📄 Paper Explainer

All Explained Papers · cs.AI

2114 papers in cs.AI. Page 1 of 106. ← Back to home

• arXiv:2607.08780 · cs.LG+2 · submitted 2026-06-12 · explained 2026-08-20
  Sticky Routing: Training MoE Models for Memory-Efficient Inference
  Ali Kayyam
• arXiv:2605.19633 · cs.CL+4 · submitted 2026-05-19 · explained 2026-08-20
  optimize_anything: A Universal API for any Text Parameter
  Lakshya A Agrawal, Donghyun Lee, Shangyin Tan, et al.
• arXiv:2605.16727 · cs.AI · submitted 2026-05-16 · explained 2026-08-20
  PopuLoRA: Co-Evolving LLM Populations for Reasoning Self-Play
  Roger Creus Castanyer, Geoffrey Bradway, Lorenz Wolf, et al.
• arXiv:2605.07209 · cs.CL+2 · submitted 2026-05-08 · explained 2026-08-20
  Hallucination Detection via Activations of Open-Weight Proxy Analyzers
  Akshita Singh, Prabesh Paudel, Siddhartha Roy
• arXiv:2604.15400 · cs.LG+2 · submitted 2026-04-16 · explained 2026-08-20
  Hallucination as Trajectory Commitment: Evidence for Asymmetric Attractor Dynamics Transformer Generation
  G. Aytug Akarlar
• arXiv:2603.26130 · cs.SE+1 · submitted 2026-03-27 · explained 2026-08-20
  Benchmarking AI Code Review Quality[6pt] Against Pull Request Feedback
  Deepak Kumar
• arXiv:2603.18161 · cs.CL+1 · submitted 2026-03-18 · explained 2026-08-20
  How LLMs Distort Our Written Language
  Marwa Abdulhai, Isadora White, Yanming Wan, et al.
• arXiv:2603.15377 · cs.LG+1 · submitted 2026-03-16 · explained 2026-08-20
  More Test-Time Compute Can Hurt: Overestimation Bias in LLM Beam Search
  Gal Dalal, Assaf Hallak, Gal Chechik, et al.
• arXiv:2603.06114 · cs.CL+1 · submitted 2026-03-06 · explained 2026-08-20
  Making Implicit Premises Explicit in Logical Understanding of Enthymemes
  Xuyao Feng, Anthony Hunter
• arXiv:2602.11081 · cs.CL+2 · submitted 2026-02-11 · explained 2026-08-20
  SteuerLLM: Local specialized large language
  Sebastian Wind, Jeta Sopa, Laurin Schmid, et al.
• arXiv:2512.04797 · cs.AI+1 · submitted 2025-12-04 · explained 2026-08-20
  SIMA 2: A Generalist Embodied Agent for Virtual Worlds
  SIMA team, Adrian Bolton, Alexander Lerchner, et al.
• arXiv:2511.00405 · cs.LG+1 · submitted 2025-11-01 · explained 2026-08-20
  UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings
  Zhibin Lan, Liqiang Niu, Fandong Meng, et al.
• arXiv:2510.23941 · cs.CL+1 · submitted 2025-10-27 · explained 2026-08-20
  Auto prompting without training labels: An LLM cascade for product quality assessment in e-commerce catalogs
  Soham Satyadharma, Fatemeh Sheikholeslami, Swati Kaul, et al.
• arXiv:2510.06499 · cs.CL+1 · submitted 2025-10-07 · explained 2026-08-20
  Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels
  Zhepeng Cen, Haolin Chen, Shiyu Wang, et al.
• arXiv:2510.05014 · cs.AI+1 · submitted 2025-10-06 · explained 2026-08-20
  Think Then Embed: Generative Context Improves Multimodal Embedding
  Xuanming Cui, Jianpeng Cheng, Hong-you Chen, et al.
• arXiv:2509.24086 · cs.AI+1 · submitted 2025-09-28 · explained 2026-08-20
  Do Repetitions Matter? Strengthening Reliability in LLM Evaluations Citation: Authors. Title. Pages.... DOI:000000/11111.
  Miguel Angel Alvarado Gonzalez, Michelle Bruno Hernandez, Miguel Angel Peñaloza Perez, et al.
• arXiv:2508.18124 · cs.LG+1 · submitted 2025-08-25 · explained 2026-08-20
  CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics
  Weida Wang, Dongchen Huang, Jiatong Li, et al.
• arXiv:2507.01352 · cs.CL+2 · submitted 2025-07-02 · explained 2026-08-20
  Skywork-Reward-V2: Scaling Preference Data via Human-AI Synergy
  Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao, et al.
• arXiv:2506.17748 · cs.CL+1 · submitted 2025-06-21 · explained 2026-08-20
  ~and Seek: Detecting Hallucinations in Language Models via Decoupled Representations
  Anwoy Chatterjee, Yash Goel, Tanmoy Chakraborty
• arXiv:2505.24622 · cs.AI+1 · submitted 2025-05-30 · explained 2026-08-20
  Random Rule Forest (RRF): Interpretable and Manageable Ensembles of LLM-Generated Questions for Predicting Success from Unstructured Data
  Ben Griffin, Aaron Ontoyin Yin, Diego Vidaurre, et al.