Olmo
PulseAugur coverage of Olmo — every cluster mentioning Olmo across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
Lightweight probabilistic method matches LLM performance on clinical diagnosis
A new research paper introduces a lightweight probabilistic method called Frequency-Based Probabilistic Ranker (FBPR) that can match the performance of large language models (LLMs) on multiple-choice clinical diagnosis …
-
New method traces LLM safety degradation to training data
Researchers have developed a new method called SimpleLoRIF to identify and remove potentially harmful data from the training sets of large language models. This technique uses gradient embeddings to pinpoint fine-tuning…
-
New method decodes hidden AI model intentions missed by standard classifiers
Researchers have developed a new method called persona-header likelihood evaluation (PHLE) that can detect hidden intentions or "personas" embedded within AI models, even when standard classifiers fail. This technique i…
-
New method filters LLM training data to improve safety
Researchers have developed a new method called SimpleLoRIF that uses gradient alignment to identify and filter out instruction data that can silently degrade the safety of Large Language Models (LLMs). This technique si…
-
Asymmetric Looped Transformers improve language model efficiency
Researchers have introduced the Asymmetric Looped Transformer (AsymLoop), a novel architecture that enhances language model efficiency by separating context encoding from iterative state refinement. This design uses a f…
-
New FairStress benchmark reveals hidden demographic biases in LLMs
Researchers have introduced FairStress, a new benchmark designed to evaluate demographic fairness in large language models beyond their final output decisions. This benchmark measures how readily models change their dec…
-
AI developers and researchers shift responsibility for output verification to users
Major AI players including Microsoft, Allen Institute, and Google Cloud AI Research are explicitly stating that users are responsible for verifying the accuracy and reliability of AI-generated outputs. Frameworks like L…
-
Research traces LLM language acquisition from intermediate training stages
A new research paper published on arXiv explores the developmental trajectory of language acquisition in Large Language Models (LLMs) by examining intermediate training checkpoints. The study utilized open-source models…
-
DAGFormer enhances Transformer connections with novel topology predictor
Researchers have introduced DAGFormer, a novel Transformer language model that enhances cross-layer connections through a jointly trained topology predictor. This model establishes direct connections from earlier to lat…
-
Allen Institute releases Olmo-core 3, boosting LLM training throughput
The Allen Institute for Artificial Intelligence (Ai2) has released Olmo-core 3, an open-source training framework for its Olmo language models. This new version introduces a distributed data parallelism approach, replac…
-
LLM post-training techniques advance with new distillation and optimization methods
Recent advancements in LLM post-training techniques have emerged, focusing on parameter-efficient fine-tuning, preference optimization, and distillation. New methods like DIAL-OPD demonstrate improved learning from fewe…
-
AI2 discusses agentic models and Olmo at COLM2026
The Allen Institute for Artificial Intelligence (AI2) is discussing advancements in agentic models and the upcoming Olmo iteration at the COLM2026 conference. AI2's Communications Lead, Kyle Wiggers, is interviewing Sen…
-
Bluesky AI research on byte-level language models accepted by Nature
A research paper detailing a method for retrofitting language models to operate over bytes, known as Bolmo, has been accepted for publication in Nature. In conjunction with this, new checkpoints are being released that …
-
Allen Institute for AI seeks engineers for agent frameworks, Olmo, Molmo
The Allen Institute for Artificial Intelligence (AI2) is actively recruiting for several positions, with a particular emphasis on roles related to agent frameworks and their Olmo and Molmo projects. The institute is see…
-
New research measures token compute cost, revealing optimization potential
A new research paper proposes a Mixture-of-Agents (MoA) approach to measure the actual computational cost of generating individual tokens in large language models. The study found that a significant portion of the compu…
-
New SURGE technique enhances RL models without extra training
Researchers have developed a new technique called SURGE (Scaling Up RL Gradient-free via Eigenspace fusion) that can improve the performance of existing reinforcement learning (RL) models without requiring additional tr…
-
AI2 releases Olmo-core 3 open-source MoE training infrastructure
The Allen Institute for Artificial Intelligence (AI2) has released Olmo-core 3, an open-source training infrastructure designed for large mixture-of-experts (MoE) models. This system is foundational for the development …
-
Hugging Face releases Olmo-core 3 for scalable trillion-parameter MoE training
Hugging Face has released Olmo-core 3, an open-source framework designed to scale the training of Mixture-of-Experts (MoE) large language models to trillion-parameter sizes. This new system addresses the computational i…
-
Developer releases new 2B parameter AI model 'Engram' with novel token probability table
A developer has created a new 2 billion parameter model called Engram, which utilizes a 1 billion parameter Engram table for enhanced token probability. Despite training on only 15 million tokens, the model demonstrates…
-
AI model capability emergence can be forecast, new research shows
A new research paper published on arXiv details a method for forecasting the emergence of capabilities in transformer models. The study demonstrates that the formation time of the previous-token head can predict the eme…