Quality follows upgrading
All Articles
arXiv:2603.13359v1 Announce Type: new Abstract: Language models are commonly fine-tuned for safety alignment to refuse harmful prompts. One approach fine-tunes them to generate categorical refusal …
arXiv:2603.13236v1 Announce Type: new Abstract: AI-related incidents are becoming increasingly frequent and severe, ranging from safety failures to misuse by malicious actors. In such complex …
arXiv:2603.13260v1 Announce Type: new Abstract: Knowledge Distillation (KD) can transfer the reasoning abilities of large models to smaller ones, which can reduce the costs to …
arXiv:2603.13256v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems enable complex, long-horizon reasoning by composing specialized agents, but practical deployment remains hindered by …
arXiv:2603.13344v1 Announce Type: new Abstract: The prevailing paradigm in Automated Heuristic Design (AHD) typically relies on the assumption that a single, fixed algorithm can effectively …
arXiv:2603.13252v1 Announce Type: new Abstract: Cross-sectional ranking models are often deployed as if point predictions were sufficient: the model outputs scores and the portfolio follows …
arXiv:2603.13956v1 Announce Type: new Abstract: Automated radiology report generation holds immense potential to alleviate the heavy workload of radiologists. Despite the formidable vision-language capabilities of …
arXiv:2603.13574v1 Announce Type: new Abstract: This paper presents a Probabilistic State Algebra as an extension of deterministic propositional logic, providing a computational framework for constructing …
arXiv:2603.13243v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate text via iterative denoising but consistently underperform on multi-step reasoning. We hypothesize this gap …
arXiv:2603.13594v1 Announce Type: new Abstract: Large language models are shifting from passive information providers to active agents intended for complex workflows. However, their deployment as …
arXiv:2603.13257v1 Announce Type: new Abstract: Deep Reinforcement Learning (DRL) agents achieve remarkable performance in continuous control but remain opaque, hindering deployment in safety-critical domains. Existing …
arXiv:2603.13452v1 Announce Type: new Abstract: Research about bias in machine learning has mostly focused on outcome-oriented fairness metrics (e.g., equalized odds) and on a single …