arXiv:2505.10924v4 Announce Type: replace
Abstract: Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. W…
arXiv:2604.26020v1 Announce Type: new
Abstract: Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs) but doing so remains a costly and time-intensive pro…
arXiv:2602.21720v2 Announce Type: replace
Abstract: Human recursive numeral systems (i.e., counting systems such as English base-10 numerals), like many other grammatical systems, are highly regular. Following prior work that relates cross-linguistic …
arXiv:2604.25850v2 Announce Type: replace
Abstract: Harnesses have become a central determinant of coding-agent performance, shaping how models interact with repositories, tools, and execution environments. Yet automating harness engineering is hard: …
arXiv:2604.26347v1 Announce Type: cross
Abstract: Objective metrics for emotional expressiveness are vital for speech generation, particularly in expressive synthesis and voice conversion requiring emotional prosody transfer. To quantify this, the fie…
arXiv:2502.14912v2 Announce Type: replace
Abstract: We present a framework for generating universal semantic embeddings of chemical elements to advance materials inference and discovery. This framework leverages ElementBERT, a domain-specific BERT-bas…
arXiv:2604.26229v1 Announce Type: new
Abstract: This study compares machine learning and deep learning approaches for cyberbullying detection in Indonesian-language Instagram comments. Using a balanced dataset of 650 comments labeled as Bullying and N…
arXiv:2505.21072v5 Announce Type: replace
Abstract: Large Language Models (LLMs) enhanced with retrieval, an approach known as Retrieval-Augmented Generation (RAG), have achieved strong performance in open-domain question answering. However, RAG remai…
arXiv:2510.14438v2 Announce Type: replace
Abstract: The hallmark of Deep Research agents lies in compositional reasoning, the capacity to aggregate distributed, heterogeneous information into coherent logical insights. However, current agentic systems…
arXiv:2601.03423v3 Announce Type: replace
Abstract: Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new model generation. We propose Cross-Architecture Proxy Tuni…