Related papers: Efficient-LVSM: Faster, Cheaper, and Better Large …

The efficiency of long-video inference remains a critical bottleneck, mainly due to the dense computation in the prefill stage of Large Multimodal Models (LMMs). Existing methods either compress visual embeddings or apply sparse attention…

Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual…

Vision-Language Large Models (VLLMs) face significant efficiency challenges when processing high-resolution inputs. The quadratic complexity in attention and autoregressive generation, as well as the constantly growing key value (KV) cache…

Existing state-of-the-art novel view synthesis methods rely on either fairly accurate 3D geometry estimation or sampling of the entire space for neural volumetric rendering, which limit the overall efficiency. In order to improve the…

High-resolution dense prediction enables many appealing real-world applications, such as computational photography, autonomous driving, etc. However, the vast computational cost makes deploying state-of-the-art high-resolution dense…

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…

In this study, we propose two novel input processing paradigms for novel view synthesis (NVS) methods based on layered scene representations that significantly improve their runtime without compromising quality. Our approach identifies and…

How do you build a sign language recognizer that works on a phone? That question drove this work. We built EfficientSign, a lightweight model which takes EfficientNet-B0 and focuses on two attention modules (Squeeze-and-Excitation for…

Visual token reduction lowers inference costs caused by extensive image features in large vision-language models (LVLMs). Unlike relevant studies that prune tokens in self-attention-only LVLMs, our work uniquely addresses…

Novel view synthesis (NVS) in low-light scenes remains a significant challenge due to degraded inputs characterized by severe noise, low dynamic range (LDR) and unreliable initialization. While recent NeRF-based approaches have shown…

We present an efficient multi-view stereo (MVS) network for 3D reconstruction from multiview images. While previous learning based reconstruction approaches performed quite well, most of them estimate depth maps at a fixed resolution using…

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…

Vision-Language Models (vLLMs) have emerged as powerful architectures for joint reasoning over visual and textual inputs, enabling breakthroughs in image captioning, cross modal retrieval, and multimodal dialogue. However, as these models…

Large language model (LLM) inference demands significant amount of computation and memory, especially in the key attention mechanism. While techniques, such as quantization and acceleration algorithms, like FlashAttention, have improved…

Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible results. In this paper, we propose CheapNVS: a fully end-to-end…

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…

Visual speech recognition models traditionally consist of two stages, feature extraction and classification. Several deep learning approaches have been recently presented aiming to replace the feature extraction stage by automatically…

Novel View Synthesis (NVS) is the task of generating new images of a scene from viewpoints that were not part of the original input. Diffusion-based NVS can generate high-quality, temporally consistent images, however, remains…

Multimodal Large Language Models (MLLMs) are commonly derived by extending pre-trained Large Language Models (LLMs) with visual capabilities. In this work, we investigate how MLLMs process visual inputs by analyzing their attention…

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM…