arXiv Machine Learning October 8, 2026 By Josh McGiff, Salma Mekaoui, Robert Shanahan, Nikola S. Nikolov

AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility

Read the original on arXiv Machine Learning →

AutoAdapt is a modular framework that automatically discovers latent domains and trains per-domain Low‑Rank Adaptation (LoRA) adapters independently in parallel, without modifying other adapters. It uses parameter‑free routing to integrate new domains, achieving performance comparable to a LoRA adapter trained on all domains while avoiding full‑model retraining. The approach prevents domain interference by construction, enabling taxonomy‑free domain specialization across 14 benchmarks and GPT‑4o evaluations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Hugging Face Trending Papers

Oct 7

AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility

Instruction-tuned models are deployed into environments where domains are heterogeneous and evolve, yet adding new domains or data typically requires costly retraining. We present AutoAdapt, a modular...

llms fine-tuning benchmarks

arXiv Machine Learning

Aug 7

SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters

arXiv:2608. 05161v1 Announce Type: cross Abstract: Instruction-tuned LLMs are deployed into environments where domains evolve, yet extending a fine-tuned model's capabilities without full retraining remains an unsolved practical challenge.

By Josh McGiff, Salma Mekaoui, Robert Shanahan, Nikola S. Nikolov

llms nlp fine-tuning

arXiv AI

6d ago

Upcycling Language Models for Multiple Specialized Domains

The paper introduces Domain‑Specialized Upcycling (DS‑Upcycling), a method that expands a dense Transformer with domain‑specific experts and a router to improve multi‑domain adaptation. Unlike prior LoRA‑based adapters that either weight all domains equally or activate all experts, DS‑Upcycling trains a domain‑aware router to select the appropriate expert while freezing other parameters. Experiments demonstrate superior average performance across domains and high routing accuracy (90‑98%) with only 256 examples per domain.

By Mingzi Cao, Xi Wang, Nikolaos Aletras

llms fine-tuning

arXiv AI

Aug 5

Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment

arXiv:2407. 21311v2 Announce Type: replace-cross Abstract: Unsupervised domain adaptation (UDA) aims to mitigate domain shift, where the distribution of labeled source data differs from that of unlabeled target data.

By Ali Abedi, Q. M. Jonathan Wu, Ning Zhang, Farhad Pourpanah

llms computer-vision fine-tuning safety

arXiv Machine Learning

Jul 21

DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation

arXiv:2607. 17467v1 Announce Type: cross Abstract: Few-shot Test-Time Domain Adaptation (FSTT-DA) seeks to adapt models to novel domains using only a handful of unlabeled target samples.

By Siobhan Reid, Zhixiang Chi, Li Gu, Omid Reza Heidari, Ziqiang Wang, Yang Wang

fine-tuning benchmarks

arXiv Machine Learning

Aug 18

Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation

arXiv:2608. 16384v1 Announce Type: cross Abstract: Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules.

By Suraj Yadav

fine-tuning benchmarks

One email a morning, machine-written

Related stories

AutoAdapt: Automatic Domain Discovery Enables Low-Cost Extensibility

SemiAdapt-Instruct: Extensible Instruction Tuning via Latent Domain-Specialised Adapters

Upcycling Language Models for Multiple Specialized Domains

Efficient unsupervised domain adaptation via self-supervised vision transformer and synergistic cross-domain alignment

DA-MergeLoRA: Hypernetwork-Based LoRA Merging for Few-Shot Test-Time Domain Adaptation

Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation