Related papers: Fortress: A Case Study in Stabilizing Search Recom…

Monte Carlo Tree Search (MCTS) has emerged as a powerful tool for decision-making in robotics, enabling efficient exploration of large search spaces. However, traditional MCTS methods struggle in environments characterized by high…

Stability selection is a versatile framework for structure estimation and variable selection in high-dimensional setting, primarily grounded in frequentist principles. In this paper, we propose an enhanced methodology that integrates…

Effectively modeling the dynamic nature of user preferences is crucial for enhancing recommendation accuracy and fostering transparency in recommender systems. Traditional user profiling often overlooks the distinction between transitory…

Evaluations of large language models (LLMs) suffer from instability, where small changes of random factors such as few-shot examples can lead to drastic fluctuations of scores and even model rankings. Moreover, different LLMs can have…

As machine learning models become increasingly prevalent in critical decision-making models and systems in fields like finance, healthcare, etc., ensuring their robustness against adversarial attacks and changes in the input data is…

Time Series Foundation Models (TSFMs) have borrowed the long context paradigm from natural language processing under the premise that feeding more history into the model improves forecast quality. But in stochastic domains, distant history…

As large language models (LLMs) are increasingly deployed in high-stakes and operational settings, evaluation strategies based solely on aggregate accuracy are often insucient to characterize system reliability. This study proposes a…

The changes in user preferences can originate from substantial reasons, like personality shift, or transient and circumstantial ones, like seasonal changes in item popularities. Disregarding these temporal drifts in modelling user…

Forecasting is an indispensable element of operational research (OR) and an important aid to planning. The accurate estimation of the forecast uncertainty facilitates several operations management activities, predominantly in supporting…

We study the problem of linear feature selection when features are highly correlated. Such settings pose two fundamental challenges. First, how should model similarity be defined? Simply counting features in common can be misleading: two…

Recommendation systems have traditionally relied on short-term engagement signals, such as clicks and likes, to personalize content. However, these signals are often noisy, sparse, and insufficient for capturing long-term user satisfaction…

Real-time inference is a challenge of real-world reinforcement learning due to temporal differences in time-varying environments: the system collects data from the past, updates the decision model in the present, and deploys it in the…

Reward models are central to both reinforcement learning (RL) with language models and inference-time verification. However, existing reward models often lack temporal consistency, leading to ineffective policy updates and unstable RL…

In this paper, we focus on improving the online face liveness detection system to enhance the security of the downstream face recognition system. Most of the existing frame-based methods are suffering from the prediction inconsistency…

We propose a framework that can incrementally expand the explanatory temporal logic rule set to explain the occurrence of temporal events. Leveraging the temporal point process modeling and learning framework, the rule content and weights…

Predictive geometric models deliver excellent results for many Machine Learning use cases. Despite their undoubted performance, neural predictive algorithms can show unexpected degrees of instability and variance, particularly when applied…

Topic models can provide us with an insight into the underlying latent structure of a large corpus of documents. A range of methods have been proposed in the literature, including probabilistic topic models and techniques based on matrix…

Reinforcement Learning (RL) is crucial for unlocking the complex reasoning capabilities of Diffusion-based Large Language Models (dLLMs). However, applying RL to dLLMs faces unique challenges in efficiency and stability. To address these…

Time series foundation models excel at diverse time series forecasting tasks, but their capacity for continuous improvement through incremental learning remains unexplored. We present the first comprehensive study investigating these…

Large Language Models (LLMs) have shown impressive performance in mathematical reasoning tasks when guided by Chain-of-Thought (CoT) prompting. However, they tend to produce highly confident yet incorrect outputs, which poses significant…