A Generalisation Signal Need Not Be a Model-Selection Signal
Research
Research News
New papers, breakthroughs and academic AI research
The Row Normalization Puzzle in Muon
Research
PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems
Research
An Empirical Study of Architectural Shift from Traditional to AI-Enabled Simulink Controllers
Research
Sharp Stationary Gaussian Approximation for Constant-Stepsize SGD
Research
Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure
Research
PhysMirror: Physics-Aware Mirror Object Generation
Research
T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement Learning
Research
Prequential E-Values for Selected-GP Near-Optimality Certificates
Research
ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load Control
Research
Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivit
Research
From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs
Research