Topic hub

Retrieval-Augmented Models

Covers techniques that combine retrieval and models, including long-term conversational memory, personalization, robustness, and modular model composition.

98 briefs

Retrieval-Augmented Models · Page 3

  1. SAGE unlearning fix: post-hoc sanitization for LLM retentionThe Brieftide
  2. Safety Reflection Pretraining for LLMs, 1.7B model testsThe Brieftide
  3. BeliefDiffusion: diffusion models + MPC for navigationThe Brieftide
  4. Attribution-Guided pruning for MoE: 5.27× memory cut on Qwen3-30BThe Brieftide
  5. CAREATTACK: Conflict-aware retriever edits for RAG attacksThe Brieftide
  6. Sparse Autoencoders: Intervention Failure and Recovery RiskThe Brieftide
  7. Large Language Models: Persona Manifold Collapse and LimitsThe Brieftide
  8. DecoSearch Text-to-SQL (DeepSeek): 88.31% Spider, 70.53% BIRDThe Brieftide
  9. HyGRAG: Hierarchical Graph RAG improves multi-hop reasoning 9.7%The Brieftide
  10. Verbal Reinforcement Learning: Closing the Feedback LoopThe Brieftide
  11. FinAcumen: Financial Multimodal Reasoning Framework PaperThe Brieftide
  12. E3RL: 4B and 8B models beat AIME SOTA by 5.349%/6.514%The Brieftide
  13. FlowRAG: Frequency-Aware Multi-Granularity GraphRAG, arXiv 16 JunThe Brieftide
  14. Fusing Foundation Models and Knowledge Graphs: A RoadmapThe Brieftide
  15. SERAF: Semantics-Enhanced Retrieval for Time Series ForecastingThe Brieftide
  16. Visual-Seeker: visual-native multimodal search surpasses rivalsThe Brieftide
  17. Trust Between AI Agents: measuring formation, breakageThe Brieftide
  18. CONCORD: Sparse Asynchronous Aggregation for Device-Cloud RAGThe Brieftide
  19. Reliability-Aware Inference reduces visual hallucinations in MLLMsThe Brieftide
  20. ChatPlanner: LLM framework for personalized transit routingThe Brieftide
  21. RecurrReason benchmark: Recurrent Reasoning on symbolic puzzlesThe Brieftide
  22. Microsoft Research Mirage: latent spatial memory, 10.57x fasterThe Brieftide
  23. Anthropic and Stanford: why larger LLMs learn rare skillsThe Brieftide
  24. LLM Research Papers 2026 (Jan–May): Curated list and trendsThe Brieftide

Explore related topics