Could somebody can help endorse me for arXiv?

https://arxiv.org/auth/endorse?x=NFZ4KD

I wrote a paper for GPU assisted LLM BPE offloading https://github.com/99degree/gpu_assisted_bpe/blob/utf/TableBPE.xml

I also wrote a paper to unify camera lens LSC and GDC by same grip map so the gain and GDC displacement can be obtain from same polynormial. https://github.com/99degree/99degree/blob/main/lsc_displacement_map.pdf And the approximation is as following. https://github.com/99degree/99degree/blob/main/lsc_displacement_map_approx.pdf

This is 99degree profile page. Please find it useful.

Technical Innovation Essay: FILM_INNOVATION.md | Essay PDF: FILM_INNOVATION.pdf

Boosted Sub-Glyph Histograms Essay: BOOSTED_SUBGLYPH_HISTOGRAMS.md | Essay PDF: BOOSTED_SUBGLYPH_HISTOGRAMS.pdf

FiLM + Low-Light Essay: FILM_LOW_LIGHT_ESSAY.md | Essay PDF: FILM_LOW_LIGHT_ESSAY.pdf

Formal Paper Draft: FILM_ISP_PAPER.md | Paper PDF: FILM_ISP_PAPER.pdf

A novel architectural approach for skin-tone-aware Image Signal Processor (ISP) parameter prediction using Feature-wise Linear Modulation (FiLM). Unlike existing methods that rely on explicit face detection or demographic classification, our method conditions the entire ISP parameter prediction network on a continuous skin-tone estimate derived directly from full-frame histogram statistics. The result is a single ONNX model that adapts its WB, CCM, tone curve, and zoom predictions per frame based on estimated scene skin tone—without face detection, demographic labels, or discrete expert switching.