Large-scale video diffusion models (V-DMs) have achieved remarkable text-to-video generation quality, yet their massive computational complexity makes deployment costly. Post-Training Quantization (PTQ) offers an appealing route to accelerate inference without retraining, but existing diffusion PTQ methods remain fragile on modern V-DMs. A key reason is that contemporary V-DMs are intrinsically multi-resolution due to multi-stage training, while most prior PTQ pipelines calibrate at a fixed resolution, causing suboptimal calibration signals and biased distributions under resolution changes. To address this gap, we propose S $^{2}$ Q-VDiT $^+$, a multi-resolution co-design PTQ framework from data, supervision, and quantizer perspectives. First, Denoising-Prior Based Multi-Resolution Sampling constructs resolution-consistent noisy latents by mapping to the clean space and re-noising, together with a trajectory-aware resolution policy across timesteps. Second, Structure-Aware Multi-Resolution Distillation enhances structural alignment via window-wise distillation and transfers resolution-aware spatial dependencies via multi-scale attention distillation. Third, Debiased Modulated Quantization mitigates skewed distributions using asymmetric weight quantization and a fuseable activation debiasing scheme. Extensive experiments on multiple state-of-the-art video generation models demonstrate that S$^{2}$ Q-VDiT$^+$ consistently outperforms strong PTQ baselines under W4A6 and W4A4, delivers up to $2.08\times$ end-to-end speedup, and reduces model storage and inference memory by up to $3.8\times$ and $2.1\times$, respectively.
Weilun Feng, Chuanguang Yang, Haotong Qin et al.· IEEE Transactions on Pattern...· 2 citations
P predictive Prompting (PrePrompt) is proposed, a novel CIL framework that circumvents correlation-based limitations by leveraging the inherent classification ability of pre-trained models to predict task-specific prompts and decomposes CIL into a two-stage prediction process: task-specific prompt prediction followed by a label prediction.
Libo Huang, Xiang-Qi Li, Jia-Rui Zhao et al.· Proceedings of the 32nd ACM...· 4 citations
Prompt-based learning has emerged as a promising paradigm for Class Incremental Learning (CIL), enabling pre-trained models to adapt efficiently to open-world scenarios. Existing methods often employ correlation-based strategies, where an image's feature serves as a query to retrieve the most relevant key prompts, with corresponding value prompts for training. However, these approaches face a fundamental challenge: fitting the entire feature space of all tasks with only a few trainable prompts severely limits the pre-trained model's retrieval capability. In this paper, we propose Predictive Prompting (PrePrompt), a novel CIL framework that circumvents correlation-based limitations by leveraging the inherent classification ability of pre-trained models to predict task-specific prompts. Specifically, PrePrompt decomposes CIL into a two-stage prediction process: task-specific prompt prediction followed by a label prediction. While theoretically sound, this framework risks bias toward recent classes due to missing historical information for calibrating older classifiers. To mitigate this, PrePrompt incorporates a feature extrapolation technique, dynamically balancing stability and plasticity across classifiers. Extensive experiments on several benchmarks demonstrate PrePrompt's superiority over state-of-the-art prompt-based CIL methods. Code is available at https://github.com/libo-huang/preprompt.
Libo Huang, Xiangqi Li, Jiarui Zhao et al.· Proceedings of the 32nd ACM...· 0 citations
RSIAT significantly outperforms state-of-the-art methods in both performance and parameter efficiency, achieving superior stability–plasticity trade-offs with minimal trainable parameters.
Jiarui Zhao, Libo Huang, Xiangqi Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
