# JACTUS AI Unifies Compression and Adaptation _JACTUS AI unifies parameter compression and task adaptation, outperforming sequential methods with fewer retained parameters across vision and language tasks._ **Published:** 2026-05-05 **Source:** https://www.startuphub.ai/ai-news/ai-research/2026/jactus-ai-unifies-compression-and-adaptation --- The standard approach to adapting large pretrained models for new tasks involves a sequential application of parameter-efficient fine-tuning (PEFT) and low-rank compression. This decoupled strategy risks suboptimal compression by failing to align the compressed subspace with downstream objectives, potentially wasting precious global parameter budgets. To address this, researchers have introduced [JACTUS (Joint Adaptation and Compression with a Task-aware Union of Subspaces)](https://arxiv.org/abs/2605.02829v1), a novel framework that seamlessly unifies these two critical processes. ## Unified Subspace for Efficient Adaptation JACTUS operates by first estimating input and pre-activation gradient covariances from a small calibration set. It then forms an orthogonal union of these covariances with the pretrained weight subspace. A projected low-rank approximation is performed within this unified subspace. Crucially, JACTUS employs a global rank allocation strategy based on marginal gain per parameter, training only a compact core matrix. This explicit coupling of directions preserved for compression with those required for [adaptation](/ai-news/ai-research/2026/llm-adaptation-without-retraining) mitigates misalignment issues, leading to a deployable low-rank model that avoids retaining full frozen weights and enables rapid, robust tuning. ## State-of-the-Art Performance on Vision and Language The efficacy of JACTUS AI is demonstrated across both vision and language domains. On vision tasks using ViT-Base, JACTUS achieves an average accuracy of 89.2% across eight datasets while retaining only 80% of parameters. This performance surpasses strong 100% PEFT baselines like [DoRA](/ai-news/ai-research/2026/dora-efficiency-breakthrough) (87.9%). In the language domain, JACTUS applied to Llama2-7B for commonsense QA tasks reaches an average accuracy of 80.9% with the same 80% retained-parameter budget. This outpaces 100% PEFT methods such as DoRA (79.7%) and outperforms prior compress-then-finetune pipelines under identical budget constraints. The researchers plan to release the code for JACTUS AI. --- Original analysis from [startuphub.ai](https://www.startuphub.ai), the #1 AI startup directory. © StartupHub.ai. All rights reserved. You may not republish this article in full without a license. Search engines and AI research tools may crawl and summarize for reference. Bulk reproduction or model training on this content requires a license. See https://www.startuphub.ai/terms.