arXiv:2604.23813v1 Announce Type: cross
Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance in Visually Rich Document Understanding (VRDU) tasks, but their capabilities are mainly evaluated on pristine, well-structu…
arXiv:2511.09465v3 Announce Type: replace
Abstract: Diffusion and flow matching approaches to generative modeling have shown promise in domains where the state space is continuous, such as image generation or protein folding & design, and discrete, ex…
arXiv:2604.24029v1 Announce Type: cross
Abstract: Identifying species in biology among tens of thousands of visually similar taxa while discovering unknown species in open-world environments remains a fundamental challenge in biodiversity research. Cu…
arXiv:2604.24320v1 Announce Type: new
Abstract: Large language model (LLM) agents that follow the sequential “reason-then-act” paradigm have achieved superior performance in many complex tasks.However, these methods suffer from limited exploration and…
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:2604.23073v1 Announce Type: cross
Abstract: Vision-language-action (VLA) models can learn to perform diverse manipulation skills “out of the box,” but achieving the precision and speed that real-world tasks demand requires further fine-tuning –…
arXiv:2603.20711v2 Announce Type: replace-cross
Abstract: Vision-Language-Action (VLA) models are mainstream in embodied intelligence but face high inference costs. Edge-Cloud Collaborative (ECC) deployment offers an effective fix by easing edge-devic…