cs.AIMay 4, 2026

Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces

Authors: Jingze Ge, Yun Liu, Xue Geng, Wanqi Dong, Wang Zhe Mark, Min Wu, Xulei Yang

Organizations: National University of Singapore · Nankai University · Institute for Infocomm Research (I2R), A*STAR

Abstract

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first compresses and then fine-tunes adapters, potentially misaligning the compressed subspace with downstream objectives and squandering a global parameter budget. To overcome this limitation, we introduce JACTUS (Joint Adaptation and Compression with a Task-aware Union of Subspaces), a single framework that unifies compression and adaptation. From a small calibration set, JACTUS estimates input and pre-activation gradient covariances, forms their orthogonal union with the pretrained weight subspace, performs a projected low-rank approximation inside this union, allocates rank globally by marginal gain per parameter, and trains only a compact core matrix. This explicitly mitigates the potential misalignment between the compressed subspace and downstream objectives by coupling the directions preserved for compression with those required for adaptation, yielding a deployable low-rank model that avoids retaining full frozen weights while enabling fast and robust tuning. On vision, JACTUS attains an average 89.2% accuracy on ViT-Base across eight datasets at 80% retained parameters, surpassing strong 100% PEFT baselines (e.g., DoRA 87.9%). On language, JACTUS achieves an 80.9% average on Llama2-7B commonsense QA at the same 80% retained-parameter budget, outperforming 100% PEFT (e.g., DoRA 79.7%) and exceeding prior compress-then-finetune pipelines under the same ratained-parameter budget. We will release code.

Explore similar work

CardsList
Jun 2, 2026cs.LG

Compress then Merge: From Multiple LoRAs into One Low-Rank Adapter

Low-rank adaptation (LoRA) enables parameter-efficient specialization of foundation models, but the proliferation of task-specific adapters fragments capabilities across many adapters, complicating reuse and deployment. We study the problem of merging TT LoRAs into a single rank-rr LoRA, thereby preserving the benefits of low-rank structure. Existing Merge-then-Compress pipelines treat the rank constraint as an afterthought: they merge adapters in the full parameter space, then compress the merged result to rank rr via truncated SVD. However, full-parameter merging may destroy the low-rank structure, making it difficult for subsequent compression to recover an effective rank-rr LoRA. We propose Compress-then-Merge (CtM), a reversed pipeline that enforces the rank-rr bottleneck before merging: CtM computes shared rr-dimensional subspaces using only the LoRA weights to capture cross-adapter common structure, projects each adapter into the shared subspaces to obtain r×rr\times r coordinates, and then applies standard merging rules in this reduced space. CtM guarantees a rank-rr LoRA by construction, avoiding post-hoc truncation, and enables efficient computation in the core space spanned by concatenated LoRA factors. Experiments across multiple models and tasks show that CtM consistently outperforms existing single-LoRA-output baselines while narrowing the performance gap to full-parameter merging methods.
Zhengbao He, Ruiqi Ding, Zhehao Huang +3
Low-Rank AdaptationLarge Language Model CompressionContext Compression
AskPDF
May 30, 2026cs.LG

ProjQ: Project-and-Quantize for Adapter-Aware LLM Compression

Post-Training Quantization (PTQ) and Low-Rank Adaptation (LoRA) constitute the standard pipeline for efficient Large Language Model (LLM) deployment. However, applying them sequentially poses a problem: PTQ often leaves behind random noise that is spread out (across the model's weights) in a way LoRA can't easily fix, meaning that LoRA ends up wasting its limited capacity trying to fix uncorrectable noise instead of improving task performance. In this paper, we propose \textbf{ProjQ}, a novel framework for constraining quantization noise to the low-rank manifold via orthogonal subspace projection. We derive an efficient alternating algorithm that shapes the quantization noise into a low-rank structure, effectively offloading dominant error components to the subsequent adapter while minimizing the residual error in the orthogonal "uncorrectable" subspace. Our theoretical analysis demonstrates that ProjQ preserves strictly greater model plasticity for downstream tasks compared to standard PTQ. Extensive experiments on LLaMA-2, Qwen2.5 and Qwen3 confirm that ProjQ consistently outperforms existing methods in both quantization error compensation and downstream task fine-tuning, achieving up to 2×2\times lower evaluation loss for compensation and matching the performance of standard 4-bit baselines on language modeling tasks with only 3 bits. The code is available on https://github.com/yy9301/ProjQ .
Wenya Yu, Chao Zhang, Li Wang +2
Large Language Model QuantizationLarge Language Model CompressionLow-Rank AdaptationLarge Language
AskPDF
Jun 26, 2026cs.LG

When One Adapter Speaks for Many: Discovering Low-Rank Redundancy in Continual Fine-Tuning

Low-Rank Adaptation (LoRA) has become the standard tool for parameter-efficient fine-tuning of large pretrained models. When applied sequentially across tasks in Continual Learning (CL), the standard assumption is that each new task requires a dedicated low-rank adapter. In this work, we challenge this assumption empirically and structurally. We show that task-specific LoRA adapters in CL exhibit significant low-rank redundancy: the subspaces spanned by adapters trained on different tasks substantially overlap, and in many cases earlier adapters can faithfully represent later tasks. Building on this observation, we propose LiteLoRA, a plug-and-play gating mechanism that learns at train time whether to recruit a new adapter or reuse existing low-rank representations. Our method reduces the number of active adapters by 20-70% while matching or exceeding state-of-the-art performance on standard CL benchmarks, revealing that structural redundancy is pervasive and that selective learning is sufficient to achieve stability without sacrificing plasticity.
Tanguy Dieudonné, Giulia Lanzillotta, Enis Simsar +2
Low-Rank Adaptation AdaptersContinual Fine-TuningContinual Learning MethodsLow-Rank FactorizationRedundancy
AskPDF