Related papers: EventPrune: Cascaded Event-Assisted Token Pruning …

Deployment of Transformer models on edge devices is becoming increasingly challenging due to the exponentially growing inference cost that scales quadratically with the number of tokens in the input sequence. Token pruning is an emerging…

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high…

Diffusion models have revolutionized generative tasks, especially in the domain of text-to-image synthesis; however, their iterative denoising process demands substantial computational resources. In this paper, we present a novel…

Transformer encoders are widely deployed in large-scale web services for natural language understanding tasks such as text classification, semantic retrieval, and content ranking. However, their high inference latency and memory consumption…

Vision-Language Navigation (VLN) enables robots to follow natural-language instructions in visually grounded environments, serving as a key capability for embodied robotic systems. Recent Vision-Language-Action (VLA) models have…

In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual…

Vision tokens in multimodal large language models often dominate huge computational overhead due to their excessive length compared to linguistic modality. Abundant recent methods aim to solve this problem with token pruning, which first…

Recently, visual token pruning has been studied to handle the vast number of visual tokens in Multimodal Large Language Models. However, we observe that while existing pruning methods perform reliably on simple visual understanding, they…

Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is…

Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…

Deeper and wider Convolutional Neural Networks (CNNs) achieve superior performance but bring expensive computation cost. Accelerating such over-parameterized neural network has received increased attention. A typical pruning algorithm is a…

Autonomous driving systems rely on robust 3D scene understanding. Recent advances in Semantic Scene Completion (SSC) for autonomous driving underscore the limitations of RGB-based approaches, which struggle under motion blur, poor lighting,…

Event-based multimodal large language models (MLLMs) enable robust perception in high-speed and low-light scenarios, addressing key limitations of frame-based MLLMs. However, current event-based MLLMs often rely on dense image-like…

As the convolutional neural network (CNN) gets deeper and wider in recent years, the requirements for the amount of data and hardware resources have gradually increased. Meanwhile, CNN also reveals salient redundancy in several tasks. The…

Point-Based Neural Rendering (PBNR) is emerging as a promising class of rendering techniques, which are permeating all aspects of society, driven by a growing demand for real-time, photorealistic rendering in AR/VR and digital twins.…

Camouflaged Object Detection (COD) aims to segment targets that share extreme textural and structural similarities with their complex environments. Leveraging their capacity for long-range dependency modeling, Transformer-based detectors…

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…

Pruning is a widely used technique for reducing the size of deep neural networks while maintaining their performance. However, such a technique, despite being able to massively compress deep models, is hardly able to remove entire layers…

Human pose estimation focuses on predicting body keypoints to analyze human motion. Currently, most pose estimation tasks rely on conventional RGB cameras. In contrast, event cameras provide high temporal resolution and low latency,…