Related papers: FastVID: Dynamic Density Pruning for Fast Video La…

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…

Recently, Vision Transformer (ViT) has continuously established new milestones in the computer vision field, while the high computation and memory cost makes its propagation in industrial production difficult. Pruning, a traditional model…

Multimodal Large Language Models (MLLMs) have shown remarkable versatility in understanding diverse multimodal data and tasks. However, these capabilities come with an increased model scale. While post-training pruning reduces model size in…

Recent research has revealed that reducing the temporal and spatial redundancy are both effective approaches towards efficient video recognition, e.g., allocating the majority of computation to a task-relevant subset of frames or the most…

The high computational cost and slow inference time are major obstacles to deploying Video Diffusion Models (VDMs). To overcome this, we introduce a new Video Diffusion Model Compression approach using individual content and motion dynamics…

Segment Anything Model 2 (SAM2), a vision foundation model has significantly advanced in prompt-driven video object segmentation, yet their practical deployment remains limited by the high computational and memory cost of processing dense…

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…

Diffusion Transformers (DiTs) deliver remarkable image and video generation quality but incur high computational cost, limiting scalability and on-device deployment. We introduce CoReDiT, a structured token pruning framework for DiTs across…

Video Language Models (VideoLMs) enable AI systems to understand temporal dynamics in videos. To fit within the maximum context window constraint, current methods use keyframe sampling which often misses both macro-level events and…

Omnimodal Large Language Models (Omni-LLMs) incur substantial computational overhead due to the large number of multimodal input tokens they process, making token reduction essential for real-world deployment. Existing Omni-LLM pruning…

Recently, multimodal large language models (MM-LLMs) have achieved significant success in various tasks, but their high computational costs limit widespread application. The main computational burden arises from processing concatenated text…

Visual encoding constitutes a major computational bottleneck in Multimodal Large Language Models (MLLMs), especially for high-resolution image inputs. The prevailing practice typically adopts global encoding followed by post-ViT…

The impressive achievements of generative models in creating high-quality videos have raised concerns about digital integrity and privacy vulnerabilities. Recent works of AI-generated content detection have been widely studied in the image…

Visual language models encounter challenges in computational efficiency and latency, primarily due to the substantial redundancy in the token representations of high-resolution images and videos. Current attention/similarity-based…

Processing long-form videos with Video Large Language Models (Video-LLMs) is computationally prohibitive. Current efficiency methods often compromise fine-grained perception through irreversible information disposal or inhibit long-range…

Vision-Language-Action (VLA) models have shown remarkable promise in robotics manipulation, yet their high computational cost hinders real-time deployment. Existing token pruning methods suffer from a fundamental trade-off: aggressive…

Recent advances in vision-language models have demonstrated remarkable performance across diverse multi-modal tasks, including document question answering that leverages structured visual cues from text, tables, and figures. However, unlike…

Large Multimodal Models (LMMs) excel in visual-language tasks by leveraging numerous visual tokens for fine-grained visual information, but this token redundancy results in significant computational costs. Previous research aimed at…

Learning a versatile language-image model is computationally prohibitive under a limited computing budget. This paper delves into the \emph{efficient language-image pre-training}, an area that has received relatively little attention…

Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV) cache expands linearly over time, leading to substantial…