Related papers: Learning Semantics, Not Addresses: Runtime Neural …

Scaling up data, parameters, and test-time computation has been the mainstream methods to improve LLM systems (LLMsys), but their upper bounds are almost reached due to the gradual depletion of high-quality data and marginal gains obtained…

Long Short-Term Memory (LSTM) is a popular approach to boosting the ability of Recurrent Neural Networks to store longer term temporal information. The capacity of an LSTM network can be increased by widening and adding layers. However,…

Transformer-based language models (LMs) track contextual information through large, hard-coded input windows. We introduce MemoryPrompt, a leaner approach in which the LM is complemented by a small auxiliary recurrent network that passes…

Sparsity has long been a central theme in LLM efficiency, but its role in context processing remains unresolved. As LLM workloads shift toward longer contexts and agentic interactions, the compute and memory bottlenecks of attention become…

Machine comprehension plays an essential role in NLP and has been widely explored with dataset like MCTest. However, this dataset is too simple and too small for learning true reasoning abilities. \cite{hermann2015teaching} therefore…

Forensic Memory Analysis (FMA) and Virtual Machine Introspection (VMI) are critical tools for security in a virtualization-based approach. VMI and FMA involves using digital forensic methods to extract information from the system to…

While linear attention architectures offer efficient inference, compressing unbounded history into a fixed-size memory inherently limits expressivity and causes information loss. To address this limitation, we introduce Random Access Memory…

Accelerating large language model (LLM) inference is critical for real-world deployments requiring high throughput and low latency. Contextual sparsity, where each token dynamically activates only a small subset of the model parameters,…

The attention mechanism can refine the extracted feature maps and boost the classification performance of the deep network, which has become an essential technique in computer vision and natural language processing. However, the memory and…

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…

Poor time predictability of multicore processors has been a long-standing challenge in the real-time systems community. In this paper, we make a case that a fundamental problem that prevents efficient and predictable real-time computing on…

Long short-term memory recurrent neural networks (LSTM-RNNs) are considered state-of-the art in many speech processing tasks. The recurrence in the network, in principle, allows any input to be remembered for an indefinite time, a feature…

Modern storage systems intensively utilize data prefetching algorithms while processing sequences of the read requests. Performance of the prefetching algorithm (for instance increase of the cache hit ratio of the cache system - CHR)…

Far-field speech recognition in noisy and reverberant conditions remains a challenging problem despite recent deep learning breakthroughs. This problem is commonly addressed by acquiring a speech signal from multiple microphones and…

Semantic segmentation of remote sensing images plays an important role in a wide range of applications including land resource management, biosphere monitoring and urban planning. Although the accuracy of semantic segmentation in remote…

Semantic top-K selection with cross-encoder rerankers underpins on-device AI services, such as retrieval-augmented generation, agent memory, and personalized recommendation. However, its latency and memory demands dominate end-to-end…

Cloud deployments disaggregate storage from compute, providing more flexibility to both the storage and compute layers. In this paper, we explore disaggregation by taking it one step further and applying it to memory (DRAM). Disaggregated…

On-device inference for Large Language Models (LLMs), driven by increasing privacy concerns and advancements of mobile-sized models, has gained significant interest. However, even mobile-sized LLMs (e.g., Gemma-2B) encounter unacceptably…

Large Language Models (LLMs) face challenges for on-device inference due to high memory demands. Traditional methods to reduce memory usage often compromise performance and lack adaptability. We propose FlexInfer, an optimized offloading…

The use of semantic features can improve the efficiency of target search in unknown environments for robotic search and rescue missions. Current target search methods rely on training with large datasets of similar domains, which limits the…