Related papers: Pluggable Pruning with Contiguous Layer Distillati…

This paper introduces a novel model compression approach through dynamic layer-specific pruning in Large Language Models (LLMs), enhancing the traditional methodology established by SliceGPT. By transitioning from constant to dynamic…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

The goal of this paper is to introduce SPADE, a framework for Structured Pruning and Adaptive Distillation for Efficient Large Language Model-based text-to-speech (LLM-TTS). Recent LLM-TTS systems achieve strong controllability and…

As we push the boundaries of performance in various vision tasks, the models grow in size correspondingly. To keep up with this growth, we need very aggressive pruning techniques for efficient inference and deployment on edge devices.…

Medical image segmentation is crucial for many healthcare tasks, including disease diagnosis and treatment planning. One key area is the segmentation of skin lesions, which is vital for diagnosing skin cancer and monitoring patients. In…

Deep learning has driven significant advances in medical image analysis, yet its adoption in clinical practice remains constrained by the large size and lack of transparency in modern models. Advances in interpretability techniques such as…

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually…

Filter level pruning is an effective method to accelerate the inference speed of deep CNN models. Although numerous pruning algorithms have been proposed, there are still two open issues. The first problem is how to prune residual…

Currently, Flow matching methods aim to compress the iterative generation process of diffusion models into a few or even a single step, with MeanFlow and FreeFlow being representative achievements of one-step generation based on Ordinary…

Dataset distillation or condensation aims to generate a smaller but representative subset from a large dataset, which allows a model to be trained more efficiently, meanwhile evaluating on the original testing data distribution to achieve…

Offline reinforcement learning (RL) methods harness previous experiences to derive an optimal policy, forming the foundation for pre-trained large-scale models (PLMs). When encountering tasks not seen before, PLMs often utilize several…

Multimodal dataset distillation aims to construct compact synthetic datasets that enable efficient compression and knowledge transfer from large-scale image-text data. However, existing approaches often fail to capture the complex,…

Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a…

Recently, 3D vision-based diffusion policies have shown strong capability in learning complex robotic manipulation skills. However, a common architectural mismatch exists in these models: a tiny yet efficient point-cloud encoder is often…

Recently, large pre-trained models have significantly improved the performance of various Natural LanguageProcessing (NLP) tasks but they are expensive to serve due to long serving latency and large memory usage. To compress these models,…

Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular,…

Prompt learning as a parameter-efficient method that has been widely adopted to adapt Vision-Language Models (VLMs) to downstream tasks. While hard-prompt design requires domain expertise and iterative optimization, soft-prompt methods rely…

Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…

Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…

Diffusion models (DMs) have demonstrated exceptional generative capabilities across various domains, including image, video, and so on. A key factor contributing to their effectiveness is the high quantity and quality of data used during…