15 posts published in the last hour
- 05:47Plenty of Room in the Middle: Revealing Opportunities on a GPU Cluster via Fine-Grained Monitoring
- 05:47WAKMan: Workload Aware KVCache Manager
- 05:47GPT-6.1 Terra
- 05:46OA-RAG: Ontology-based Agentic RAG for Faithful LLM Reasoning
- 05:46BUZZ HPC Lands $129M Fixed-Rate Credit Facility for Cohere GPU Cluster
- 05:46How Stable Are LLM-Generated Proofs Under Program Refactoring? A Stress Test for Verifiable Code Generation
- 05:46webframe: evaluated as a scraper and a sandbox
- 05:45Executable Archaeology of Programs That Model Programming: Reanimating the Heuristic Compiler (1961) and KBEmacs (1984)
- 05:10AI News Brief Roundup: 2026-10-28 Overnight
- 05:06BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals
- 05:05Spiking Neural Networks Are Harder to Steal: A Benchmark Study of Model Stealing Attacks
- 05:05When Retrieval Is Not Enough: Obsolete Facts in Agent Memory
- 05:05Ontology-guided multi-agent reasoning for explainable differential diagnosis
- 05:05OpenAI announces three big science discoveries and a new way to work with academics
- 05:04A Smart Instant Book Filter Model based on Dual-Objective Optimization