Brieftide
Topic hub
Model Serving Systems
Covers algorithms and systems for routing, scheduling, and optimization of inference workloads and multi-agent request flows for large models.
71 briefs
Model Serving Systems · Page 2
- Hierarchical Multi-Agent RL: Constraint Manifold ControlThe Brieftide
- Large Language Models scaling exponents: Succi & Coveney arXivThe Brieftide
- Amazon Bedrock AgentCore: Pool model multi‑tenancy patternsThe Brieftide
- Agentic AI and NVIDIA: Building Autonomous Telco NetworksThe Brieftide
- Black-Box Uncertainty Estimation for LLMs: 24-method BenchmarkThe Brieftide
- ViT-based confidence scoring of student scientific drawingsThe Brieftide
- Negi and Yilmaz: Optimal Scheduling in QA Forums and CapacityThe Brieftide
- MetaResearcher: Self-Reflective RL for Scalable ResearchThe Brieftide
- PROPEL: Training Task Generators at the Learnable FrontierThe Brieftide
- ARIADNE adapter routing for PEFT, recovers 97.44% on Llama 3.2 1BThe Brieftide
- Shock-wave Theory and Symmetry-reduced SGD, Miyagawa 2026The Brieftide
- LLM Agents for 6G: Mitigating Anchoring Bias, 25% Energy SavingsThe Brieftide
- R2D-RL: RoboCup 2D Soccer RL environment and benchmarkThe Brieftide
- DecoSearch Text-to-SQL (DeepSeek): 88.31% Spider, 70.53% BIRDThe Brieftide
- DivInit improves agentic search on multi-hop QA by 5-7 pointsThe Brieftide
- EComAgentBench: 662-task shopping agent benchmark with hiddenThe Brieftide
- Learn to Cluster: Quantifying Pedestrian Social Interaction (2026)The Brieftide
- Neurosymbolic inference gets a homotopy-type-theoretic liftThe Brieftide
- Dissecting model behavior: SSA paper, 138k trajectoriesThe Brieftide
- LLMs as Optimizers: Direct vs Tool-Augmented vs Tool-CreatingThe Brieftide
- Cattle identification: ML and deep learning review (2026)The Brieftide
- ChatPlanner: LLM framework for personalized transit routingThe Brieftide
- S1-DeepResearch-32B: state-of-the-art on 20 research benchmarksThe Brieftide
- PyTorch profiling: nn.Linear to a fused MLP, traces and kernelsThe Brieftide