Research Papers
Attention Heatmap Drift in a Contrastively Pretrained Vision–Language Model: A Controlled Matched-Learning-Rate Comparison of Full Fine-Tuning and Low-Rank Adaptation featured image

Attention Heatmap Drift in a Contrastively Pretrained Vision–Language Model: A Controlled Matched-Learning-Rate Comparison of Full Fine-Tuning and Low-Rank Adaptation

A controlled matched-learning-rate study of CLIP attention heatmap drift under full fine-tuning and low-rank adaptation.

avatar
Ruize Xia
Read more
Real-Time On-Device Diffusion: Practical Acceleration via Fused Low-Bit Kernels featured image

Real-Time On-Device Diffusion: Practical Acceleration via Fused Low-Bit Kernels

A systems paper on accelerating diffusion inference with fused low-bit kernels and cache-update fusion.

avatar
Ruize Xia
Read more

Value-Aligned Evaluation for Everyday AI

A framework for evaluating AI by explanation, contestability, accessibility, and fit—not just accuracy.

avatar
Ruize Xia
Read more

Human Judgment in the Loop

Why meaningful human oversight requires more than rubber-stamping machine output.

avatar
Ruize Xia
Read more
Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation featured image

Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation

An IEEE Access article on a single-GPU diffusion baseline for text-to-sign language video generation.

avatar
Ruize Xia
Read more