Seunghyun Yoon

Human corrections can directly reshape AI inference in real-time, eliminating the need for separate instructions or records.

LLMs frequently recognize boundary violations yet still generate out-of-character responses, revealing a critical compliance failure in character role-play.

Achieving multi-stage captioning quality in a single-pass model, SimLoss FFT runs 20 times faster while maintaining high precision and recall.

Naju achieves unprecedented long-sequence memory retention and overwriting capabilities, outperforming traditional models while ensuring linear efficiency.

Code-switching in multilingual models reveals a surprising grammar-frame effect that can significantly degrade performance, but a new intervention can effectively mitigate these issues.

LLMs are revolutionizing conversational AI research, and this survey offers a structured guide to navigating the rapidly evolving landscape of LLM-powered user simulation.

LVLMs can generate more factual and detailed image captions at a lower compute cost by reflecting on their past mistakes and systematically attending to overlooked details.

Ditch quadratic attention in your ViTs without sacrificing performance: ViT-AdaLA distills knowledge from pre-trained VFMs into linear attention architectures, achieving state-of-the-art results on classification and segmentation.