Related papers: OccamToken: Efficient VLM Inference with Training-…

Large Vision-Language Models (VLMs) have achieved remarkable success in multi-modal reasoning, but their inference time efficiency remains a significant challenge due to the memory overhead during decoding, especially when the query and…

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…

The rapid progress of large language models (LLMs) has laid the foundation for multimodal models. However, visual language models (VLMs) still face heavy computational costs when extended from images to videos due to high frame rates and…

Token pruning has emerged as an effective approach to reduce the substantial computational overhead of Large Vision-Language Models (LVLMs) by discarding less informative visual tokens while preserving performance. However, existing methods…

Recent advances on Multi-modal Large Language Models have demonstrated that high-resolution image input is crucial for model capabilities, especially for fine-grained tasks. However, high-resolution images lead to a quadratic increase in…

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by…

Recent progress in vision-language models (VLMs) has led to impressive results in document understanding tasks, but their high computational demands remain a challenge. To mitigate the compute burdens, we propose a lightweight token pruning…

Multimodal large language models (MLLMs) demand considerable computations for inference due to the extensive parameters and the additional input tokens needed for visual information representation. Herein, we introduce Visual Tokens…

As the open community of large language models (LLMs) matures, multimodal LLMs (MLLMs) have promised an elegant bridge between vision and language. However, current research is inherently constrained by challenges such as the need for…

KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…

Vision Language Models (VLMs) struggle with long-form videos due to the quadratic complexity of attention mechanisms. We propose Language-Guided Temporal Token Pruning (LGTTP), which leverages temporal cues from queries to adaptively prune…

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

Video Large Language Models (VLLMs) incur substantial prefilling cost due to the large number of visual tokens. While attention-based token pruning offers a promising acceleration strategy, applying it at shallow decoder layers often causes…

Pre-trained vision-language models (VLMs) have achieved impressive results in a range of vision-language tasks. However, popular VLMs usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and…

While Reinforcement Learning with Verifiable Rewards (RLVR) has advanced the reasoning capabilities of Large Vision-Language Models (LVLMs), most existing methods in multimodal reasoning neglect the critical role of visual perception within…

In this study, we identify the inefficient attention phenomena in Large Vision-Language Models (LVLMs), notably within prominent models like LLaVA-1.5, QwenVL-Chat and Video-LLaVA. We find out that the attention computation over visual…

Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that…

Video Large Language Models (VLLMs) excel in video understanding, but their excessive visual tokens pose a significant computational challenge for real-world applications. Current methods aim to enhance inference efficiency by visual token…

With recent progress in joint modeling of visual and textual representations, Vision-Language Pretraining (VLP) has achieved impressive performance on many multimodal downstream tasks. However, the requirement for expensive annotations…

Transformer-based Large Language Models (LLMs) have become increasingly important. However, due to the quadratic time complexity of attention computation, scaling LLMs to longer contexts incurs extremely slow inference speed and high GPU…