Article
ToyBlocks: A controlled world for robot learning and evaluation
allenai
• • 12
Kyle Wiggers
Ai2Comms
AI & ML interests
None yet
Recent Activity
published an article 2 days ago
ToyBlocks: A controlled world for robot learning and evaluation published an article 5 days ago
StateBench: Testing how language models track state changes over long documents published a dataset 5 days ago
allenai/state-benchOrganizations
published an article 2 days ago
published an article 5 days ago
Article
StateBench: Testing how language models track state changes over long documents
allenai
• • 17 published an article 12 days ago
Article
Can we trust LLMs to judge whether a research idea is novel?
allenai
• • 18 published an article 16 days ago
Article
LitPivot: Developing research ideas through dynamic contextualization within the literature landscape
allenai
• • 39 published an article 17 days ago
Article
OlmoEarth v1.3: State-of-the-art embeddings for the whole planet
allenai
• • 15 published an article 19 days ago
Article
FairStress: A deeper evaluation of fairness in LLM decision-making
allenai
• • 8 published an article 25 days ago
Article
HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the cost
allenai
• • 14 published an article about 1 month ago
Article
Impactful scheduling for GPU clusters
allenai
• • 54 published an article about 1 month ago
Article
Open-sourcing AstaBrief, the fast report-generation model in Asta
allenai
• • 28 published an article about 1 month ago
Article
Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEs
allenai
• • 26 published an article 2 months ago
Article
BenchMIRT: What are LLM benchmarks actually measuring?
allenai
• • 27 published an article 3 months ago
Article
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
allenai
• • 19 published an article 3 months ago
Article
TutorMoments: Do AI tutors know when to help and when to hold back?
allenai
• • 32 published an article 3 months ago
Article
The OlmoEarth Platform: Geospatial inference at planetary scale
allenai
• • 40 published an article 4 months ago
Article
What building Shippy taught us about building agents
allenai
• • 23 published an article 4 months ago
Article
DiScoFormer: One transformer for density and score, across distributions
allenai
• • 6 published an article 5 months ago
Article
Which tokens does a hybrid model predict better?
allenai
• • 9 published an article 5 months ago
Article
MolmoMotion: Language-guided 3D motion forecasting
allenai
• • 11 published an article 5 months ago
Article
olmo-eval: An evaluation workbench for the model development loop
allenai
• • 18 published an article 6 months ago
Article
OlmoEarth v1.1: A more efficient family of Earth observation models
allenai
• • 27