相关论文: POP: Online Structural Pruning Enables Efficient I…

Large language models (LLMs) excel at language understanding and generation, but their enormous computational and memory requirements hinder deployment. Compression offers a potential solution to mitigate these constraints. However, most…

Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \textit{e}.\textit{g}., Transformers, have attracted the…

Generative modeling has recently undergone remarkable advancements, primarily propelled by the transformative implications of Diffusion Probabilistic Models (DPMs). The impressive capability of these models, however, often entails…

Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offline calibration data that may not generalize across inputs.…

Large scale deep learning provides a tremendous opportunity to improve the quality of content recommendation systems by employing both wider and deeper models, but this comes at great infrastructural cost and carbon footprint in modern data…

Current VLM-based VQA methods often process entire images, leading to excessive visual tokens that include redundant information irrelevant to the posed question. This abundance of unnecessary image details creates numerous visual tokens,…

Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computational costs, the deployment and application of LLMs are often…

Large Language Models (LLMs) demonstrate impressive performance across natural language tasks but incur substantial computational and storage costs due to their scale. Post-training structured pruning offers an efficient solution. However,…

Instruction tuning has optimized the specialized capabilities of large language models (LLMs), but it often requires extensive datasets and prolonged training times. The challenge lies in developing specific capabilities by identifying…

Large Vision Language Models (LVLMs) have been widely adopted to guide vision foundation models in performing reasoning segmentation tasks, achieving impressive performance. However, the substantial computational overhead associated with…

Large Language Models (LLMs) have demonstrated exceptional performance in natural language processing tasks, yet their massive size makes serving them inefficient and costly. Semi-structured pruning has emerged as an effective method for…

Visual AutoRegressive (VAR) models based on next-scale prediction enable efficient hierarchical generation, yet the inference cost grows quadratically at high resolutions. We observe that the computationally intensive later scales…

Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two…

Online conformal prediction has demonstrated its capability to construct a prediction set for each incoming data point that covers the true label with a predetermined probability. To cope with potential distribution shift, multi-model…

Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely on retraining or multi-stage optimization, which limits post-training deployment. We propose CORP,…

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Structured pruning is a commonly used convolutional neural network (CNN) compression approach. Pruning rate setting is a fundamental problem in structured pruning. Most existing works introduce too many additional learnable parameters to…

Large Language Models (LLMs) have demonstrated remarkable abilities in tackling a wide range of complex tasks. However, their huge computational and memory costs raise significant challenges in deploying these models on resource-constrained…

Structured pruning is a promising approach to create smaller, faster large language models. However, existing methods typically rely on computing the gradient via backward passes, which can inflate memory requirements and compute costs. In…

Existing pruning techniques for large language models (LLMs) targeting domain-specific applications typically follow a two-stage process: pruning the pretrained general-purpose LLMs and then fine-tuning the pruned LLMs on specific domains.…