Post-training Quantization for Hybrid Iterative Generative Models

• URL: http://arxiv.org/abs/2608.13932v1
• Date: Fri, 14 Aug 2026 04:07:14 GMT
• Title: Post-training Quantization for Hybrid Iterative Generative Models
• Abstract summary: Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity.<n>Post-training Quantization (PTQ) is appealing for acceleration, while directly applying vanilla PTQ to hybrid IGMs can trigger model collapse.<n>We introduce HyGenQ, a PTQ framework for hybrid IGMs.<n>It successfully quantizes representative hybrid IGMs to 8-bit precision (W8A8), significantly outperforming existing baselines and validating its robustness across different model families.
• Score: 52.791973512723324
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Iterative Generative Models (IGMs) span autoregressive and diffusion paradigms, and hybrid variants that couple them can achieve remarkable image-generation fidelity. However, their iterative inference incurs substantial computational overhead, making Post-training Quantization (PTQ) appealing for acceleration, while directly applying vanilla PTQ to hybrid IGMs can trigger model collapse. By analyzing these failures, we identify two critical challenges: Excessive Outliers (EOs) in the activations create an irreconcilable trade-off between preserving normal precision and covering EOs, resulting in severe degradation in generation quality; Amplified Anomalies (AAs) arising unpredictably from minor quantization errors, create a mismatch between calibration and inference, thus iteratively triggering model collapse. To address these challenges, we introduce HyGenQ, a PTQ framework for hybrid IGMs. HyGenQ comprises Hierarchical Cluster Decoupling (HCD) and Scaling Recalibration (SR). HCD identifies and decouples outlier channels via a multi-stage clustering process, effectively isolating EOs while maintaining normal value precision, thereby alleviating performance degradation. SR scales AAs beyond Gaussian Bound, thereby avoiding model collapse caused by aggressive truncation. Extensive experiments demonstrate that HyGenQ successfully quantizes representative hybrid IGMs to 8-bit precision (W8A8), significantly outperforming existing baselines and validating its robustness across different model families.

Related papers

• Q-ARVD: Quantizing Autoregressive Video Diffusion Models [98.30793646153926]
  Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming video generation.<n>However, the substantial inference cost of ARVDs remains a major obstacle to practical deployment.<n>We propose Q-ARVD, a novel framework for accurate ARVD quantization.
  arXiv  Detail & Related papers  (2026-05-20T11:58:30Z)
• Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models [50.45915413315706]
  We prove the existence of fundamental limitations for non-hybrid models.<n>We construct hybrid models of small size and working memory that provably solve these tasks.<n>We additionally demonstrate that hybrid models exhibit stronger length generalization and out-of-distribution robustness than non-hybrids.
  arXiv  Detail & Related papers  (2026-03-09T19:20:01Z)
• Information Fidelity in Tool-Using LLM Agents: A Martingale Analysis of the Model Context Protocol [69.11739400975445]
  We introduce the first theoretical framework for analyzing error accumulation in Model Context Protocol (MCP) agents.<n>We show that cumulative distortion exhibits linear growth and high-probability deviations bounded by $O(sqrtT)$.<n>Key findings include: semantic weighting reduces distortion by 80%, and periodic re-grounding approximately every 9 steps suffices for error control.
  arXiv  Detail & Related papers  (2026-02-10T21:08:53Z)
• CausalCLIP: Causally-Informed Feature Disentanglement and Filtering for Generalizable Detection of Generated Images [3.281374657433808]
  CausalCLIP is a framework that explicitly disentangles causal from non-causal features and employs targeted filtering guided by causal inference principles.<n>When tested on unseen generative models from different series, CausalCLIP demonstrates strong generalization ability, achieving improvements of 6.83% in accuracy and 4.06% in average precision over state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-15T12:48:27Z)
• Hybrid second-order gradient histogram based global low-rank sparse regression for robust face recognition [4.582941396468189]
  Low-rank regression models have been widely adopted in face recognition due to their robustness against illumination variations.<n>Existing methods often suffer from insufficient feature representation and limited modeling of structured corruption across samples.<n>This paper proposes a Hybrid second-order gradient Histogram based Global Low-Rank Sparse Regression model.
  arXiv  Detail & Related papers  (2025-11-08T07:31:38Z)
• Bifidelity Karhunen-Loève Expansion Surrogate with Active Learning for Random Fields [0.4899818550820576]
  We present a bifidelity Karhunen-Loeve expansion (KLE) surrogate model for field-valued quantities of interest (QoIs) under uncertain inputs.<n>We form an active learning strategy that adaptively selects new HF evaluations based on the surrogate's generalization error.<n>New HF samples are then acquired by maximizing an expected improvement criterion, targeting regions of high surrogate error.
  arXiv  Detail & Related papers  (2025-11-05T04:14:44Z)
• Quantum-Enhanced Generative Models for Rare Event Prediction [0.0]
  We propose the Quantum-Enhanced Generative Model (QEGM), a hybrid classical-quantum framework that integrates deep latent-variable models with variational quantum circuits.<n>We evaluate QEGM on synthetic Gaussian mixtures and real-world datasets spanning finance, climate, and protein structure.<n>Results demonstrate that QEGM reduces tail KL divergence by up to 50 percent compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-11-03T20:24:55Z)
• Fast Autoregressive Models for Continuous Latent Generation [49.079819389916764]
  Autoregressive models have demonstrated remarkable success in sequential data generation, particularly in NLP.<n>Recent work, the masked autoregressive model (MAR) bypasses quantization by modeling per-token distributions in continuous spaces using a diffusion head.<n>We propose Fast AutoRegressive model (FAR), a novel framework that replaces MAR's diffusion head with a lightweight shortcut head.
  arXiv  Detail & Related papers  (2025-04-24T13:57:08Z)
• GenIAS: Generator for Instantiating Anomalies in time Series [54.959865643340535]
  We develop a generative model for time series anomaly detection (TSAD) using a variational autoencoder.<n>GenIAS is designed to produce diverse and realistic synthetic anomalies for TSAD tasks.<n>Our experiments demonstrate that GenIAS consistently outperforms seventeen traditional and deep anomaly detection models.
  arXiv  Detail & Related papers  (2025-02-12T10:10:04Z)
• Dissecting Arbitrary-scale Super-resolution Capability from Pre-trained Diffusion Generative Models [24.82036158180386]
  Diffusion-based Generative Models (DGMs) have achieved unparalleled performance in synthesizing high-quality visual content. Recent solutions for these tasks often train architecture-specific DGMs from scratch, or require iterative fine-tuning and distillation on pre-trained DGMs. We propose Diff-SR, a first ASSR attempt based solely on pre-trained DGMs, without additional training efforts.
  arXiv  Detail & Related papers  (2023-06-01T14:20:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.