On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “mid-training”

Learning to Reason as Action Abstractions with Scalable Mid-Training RLcs.LG

Mid-training improves RL by identifying compact action abstractions.

problem Unlocking full potential of RL with large language models.

method RA3 algorithm that optimizes sequential variational lower bound and discovers latent structures via RL.

result Improves performance by 8 points on HumanEval and 4 points on MBPP.

reinforcement learning mid-training action abstractions scalable algorithms language models

2025-09-30abs ↗pdf ↗

A Scalable Measure of Loss Landscape Curvature for Analyzing the Training Dynamics of LLMscs.LG

We introduce a scalable measure of curvature for analyzing training dynamics of large language models.

problem Analyzing the training dynamics of large language models due to high computational cost of measuring Hessian sharpness.

method We introduce critical sharpness and relative critical sharpness as computationally efficient measures capturing Hessian sharpness phenomena.

result We provide the first demonstration of sharpness phenomena at scale up to 7B parameters.

Large Language Models Training Dynamics Curvature Analysis Critical Sharpness Relative Critical Sharpness

2026-01-23abs ↗pdf ↗