Related papers: RepFlow: Minimizing Flow Completion Times with Rep…

Partially Supervised Multi-Task Learning (PS-MTL) aims to leverage knowledge across tasks when annotations are incomplete. Existing approaches, however, have largely focused on the simpler setting of homogeneous, dense prediction tasks,…

Due to rapid advancement in modern technology, as one of the major concerns is the stability of business. The organizations depend on their systems to provide robust and faster processing of information for their operations. Efficient data…

Long context fine-tuning of large language models(LLMs) involves training on datasets that are predominantly composed of short sequences and a small proportion of longer sequences. However, existing approaches overlook this long-tail…

Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-colocated RL frameworks suffer from significant scalability bottlenecks, while task-separated RL…

Centralized trajectory optimization in the joint space of multiple robots allows access to a larger feasible space that can result in smoother trajectories, especially while planning in tight spaces. Unfortunately, it is often…

Parallel dataflow systems have become a standard technology for large-scale data analytics. Complex data analysis programs in areas such as machine learning and graph analytics often involve control flow, i.e., iterations and branching.…

To increase performance and efficiency, systems use FPGAs as reconfigurable accelerators. A key challenge in designing these systems is partitioning computation between processors and an FPGA. An appropriate division of labor may be…

Modern information technology services largely depend on cloud infrastructures to provide their services. These cloud infrastructures are built on top of datacenter networks (DCNs) constructed with high-speed links, fast switching gear, and…

Token-based replay used to be the standard way to conduct conformance checking. With the uptake of more advanced techniques (e.g., alignment based), token-based replay got abandoned. However, despite decomposition approaches and heuristics…

Recent advances in high-speed mobile networks have revealed new bottlenecks in ubiquitous TCP protocol deployed in the Internet. In addition to differentiating non-congestive loss from congestive loss, our experiments revealed two…

FAST-TCP achieves better performance than traditional TCP-Reno schemes, but unfortunately it is inherently unfair to older connections due to wrong estimations of the round-trip propagation delay. This paper presents a model for this…

Booming time-critical services, such as automated manufacturing and remote operations, stipulate increasing demands for facilitating large-scale Industrial Internet of Things (IoT). Recently, a cycle specified queuing and forwarding (CSQF)…

Diffusion and flow-matching models achieve remarkable generative performance but at the cost of many sampling steps, this slows inference and limits applicability to time-critical tasks. The ReFlow procedure can accelerate sampling by…

In data-parallel computing frameworks, intermediate parallel data is often produced at various stages which needs to be transferred among servers in the datacenter network (e.g. the shuffle phase in MapReduce). A stage often cannot start or…

As safety-critical applications increasingly rely on data-parallel floating-point computations, there is an increasing need for flexible and configurable fault tolerance in parallel floating-point accelerators such as tensor engines. While…

As deep learning models scale, sparse computation and specialized dataflow hardware have emerged as powerful solutions to address efficiency. We propose FuseFlow, a compiler that converts sparse machine learning models written in PyTorch to…

Cloud applications have reshaped the model of services and infrastructure of the Internet. Search engines, social networks, content delivery and retail and e-commerce sites belong to this group of applications. An important element in the…

Because of the open nature of the Wireless Sensor Networks (WSN), the Denial of the Service (DoS) becomes one of the most serious threats to the stability of the resourceconstrained sensor nodes. In this paper, we develop AccFlow which is…

We explore here surprising links between the time-cost-tradeoff problem and the minimum cost flow problem that lead to fast, strongly polynomial, algorithms for both problems. One of the main results is a new algorithm for the unit capacity…

Fault tolerance overhead of high performance computing (HPC) applications is becoming critical to the efficient utilization of HPC systems at large scale. HPC applications typically tolerate fail-stop failures by checkpointing. Another…