📄 Paper Explainer

All Explained Papers

4176 papers explained. Page 8 of 209. ← Back to home

• arXiv:2410.06992 · explained 2026-08-23
  SWE-Bench+: Enhanced Coding Benchmark for
• arXiv:2509.03531 · explained 2026-08-23
  Real-Time Detection of Hallucinated Entities in Long-Form Generation
• arXiv:2503.12123 · explained 2026-08-23
  MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling
• arXiv:1602.01783 · explained 2026-08-23
  Asynchronous Methods for Deep Reinforcement Learning
• arXiv:1412.6980 · explained 2026-08-23
  Adam: A Method for Stochastic Optimization
• arXiv:2406.03476 · explained 2026-08-23
  Does your data spark joy? Performance gains from domain
• arXiv:2005.11401 · explained 2026-08-23
  Retrieval-Augmented Generation for
• arXiv:2309.17179 · explained 2026-08-23
  AlphaZero-Like Tree-Search can Guide Large Language Model Decoding and Training
• arXiv:2310.02226 · explained 2026-08-23
  Published as a conference paper at ICLR 2024
• arXiv:2505.16022 · explained 2026-08-23
  NOVER: Incentive Training for Language Models via Verifier-Free Reinforcement Learning
• arXiv:2401.09379 · explained 2026-08-23
  Merging uncertainty sets via majority vote
• arXiv:2508.20453 · explained 2026-08-23
  MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers
• arXiv:2410.10813 · explained 2026-08-22
  Published as a conference paper at ICLR 2025
• arXiv:1606.02396 · explained 2026-08-22
  Deep Successor Reinforcement Learning
• arXiv:1606.05312 · explained 2026-08-22
  Successor Features for
• arXiv:1207.4708 · explained 2026-08-22
  The Arcade Learning Environment:
• arXiv:2512.22087 · explained 2026-08-22
  Context as a Tool: Context Management for Long-Horizon SWE-Agents
• arXiv:2410.13229 · explained 2026-08-22
  Quamba: A Post-Training Quantization Recipe for Selective State
• arXiv:1706.1970 · explained 2026-08-22
  ORTOEDRES AMB LONGITUD D’ARESTES ENTERES
• arXiv:2302.04166 · explained 2026-08-22
  GPTScore: Evaluate as You Desire