CACHEFORGE: LLM-Guided End-to-End Generative Cache Replacement Policy for Performance and Hardware Efficiency
Research
Research News
New papers, breakthroughs and academic AI research
Mathematical Invariant-Enabled Topological Neural Networks for Molecular and Materials Property Prediction
Research
Stability of Measure-to-Measure Transformers on Sub-Gaussian Data
Research
The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models
Research
Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks
Research
Nash Social Welfare for Multi Armed Bandits: Trajectory-wise Expected and High Probability Regret
Research
Do I Need the Cloud? Uncertainty-Aware Step-Level Handoff for Small Language Model Agents
Research
High-dimensional online calibration from harmonic weights
Research
Scen-Opt: A Scenario Optimization Toolbox for Data-Driven Convex Programming
Research
Trustworthy Method Comparison with AI Judges: Estimation and Design under Order, Batch, and Aggregation Effects
Research
Stochastic Gradient Descent Ascent is Suboptimal for Nonconvex-PL Min-Max Games
Research
Forecast Accuracy Is Not Trading Profit: Evolving Small Recurrent Networks for Stock Return Prediction
Research