Related papers: Guard: Scalable Straggler Detection and Node Healt…

The application of large language models to code generation has evolved from one-shot generation to iterative refinement, yet the evolution of security throughout iteration remains insufficiently understood. Through comparative experiments…

As the potential for neural networks to augment our daily lives grows, ensuring their quality through effective testing, debugging, and maintenance is essential. This is especially the case as we acknowledge the prospects of negative…

Pre-training large language models on massive GPU clusters has made hardware faults routine rather than rare, driving the need for resilient training systems. Yet existing frameworks either focus on specific parallelism schemes or risk…

We present two novel federated learning (FL) schemes that mitigate the effect of straggling devices by introducing redundancy on the devices' data across the network. Compared to other schemes in the literature, which deal with stragglers…

AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…

Performance debugging in production is a fundamental activity in modern service-based systems. The diagnosis of performance issues is often time-consuming, since it requires thorough inspection of large volumes of traces and performance…

Achieving robust safety alignment in large language models (LLMs) while preserving their utility remains a fundamental challenge. Existing approaches often struggle to balance comprehensive safety with fine-grained controllability at the…

Identifying critical nodes and links in graphs is a crucial task. These nodes/links typically represent critical elements/communication links that play a key role in a system's performance. However, a majority of the methods available in…

Retrieval-Augmented Code Generation (RACG) leverages external knowledge to enhance Large Language Models (LLMs) in code synthesis, improving the functional correctness of the generated code. However, existing RACG systems largely overlook…

Edge Federation is a new computing paradigm that seamlessly interconnects the resources of multiple edge service providers. A key challenge in such systems is the deployment of latency-critical and AI based resource-intensive applications…

Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set…

To run a cloud application with the required service quality, operators have to continuously monitor the cloud application's run-time status, detect potential performance anomalies, and diagnose the root causes of anomalies. However,…

In this paper, we propose Helios, a heterogeneity-aware FL framework to tackle the straggler issue. Helios identifies individual devices' heterogeneous training capability, and therefore the expected neural network model training volumes…

Guardrails are critical for the safe deployment of Large Language Models (LLMs)-powered software. Unlike traditional rule-based systems with limited, predefined input-output spaces that inherently constrain unsafe behavior, LLMs enable…

Large Language Model (LLM) training is frequently interrupted by a heterogeneous spectrum of failures, from common GPU crashes to catastrophic cluster-wide outages. Existing checkpointing systems rely on monolithic, single-tier storage…

In this paper, we consider a decentralized learning problem in the presence of stragglers. Although gradient coding techniques have been developed for distributed learning to evade stragglers, where the devices send encoded gradients with…

Straggler task detection is one of the main challenges in applying MapReduce for parallelizing and distributing large-scale data processing. It is defined as detecting running tasks on weak nodes. Considering two stages in the Map phase…

We consider distributed gradient descent in the presence of stragglers. Recent work on \em gradient coding \em and \em approximate gradient coding \em have shown how to add redundancy in distributed gradient descent to guarantee convergence…

The deployment of Large Reasoning Models (LRMs) in high-stakes decision-making pipelines has introduced a novel and opaque attack surface: reasoning backdoors. In these attacks, the model's intermediate Chain-of-Thought (CoT) is manipulated…

SOTA decentralized SGD algorithms can overcome the bandwidth bottleneck at the parameter server by using communication collectives like Ring All-Reduce for synchronization. While the parameter updates in distributed SGD may happen…