Ai2

non-profit

Verified

https://allenai.org/

AI & ML interests

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

Recent Activity

dirkraft updated a dataset about 10 hours ago

allenai/asta-bench-submissions

Regan updated a dataset about 12 hours ago

allenai/asta-bench-results

jordi-ai2 updated a dataset about 13 hours ago

allenai/molmospaces

View all activity

Papers

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

View all Papers

allenai 's Papers 14

Submitted by

taesiri

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs

allenai

Submitted by

taesiri

MolmoB0T: Large-Scale Simulation Enables Zero-Shot Manipulation

allenai

Submitted by

TengXiao

Meta-Reinforcement Learning with Self-Reflection for Agentic Search

allenai

Submitted by

Duan

TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics

allenai

Submitted by

taesiri

How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs

allenai

Submitted by

Duan

Recurrent-Depth VLA: Implicit Test-Time Compute Scaling of Vision-Language-Action Models via Latent Iterative Reasoning

allenai

Submitted by

Duan

VLS: Steering Pretrained Robot Policies via Vision-Language Models

allenai

Submitted by

Benjamin Minixhofer

Bolmo: Byteifying the Next Generation of Language Models

allenai

Submitted by

taesiri

Olmo 3

allenai

Submitted by

Jitesh Jain

SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning

allenai

Submitted by

taesiri

OlmoEarth: Stable Latent Image Modeling for Multimodal Earth Observation

allenai

Submitted by

taesiri

olmOCR 2: Unit Test Rewards for Document OCR

allenai

Submitted by

Duan

MolmoAct: Action Reasoning Models that can Reason in Space

allenai

olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models

allenai