Minimizing Hyperbolic Embedding Distortion with LLM-Guided Hierarchy Restructuring
arXiv:2511.20679v1 Announce Type: new Abstract: Hyperbolic geometry is an effective geometry for embedding hierarchical data structures. Hyperbolic learning has therefore…
LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework
arXiv:2511.20403v2 Announce Type: replace-cross Abstract: Unit testing is an essential but resource-intensive step in software development, ensuring individual code units…
Generating Separated Singing Vocals Using a Diffusion Model Conditioned on Music Mixtures
arXiv:2511.21342v1 Announce Type: cross Abstract: Separating the individual elements in a musical mixture is an essential process for music analysis…
SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding
arXiv:2511.21339v1 Announce Type: cross Abstract: Recent advances in multimodal large language models (LLMs) have highlighted their potential for medical and…
R3A: Reliable RTL Repair Framework with Multi-Agent Fault Localization and Stochastic Tree-of-Thoughts Patch Generation
arXiv:2511.20090v2 Announce Type: replace-cross Abstract: Repairing RTL bugs is crucial for hardware design and verification. Traditional automatic program repair (APR)…
Leibniz’s Monadology as Foundation for the Artificial Age Score: A Formal Architecture for Al Memory Evaluation
arXiv:2511.17541v1 Announce Type: new Abstract: This paper develops a mathematically rigorous, philosophically grounded framework for evaluating artificial memory systems, rooted…
GRAPHIC–Guidelines for Reviewing Algorithmic Practices in Human-centred Design and Interaction for Creativity
arXiv:2511.17443v2 Announce Type: replace-cross Abstract: Artificial Intelligence (AI) has been increasingly applied to creative domains, leading to the development of…
Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models
arXiv:2511.18890v1 Announce Type: cross Abstract: Efficient deployment of small language models (SLMs) is essential for numerous real-world applications with stringent…
CoreEval: Automatically Building Contamination-Resilient Datasets with Real-World Knowledge toward Reliable LLM Evaluation
arXiv:2511.18889v1 Announce Type: cross Abstract: Data contamination poses a significant challenge to the fairness of LLM evaluations in natural language…
Beyond Multiple Choice: Verifiable OpenQA for Robust Vision-Language RFT
arXiv:2511.17405v2 Announce Type: replace-cross Abstract: Multiple-choice question answering (MCQA) has been a popular format for evaluating and reinforcement fine-tuning (RFT)…