arXiv:2604.23948v1 Announce Type: cross Abstract: The Korean writing system, textitHangeul, has a unique character representation rigidly following the invention principles recorded in textitHunminjeongeum.footnotetextitHunminjeongeum is a book published in 1446 that describes the principles of invention and usage of textitHangeul, devised by King Sejong citeHunminjeongeum_Guide. However, existing pre-trained language models (PLMs) for Korean have overlooked these […]
What Did They Mean? How LLMs Resolve Ambiguous Social Situations across Perspectives and Roles
arXiv:2604.23942v1 Announce Type: cross Abstract: People increasingly turn to large language models (LLMs) to interpret ambiguous social situations: a delayed text reply, an unusually cold supervisor, a teacher’s mixed signals, or a boundary-crossing friend. Yet in many such cases, no stable interpretation can be verified from the available evidence alone. We study how LLMs respond […]
Is Vibe Coding the Future? An Empirical Assessment of LLM Generated Codes for Construction Safety
arXiv:2604.12311v2 Announce Type: replace-cross Abstract: The emergence of vibe coding, a paradigm where non-technical users instruct Large Language Models (LLMs) to generate executable codes via natural language, presents both significant opportunities and severe risks for the construction industry. While empowering construction personnel such as the safety managers, foremen, and workers to develop tools and software, […]
Out of Spuriousity: Improving Robustness to Spurious Correlations without Group Annotations
arXiv:2407.14974v2 Announce Type: replace-cross Abstract: Machine learning models are known to learn spurious correlations, i.e., features having strong relations with class labels but no causal relation. Relying on those correlations leads to poor performance in the data groups without these correlations and poor generalization ability. To improve the robustness of machine learning models to spurious […]
Towards a Quantitative Theory of Digraph-Based Complexes and its Applications in Brain Network Analysis
arXiv:2409.09862v4 Announce Type: replace Abstract: In this work, we developed new mathematical methods for analyzing network topology and applied these methods to the analysis of brain networks. More specifically, we rigorously developed quantitative methods based on complexes constructed from digraphs (digraph-based complexes), such as path complexes and directed clique complexes (alternatively, we refer to these […]
The Consensus Trap: Dissecting Subjectivity and the “Ground Truth” Illusion in Data Annotation
arXiv:2602.11318v3 Announce Type: replace Abstract: In machine learning, “ground truth” refers to the assumed correct labels used to train and evaluate models. However, the foundational “ground truth” paradigm rests on a positivistic fallacy that treats human disagreement as technical noise rather than a vital sociotechnical signal. This systematic literature review analyzes research published between 2020 […]
Kwai Summary Attention Technical Report
arXiv:2604.24432v1 Announce Type: cross Abstract: Long-context ability, has become one of the most important iteration direction of next-generation Large Language Models, particularly in semantic understanding/reasoning, code agentic intelligence and recommendation system. However, the standard softmax attention exhibits quadratic time complexity with respect to sequence length. As the sequence length increases, this incurs substantial overhead in […]
TeachMaster: Generative Teaching via Code
arXiv:2601.04204v2 Announce Type: replace-cross Abstract: The scalability of high-quality online education is hindered by the high costs and slow cycles of manual content creation. Despite advancements in video generation, current approaches often fail to ensure pedagogical structure and precise control due to their pixel-level, black-box nature. In this paper, we propose Generative Teaching, a novel […]
The AI Codebase Maturity Model: From Assisted Coding to Fully Autonomous Systems
arXiv:2604.09388v2 Announce Type: replace-cross Abstract: AI coding tools are widely adopted, but most teams plateau at prompt-and-review without a framework for systematic progression. This paper presents the AI Codebase Maturity Model (ACMM), a 6-level framework describing how codebases evolve from basic AI-assisted coding to fully autonomous systems. Inspired by CMMI, each level is defined by […]
LearnAlign: Data Selection for LLM Reinforcement Learning with Improved Gradient Alignment
arXiv:2506.11480v4 Announce Type: replace-cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a key technique for enhancing LLMs’ reasoning abilities, yet its data inefficiency remains a major bottleneck. To address this critical yet challenging issue, we present a novel gradient-alignment-based method, named LearnAlign, which intelligently selects the learnable and representative training reasoning data for […]
Cataract-LMM Large-Scale Multi-Source Multi-Task Benchmark for Deep Learning in Surgical Video Analysis
arXiv:2510.16371v2 Announce Type: replace-cross Abstract: The development of computer-assisted surgery systems relies on large-scale, annotated datasets. Existing cataract surgery resources lack the diversity and annotation depth required to train generalizable deep-learning models. To address this gap, we present a dataset of 3,000 phacoemulsification cataract surgery videos acquired at two surgical centers from surgeons with varying […]
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
arXiv:2603.25562v2 Announce Type: replace-cross Abstract: On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implementation, however, usually reduces distribution matching to a sampled-token log-ratio, which can make the learning signal fragile on long rollouts whose prefixes drift away from […]