Screening a phone call for fraud needs a trustworthy probability after every caller turn, in milliseconds. Jev-style typed decisions promise exactly that: declared options go in, one calibrated probability per option comes out of a single forward pass, with no generated text. We test an open implementation of this read...
It is found that CD eliminates all structural failures across all models, but content accuracy reveals a persistent semantic gap that is scale-dependent: type coercion failures are fully CD-rescuable, while instruction-semantic failures remain CD-resistant.
Euston is presented, an 8B mathematical claim-verification model trained to resist the all-false composition of the official evaluation sets and the low precision implied at realistic error prevalence, which is principally the all-false composition of the official evaluation sets.
Semantic-Geometric Decoupled Routing is proposed, a training-free block routing framework that shifts semantic aggregation to the pre-RoPE space and reconstructs geometric bias with an offline structural prior and relative block distances and yields an explicit closed-form block routing score without token-level search...
Xin-Wei Long, Wei-Gao Sun, Weibo Gao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Experimental results demonstrate the method outperforms commercial general and medical LLMs and open-source models and human evaluation further supports the quality of the generated guidance and the feasibility of personalized sleep guidance with SLMs.
Yu-Sheng Tan, Run-Ning Zhao, Sofia Angel et al.· 0 citations
We present Apollo Restore, a 24-billion-parameter large language model for restoring lacunae---physical gaps---in fragmentary Ancient Greek texts. Fine-tuned from Mistral Small with a fill-in-the-middle objective, Apollo Restore reconstructs missing spans without requiring oracle knowledge of their length. To our knowl...
Hope McGovern, A. Dolganov, Samuel Belkadi et al.· 0 citations
Pseudo Self-Distillation is presented, a framework that enables small language models to construct hierarchical memory representations by distilling behavior from a strong black-box oracle through a multi-stage training pipeline, with off-policy PSD achieving the strongest results across most conditions.
Pirzada Suhail, Meng-Lin Xia, Xu-Chao Zhang et al.· 0 citations
The experiments show that existing molecular LLMs and strong proprietary models such as GPT-5.2 and Gemini-3-Flash show limited reliability in substituent contribution prediction, and training on MolSC substantially improves this ability and achieves strong performance across diverse downstream molecular tasks.
Hyuntae Park, Sooyeon Kim, J. Park et al.· 0 citations
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, but fine-tuning them with reinforcement learning (RL) remains constrained by the cost of real-world robot interaction. Model-based reinforcement learning (MBRL) reduces this cost by using a learned world model to generate...
Yi-Fei Sheng, Hao-Xiang Ren, Zhi-Long Zhang et al.· 0 citations
Running large language models locally on integrated graphics is now practical, but the community's model-selection advice is dominated by vibes: "just grab a 2B at Q4." This report presents a controlled, single-machine measurement study of twelve model/quantization configurations across three model families (Qwen2.5-1....
D. Zaragoza Rodriguez· Zenodo (CERN European Organi...· 0 citations
Protein secondary structure prediction (PSSP) on the CB513 benchmark [30] has been near a plateau for close to a decade, and many recent models add protein language-model (pLM) representations on top of increasingly elaborate encoders. How much of a reported gain comes from the representation, and how much from the enc...
Afaque Alam, Mukesh Kumar· Zenodo (CERN European Organi...· 0 citations
A planet’s sphere of influence is taken to be one radius. This paper shows that there are three definitions, with exponents 1/3, 2/5 and 1/2──so changing the mass ratio moves the three apart. No new theorem or law is claimed. Scope of this paper (scope note): No new theorem or law is claimed──the Hill radius and Laplac...
Yuuki Yamagishi· Zenodo (CERN European Organi...· 0 citations
