Improving Open-Set Text Classification with Uncertainty Estimation
Discover how uncertainty estimation enhances accuracy and reliability in open-set text classification systems using the HolUE method.
Medical Reasoning with Large Language Models: Survey & MR-Bench
Explore how large language models enhance medical reasoning with MR-Bench, bridging gaps in clinical AI decision-making for safer healthcare.
WAND: Efficient Windowed Attention for Text-to-Speech
Discover WAND, a novel method using windowed attention and knowledge distillation to boost efficiency in autoregressive text-to-speech models.
Exploiting Denoising Flaws in Diffusion Language Models
Discover how denoising irreversibility exposes vulnerabilities in diffusion language models and explore strategies to enhance AI safety and robustness.
EMA Limits in Sequence Models: Balancing Structure & Content
Explore EMA's role and limits in sequence models, revealing the need for input-dependent selection to improve temporal structure encoding and reduce inform...