Archive, newest first. Filter by topic, impact and company →
Problem This paper addresses the gap in literature regarding the implementation of embedded machine learning (ML) workflows specifically tailored for microcontroller-class edge devices. While existing research often discusses ML in…
Problem This work addresses a significant gap in the security analysis of prompt templates used in large language models (LLMs), specifically focusing on Handlebars, a widely adopted templating engine in…
Problem This preprint addresses the gap in understanding the capabilities of current AI systems in solving research-level mathematics problems. Despite advancements in AI, there is limited empirical evaluation of their…
Problem Recent advancements in deep learning for reconstructing Landsat and Sentinel-2 reflectance time series have been hindered by limitations in spectral coverage, geographic scalability, and reliance on patch-based designs with…
Problem This work addresses the limitations of deploying State Space Models (SSMs) like Mamba-2 on edge devices due to their substantial memory requirements. Prior research, specifically Slender-Mamba, necessitated training from…
Problem This paper addresses the need for a flexible navigation model capable of adapting to various tasks in agentic navigation systems, such as instruction following, object search, target tracking, and…
Problem The paper addresses the gap in multi-objective reinforcement learning (MORL) concerning fairness in policy selection, particularly in scenarios with dynamic or unknown user preferences. Existing single-policy MORL methods, which…
Problem This work addresses the gap in effective natural language (NL) querying of structured databases, specifically within the context of astronomical data. The authors highlight the challenges of translating NL…
Problem The paper addresses the minimum zero-forcing set (ZFS) problem on undirected graphs, which is known to be NP-hard. This problem involves determining the smallest set of nodes that can…
Problem This paper addresses the limitations of existing network planning optimization frameworks, which primarily rely on mixed integer programming (MIP) solvers, heuristics, and deep reinforcement learning (DRL) models. These methods…
Problem The paper addresses the limitations of existing Retrieval-Augmented Generation (RAG) frameworks, which are primarily designed for factual question-answering and do not align with the interpretive methodologies of historical studies.…
Problem Graphical user interface (GUI) grounding necessitates precise identification of small elements in high-resolution screenshots, requiring vision-language models (VLMs) to predict accurate screen coordinates. The authors identify a gap in…
Problem The paper addresses the gap in the formal verification of blockchain consensus protocols, specifically Bitcoin's Proof of Work, using automated theorem proving. Traditional formal verification methods are labor-intensive and…
Problem The paper addresses the challenge of deploying Structured State Space Models (SSMs), such as S4 and S4D, in resource-constrained environments due to their high computational and memory requirements. Despite…
Problem This work addresses the gap in understanding how large language models (LLMs) achieve compositional generalization in reasoning tasks. While post-training pipelines combining supervised fine-tuning (SFT) and reinforcement learning (RL)…
Problem The paper addresses a significant gap in the understanding of gradient descent dynamics when operating at the edge of stability (EoS), where the largest eigenvalue of the loss Hessian…
Problem — This work addresses the gap in causal discovery methods that effectively utilize second-order statistics from observational and interventional data. Existing methods often rely on higher-order moments, which can…
Problem The paper addresses the limitations of existing score-based diffusion models, which typically rely on Brownian perturbations that impose memoryless noising. This work is particularly relevant as it presents a…
Problem The paper addresses the limitations of existing neural surface representations, which often compromise on compactness, explicitness, and smoothness. Current methods, particularly implicit fields, necessitate iso-surfacing for practical applications, while…
Problem The paper addresses the limitations of existing reward-guided sampling methods in diffusion models, which either degrade sample quality due to gradient-based guidance or lack gradient signals in search-based methods.…
Problem Medical image classification, particularly in pathological scar assessment, faces significant challenges due to data scarcity stemming from high annotation costs, privacy issues, and the rarity of certain conditions. This…
Problem This study addresses a significant gap in the literature regarding user interactions with large language models (LLMs) concerning digital security and privacy (S&P). Prior research has predominantly focused on…
Problem The paper addresses the critical gap in evaluating the robustness of Large Language Model (LLM) based agents against pseudoscientific content, particularly as these systems are increasingly deployed for autonomous…
Problem This work addresses the gap in understanding how large language models (LLMs) can emulate peer-like support in caregiver communities, particularly for those caring for individuals with Alzheimer's Disease and…
Problem The paper addresses the limitations of existing hybrid attention mechanisms in large language models (LLMs), which typically rely on hand-crafted rules or simplistic post-hoc heuristics for the allocation of…
Problem The paper addresses the gap in the capability of large language model (LLM) agents to effectively compose multiple external skills for complex tasks. While existing systems primarily focus on…
Problem Current deep learning architectures for time series forecasting lack the capability to provide actionable insights through counterfactual explanations. Existing methods rely on instance-wise optimization, which leads to inconsistencies, high…
Problem Current vision-language-action models (VLAs) excel in robotic manipulation tasks but lack mechanisms for quantifying prediction confidence and detecting unreliable actions. This gap is critical, particularly in non-stationary environments where…
Problem The paper addresses a significant gap in the factuality verification of tool-using LLM agents that utilize the Model Context Protocol (MCP). Traditional metrics for factuality verification often overlook the…
Problem This work addresses a significant gap in the literature regarding cross-lingual transfer in the context of few-shot In-Context Learning (ICL). While previous research has extensively examined cross-lingual transfer in…
