PXAI Audio Feed
31/03 15:15 dev.to

Distributed LLM Inference Across NVIDIA Blackwell and Apple Silicon Over 10GbE

distributed inferenceheterogeneous GPUs10GbENVIDIA BlackwellApple Siliconlarge language model
31/03 10:12 dev.to

Generative AI and Non-Determinism

generative AInon‑determinismlarge language modelcomputation theorycreativitypredictability
31/03 07:00 arxiv.org

Robust Batch-Level Query Routing for Large Language Models under Cost and Capacity Constraints

batch routinglarge language modelsresource‑awarecost optimizationrobustnessGPU constraints
31/03 07:00 arxiv.org

When Verification Hurts: Asymmetric Effects of Multi-Agent Feedback in Logic Proof Tutoring

logic tutoringlarge language modelsstep‑level feedbackknowledge graphsymbolic reasoningbenchmark
31/03 07:00 arxiv.org

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

vision‑language modelssemantic hierarchyCLIPagglomerative clusteringontology alignmentexplainable AI
31/03 07:00 arxiv.org

MediHive: A Decentralized Agent Collective for Medical Reasoning

MediHivedecentralized multi‑agent systemmedical reasoninglarge language modelshealthcare AIuncertainty management
31/03 06:08 dev.to

How I Designed a Camera Scoring System for VLM-Based Activity Recognition — and Why It Looks Different in the Real World

camera selectionvision‑language modelactivity recognitionroboticsalgorithm designviewpoint scoring
31/03 04:23 github.com

Universal Claude.md – cut Claude output tokens by 63%

Claudetoken reductionprompt engineeringAI efficiencyoutput optimizationcost savings
31/03 02:10 dev.to

Quantization — Deep Dive + Problem: Smallest Window Containing All Features

quantizationlarge language modelsdeployment optimizationmemory efficiencycomputational efficiencyinteger precision
31/03 02:10 dev.to

Quantization — Deep Dive + Problem: Smallest Window Containing All Features

quantizationlarge language modelsdeployment optimizationmemory efficiencycomputational efficiencyinteger precision
Comments
Loading...
0