Related papers: Token-Efficient Change Detection in LLM APIs
With the increasing integration of smart meters in electrical grids worldwide, detecting energy theft has become a critical and ongoing challenge. Artificial intelligence (AI)-based models have demonstrated strong performance in identifying…
Recent advances in machine learning have led to increased deployment of black-box classifiers across a wide variety of applications. In many such situations there is a critical need to both reliably assess the performance of these…
Third-party Large Language Model (LLM) API gateways are rapidly emerging as unified access points to models offered by multiple vendors. However, the internal routing, caching, and billing policies of these gateways are largely undisclosed,…
Continuous cloud service performance benchmarking is essential for detecting performance bugs early before deploying them to production. However, detecting performance regressions using application benchmarks, which usually treat the system…
Adversarial robustness in structured data remains an underexplored frontier compared to vision and language domains. In this work, we introduce a novel black-box, decision-based adversarial attack tailored for tabular data. Our approach…
Although beam emittance is critical for the performance of high-brightness accelerators, optimization is often time limited as emittance calculations, commonly done via quadrupole scans, are typically slow. Such calculations are a type of…
Chain-of-thought (CoT) reasoning improves large language models (LLMs) on difficult tasks, but it also makes inference expensive because every intermediate step must be generated as a discrete token. Latent reasoning reduces visible token…
Black-box prompt tuning employs derivative-free optimization algorithms to learn prompts within low-dimensional subspaces rather than back-propagating through the network of Large Language Models (LLMs). Recent studies reveal that black-box…
The deployment of large-scale generative models is often restricted by their potential risk of causing harm to users in unpredictable ways. We focus on the problem of black-box red teaming, where a red team generates test cases and…
We present a general and flexible framework for detecting regime changes in complex, non-stationary data across multi-trial experiments. Traditional change point detection methods focus on identifying abrupt changes within a single time…
Despite emerging research on Language Models (LM), few approaches analyse the invertibility of LMs. That is, given a LM and a desirable target output sequence of tokens, determining what input prompts would yield the target output remains…
Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoint is actually serving the advertised model. We introduce KBF, a low-cost black-box…
Effective problem solving with Large Language Models (LLMs) can be enhanced when they are paired with external search algorithms. By viewing the space of diverse ideas and their follow-up possibilities as a tree structure, the search…
Large Language Models (LLMs) typically generate outputs token by token using a fixed compute budget, leading to inefficient resource utilization. To address this shortcoming, recent advancements in mixture of expert (MoE) models,…
As the development of Large Models (LMs) progresses rapidly, their safety is also a priority. In current Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) safety workflow, evaluation, diagnosis, and alignment are…
The computational cost of training multimodal large language models (MLLMs) grows rapidly with the number of processed tokens. Existing efficiency methods mainly target inference via token reduction or merging, offering limited benefits…
This paper details a number of indoor localization techniques developed for real-time monitoring of older adults. These were developed within the framework of the i-Light research project that was funded by the European Union. The project…
Perception systems operate as a subcomponent of the general autonomy stack, and perception system designers often need to optimize performance characteristics while maintaining safety with respect to the overall closed-loop system. For this…
Code Linting tools are vital for detecting potential defects in Verilog code. However, the limitations of traditional Linting tools are evident in frequent false positives and redundant defect reports. Recent advancements in large language…
Parameter settings profoundly impact the performance of machine learning algorithms and laboratory experiments. The classical grid search or trial-error methods are exponentially expensive in large parameter spaces, and Bayesian…