arXiv:2508.11354v3 Announce Type: replace-cross Abstract: Purpose: This study introduces the first adaptation of RETFound for joint optic disc (OD) and optic cup (OC) segmentation. RETFound is a well-known foundation model developed for fundus camera and optical coherence tomography images, which…
arXiv:2601.10863v3 Announce Type: replace Abstract: Traditional time series forecasting methods optimize for accuracy alone. This objective neglects temporal consistency, in other words, how consistently a model predicts the same future event as the forecast origin changes. We introduce the forecast…
arXiv:2604.20921v1 Announce Type: new Abstract: We evaluated whether a glaucoma risk assessment (GRA) model trained on All of Us national data can identify patients at high probability of glaucoma using only systemic electronic health records (EHR) at an independent institution.…
arXiv:2407.19664v3 Announce Type: replace Abstract: Previous research on selective protection for neural network components typically exploits only static vulnerability differences. Although these methods improve upon classical modular redundancy, they still incur substantial overhead for neural network workloads that are both…
arXiv:2604.20917v1 Announce Type: new Abstract: Large language models (LLMs) have shown remarkable capabilities across diverse coding tasks. However, their adoption requires a true understanding of program execution rather than relying on surface-level patterns. Existing benchmarks primarily focus on predicting program…
arXiv:2604.20920v1 Announce Type: new Abstract: Scaling large language models to long contexts is challenging due to the quadratic computational cost of full attention. Mitigation approaches include KV-cache selection or compression techniques. We instead provide an effective and end-to-end learnable bridge…
arXiv:2604.20915v1 Announce Type: new Abstract: Transformers suffer from a high computational cost that grows with sequence length for self-attention, making inference in long streams prohibited by memory consumption. Constant-memory alternatives such as RNNs and SSMs compress history into states with…
arXiv:2604.20913v1 Announce Type: new Abstract: Large language models are increasingly deployed on CPU-only platforms where memory bandwidth is the primary bottleneck for autoregressive generation. Weight quantization to four bits or below reduces memory pressure, yet existing systems still dequantize weights…
arXiv:2604.20909v1 Announce Type: new Abstract: Downhole drilling telemetry presents a fundamental labeling asymmetry: surface sensor data are generated continuously at 1~Hz, while labeled downhole measurements are costly, intermittent, and scarce. Current machine learning approaches for downhole metric prediction universally adopt…
arXiv:2604.21698v1 Announce Type: cross Abstract: Persistent homology, a method from topological data analysis, extracts robust, multi-scale features from data. It produces stable representations of time series by applying varying thresholds to their values (a process known as a textit{filtration}). We…
