Quality follows upgrading
Ever a pioneer, ever a student — learning through our mistakes and failures
전체 전문분석자료
arXiv:2602.15206v1 Announce Type: new Abstract: Reward learning typically relies on a single feedback type or combines multiple feedback types using manually weighted loss terms. Currently, …
arXiv:2602.15222v1 Announce Type: new Abstract: Reward models are central to large language model (LLM) post-training. However, past work has shown that they can reward spurious …
arXiv:2602.15236v1 Announce Type: new Abstract: Virtual screening aims to efficiently identify active ligands from massive chemical libraries for a given target pocket. Recent CLIP-style models …
arXiv:2602.15238v1 Announce Type: new Abstract: Adversarial training for LLMs is one of the most promising methods to reliably improve robustness against adversaries. However, despite significant …
arXiv:2602.15239v1 Announce Type: new Abstract: Transformers have achieved remarkable success across domains, motivating the rise of Graph Transformers (GTs) as attention-based architectures for graph-structured data. …
arXiv:2602.15253v1 Announce Type: new Abstract: Neural scaling laws -- power-law relationships between loss, model size, and data -- have been extensively documented for language and …
arXiv:2602.15260v1 Announce Type: new Abstract: On-policy distillation (OPD), which samples trajectories from the student model and supervises them with a teacher at the token level, …
arXiv:2602.15283v1 Announce Type: new Abstract: Modern deep neural networks achieve high predictive accuracy but remain poorly calibrated: their confidence scores do not reliably reflect the …
arXiv:2602.15304v1 Announce Type: new Abstract: Collaborative clinical decision support is often constrained by governance and privacy rules that prevent pooling patient-level records across institutions. We …
arXiv:2602.15322v1 Announce Type: new Abstract: Training large language models (LLMs) relies almost exclusively on dense adaptive optimizers with increasingly sophisticated preconditioners. We challenge this by …
arXiv:2602.15330v1 Announce Type: new Abstract: The long-tail distribution, where a few head labels dominate while rare tail labels abound, poses a persistent challenge for large-scale …
arXiv:2602.15332v1 Announce Type: new Abstract: Understanding how language models carry out long-horizon reasoning remains an open challenge. Existing interpretability methods often highlight tokens or spans …