MultiBanAbs: A Comprehensive Multi-Domain Bangla Abstractive Text Summarization Dataset
arXiv:2511.19317v1 Announce Type: cross Abstract: This study developed a new Bangla abstractive summarization dataset to generate concise summaries of Bangla…
Scaling and Transferability of Annealing Strategies in Large Language Model Training
arXiv:2512.13705v1 Announce Type: cross Abstract: Learning rate scheduling is crucial for training large language models, yet understanding the optimal annealing…
PortAgent: LLM-driven Vehicle Dispatching Agent for Port Terminals
arXiv:2512.14417v1 Announce Type: new Abstract: Vehicle Dispatching Systems (VDSs) are critical to the operational efficiency of Automated Container Terminals (ACTs).…
Sparse Multi-Modal Transformer with Masking for Alzheimer’s Disease Classification
arXiv:2512.14491v1 Announce Type: new Abstract: Transformer-based multi-modal intelligent systems often suffer from high computational and energy costs due to dense…
HydroGEM: A Self Supervised Zero Shot Hybrid TCN Transformer Foundation Model for Continental Scale Streamflow Quality Control
arXiv:2512.14106v1 Announce Type: new Abstract: Real-time streamflow monitoring networks generate millions of observations annually, yet maintaining data quality across thousands…
Efficient Adaptive Rejection Sampling for Accelerating Speculative Decoding in Large Language Models
arXiv:2512.13194v2 Announce Type: replace-cross Abstract: Speculative Decoding is a prominent technique for accelerating the autoregressive inference of large language models…
From YOLO to VLMs: Advancing Zero-Shot and Few-Shot Detection of Wastewater Treatment Plants Using Satellite Imagery in MENA Region
arXiv:2512.14312v1 Announce Type: cross Abstract: In regions of the Middle East and North Africa (MENA), there is a high demand…
Semantic Mismatch and Perceptual Degradation: A New Perspective on Image Editing Immunity
arXiv:2512.14320v1 Announce Type: cross Abstract: Text-guided image editing via diffusion models, while powerful, raises significant concerns about misuse, motivating efforts…
Non-Resolution Reasoning (NRR): A Computational Framework for Contextual Identity and Ambiguity Preservation
arXiv:2512.13478v2 Announce Type: replace-cross Abstract: Current artificial intelligence systems, despite remarkable capabilities in text generation and pattern recognition, exhibit a…
Leveraging LLMs for Structured Data Extraction from Unstructured Patient Records
arXiv:2512.13700v1 Announce Type: new Abstract: Manual chart review remains an extremely time-consuming and resource-intensive component of clinical research, requiring experts…