Related papers: RAPID: Redundancy-Aware and Compatibility-Optimal …

The conventional deep learning paradigm often involves training a deep model on a server and then deploying the model or its distilled ones to resource-limited edge devices. Usually, the models shall remain fixed once deployed (at least for…

Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action generation. However, they often struggle in scenarios requiring precise spatial…

Edge computing facilitates deep learning in resource-constrained environments, but challenges such as resource heterogeneity and dynamic constraints persist. This paper introduces AMP4EC, an Adaptive Model Partitioning framework designed to…

Pruning is a typical acceleration technique for compute-bound models by removing computation on unimportant values. Recently, it has been applied to accelerate Vision-Language-Action (VLA) model inference. However, existing acceleration…

In today's era of Internet of Things (IoT), where massive amounts of data are produced by IoT and other devices, edge computing has emerged as a prominent paradigm for low-latency data processing. However, applications may have diverse…

Vision-Language-Action (VLA) models offer a compelling framework for tackling complex robotic manipulation tasks, but they are often expensive to train. In this paper, we propose a novel VLA approach that leverages the competitive…

Vision-Language-Action (VLA) models have emerged as a promising paradigm for end-to-end autonomous driving, yet their reliance on implicit parametric knowledge limits generalization in long-tail scenarios. While Retrieval-Augmented…

Current virtual reality (VR) headsets encounter a trade-off between high processing power and affordability. Consequently, offloading 3D rendering to remote servers helps reduce costs, battery usage, and headset weight. Maintaining network…

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

In robotics, Vision-Language-Action (VLA) models that integrate diverse multimodal signals from multi-view inputs have emerged as an effective approach. However, most prior work adopts static fusion that processes all visual inputs…

Recent advancements in Vision-Language (VL) models have sparked interest in their deployment on edge devices, yet challenges in handling diverse visual modalities, manual annotation, and computational constraints remain. We introduce…

Vision-Language-Action (VLA) models demonstrate remarkable potential for generalizable robotic manipulation. The performance of VLA models can be improved by integrating with action chunking, a critical technique for effective control.…

In this paper, we propose GTA-VLA(Guide, Think, Act), an interactive Vision-Language-Action (VLA) framework that enables spatially steerable embodied reasoning by allowing users to guide robot policies with explicit visual cues. Existing…

Intelligent applications based on machine learning are impacting many parts of our lives. They are required to operate under rigorous practical constraints in terms of service latency, network bandwidth overheads, and also privacy. Yet…

A growing number of critical workflow applications leverage a streamlined edge-hub-cloud architecture, which diverges from the conventional edge computing paradigm. An edge device, in collaboration with a hub device and a cloud server,…

Serverless computing has emerged as a compelling solution for cloud-based model inference. However, as modern large language models (LLMs) continue to grow in size, existing serverless platforms often face substantial model startup…

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Dynamic computation has emerged as a promising avenue to enhance the inference efficiency of deep networks. It allows selective activation of computational units, leading to a reduction in unnecessary computations for each input sample.…

The scaling of large language models to encode all the world's knowledge in model parameters is unsustainable and has exacerbated resource barriers. Retrieval-Augmented Generation (RAG) presents a potential solution, yet its application to…

In this paper, we introduce $\text{EVL}_{\text{Gen}}$, a streamlined framework designed for the pre-training of visually conditioned language generation models with high computational demands, utilizing frozen pre-trained large language…