Related papers: DAK-UCB: Diversity-Aware Prompt Routing for LLMs a…

Text-to-image models have shown remarkable progress in generating high-quality images from user-provided prompts. Despite this, the quality of these images varies due to the models' sensitivity to human language nuances. With advancements…

An automatic machine learning (AutoML) task is to select the best algorithm and its hyper-parameters simultaneously. Previously, the hyper-parameters of all algorithms are joint as a single search space, which is not only huge but also…

Existing large language models (LLMs) are advancing rapidly and produce outstanding results in image generation tasks, yet their content safety checks remain vulnerable to prompt-based jailbreaks. Through preliminary testing on platforms…

The last decade has witnessed many successes of deep learning-based models for industry-scale recommender systems. These models are typically trained offline in a batch manner. While being effective in capturing users' past interactions…

Sampling multiple responses improves language model reasoning, but uniform compute allocation is inefficient: easy questions are over-sampled while hard questions remain under-explored. We propose Uncertainty-Aware Budget Allocation (UAB),…

We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact with sequentially displayed items simultaneously. Unlike…

We study how to use naturally available user feedback, such as clicks, to optimize large language model (LLM) pipelines for generating personalized sentences using prompts. Naive approaches, which estimate the policy gradient in the prompt…

Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previous methods either adopt a fixed speculative decoding…

Adaptive monitoring of a large population of dynamic processes is critical for the timely detection of abnormal events under limited resources in many healthcare and engineering systems. Examples include the risk-based disease screening and…

Cognitive biases, systematic deviations from rationality in judgment, pose significant challenges in generating objective content. This paper introduces a novel approach for real-time cognitive bias detection in user-generated text using…

In this paper, we propose and study opportunistic contextual bandits - a special case of contextual bandits where the exploration cost varies under different environmental conditions, such as network load or return variation in…

The rise of large-scale pretrained models has made it feasible to generate predictive or synthetic features at low cost, raising the question of how to incorporate such surrogate predictions into downstream decision-making. We study this…

Previous works in prompt engineering for large language models have introduced different gradient-free probability-based prompt selection methods that aim to choose the optimal prompt among the candidates for a given task but have failed to…

We explore the sequential decision making problem where the goal is to estimate uniformly well a number of linear models, given a shared budget of random contexts independently sampled from a known distribution. The decision maker must…

The causal bandit problem seeks to identify, through sequential experimentation, an intervention that maximizes the expected reward in a causal system modeled by a directed acyclic graph (DAG). Existing methods typically assume that the…

Controlling diversity in LLM-agent simulations is essential for balancing stability in structured tasks with variability in open-ended interactions. However, we observe that dialogue diversity tends to degrade over long-term simulations. To…

Large Language Models (LLMs) such as Gemma-2B have shown strong performance in various natural language processing tasks. However, general-purpose models often lack the domain expertise required for cybersecurity applications. This work…

Continual learning requires machine learning models to continuously acquire new knowledge in dynamic environments while avoiding the forgetting of previous knowledge. Prompt-based continual learning methods effectively address the issue of…

We study the problem of training an accurate linear regression model by procuring labels from multiple noisy crowd annotators, under a budget constraint. We propose a Bayesian model for linear regression in crowdsourcing and use variational…

The design of personalized incentives or recommendations to improve user engagement is gaining prominence as digital platform providers continually emerge. We propose a multi-armed bandit framework for matching incentives to users, whose…