📄 Paper Explainer

All Explained Papers · cs.AI

382 papers in cs.AI. Page 3 of 20. ← Back to home

• arXiv:2605.14790 · cs.CL+1 · submitted 2026-05-14 · explained 2026-05-20
  Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation
  Songyang Gao, Yinghui Xia, Siyi Liu, et al.
• arXiv:2605.15000 · cs.CL+1 · submitted 2026-05-14 · explained 2026-05-20
  Quantifying and Mitigating Premature Closure in Frontier LLMs
  Rebecca Handler, Suhana Bedi, Nigam Shah
• arXiv:2605.15016 · cs.CL+1 · submitted 2026-05-14 · explained 2026-05-17
  COTCAgent: Preventive Consultation via Probabilistic Chain-of-Thought Completion
  Zihan Deng, Xiaozhen Zhong, Chuanzhi Xu
• arXiv:2605.15034 · cs.CL+3 · submitted 2026-05-14 · explained 2026-05-17
  AI Knows When It's Being Watched: Functional Strategic Action and Contextual Register Modulation in Large Language Models
  Vinicius Covas, Jorge Alberto Hidalgo Toledo
• arXiv:2605.15077 · cs.CL+2 · submitted 2026-05-14 · explained 2026-05-17
  Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs
  Guangyu Feng, Huanzhi Mao, Prabal Dutta, et al.
• arXiv:2605.15081 · cs.CL+1 · submitted 2026-05-14 · explained 2026-05-17
  ML-Embed: Inclusive and Efficient Embeddings for a Multilingual World
  Ziyin Zhang, Zihan Liao, Hang Yu, et al.
• arXiv:2605.15102 · cs.CL+1 · submitted 2026-05-14 · explained 2026-05-17
  Improving Multi-turn Dialogue Consistency with Self-Recall Thinking
  Renning Pang, Tian Lan, Leyuan Liu, et al.
• arXiv:2605.15156 · cs.CL+2 · submitted 2026-05-14 · explained 2026-05-17
  MeMo: Memory as a Model
  Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, et al.
• arXiv:2605.15168 · cs.CL+3 · submitted 2026-05-14 · explained 2026-05-17
  Text Knows What, Tables Know When: Clinical Timeline Reconstruction via Retrieval-Augmented Multimodal Alignment
  Sayantan Kumar, Shahriar Noroozizadeh, Juyong Kim, et al.
• arXiv:2605.14764 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  Compositional Sparsity as an Inductive Bias for Neural Architecture Design
  Hongyu Lin, Antonio Briola, Yuanrong Wang, et al.
• arXiv:2605.14773 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
  Suorong Yang, Hanqi Zhu, Hai Gan, et al.
• arXiv:2605.14841 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  GPart: End-to-End Isometric Fine-Tuning via Global Parameter Partitioning
  Paolo Mandica, Michał Brzozowski, Zuzanna Dubanowska, et al.
• arXiv:2605.14844 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  XFP: Quality-Targeted Adaptive Codebook Quantization with Sparse Outlier Separation for LLM Inference
  Thomas Witt
• arXiv:2605.14855 · cs.LG+2 · submitted 2026-05-14 · explained 2026-05-17
  Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers This work has been carried out within the DARCII project, funding code 50NA2401, sponsored by the German Federal Ministry for Economic Affairs and Climate Action (BMWK) and supported by the German Aerospace Center (DLR), the Bundesnetzagentur (BNetzA), and the Federal Agency for Cartography and Geodesy (BKG). This work was also supported by the Bavarian Ministry for Economic Affairs, Infrastructure, Transport and Technology through the Center for Analytics Data Applications (ADA-Center) within the framework of ``BAYERN DIGITAL II'' (20-3410-2-9-8).
  Lukas Schelenz, Shobha Rajanna, Denis Gosalci, et al.
• arXiv:2605.14867 · cs.LG+2 · submitted 2026-05-14 · explained 2026-05-17
  REALM: Retrospective Encoder Alignment for LFP Modeling
  Peicheng Wu, Zhenyu Bu, Runze Ma, et al.
• arXiv:2605.14897 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  Critic-Driven Voronoi-Quantization for Distilling Deep RL Policies to Explainable Models
  Senne Deproost, Denis Steckelmacher, Ann Nowé
• arXiv:2605.14937 · cs.LG+2 · submitted 2026-05-14 · explained 2026-05-17
  Goal-Conditioned Model Predictive Control with Object-Centric Representations
  Jonathan Spieler, Angel Villar-Corrales, Sven Behnke
• arXiv:2605.14940 · cs.LG+2 · submitted 2026-05-14 · explained 2026-05-17
  Not All Symbols Are Equal: Importance-Aware Constellation Design for Semantic Communication-4mm
  Albert Shaju, Christo Kurisummoottil Thomas, Mayukh Roy Chowdhury
• arXiv:2605.14982 · cs.LG+1 · submitted 2026-05-14 · explained 2026-05-17
  Second-Order Actor-Critic Methods for Discounted MDPs via Policy Hessian Decomposition
  Sanjeev Manivannan, Shuban V
• arXiv:2605.15012 · cs.LG+2 · submitted 2026-05-14 · explained 2026-05-17
  Boosting Reinforcement Learning with Verifiable Rewards via Randomly Selected Few-Shot Guidance
  Kai Yan, Alexander G. Schwing, Yu-Xiong Wang