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

Network pruning is an effective technique for enabling lightweight Large Vision-Language Models (LVLMs), which primarily incorporates both weights and activations into the importance metric. However, existing efforts typically process…

Recent multimodal large language models are computationally expensive because Transformers must process a large number of visual tokens. We present ReDiPrune, a training-free token pruning method applied before the vision-language…

Recently Text-to-Video (T2V) synthesis has undergone a breakthrough by training transformers or diffusion models on large-scale datasets. Nevertheless, inferring such large models incurs huge costs.Previous inference acceleration works…

The rapid increase in the size of large language models (LLMs) has significantly escalated their computational and memory demands, posing challenges for efficient deployment, especially on resource-constrained devices. Structured pruning…

Vision-Language Models (VLMs) have become central to autonomous driving systems, yet their deployment is severely bottlenecked by the massive computational overhead of multi-view camera and multi-frame video input. Existing token pruning…

Pruning is an effective method for compressing Large Language Models, but finding an optimal, non-uniform layer-wise sparsity allocation remains a key challenge. While heuristic methods are fast but yield suboptimal performance, more…

The advent of real-time large multimodal models (LMMs) like GPT-4o has sparked considerable interest in efficient LMMs. LMM frameworks typically encode visual inputs into vision tokens (continuous representations) and integrate them and…

As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visual tokens accumulated across frames. Training-free token compression has emerged as a…

Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising solution for accelerating inference, this paper, however,…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…

Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame spatial redundancy or prunes inside the LLM with…

Large Vision-Language Models (VLMs) have been extended to understand both images and videos. Visual token compression is leveraged to reduce the considerable token length of visual inputs. To meet the needs of different tasks, existing…

Robotic manipulation with Vision-Language-Action models requires efficient inference over long-horizon multi-modal context, where attention to dense visual tokens dominates computational cost. Existing methods optimize inference speed by…

Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computational overheads pose great challenges for practical deployment. Some recent works have proposed…

Large Multimodal Models (LMMs) have demonstrated impressive performance in short video understanding tasks but face great challenges when applied to long video understanding. In contrast, Large Language Models (LLMs) exhibit outstanding…

Low-Light Video Enhancement (LLVE) has received considerable attention in recent years. One of the critical requirements of LLVE is inter-frame brightness consistency, which is essential for maintaining the temporal coherence of the…

Video diffusion models have achieved impressive realism and controllability but are limited by high computational demands, restricting their use on mobile devices. This paper introduces the first mobile-optimized video diffusion model.…

Multimodal Large Language Models (MLLMs) suffer from substantial computational overhead due to the high redundancy in visual token sequences. Existing approaches typically address this issue using single-layer Vision Transformer (ViT)…

Vision-language models (VLMs) have achieved remarkable multimodal understanding and reasoning capabilities, yet remain computationally expensive due to dense visual tokenization. Existing efficiency approaches either merge redundant visual…