Brieftide
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 2
- MKG-RAG-Bench: new benchmark for multimodal KG retrievalThe Brieftide
- PMDformer: Patch-Mean Transformer for Long-Term ForecastingThe Brieftide
- Knowledge-augmented Agentic AI for psychiatric medication infoThe Brieftide
- Generative Retrieval MO-DiT+HPPO: arXiv paper and resultsThe Brieftide
- Estimating Uncertainty in Classifier Performance: LLMsThe Brieftide
- Selective Parametric Consolidation: EVAF, loop-drift benchmarksThe Brieftide
- Causal Reinforcement Learning: arXiv primer by Bareinboim et alThe Brieftide
- TS-RAG: Taxonomic Strategy RAG raises persuasion win rate to 78.5%The Brieftide
- FedEPD: Federated Long-Tailed Graph Learning, 4.97% gainThe Brieftide
- ReMMD: Multilingual Multi-Image Benchmark and Agent ReleaseThe Brieftide
- Causal Caution in LLMs: Suppression in Practical AdviceThe Brieftide
- CompressKV: KV-cache compression keeps 97% with 3%The Brieftide
- MemClaw: Governed Shared Memory for Multi-Agent LLMsThe Brieftide
- Quranic ASR: Wav2Vec2-XLSR-53 hits WER 0.08, beats CitrinetThe Brieftide
- MACR: Explicit Knowledge Conflict Resolution for LLMsThe Brieftide
- ViT-based confidence scoring of student scientific drawingsThe Brieftide
- Selective Verification (Sevra): budget-aware reasoning, benchmarksThe Brieftide
- Negi and Yilmaz: Optimal Scheduling in QA Forums and CapacityThe Brieftide
- Multi-Agent Transactive Memory: shared agent trajectoriesThe Brieftide
- Residual-Space Evolutionary Optimization via Flow ModelsThe Brieftide
- MetaResearcher: Self-Reflective RL for Scalable ResearchThe Brieftide
- REVEAL++: Differentiable retinal vision-language model for AD riskThe Brieftide
- CombEval: Benchmarking combinatorial counting in 11 LLMsThe Brieftide
- User as Engram: Per-user memory edits, arXiv paper 2026 by BojieThe Brieftide