Entity · organization
Allen Institute for AI
organizationactive
allen-institute-for-ai-970b6fe9·8 events·first seen Aliases: Allen Institute for AI
Co-occurring entities
More like this (12)
Recent events (8)
Allen AI launches OlmoEarth Platform for planetary-scale geospatial inference
Allen Institute for AI (AllenAI) has published a blog post on Hugging Face describing the OlmoEarth Platform, a system designed for geospatial inference at planetary scale. The post covers the infrastructure underpinning large-scale Earth observation and geospatial AI workloads. This represents a domain-specific AI deployment combining large-scale inference infrastructure with geospatial data, relevant to both the open-weights/open-science AI ecosystem and scientific AI applications.
Allen AI shares lessons from building Shippy agent system
Allen AI published a technical blog post on the Hugging Face platform documenting lessons learned from building Shippy, an AI agent system. The post covers practical insights about agent architecture and development challenges encountered during the project. As a practitioner-level retrospective from a respected research organization, it offers signal on real-world agent-building patterns.
Formal framework for valid extractable memorization claims in LLMs
A new arXiv preprint proposes a principled methodology for making valid extractable memorization claims about LLMs, addressing both over- and under-statement problems in prior work. The core contribution is a 'matched comparison' approach that measures generation probabilities of training sequences against comparable non-training sequences to establish a calibrated baseline for predictability. Two formalizations are offered: a conformal test for population-level claims and a census method for single-document claims. Applied to OLMo 2 32B on Wikipedia and Llama 3.1 70B on books, the framework reveals significant false-positive rates in naive extraction studies and supports memorization claims at probability thresholds as low as 1e-27.
LACUNA testbed introduces ground-truth parameter-level evaluation for LLM unlearning
Researchers introduce LACUNA, the first unlearning testbed with ground-truth parameter-level localization, designed to evaluate whether LLM unlearning methods truly erase knowledge from model weights or merely suppress it at the output level. The testbed injects PII of synthetic individuals into predefined parameters of 1B and 7B OLMo-based models via masked continual pretraining, enabling direct measurement of localization precision. Benchmarking current SOTA unlearning methods reveals they are highly imprecise and vulnerable to resurfacing attacks despite strong output-level performance, while successful localization enables even simple gradient-based methods to achieve robust erasure. The work addresses a critical gap in unlearning evaluation methodology relevant to privacy compliance and AI safety.
Allen AI introduces DiScoFormer: unified transformer for density estimation and score functions
Allen AI presents DiScoFormer, a single transformer architecture capable of jointly estimating probability densities and score functions across different distributions. The work is published on the Hugging Face blog, suggesting an accompanying model or code release. Unifying density and score estimation in one model has implications for generative modeling, diffusion models, and probabilistic inference.
AllenAI analysis: which tokens do hybrid models predict better than pure transformers?
A Hugging Face blog post from AllenAI investigates the token-level prediction differences between hybrid models (combining attention and state-space or other mechanisms) and standard transformer architectures. The analysis aims to characterize where hybrid architectures gain or lose predictive advantage at the token level. This kind of mechanistic comparison is relevant to ongoing debates about when hybrid designs are worth their added complexity.
MolmoMotion: Language-guided 3D motion forecasting from Allen AI
Allen AI published a blog post on Hugging Face introducing MolmoMotion, a system for language-guided 3D motion forecasting. The work extends the Molmo model family into motion prediction tasks, combining natural language conditioning with 3D spatial reasoning. The post appears to be an announcement or demonstration of the capability, though the body content was not available for detailed review.
OLMo Hybrid and Future LLM Architectures
Interconnects covers the latest OLMo hybrid model release and discusses emerging trends in open-source post-training tooling. The piece examines architectural directions for future large language models. As a tier-2 commentary source, it provides analysis rather than primary research findings.