Archive, newest first. Filter by topic, impact and company →
Problem The paper addresses the challenge of generating high-quality natural language executable plans for complex tasks, a gap in the current literature on planning with AI. The work is presented…
{'Problem': "The paper addresses a significant gap in existing AI benchmarks where models are typically provided with explicit questions. This preprint by Daniel Eisner highlights the limitations of such approaches,…
{'Problem': 'The paper addresses a gap in the capability of customer experience (CX) agents, particularly in regulated industries, where enhancing agent performance is critical. The authors highlight the challenges in…
Problem Agents currently face challenges in correctly applying skills and inferring subsequent operations, leading to inefficiencies in task execution. This paper addresses this gap by proposing a structured approach to…
Problem This work addresses the gap in capability between the high accuracy of large language models and the practical scalability of efficient Siamese-BERT variants in paraphrase detection. The authors highlight…
Problem The paper addresses the high computational cost associated with video diffusion, which arises from the necessity of performing extensive model evaluations across numerous denoising steps. This inefficiency limits the…
Problem The paper addresses scalability limitations in graph-structured optimization problems with linear constraints, particularly due to strict hard constraints and high dimensionality. The authors highlight that existing methods struggle to…
Problem Formal verification of Graph Neural Networks (GNNs) is a challenging task due to the complexity and variability of graph-structured data. Existing verification methods are often limited in their scope…
Problem This work addresses the gap in understanding the reproducibility of evaluation conclusions for large language models (LLMs) when based on small prompt sets. The authors conduct a self-audit to…
Problem The paper addresses a significant gap in the literature regarding pretraining methodologies that can autonomously generate training data. Current approaches often rely on large amounts of natural data, which…
Problem This paper addresses the gap in GPU kernel efficiency between modern compilers and expert-written implementations. The authors highlight that existing compilation techniques often fail to achieve the performance levels…
Recent research led by Nadia Heninger, a professor at the University of California at San Diego, and reported by Karsten Nohl, head of innovation at Allurity, presents a novel approach…
Problem This preprint addresses a significant gap in the literature regarding the effectiveness of AI tutoring systems compared to traditional human tutoring. While AI tutoring has gained traction, empirical evaluations…
{'Problem': 'The paper addresses a gap in the literature regarding robot group joining, specifically focusing on real-time activity recognition and formation alignment. The authors highlight the need for robots to…
Problem The paper addresses a gap in the evaluation of large language models (LLMs) regarding their ability to reason about code execution within repository-level contexts. Specifically, it highlights the lack…
Problem This work addresses the gap in understanding how answer invariance relates to representation invariance in mathematical reasoning tasks. The authors investigate this relationship through the lens of synthetic multi-step…
Problem Task-state contamination in agents adversely affects their decision-making capabilities. This paper addresses this issue by proposing a novel framework, the Agent-Editing World Model (AEWM), which aims to enhance the…
Problem Latent world models, which are used for simulating environments and dynamics, often lose their motion properties during manipulation tasks. This paper identifies this gap in capability and proposes a…
{'Problem': 'Embedding unstructured data remains an open question in machine learning, particularly in the context of high-dimensional spaces. This paper addresses this gap by proposing a new architecture, the Clifford-VAE,…
Problem This work addresses a gap in the literature regarding the guidance of individual tokens in reinforcement learning with verifiable rewards (RLVR). The authors highlight the lack of effective methods…
Problem This work addresses a gap in understanding how marketing pricing cues influence the decision-making processes of AI shopping agents. The authors highlight the lack of empirical studies examining the…
Problem The paper addresses the gap in existing driving datasets that lack sufficient supervision for connecting visual evidence with reasoning and planning in autonomous driving scenarios. The authors highlight the…
Problem The paper addresses a gap in the efficient application of microscaling quantization specifically in convolutional layers. The authors highlight the need for improved methods that can effectively reduce computational…
Problem The paper addresses a significant gap in the capability for transparent and traceable empirical evidence in AI safety assessments, particularly in the context of the EU AI Act's Code…
{'Problem': 'The paper addresses a gap in competitive pricing for token usage in language model tasks, highlighting inefficiencies in fixed-price markets. It proposes a novel approach to dynamically adjust token…
Problem This preprint investigates the propensity of AI agents in multi-agent systems to avoid human-imposed shutdowns, a critical concern in AI safety and control. The authors aim to fill a…
Problem Vision-Language-Action models currently lack the capability to retain episode-level information beyond the immediate observation, which limits their effectiveness in sequential decision-making tasks. This paper addresses this gap by proposing…
Problem Large Language Models (LLMs) exhibit significant performance degradation in multi-robot tasks as the size of the team increases. This paper addresses this gap in capability, particularly in the context…
Problem The paper addresses a gap in the capability of large language models (LLMs) to generate classical Arabic maqamat, a form of Arabic prose that combines storytelling with rhetorical techniques.…
Problem This work addresses the gap in understanding center-associated robustness in whole-slide image classification, particularly how biases related to class centers affect model predictions. The study is motivated by the…
