBlocks data quick link

#1 opened 4 days ago by

in allenai/toyblocks-data 3 days ago

updated dataset card safety disclosure

#1 opened 3 days ago by

in allenai/Molmo2-4B-tb 3 days ago

added license detail to model card description

#3 opened 3 days ago by

Revised model card safety disclosure

#2 opened 3 days ago by

in allenai/maniflow-tb 3 days ago

Adding model card safety disclosure

#1 opened 3 days ago by

published an article 3 days ago

Article

ToyBlocks: A controlled world for robot learning and evaluation

allenai

•

3 days ago

• 18

updated a dataset 4 days ago

allenai/asta-bench-submissions

Updated 4 days ago • 239 • 3

updated a dataset 4 days ago

allenai/toyblocks-data

Viewer • Updated 3 days ago • 144M • 3.58k • 4

published 2 models 4 days ago

allenai/Molmo2-4B-tb

Robotics • Updated 3 days ago • 60 • 2

allenai/maniflow-tb

Robotics • Updated 3 days ago • 63 • 3

in allenai/Molmo2-4B-tb 4 days ago

Add ToyBlocks data quick link

#1 opened 4 days ago by

updated a dataset 4 days ago

allenai/toyblocks-data

Viewer • Updated 3 days ago • 144M • 3.58k • 4

updated a collection 4 days ago

ToyBlocks

All datasets and models about ToyBlocks FoundationWorlds. • 3 items • Updated 3 days ago • 1

published a dataset 4 days ago

allenai/toyblocks-data

Viewer • Updated 3 days ago • 144M • 3.58k • 4

updated a model 4 days ago

allenai/maniflow-tb

Robotics • Updated 3 days ago • 63 • 3