SCRN 🏳️‍⚧️ (@SCRNinVR) header
SCRN 🏳️‍⚧️ (@SCRNinVR) profile picture

I make shadurs with a 'u', and I also do ML stuff. https://teapawt.net/t.co/F1iLxFROjf https://teapawt.net/t.co/HZcpV1omv4

In a Treehouse
Joined June 2020
Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)Photo by SCRN 🏳️‍⚧️ (@SCRNinVR)
SCRN 🏳️‍⚧️ retweeted
IT'S FINALLY HERE! AudioOrbs v2.0! This has been a long time coming! Sorry for keeping you all waiting for so long, but there's LOTS of new stuff! The big feature this time is Themes! Chose between many themes that change the environment and effects! #VRChat #VRChat_world
22
172
6
1,356
157,111
SCRN 🏳️‍⚧️ retweeted
Remember this meme from 2022 which contrasted DALL·E “mini” against DALL·E 2? We’re going to see the same thing now for large language model: Community-developed LLMs, some without any forced ‘alignment’ or ‘moralizing’ censorship, vs closed mainstream LLMs run by big companies.
11
35
6
264
43,256
SCRN 🏳️‍⚧️ retweeted
Scaling Transformer to 1M tokens and beyond with RMT Recurrent Memory Transformer retains information across up to 2 million tokens. During inference, the model effectively utilized memory for up to 4,096 segments with a total length of 2,048,000 tokens—significantly exceeding the largest input size reported for transformer models (64K tokens for CoLT5 (Ainslie et al., 2023), and 32K tokens for GPT-4 (OpenAI, 2023)). This augmentation maintains the base model’s memory size at 3.6 GB in our experiments abs: arxiv.org/abs/2304.11062 github: github.com/booydar/t5-experi…
89
737
316
3,165
1,722,888
SCRN 🏳️‍⚧️ retweeted
idk why everybody is freaking out. just tell it to smoke some weed
396
4,086
273
42,427
1,979,436
SCRN 🏳️‍⚧️ retweeted
I am releasing version 2.0.0 of my optimizer. Now VPM & UPM compatible! Additionally it merges simple toggles in the fx layer into one big direct blend tree. There is also improved merging of blendshapes that get animated in a fixed ratio to each other.
2
10
1
64
9,550
SCRN 🏳️‍⚧️ retweeted
My Lighthouse in the Snow world is finally out! Enjoy a serene experience with music and raymarchers. Available on PC and Quest! World link in replies #VRChat #unity3d #shaders
7
29
1
158
10,396
SCRN 🏳️‍⚧️ retweeted
How neat. Researchers claim to have found, at long last, an "einstein" tile - a shape that tiles the plane in a pattern that never repeats. First two authors appear to have no academic affiliations. arxiv.org/abs/2303.10798
102
954
203
6,501
1,121,213
SCRN 🏳️‍⚧️ retweeted
Presenting Long Suffering by @ElIZAGRACEMUSIC This is one of my favorite songs. I loved making this performance with the help of @TheHoizen and cinematography by @Depereo_ This song is a strong emotional one. I hope I conveyed those feelings through this youtube.com/watch?v=-lXEY52i…
3
10
1
30
6,648
SCRN 🏳️‍⚧️ retweeted
Not cool, @OpenAI 🙃
14
78
16
863
107,581
SCRN 🏳️‍⚧️ retweeted
page 37 of the GPT-4 paper: cdn.openai.com/papers/gpt-4.…
36
329
51
2,093
324,350
SCRN 🏳️‍⚧️ retweeted
Announcing GPT-4, a large multimodal model, with our best-ever results on capabilities and alignment: openai.com/product/gpt-4
2,004
15,920
5,348
59,563
12,483,970
SCRN 🏳️‍⚧️ retweeted
Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models build a system called Visual ChatGPT, incorporating different Visual Foundation Models, to enable the user to interact with ChatGPT by 1) sending and receiving not only languages but also images 2) providing complex visual questions or visual editing instructions that require the collaboration of multiple AI models with multi-steps. 3) providing feedback and asking for corrected results abs: arxiv.org/abs/2303.04671
14
226
24
952
251,554
Today we release LLaMA, 4 foundation models ranging from 7B to 65B parameters. LLaMA-13B outperforms OPT and GPT-3 175B on most benchmarks. LLaMA-65B is competitive with Chinchilla 70B and PaLM 540B. The weights for all models are open and available at research.facebook.com/public… 1/n
148
1,332
339
6,469
3,227,930
SCRN 🏳️‍⚧️ retweeted
Version 1.10 of my optimizer is out. This release has some improvements to the generated mesh VRAM size. (expect 0-20% reduction) It also improves how I handle material property animations and material swaps. github.com/d4rkc0d3r/d4rkAva…
2
13
90
5,070
SCRN 🏳️‍⚧️ retweeted
The all new v6 of my shader package is out! Many bug fixes, totally reworked UI. A Toon shader and much more! Check it out right here: github.com/orels1/orels-Unit…
12
44
2,973
SCRN 🏳️‍⚧️ retweeted
Anyone likes bowling? Still plenty of work to be done, but super happy with the results so far! #VRChat #unity3d
10
27
2
196
13,024
SCRN 🏳️‍⚧️ retweeted
SmartObjectSync 1.0 - Drop-in replacement for VRC_ObjectSync Red is VRChat's Object Sync. Green is mine. The goal is to have less glitchiness in physics interactions without expensive update loops github.com/MMMaellon/SmartOb…
25
388
18
1,625
122,933
SCRN 🏳️‍⚧️ retweeted
The answer to solving the problem of sexual orientation is too use sexual quaternions. Unfortunately no one understands them.
13
44
3
537
46,091
SCRN 🏳️‍⚧️ retweeted
Mastering Diverse Domains through World Models abs: arxiv.org/abs/2301.04104 project page: danijar.com/project/dreamerv…
3
77
11
350
123,309