Goto

Collaborating Authors

 Europe






Explainable and Efficient Randomized Voting Rules

Neural Information Processing Systems

With a rapid growth in the deployment of AI tools for making critical decisions (or aiding humans in doing so), there is a growing demand to be able to explain to the stakeholders how these tools arrive at a decision.




ExtrapolationandSpectralBiasofNeuralNetswith HadamardProduct:aPolynomialNetStudy

Neural Information Processing Systems

Weprovetheir equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK. Based on our results, we elucidate the separation ofPNNs overstandard neural networks with respect toextrapolation andspectralbias.


ExtrapolationandSpectralBiasofNeuralNetswith HadamardProduct:aPolynomialNetStudy

Neural Information Processing Systems

Weprovetheir equivalence to the kernel regression predictor with the associated NTK, which expands the application scope of NTK. Based on our results, we elucidate the separation ofPNNs overstandard neural networks with respect toextrapolation andspectralbias.


Adaptive Image Quality Assessment via Teaching Large Multimodal Model to Compare

Neural Information Processing Systems

While recent advancements in large multimodal models (LMMs) have significantly improved their abilities in image quality assessment (IQA) relying on absolute quality rating, how to transfer reliable relative quality comparison outputs to continuous perceptual quality scores remains largely unexplored.