📄 Paper Explainer

All Explained Papers

4342 papers explained. Page 6 of 218. ← Back to home

• arXiv:2609.38016 · explained 2026-10-02
  Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy
• arXiv:2609.38006 · explained 2026-10-02
  HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model Deployment
• arXiv:2609.37991 · explained 2026-10-01
  Which Attention Heads are like the Human Head? Not the Ones that Compute
• arXiv:2609.38142 · explained 2026-10-01
  AdviSD: Learning to Advise Frontier LLMs via Targeted Multi-Turn Self-Distillation
• arXiv:2609.31184 · explained 2026-09-29
  Accounting for Bias Enables Sustainable LLM Evaluation
• arXiv:2609.31354 · explained 2026-09-29
  Mutable Transcripts: Mitigating Context Pollution through Editable Conversation State
• arXiv:2609.31568 · explained 2026-09-29
  DeepEdu-v1: Efficient and Scalable Agentic LLMs for Vietnamese Education
• arXiv:2609.31214 · explained 2026-09-29
  Which Influence Are We Estimating? The Role of Counterfactual Specifications in Data Attribution
• arXiv:2609.31167 · explained 2026-09-29
  Neural State Prediction: Obstructing Shortcut Learning in EEG Foundation Models
• arXiv:2609.31563 · explained 2026-09-29
  Multi-agent Scaling Across Disjunctive and Compensatory Tasks
• arXiv:2609.31201 · explained 2026-09-28
  Samples, Sources, Space: Decomposing Data Scale in Spatially Structured Representation Learning of Human Brain Microarchitecture
• arXiv:2609.31235 · explained 2026-09-28
  Purin: A Biology-inspired Mechanism for Artificial Neural Networks
• arXiv:2609.31430 · explained 2026-09-28
  Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents
• arXiv:2609.26160 · explained 2026-09-28
  The Free-Recipe Limit: Every Recipe Effect Measures Which Premise of an Idealised Learner Broke
• arXiv:2609.26279 · explained 2026-09-27
  FISSION: Label Augmentation for Bot Detection
• arXiv:2609.26642 · explained 2026-09-27
  The Delegation Blind Spot: Auditing Product Decisions from Agent Choices
• arXiv:2609.26293 · explained 2026-09-27
  Dual-Frontier: When Can an Agent Trust Its World Model?
• arXiv:2609.20754 · explained 2026-09-26
  RAFT: A Stateful Retrieval-Augmented Framework for Troubleshooting Agents
• arXiv:2609.20455 · explained 2026-09-26
  GraphSkillAA: Attribution-Guided Skill-Graph Updating with Targeted Validation and Rollback
• arXiv:2609.20581 · explained 2026-09-26
  Limits of Confidence in Diffusion