arXiv:2411.04257v3 Announce Type: replace Abstract: Contemporary large language model (LLM) training pipelines require the assembly of internet-scale databases full of text data from a variety of sources (e.g., web, academic, and publishers). Preprocessing these datasets via deduplication — detecting and…
arXiv:2512.02180v1 Announce Type: new Abstract: The electrocardiogram (ECG) is a key diagnostic tool in cardiovascular health. Single-lead ECG recording is integrated into both clinical-grade and consumer wearables. While self-supervised pretraining of foundation models on unlabeled ECGs improves diagnostic performance, existing…
arXiv:2505.18738v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) is a widely adopted parameter-efficient fine-tuning (PEFT) method validated across NLP and CV domains. However, LoRA faces an inherent low-rank bottleneck: narrowing its performance gap with full finetuning requires increasing the rank…
arXiv:2512.02194v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) have been widely used for interpretability of neural networks, but their learned features often vary across seeds and hyperparameter settings. We introduce Ordered Sparse Autoencoders (OSAE), which extend Matryoshka SAEs by (1)…
arXiv:2508.14101v2 Announce Type: replace Abstract: Hypergraphs offer a generalized framework for capturing high-order relationships between entities and have been widely applied in various domains, including healthcare, social networks, and bioinformatics. Hypergraph neural networks, which rely on message-passing between nodes over…
arXiv:2512.02200v1 Announce Type: new Abstract: The ‘Doughnut’ of social and planetary boundaries has emerged as a popular framework for assessing environmental and social sustainability. Here, we provide a proof-of-concept analysis that shows how machine learning (ML) methods can be applied…
arXiv:2510.17923v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for advancing Large Language Models (LLMs), achieving remarkable performance in complex reasoning domains such as mathematics and code generation. However, current RL methods face a fundamental…
arXiv:2512.02206v1 Announce Type: new Abstract: Sperm whales communicate in short sequences of clicks known as codas. We present WhAM (Whale Acoustics Model), the first transformer-based model capable of generating synthetic sperm whale codas from any audio prompt. WhAM is built…
arXiv:2512.00783v2 Announce Type: replace Abstract: To address the gap in humanoid robot cognitive systems regarding the lack of a time-updable mediating thought space between semantics and continuous control, this study constructs and trains a VLA model named “Sigma” that runs…
arXiv:2512.02213v1 Announce Type: new Abstract: Effective text generation and chat interfaces for low-resource languages (LRLs) remain a challenge for state-of-the-art large language models (LLMs) to support. This is mainly due to the difficulty of curating high-quality instruction datasets for LRLs,…
