Related papers: LA-IMR: Latency-Aware, Predictive In-Memory Routin…

Machine learning (ML) inference serving systems host deep neural network (DNN) models and schedule incoming inference requests across deployed GPUs. However, limited support for task prioritization and insufficient latency estimation under…

Implicit Neural Representations (INRs) are proving to be a powerful paradigm in unifying task modeling across diverse data domains, offering key advantages such as memory efficiency and resolution independence. Conventional deep learning…

Deep learning has been used to demonstrate end-to-end neural network learning for autonomous vehicle control from raw sensory input. While LiDAR sensors provide reliably accurate information, existing end-to-end driving solutions are mainly…

RRAM-based in-memory computing (IMC) offers high energy efficiency but suffers from conductance drift that severely degrades long-term accuracy. Existing approaches including retraining, noise-aware training, and Batch Normalization…

Ensuring both safety and efficiency in decision-making for autonomous driving systems remains a fundamental challenge. Traditional Deep Reinforcement Learning (DRL) suffers from unsafe random exploration and slow convergence, while Large…

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but…

An implicit neural representation (INR) is a neural network that approximates a spatiotemporal function. Many memory-intensive visualization tasks, including modern 4D CT scanning methods, represent data natively as INRs. While INRs are…

With rapid advances in containerization techniques, the serverless computing model is becoming a valid candidate execution model in edge networking, similar to the widely used cloud model for applications that are stateless, single purpose…

With the wide adoption of language models for IR -- and specifically RAG systems -- the latency of the underlying LLM becomes a crucial bottleneck, since the long contexts of retrieved passages lead large prompts and therefore, compute…

In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…

Edge computing processes data near its source, reducing latency and enhancing security compared to traditional cloud computing while providing its benefits. This paper explores edge computing for migrating an existing safety-critical…

Efficiently harnessing GPU compute is critical to improving user experience and reducing operational costs in large language model (LLM) services. However, current inference engine schedulers overlook the attention backend's sensitivity to…

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due…

Recently, Unmanned Aerial Vehicles (UAVs) have shown impressive performance in many critical applications, such as surveillance, search and rescue operations, environmental monitoring, etc. In many of these applications, the UAVs capture…

As autonomous systems increasingly rely on onboard sensing for localization and perception, the parallel tasks of motion planning and state estimation become more strongly coupled. This coupling is well-captured by augmenting the planning…

Predictive linear and nonlinear models based on kernel machines or deep neural networks have been used to discover dependencies among time series. This paper proposes an efficient nonlinear modeling approach for multiple time series, with a…

Large reasoning models (LRMs) achieve strong accuracy through test-time scaling, generating longer chains of thought or sampling multiple solutions, but at steep costs in tokens and latency. We argue that memory is a core ingredient for…

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender…

The ability of humans to rapidly learn new knowledge while retaining old memories poses a significant challenge for current deep learning models. To handle this challenge, we draw inspiration from human memory and learning mechanisms and…

The rapid advancement of Large Language Models (LLMs) has revolutionized various aspects of human life, yet their immense computational and energy demands pose significant challenges for efficient inference. The memory wall, the growing…