Related papers: Constable: Improving Performance and Power Efficie…

Consistency properties provided by most key-value stores can be classified into sequential consistency and eventual consistency. The former is easier to program with but suffers from lower performance whereas the latter suffers from…

Modern software systems have become increasingly complex, which makes them difficult to test and validate. Detecting software partial anomalies in complex systems at runtime can assist with handling unintended software behaviors, avoiding…

Robust loss minimization is an important strategy for handling robust learning issue on noisy labels. Current approaches for designing robust losses involve the introduction of noise-robust factors, i.e., hyperparameters, to control the…

Adapters are often selected and deployed based on nominal labels (e.g., instruction-tuned), which implicitly suggest what capability improves after adaptation. We test whether nominal training objectives reliably align with realized…

Reinforcement learning is able to solve complex sequential decision-making tasks but is currently limited by sample efficiency and required computation. To improve sample efficiency, recent work focuses on model-based RL which interleaves…

Iterative Learning Control (ILC) schemes can guarantee properties such as asymptotic stability and monotonic error convergence, but do not, in general, ensure adherence to output constraints. The topic of this paper is the design of a…

Controller design faces a trade-off between robustness and performance, and the reliability of linear controllers has caused many practitioners to focus on the former. However, there is renewed interest in improving system performance to…

Reinforcement learning (RL) with verifiable rewards has proven effective at post-training LLMs for coding, yet deploying separate task-specific specialists incurs costs that scale with the number of tasks, motivating a unified multi-task RL…

Continual learning empowers models to adapt autonomously to the ever-changing environment or data streams without forgetting old knowledge. Prompt-based approaches are built on frozen pre-trained models to learn the task-specific prompts…

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as…

Machine learning force fields (MLFFs) are an attractive alternative to ab-initio methods for molecular dynamics (MD) simulations. However, they can produce unstable simulations, limiting their ability to model phenomena occurring over…

Efficient data access in High-Performance Computing (HPC) systems is essential to the performance of intensive computing tasks. Traditional optimizations of the I/O stack aim to improve peak performance but are often workload specific and…

Compound LLM training workloads-such as knowledge distillation and multimodal LLM (MLLM) training-are gaining prominence. These typically comprise heterogeneous components differing in parameter scale, execution mode (forward-only or full…

Many ML applications and products train on medium amounts of input data but get bottlenecked in real-time inference. When implementing ML systems, conventional wisdom favors segregating ML code into services queried by product code via…

Memory, as the basis of learning, determines the storage, update and forgetting of knowledge and further determines the efficiency of learning. Featured with the mechanism of memory, a radial basis function neural network based learning…

Branch instructions dependent on hard-to-predict load data are the leading branch misprediction contributors. Current state-of-the-art history-based branch predictors have poor prediction accuracy for these branches. Prior research backs…

We propose a new model for augmenting algorithms with predictions by requiring that they are formally learnable and instance robust. Learnability ensures that predictions can be efficiently constructed from a reasonable amount of past data.…

Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…

Machine learning (ML) models are increasingly trained in clusters with non-dedicated workers possessing heterogeneous resources. In such scenarios, model training efficiency can be negatively affected by stragglers -- workers that run much…

Large language models have shown their ability to become effective few-shot learners with prompting, revolutionizing the paradigm of learning with data scarcity. However, this approach largely depends on the quality of prompt…