OlmoEarth v1.2: A more efficient family of OlmoEarth models

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

OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research

arXiv:2607. 16669v1 Announce Type: cross Abstract: OpenLanguageModel (OLM) is an open-source PyTorch library for building and pretraining small language models while keeping their machinery visible.

AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference

arXiv:2604. 15622v3 Announce Type: replace-cross Abstract: Always-on contextual AI runs language-aligned vision foundation models (VFMs) on edge devices, where the on-device model is the dominant continuous compute cost under strict latency and power limits.

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

The paper presents Puro-2B, an open-source language model pretraining recipe that enables training models up to 1.4 trillion tokens on consumer-grade RTX 5090 GPUs using FP8 precision. The authors achieve a best model with a compute cost under $6.9K, approaching Qwen2.5-1.5B performance, and introduce a Puro Cost Scaling Law indicating that about $4.4K suffices to match Qwen2-1.5B. Additionally, they analyze how pretraining data curricula affect downstream performance, providing a full training pipeline and releasing all resources under Apache 2.0.

OpWeave: Flexible Operator Disaggregation for Heterogeneous LLM Serving

arXiv:2609.14237v1 Announce Type: cross Abstract: LLM serving systems increasingly disaggregate inference into finer-grained stages, with recent approaches separating attention from FFN or MoE execut...

SIMPLER: Efficient Foundation Model Adaptation via Similarity-Guided Layer Pruning for Earth Observation

SIMPLER is a pre‑fine‑tuning method that reduces inference and deployment costs for Earth Observation foundation models by pruning redundant layers. It uses layer‑wise representation similarity on unlabeled task data to identify and remove up to 79% of parameters without requiring gradients, magnitude heuristics, or hyperparameter tuning. Experiments on Prithvi‑EO‑2, TerraMind, and ImageNet‑pretrained ViT‑MAE show that SIMPLER retains 94% of baseline performance while achieving 2.1× faster training and 2.6× faster inference.

Predict before you train: Scaling Laws for particle physics foundation models

arXiv:2607. 23377v1 Announce Type: cross Abstract: The largest machine learning models in particle physics are also the most expensive to train, yet the return on scaling a given architecture cannot be estimated before that compute is spent.

Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation

arXiv:2601. 22813v2 Announce Type: replace Abstract: The NVFP4 lower-precision format, supported in hardware by NVIDIA Blackwell GPUs, promises to allow, for the first time, end-to-end fully-quantized pre-training of massive models such as LLMs.

MONA: Muon Optimizer with Nesterov Acceleration for Scalable Language Model Training

MONA is a new optimizer that extends the Muon optimizer by adding a Nesterov‑style acceleration term derived from an exponential moving average of gradient differences. The paper provides a convergence analysis showing that this term offers curvature‑aware corrections while maintaining Muon’s spectral‑norm regularization. Empirical results demonstrate that MONA outperforms both Muon and AdamW on Mixture‑of‑Experts pretraining across models ranging from 1 B to 68 B parameters, and achieves state‑of‑the‑art performance on downstream benchmarks after fine‑tuning the largest model.

FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel

arXiv:2508. 18224v3 Announce Type: replace-cross Abstract: Recent advances in sparse attention mechanisms have demonstrated strong potential for reducing the computational cost of long-context training and inference in large language models (LLMs).

TACO: Ternary Absolute-max Column-wise One-sparse Optimizer for LLM Fine-Tuning

The paper introduces TACO, a new optimizer for fine‑tuning large language models that drastically reduces optimizer state memory while preserving first‑order gradients. TACO selects the sign of the largest magnitude entry in each column of weight matrices, achieving a 174× reduction in persistent optimizer memory compared to AdamW8bit and a 2.9× decrease in peak training memory on OPT‑13B. This allows full‑parameter fine‑tuning of 30–32B‑parameter models on a single 80 GB GPU across multiple model families and tasks, with comparable accuracy and runtime to existing methods.

HIERA: Workload-Aware Planning Across Implementation Spaces for GPU Kernel Optimization

arXiv:2608.21157v1 Announce Type: cross Abstract: High-performance GPU kernels underpin modern deep learning and scientific computing. As workloads become increasingly diverse and GPU hardware evolve...