Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank

• URL: http://arxiv.org/abs/2512.08648v2
• Date: Sat, 13 Dec 2025 12:55:04 GMT
• Title: Repulsor: Accelerating Generative Modeling with a Contrastive Memory Bank
• Authors: Shaofeng Zhang, Xuanqi Chen, Ning Liao, Haoxiang Zhao, Xiaoxing Wang, Haoru Tan, Sitong Wu, Xiaosong Jia, Qi Fan, Junchi Yan,
• Abstract summary: mname is a plug-and-play training framework that requires no external encoders.<n>mname achieves a state-of-the-art FID of textbf2.40 within 400k steps, significantly outperforming comparable methods.
• Score: 65.00301565190824
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The dominance of denoising generative models (e.g., diffusion, flow-matching) in visual synthesis is tempered by their substantial training costs and inefficiencies in representation learning. While injecting discriminative representations via auxiliary alignment has proven effective, this approach still faces key limitations: the reliance on external, pre-trained encoders introduces overhead and domain shift. A dispersed-based strategy that encourages strong separation among in-batch latent representations alleviates this specific dependency. To assess the effect of the number of negative samples in generative modeling, we propose {\mname}, a plug-and-play training framework that requires no external encoders. Our method integrates a memory bank mechanism that maintains a large, dynamically updated queue of negative samples across training iterations. This decouples the number of negatives from the mini-batch size, providing abundant and high-quality negatives for a contrastive objective without a multiplicative increase in computational cost. A low-dimensional projection head is used to further minimize memory and bandwidth overhead. {\mname} offers three principal advantages: (1) it is self-contained, eliminating dependency on pretrained vision foundation models and their associated forward-pass overhead; (2) it introduces no additional parameters or computational cost during inference; and (3) it enables substantially faster convergence, achieving superior generative quality more efficiently. On ImageNet-256, {\mname} achieves a state-of-the-art FID of \textbf{2.40} within 400k steps, significantly outperforming comparable methods.

Related papers

• Image Tokenizer Needs Post-Training [76.91832192778732]
  We propose a novel tokenizer training scheme, focusing on improving latent space construction and decoding respectively.<n>Specifically, we propose a plug-and-play tokenizer training scheme, which significantly enhances the robustness of tokenizer.<n>We further optimize the tokenizer decoder regarding a well-trained generative model to mitigate the distribution difference between generated and reconstructed tokens.
  arXiv  Detail & Related papers  (2025-09-15T21:38:03Z)
• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• CRISP: Clustering Multi-Vector Representations for Denoising and Pruning [7.580000668015255]
  Multi-vector models such as ColBERT deliver state-of-the-art performance by representing queries and documents by contextualized token-level embeddings.<n>A common approach to mitigate this overhead is to cluster the model's frozen vectors, but this strategy's effectiveness is limited by the intrinsic clusterability of these embeddings.<n>We introduce CRISP, a novel multi-vector training method which learns inherently clusterable representations directly within the end-to-end training process.
  arXiv  Detail & Related papers  (2025-05-16T17:26:16Z)
• Towards Scalable Modeling of Compressed Videos for Efficient Action Recognition [6.168286187549952]
  We propose a hybrid end-to-end framework that factorizes learning across three key concepts to reduce inference cost by $330times$ versus prior art.<n> Experiments show that our method results in a lightweight architecture achieving state-of-the-art video recognition performance.
  arXiv  Detail & Related papers  (2025-03-17T21:13:48Z)
• One-Step Diffusion Model for Image Motion-Deblurring [85.76149042561507]
  We propose a one-step diffusion model for deblurring (OSDD), a novel framework that reduces the denoising process to a single step.<n>To tackle fidelity loss in diffusion models, we introduce an enhanced variational autoencoder (eVAE), which improves structural restoration.<n>Our method achieves strong performance on both full and no-reference metrics.
  arXiv  Detail & Related papers  (2025-03-09T09:39:57Z)
• PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection [68.8373788348678]
  Visual instruction tuning adapts pre-trained Multimodal Large Language Models to follow human instructions.<n>PRISM is the first training-free framework for efficient visual instruction selection.<n>It reduces the end-to-end time for data selection and model tuning to just 30% of conventional pipelines.
  arXiv  Detail & Related papers  (2025-02-17T18:43:41Z)
• Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think [72.48325960659822]
  One main bottleneck in training large-scale diffusion models for generation lies in effectively learning these representations.<n>We study this by introducing a straightforward regularization called REPresentation Alignment (REPA), which aligns the projections of noisy input hidden states in denoising networks with clean image representations obtained from external, pretrained visual encoders.<n>The results are striking: our simple strategy yields significant improvements in both training efficiency and generation quality when applied to popular diffusion and flow-based transformers, such as DiTs and SiTs.
  arXiv  Detail & Related papers  (2024-10-09T14:34:53Z)
• PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models [32.33892531885448]
  Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks.<n>But their efficiency is hindered by significant computational and memory demands from processing long contexts in multimodal inputs.<n>We introduce PAR (Prompt-Aware Token Reduction), a novel and plug-and-play approach that reduces visual tokens efficiently without compromising model performance.
  arXiv  Detail & Related papers  (2024-10-09T07:13:22Z)
• Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [41.299675080384]
  Mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression.
  arXiv  Detail & Related papers  (2024-01-03T05:26:57Z)
• Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations [8.163697683448811]
  We introduce EfficientMORL, an efficient framework for the unsupervised learning of object-centric representations. We show that optimization challenges caused by requiring both symmetry and disentanglement can be addressed by high-cost iterative amortized inference. We demonstrate strong object decomposition and disentanglement on the standard multi-object benchmark while achieving nearly an order of magnitude faster training and test time inference.
  arXiv  Detail & Related papers  (2021-06-07T14:02:49Z)

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.