Related papers: Modeling the Invariance of Virtual Pointers in LLV…

Index structures often materialize one or multiple levels of explicit indirections (aka pointers) to allow for a quick traversal to the data of interest. Unfortunately, dereferencing a pointer to go from one level to the other is costly…

The C/C++ memory model provides an interface and execution model for programmers of concurrent (shared-variable) code. It provides a range of mechanisms that abstract from underlying hardware memory models -- that govern how multicore…

While large language models (LLMs) have shown promise in the table question answering (TQA) task through prompt engineering, they face challenges in industrial applications, including structural heterogeneity, difficulties in target data…

Stateful tool-using LLM agents treat the context window as working memory, yet today's agent harnesses manage residency and durability as best-effort, causing recurring failures: lost state after compaction, bypassed flushes on reset, and…

Continual Learning (CL) enables machine learning models to learn from continuously shifting new training data in absence of data from old tasks. Recently, pretrained vision transformers combined with prompt tuning have shown promise for…

The growing success of Vision-Language-Action (VLA) models stems from the promise that pretrained Vision-Language Models (VLMs) can endow agents with transferable world knowledge and vision-language (VL) grounding, laying a foundation for…

Applications of reinforcement learning (RL) to stabilization problems of real systems are restricted since an agent needs many experiences to learn an optimal policy and may determine dangerous actions during its exploration. If we know a…

Machine learning (ML) models are constructed by expert ML practitioners using various coding languages, in which they tune and select models hyperparameters and learning algorithms for a given problem domain. They also carefully design an…

In-context learning (ICL) enables large language models to perform few-shot learning by conditioning on labeled examples in the prompt. Despite its flexibility, ICL suffers from instability -- especially as prompt length increases with more…

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…

Modern out-of-order processors have increased capacity to exploit instruction level parallelism (ILP) and memory level parallelism (MLP), e.g., by using wide superscalar pipelines and vector execution units, as well as deep buffers for…

The rise of (multimodal) large language models (LLMs) has shed light on software agent -- where software can understand and follow user instructions in natural language. However, existing approaches such as API-based and GUI-based agents…

The lambda calculus is a widely accepted computational model of higher-order functional pro- grams, yet there is not any direct and universally accepted cost model for it. As a consequence, the computational difficulty of reducing lambda…

Disaggregated memory is promising for improving memory utilization in computer clusters in which memory demands significantly vary across computer nodes under utilization. It allows applications with high memory demands to use memory in…

Virtualization technology facilitates a dynamic, demand-driven allocation and migration of servers. This paper studies how the flexibility offered by network virtualization can be used to improve Quality-of-Service parameters such as…

Objective-C is still the language of choice if users want to run their simulation efficiently under the Swarm environment since the Swarm environment itself was written in Objective-C. The language is a fast, object-oriented and easy to…

Motivated by the increasing shift to multicore computers, recent work has developed language support for responsive parallel applications that mix compute-intensive tasks with latency-sensitive, usually interactive, tasks. These…

We present a framework for efficiently performing Monte Carlo wave-function simulations in cavity QED with moving particles. It relies heavily on the object-oriented programming paradigm as realised in C++, and is extensible and applicable…

As Large Language Models (LLMs) move from curated training sets into open-ended real-world environments, a fundamental limitation emerges: static training cannot keep pace with continual deployment environment change. Scaling training-time…

The visual projector serves as an essential bridge between the visual encoder and the Large Language Model (LLM) in a Multimodal LLM (MLLM). Typically, MLLMs adopt a simple MLP to preserve all visual contexts via one-to-one transformation.…