Abstract

用途と対象者

公式サイトと情報源

関連特集

• LowRAM: Low-Rank Keys and Amortised Values for Composable KV Cache Compression at Test-Time2026-11-06
• Not All Loops Cost the Same: Phase-Dependent Depth for Serving Looped Transformers2026-11-06
• NUMA-Torch: Compiler-Driven NUMA-Aware LLM Prefill on Multi-Socket CPUs2026-11-06
• ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction2026-11-06
• Selective, Risk-Controlled Emotion Forecasting in Conversation: From a Persistence Barrier to Departure Detection with Conformal Guarantees2026-11-06
• The Two-Ledger Model: Transaction-Grain Cost Accounting for Multi-Agent AI Systems Across Clouds, Models, and Systems of Record2026-11-06
• Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity2026-11-06
• Uncertainty calibration in Bayesian M/EEG source imaging2026-11-06
• When Every Choice Is Correct: A Causal Study of Numerical Preference in Language Models2026-11-06
• A Controlled Experimental Evaluation of Configuration and Cache Architecture in LLM Serving Engines2026-11-05