CommentsV1.1 appeared in NeurIPS 2025 main conference; V2 adds GDN experiments, tightens others for a stronger, fairer comparison, and reorganizes sections; V3 adds Result 2.1 and Section 5.2 on how Canon layers improve hierarchical feature learning, from our Jan 2026 talk
KletterMix: Climbing Toward High-Quality German Pretraining Data - The Full Report
KletterMix: 攀登高质量德语预训练数据
Maurice Kraus, Ruben Härle, Sebastian Sztwiertnia, Abbas Goher Khan, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Kristian Kersting
机构
*
AI & ML Group, TU Darmstadt(人工智能与机器学习小组,德累斯顿技术大学)
;
Lab1141
;
Lamarr Institute(拉马尔研究所)
;
Fraunhofer IAIS(弗劳恩霍夫人工智能研究所)
;
hessian.AI(海斯坦.AI)
;
German Research Center for AI (DFKI)(德国人工智能研究中心(DFKI))
;
Centre for Cognitive Science, TU Darmstadt(认知科学中心,德累斯顿技术大学)
Towards Robust Reinforcement Learning for Small-Scale Language Model Agents
迈向用于小规模语言模型智能体的稳健强化学习
Md Rezwanul Haque, Md. Milon Islam, Fakhri Karray
机构
*
University of Waterloo(滑铁卢大学)
;
Khulna University of Engineering & Technology(库尔纳工程技术大学)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
专题命中
指令微调
:language model(title,abstract);SLM(abstract,abstract_cn);SFT(abstract,abstract_cn);small language model(abstract)
Comments18 pages, 7 tables. v2: corrections to the classical sources (Quintilian, Cicero) and to several cited figures, and Appendix B corpus statistics aligned to the delivered dataset; measurements, results and conclusions unchanged. Data, code, and the trained LoRA adapter: https://federicoboggia.binatomy.com/pubblicazioni/
CHARM: A Multimodal Graph Foundation Model with Hierarchical Context Modeling for Zero-Shot Transfer
CHARM:一种用于零样本迁移的具有分层上下文建模的多模态图基础模型
Ankang Yang, Jitao Zhao, Di Jin, Yuxiao Huang, Dongxiao He
机构
*
School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University(天津大学智能与计算学部计算机科学与技术学院)
;
Data Science Program, Columbian College of Arts and Sciences, The George Washington University(乔治华盛顿大学文理学院哥伦比亚艺术与科学学院数据科学项目)
专题命中
指令微调
:foundation model(title,abstract);LLM(abstract,abstract_cn);large language model(abstract);language model(abstract)
Comments73 pages, 13 figures. Version 3 adds a powered and independently replicated Horizon Logic study; within-family and out-of-family recurrent-depth replication; a powered Thinking replication attempt; validated selective-prediction and all-well-formed content-selection conversions; exact-compute loop-allocation and minimal LoRA binding tests; and an expanded evaluation-integrity account
Adding LLMs to the psycholinguistic norming toolbox: A practical guide to getting the most out of human ratings
Javier Conde, María Grandury, Tairan Fu, Carlos Arriaga, Gonzalo Martínez, Thomas Clark, Sean Trott, Clarence Gerald Green, Pedro Reviriego, Marc Brysbaert
专题命中
指令微调
:LLM(abstract);large language model(abstract);language model(abstract);分类 cs.CL