Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
Academic
arXiv:2603.02422v1 Announce Type: cross Abstract: Exponential growth in the quantity of digital news, social media, and other textual sources makes it difficult for humans to …
arXiv:2603.02482v1 Announce Type: cross Abstract: Safety evaluation and red-teaming of large language models remain predominantly text-centric, and existing frameworks lack the infrastructure to systematically test …
arXiv:2603.02556v1 Announce Type: cross Abstract: Reasoning has emerged as a key capability of large language models. In linguistic tasks, this capability can be enhanced by …
arXiv:2603.02565v1 Announce Type: cross Abstract: The Generator-Evaluator (G-E) framework, i.e., evaluating K sequences from a generator and selecting the top-ranked one according to evaluator scores, …
arXiv:2603.02637v1 Announce Type: cross Abstract: Modern machine learning (ML) workloads increasingly rely on GPUs, yet achieving high end-to-end performance remains challenging due to dependencies on …
arXiv:2603.02215v1 Announce Type: new Abstract: Chemical reaction prediction is pivotal for accelerating drug discovery and synthesis planning. Despite advances in data-driven models, current approaches are …
arXiv:2603.02216v1 Announce Type: new Abstract: Effective information seeking in multi-turn medical dialogues is critical for accurate diagnosis, especially when dealing with incomplete information. Aligning Large …
arXiv:2603.02217v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) models scale capacity efficiently, but their massive parameter footprint creates a deployment-time memory bottleneck. We organize retraining-free MoE …
arXiv:2603.02219v1 Announce Type: new Abstract: Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe …
arXiv:2603.02220v1 Announce Type: new Abstract: Time series forecasting (TSF) remains a challenging problem due to the intricate entanglement of intraperiod-fluctuations and interperiod-trends. While recent advances …
arXiv:2603.02221v1 Announce Type: new Abstract: In healthcare tabular predictions, classical models with feature engineering often outperform neural approaches. Recent advances in Large Language Models enable …
arXiv:2603.02222v1 Announce Type: new Abstract: MedCalc-Bench is a widely used benchmark for evaluating LLM performance on clinical calculator tasks, with state-of-the-art direct prompting scores plateauing …