Showing cs.AIShow all
2 papers · 1 filter
cs.AI2024
Truth or Deceit? A Bayesian Decoding Game Enhances Consistency and Reliability
Weitong Zhang, Chengqi Zang, Bernhard Kainz
Large Language Models (LLMs) often produce outputs that -- though plausible -- can lack consistency and reliability, particularly in ambiguous or complex scenarios. Challenges aris…
cs.AI2024
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
Weitong Zhang, Chengqi Zang, Liu Li +3
Inverse problems describe the process of estimating the causal factors from a set of measurements or data. Mapping of often incomplete or degraded data to parameters is ill-posed,…