arXiv:2509.25393v2 Announce Type: replace-cross Abstract: Forecasting high-resolution land subsidence is a critical yet challenging task due to its complex, non-linear dynamics. While standard architectures like ConvLSTM often fail to model long-range dependencies, we argue that a more fundamental limitation of…
arXiv:2510.00615v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents in dynamic, real-world environments, where success requires both reasoning and effective tool use. A central challenge for agentic tasks is the growing context length, as agents…
arXiv:2509.23019v2 Announce Type: replace-cross Abstract: Watermarking for large language models (LLMs) embeds a statistical signal during generation to enable detection of model-produced text. While watermarking has proven effective in benign settings, its robustness under adversarial evasion remains contested. To advance…
arXiv:2510.00552v1 Announce Type: new Abstract: Organizations increasingly adopt Retrieval-Augmented Generation (RAG) to enhance Large Language Models with enterprise-specific knowledge. However, current data quality (DQ) frameworks have been primarily developed for static datasets, and only inadequately address the dynamic, multi-stage nature…
arXiv:2506.04408v2 Announce Type: replace-cross Abstract: Humans have a remarkable ability to acquire and understand grammatical phenomena that are seen rarely, if ever, during childhood. Recent evidence suggests that language models with human-scale pretraining data may possess a similar ability by…
arXiv:2510.00523v1 Announce Type: new Abstract: Multimodal representation learning models have demonstrated successful operation across complex tasks, and the integration of vision-language models (VLMs) has further enabled embedding models with instruction-following capabilities. However, existing embedding models lack visual-interactive capabilities to specify…
arXiv:2510.00492v1 Announce Type: new Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with emph{external verifiers} or emph{reward models} that distinguish correct reasoning from flawed logic. Prior work generally assumes that process reward models (PRMs),…
arXiv:2411.07335v3 Announce Type: replace-cross Abstract: Multimodal learning holds promise for richer information extraction by capturing dependencies across data sources. Yet, current training methods often underperform due to modality competition, a phenomenon where modalities contend for training resources leaving some underoptimized.…
arXiv:2510.00480v1 Announce Type: new Abstract: Invasion team sports such as soccer produce a high-dimensional, strongly coupled state space as many players continuously interact on a shared field, challenging quantitative tactical analysis. Traditional rule-based analyses are intuitive, while modern predictive machine…
arXiv:2510.00436v1 Announce Type: new Abstract: Automated approaches to answer patient-posed health questions are rising, but selecting among systems requires reliable evaluation. The current gold standard for evaluating the free-text artificial intelligence (AI) responses–human expert review–is labor-intensive and slow, limiting scalability.…
