Tag
The GLM 5.3 Flash model demonstrates a breakthrough in efficiency for browser applications, surpassing previous Pareto optimal trade-offs.
TestNav is a Pareto-guided framework for compositional robustness testing in deep learning models, optimizing for both performance degradation and input fidelity to identify severe yet realistic failures.
This paper introduces a Pareto-guided teacher alignment method for fair personalized text generation, aiming to balance multiple objectives in language model outputs.
This paper proposes PAFO, a Pareto fairness optimization framework to mitigate personalized reward bias in reward models for LLMs, improving accuracy for minority user groups without harming majority groups.