diffusion models 1sign language synthesis 1single-gpu training 1spatiotemporal attention 1text-to-video generation 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
Text2Sign: A Single-GPU Diffusion Baseline for Text-to-Sign Language Video Generation
Ruize Xia
The paper introduces Text2Sign, a diffusion-based model that generates short, low‑resolution sign‑language video clips from text using a single GPU by leveraging a frozen vision‑la…
cs.LG2026
Matched-Learning-Rate Analysis of Attention Drift and Transfer Retention in Fine-Tuned CLIP
Ruize Xia
CLIP adaptation can improve in-domain accuracy while degrading out-of-domain transfer, but comparisons between Full Fine-Tuning (Full FT) and LoRA are often confounded by different…