arXiv:2604.24348v1 Announce Type: new
Abstract: The evolution of Multimodal Large Language Models (MLLMs) has shifted the focus from text generation to active behavioral execution, particularly via OS agents navigating complex GUIs. However, the trans…
arXiv:2604.24361v1 Announce Type: new
Abstract: Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorly understood. To bridge this gap, we introduce CanM…
arXiv:2604.24372v1 Announce Type: cross
Abstract: LLM-guided evolutionary search has emerged as a promising paradigm for automated algorithm discovery, yet most systems track search progress primarily through executable programs and scalar fitness. Ev…
arXiv:2604.24374v1 Announce Type: new
Abstract: Representation learning is fundamental to NLP, but building embeddings that work well at different computational budgets is challenging. Matryoshka Representation Learning (MRL) offers a flexible inferen…
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 …
arXiv:2505.16518v3 Announce Type: replace-cross
Abstract: Incorporating external knowledge is crucial for knowledge-intensive tasks, such as question answering and fact checking. However, language models (LMs) may ignore relevant information that cont…
arXiv:2604.24515v1 Announce Type: new
Abstract: Multi-hop Question Answering (MHQA) aims to answer questions that require multi-step reasoning. It presents two key challenges: generating correct reasoning paths in response to the complex user queries,…
arXiv:2507.09245v2 Announce Type: replace
Abstract: The Swa-bhasha Resource Hub provides a comprehensive collection of data resources and algorithms developed for Romanized Sinhala to Sinhala transliteration between 2020 and 2025. These resources have…
arXiv:2604.24536v1 Announce Type: new
Abstract: Large Language Models (LLMs) excel academically but struggle with social intelligence tasks, such as creating good compromises. In this paper, we present methods for generating empathically neutral compr…
arXiv:2508.10180v3 Announce Type: replace
Abstract: Data valuation is essential for enhancing the transparency and accountability of large language models (LLMs) and vision-language models (VLMs). However, existing methods typically rely on gradient c…