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.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

2 results for “Post-alignment”

Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Informationcs.LG

Unified framework simplifies DPO algorithms for LLM alignment.

problem Vast number of DPO variants complicates model alignment.

method Mutual information inspired unifying framework with flexible priors.

result Many DPO variants can be derived from the new framework.

LLM alignment DPO Mutual information Post-alignment Flexible priors

2025-01-02abs ↗pdf ↗

Improving Model Fusion by Training-time Neuron Alignment with Fixed Neuron Anchorscs.LG

This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.

problem Diverse neuron permutations across different settings hinder model fusion performances.

method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.

result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.

model fusion neuron alignment federated learning pretrained models multi-model fusion

2024-02-02abs ↗pdf ↗