Research

Paper

AI LLM March 24, 2026

PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference

Authors

Qirui Wang, Qi Guo, Yiding Sun, Junkai Yang, Dongxu Zhang, Shanmin Pang, Qing Guo

Abstract

Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity.

Metadata

arXiv ID: 2603.22943
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-24
Fetched: 2026-03-25 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.22943v1</id>\n    <title>PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference</title>\n    <updated>2026-03-24T08:39:35Z</updated>\n    <link href='https://arxiv.org/abs/2603.22943v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.22943v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Personalized text-to-image generation lets users fine-tune diffusion models into repositories of concept-specific checkpoints, but serving these repositories efficiently is difficult for two reasons: natural-language requests are often ambiguous and can be misrouted to visually similar checkpoints, and standard post-training quantization can distort the fragile representations that encode personalized concepts. We present PersonalQ, a unified framework that connects checkpoint selection and quantization through a shared signal -- the checkpoint's trigger token. Check-in performs intent-aligned selection by combining intent-aware hybrid retrieval with LLM-based reranking over checkpoint context and asks a brief clarification question only when multiple intents remain plausible; it then rewrites the prompt by inserting the selected checkpoint's canonical trigger. Complementing this, Trigger-Aware Quantization (TAQ) applies trigger-aware mixed precision in cross-attention, preserving trigger-conditioned key/value rows (and their attention weights) while aggressively quantizing the remaining pathways for memory-efficient inference. Experiments show that PersonalQ improves intent alignment over retrieval and reranking baselines, while TAQ consistently offers a stronger compression-quality trade-off than prior diffusion PTQ methods, enabling scalable serving of personalized checkpoints without sacrificing fidelity.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-24T08:39:35Z</published>\n    <arxiv:comment>Accepted in ICME 2026</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Qirui Wang</name>\n    </author>\n    <author>\n      <name>Qi Guo</name>\n    </author>\n    <author>\n      <name>Yiding Sun</name>\n    </author>\n    <author>\n      <name>Junkai Yang</name>\n    </author>\n    <author>\n      <name>Dongxu Zhang</name>\n    </author>\n    <author>\n      <name>Shanmin Pang</name>\n    </author>\n    <author>\n      <name>Qing Guo</name>\n    </author>\n  </entry>"
}