相关论文: Lattice: A Confidence-Gated Hybrid System for Unce…

Selective classification enables models to make predictions only when they are sufficiently confident, aiming to enhance safety and reliability, which is important in high-stakes scenarios. Previous methods mainly use deep neural networks…

We develop a resilient binary hypothesis testing framework for decision making in adversarial multi-robot crowdsensing tasks. This framework exploits stochastic trust observations between robots to arrive at tractable, resilient decision…

While Large Language Models (LLMs) have catalyzed breakthroughs in automated code generation, Small Language Models (SLMs) often encounter reasoning bottlenecks and failure loops when addressing complex logical requirements. To overcome…

To interact with humans in collaborative environments, machines need to be able to predict (i.e., anticipate) future events, and execute actions in a timely manner. However, the observation of the human limb movements may not be sufficient…

In many sequential tasks, a model needs to remember relevant events from the distant past to make correct predictions. Unfortunately, a straightforward application of gradient based training requires intermediate computations to be stored…

We develop a resilient binary hypothesis testing framework for decision making in adversarial multi-robot crowdsensing tasks. This framework exploits stochastic trust observations between robots to arrive at tractable, resilient decision…

Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper, we propose a novel Bayesian model-agnostic meta-learning…

Hippocampal formation (HF) can rapidly adapt to varied environments and build flexible working memory (WM). To mirror the HF's mechanism on generalization and WM, we propose a model named Generalization and Associative Temporary Encoding…

This paper addresses the critical challenge of stochastic latent heterogeneity in online decision-making, where individuals' responses to actions vary not only with observable contexts but also with unobserved, randomly realized subgroups.…

We present the Bayesian Linguistic Forecaster (BLF), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is built on three ideas. (1) Linguistic belief state: a…

DNA sequence classification requires not only high predictive accuracy but also the ability to uncover latent site interactions, combinatorial regulation, and epistasis-like higher-order dependencies. Although the standard Transformer…

A simple lattice model that allows hysteresis loops with exchange bias to be reproduced is presented. The model is based on the metastable Random Field Ising model, driven by an external field, with synchronous local relaxation dynamics.…

Retrieval Augmented Generation (RAG) systems remain vulnerable to hallucinated answers despite incorporating external knowledge sources. We present LettuceDetect a framework that addresses two critical limitations in existing hallucination…

Large Language Models (LLMs) deployed in production environments face a fundamental safety-utility trade-off either a strict filtering mechanisms prevent harmful outputs but often block benign queries or a relaxed controls risk unsafe…

LLM agents with tool-calling capabilities often fail when user instructions are ambiguous or incomplete, leading to incorrect invocations and task failures. Existing approaches operate in unstructured language spaces, generating clarifying…

Lattice-linearity was introduced as a way to model problems using predicates that induce a lattice among the global states (Garg, SPAA 2020). A key property of \textit{the predicate} representing such problems is that it induces…

This paper presents CADL (Cognitive-Adaptive Deception Layer), an adaptive deception framework achieving 99.88% detection rate with 0.13% false positive rate on the CICIDS2017 dataset. The framework employs ensemble machine learning (Random…

Safety-critical perception systems require both reliable uncertainty quantification and principled abstention mechanisms to maintain safety under diverse operational conditions. We present a novel dual-threshold conformalization framework…

The paper investigates the Lattice Agreement (LA) problem in asynchronous systems. In LA each process proposes an element $e$ from a predetermined lattice, and has to decide on an element $e'$ of the lattice such that $e \leq e'$. Moreover,…

We introduce a data-driven forecasting method for high-dimensional chaotic systems using long short-term memory (LSTM) recurrent neural networks. The proposed LSTM neural networks perform inference of high-dimensional dynamical systems in…