相关论文: AutoNeural: Co-Designing Vision-Language Models fo…

We present a single neural network architecture composed of task-agnostic components (ViTs, convolutions, and LSTMs) that achieves state-of-art results on both the ImageNav ("go to location in <this picture>") and ObjectNav ("find a chair")…

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…

While neural network hardware accelerators provide a substantial amount of raw compute throughput, the models deployed on them must be co-designed for the underlying hardware architecture to obtain the optimal system performance. We present…

The rapid growth of LLMs demands high-throughput, memory-capacity-intensive inference on resource-constrained edge devices, where single-batch decoding remains fundamentally memory-bound. Existing out-of-core GPU-based and SSD-like…

We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted to run on mobile devices. It is an amalgamation of a myriad of architectural designs and techniques that are mobile-oriented, which comprises a set of…

Neural networks have become dominant computational workloads across cloud and edge platforms, but their rapid growth in model size and deployment diversity has exposed hardware bottlenecks increasingly dominated by memory movement,…

Vision-language models (VLMs) have demonstrated impressive multimodal comprehension capabilities and are being deployed in an increasing number of online video understanding applications. While recent efforts extensively explore advancing…

Vision-Language Models (VLM) exhibit strong reasoning capabilities, showing promise for end-to-end autonomous driving systems. Chain-of-Thought (CoT), as VLM's widely used reasoning strategy, is facing critical challenges. Existing textual…

Large Vision-Language Models (VLMs) deliver exceptional performance but require significant computational resources, limiting their deployment on mobile and edge devices. Smaller VLMs typically mirror design choices of larger models, such…

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime…

State-of-art NPUs are typically architected as a self-contained sub-system with multiple heterogeneous hardware computing modules, and a dataflow-driven programming model. There lacks well-established methodology and tools in the industry…

Edge computing processes data where it is generated, enabling faster decisions, lower bandwidth usage, and improved privacy. However, edge devices typically operate under strict constraints on processing power, memory, and energy…

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this…

While deep learning models have shown strong performance in simulating neural responses, they often fail to clearly separate stable visual encoding from condition-specific adaptation, which limits their ability to generalize across stimuli…

Integrating large language models (LLMs) into autonomous driving motion planning has recently emerged as a promising direction, offering enhanced interpretability, better controllability, and improved generalization in rare and long-tail…

Vision-Language Models (VLMs) are increasingly tasked with ultra-long multimodal understanding. While linear architectures offer constant computation and memory footprints, they often struggle with high-frequency visual perception compared…

While deep neural network (DNN)-based video denoising has demonstrated significant performance, deploying state-of-the-art models on edge devices remains challenging due to stringent real-time and energy efficiency requirements.…

Multimodal large language model (MLLM) inference splits into two phases with opposing hardware demands: vision encoding is compute-bound, while language generation is memory-bandwidth-bound. We show that under standard transformer KV…

Transformers and vision-language models (VLMs) have emerged as dominant architectures in computer vision and multimodal AI, offering state-of-the-art performance in tasks such as image classification, object detection, visual question…

Multimodal large language models (MLLMs) have shown promising potential in Vision-Language Navigation (VLN). However, their practical development is severely hindered by the substantial training overhead. We recognize two key issues that…