Related papers: On Value Recomputation to Accelerate Invisible Spe…

Machine unlearning is a key defense mechanism for removing unauthorized concepts from text-to-image diffusion models, yet recent evidence shows that latent visual information often persists after unlearning. Existing adversarial approaches…

In Cloud Computing, the resource provisioning approach used has a great impact on the processing cost, especially when it is used for Big Data processing. Due to data variety, the performance of virtual machines (VM) may differ based on the…

To usher in the next round of client AI innovation, there is an urgent need to enable efficient, lossless inference of high-accuracy large language models (LLMs) and vision language models (VLMs), jointly referred to as xLMs, on client…

Machine vision tasks present challenges for resource constrained edge devices, particularly as they execute multiple tasks with variable workloads. A robust approach that can dynamically adapt in runtime while maintaining the maximum…

Accurately predicting task performance at runtime in a cluster is advantageous for a resource management system to determine whether a task should be migrated due to performance degradation caused by interference. This is beneficial for…

Large language models (LLMs) have recently shown strong potential in vulnerability detection (VD). However, accurately detecting vulnerabilities in real-world repositories requires reasoning over complex contextual interactions. Existing…

We provide a queueing-theoretic framework for job replication schemes based on the principle "\emph{replicate a job as soon as the system detects it as a \emph{straggler}}". This is called job \emph{speculation}. Recent works have analyzed…

I introduce Virtual Parameter Sharpening (VPS), an inference-time technique that augments frozen transformer linear layers with dynamic, activation-conditioned low-rank perturbations. Unlike parameter-efficient fine-tuning methods such as…

Large language models (LLMs) often struggle with maintaining accuracy throughout multiple multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and it ultimately…

Practical attacks that exploit speculative execution can leak confidential information via microarchitectural side channels. The recently-demonstrated Spectre attacks leverage speculative loads which circumvent access checks to read…

Missing values are a fundamental problem in data science. Many datasets have missing values that must be properly handled because the way missing values are treated can have large impact on the resulting machine learning model. In medical…

Time-aware data valuation enhances training efficiency and model robustness, as early detection of harmful samples could prevent months of wasted computation. However, existing methods rely on model retraining or convergence assumptions or…

This paper presents VLCache, a cache reuse framework that exploits both Key-Value (KV) cache and encoder cache from prior multimodal inputs to eliminate costly recomputation when the same multimodal inputs recur. Unlike previous heuristic…

In this paper, we use evidence-specific value abstraction for speeding Bayesian networks inference. This is done by grouping variable values and treating the combined values as a single entity. As we show, such abstractions can exploit…

Speculative Decoding (SD) accelerates inference in large language models by using a smaller draft model to propose tokens, which are then verified by a larger target model. However, the throughput gains of SD are fundamentally limited by a…

The planning problem constitutes a fundamental aspect of the autonomous driving framework. Recent strides in representation learning have empowered vehicles to comprehend their surrounding environments, thereby facilitating the integration…

Daily Value-at-Risk (VaR) for option books requires more than an accurate quantile forecast. It first requires a precise definition of the loss target. Before any model is evaluated, the protocol must fix the book construction rule, the…

Model-based offline reinforcement learning trains policies using pre-collected datasets and learned environment models, eliminating the need for direct real-world environment interaction. However, this paradigm is inherently challenged by…

Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…

Speculative decoding has emerged as an effective method to reduce latency and inference cost of LLM inferences. However, there has been inadequate attention towards the energy requirements of these models. To address this gap, this paper…