AI
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
Researchers have proposed a new framework called ClientMorpher for federated instruction fine-tuning...
AI
Physics-informed VAE-EVT for Tail Aware Radio Map Prediction
Researchers have developed a new AI framework for predicting radio signal strength in areas where co...
AI
The Benchmark Trap: Structures of Power and Injustice in AI Evaluations
AI benchmarks are not neutral tools of evaluation but rather socio-technical artefacts that shape co...
AI
Incoherent by Design? On the Moral Self-Consistency of LLMs
Researchers have found that large language models (LLMs) often fail to consistently apply moral prin...
AI
UC-PSRO: Utility-Conditioned Policy-Space Response Oracles with a Communication-Dropout Curriculum for Game-Theoretic Course-of-Action Generation in Adversarial Swarms
Researchers have developed a new approach to generating game-theoretically optim...
AI
FedPA-LoRA: Product-Aligned Framework for Mitigating Aggregation and Initialization Errors in Heterogeneous Federated LoRA
Researchers have proposed a new framework called FedPA-LoRA to improve the perfo...
AI
Grounding Healthcare LLMs in a Causal Knowledge Graph: Framework, Metrics, and a Cardiovascular Pilot
Researchers propose a new framework for evaluating large language models in heal...
AI
A concentration result for multilayer feedforward neural networks
Researchers have made a breakthrough in understanding how multilayer feedforward...