2 papers
cs.SD2026
Prompt-Consistency Inference for Zero-Shot Flow-Matching Text-to-Speech Models
Vasily Zadorozhnyy, Can Goksen, Kazuhito Koishida +1
In recent years, flow-matching models have produced significant improvements in zero-shot text-to-speech synthesis. Conditioned on an audio prompt and text, these models learn a ve…
cs.CL2025
Self-reflecting Large Language Models: A Hegelian Dialectical Approach
Sara Abdali, Michael Solodko, Can Goksen +4
In this paper, we introduce a self-reflection framework for Large Language Models (LLMs) grounded in the Hegelian Dialectic, a philosophical method in which an initial proposition…