Channel
@vlivashkin_reads
On this record: Growth · Engagement · What this channel posts · Reactions · Posts · Citations · Cite this entry
80subscribers
+0 since we began measuring on 6 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1001464440773 |
|---|---|
| Type | Channel |
| Username | @vlivashkin_reads |
| Description | Читаю и пересказываю пейперы. ЛС: @vlivashkin |
| Created | Between 1 April 2019 and 31 October 2021 — estimated from Telegram’s id allocation, not measured. How this range is calculated. |
| First recorded | 9 August 2026 |
| Last confirmed live | 12 September 2026 |
| Measurements held | 2 |
| On Telegram | t.me/vlivashkin_reads |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 9 Aug 2026, 19:01 | 80 | no change |
| 6 Aug 2026, 22:41 | 80 | first reading |
15 posts held, back to 12 December 2022 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 page of Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 15 posts for this entry, the most recent from 16 September 2024. An engagement rate over an empty window would be a number about nothing.
Lifetime counters from Telegram’s own channel header, read 9 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
20 reactions across 6 posts, in 4 distinct kinds. The most used accounts for 60.0% of them.
| Reaction | Count | Share | Share, drawn |
|---|---|---|---|
| 👍 | 12 | 60.0% | |
| 🔥 | 6 | 30.0% | |
| 👀 | 1 | 5.00% | |
| 🤪 | 1 | 5.00% |
No sentiment is inferred, and none should be read in. This table is ordered by count and by nothing else. Emoji do not carry stable meaning across languages or communities — 🙏 is thanks in one channel and mourning in another — so we publish which ones were pressed and how often, and pass no judgement on what an audience meant by them.
Precision. Telegram publishes reaction counts per emoji and short-forms each one — 4.34K, 1.2M — so any single kind at or above 1,000 reaches us at three significant figures, and only counts below 1,000 are exact. The shares above are ratios of those figures and carry the same error. This is also why the total here can differ slightly from a reaction total printed elsewhere on the page: both are sums of the same rounded parts, taken over samples with different edges.
Coverage. Reactions were read on 6 of the 15 sampled posts in this sample. Summed by Telegram’s own count on each post — not by adding up the per-emoji breakdown above — those same posts carry 20 reactions in total: the kind of figure the paragraph above means by “a reaction total printed elsewhere on the page”.
Measured over the 15 most recent posts we hold, published 12 December 2022 to 16 September 2024, using the newest reading held for each. Telegram Stars are excluded: they are a payment, not a reaction, and they have their own section.
Ого уже месяц прошел) Сори, выпал из-за переезда + меня повело в сторону разбора вещей из чемодана ахаха я убью себя В общем в этот раз будет не продолжение по диффузионкам, а внезапно GAN Face Animation Models. Поразительно, какую живучую архитектуру придумали в MonkeyNet, что она сохранилась до наших дней только с точечными улучшениями прямо как архитектура таунхаусов в Англии GAN Face Animation Models MonkeyNet, …
🔥4🤪1
Diffusion Models Part 5: Video Diffusion Models VDM, Gen-1, AnimateDiff, SparseCtrl https://telegra.ph/Diffusion-Models-Part-5-Video-Generation-08-13
👍1
vlivashkin reads pinned «Привет! Захотелось систематизировать свои знания по диффузионкам, и для этого хочу пописать серию постов. Начну с самой базы, дойду до SOTA, посмотрю как делают прикладные штуки, как дообучают и тд. Если вы не очень погружены, то, надеюсь, вам будет это интересно!…»
Diffusion Models Part 4: Finetuning LoRA, DoRA, DreamBooth, ControlNet, Uni-ControlNet, T2I-Adapter, IP-Adapter https://telegra.ph/Stable-Diffusion-Part-4-Finetuning-08-11
👍2
Дописал в этом же посте про Flux ^
Diffusion Models Part 3: SD3 + Flux https://telegra.ph/Diffusion-Models-Part-3-SD3-08-07
👍3
Вторая часть! В этот раз рассматриваем SD1-2 и SDXL Diffusion Models Part 2: Stable Diffusion https://telegra.ph/Diffusion-Models-Part-2-Stable-Diffusion-08-06
👀1
Привет! Захотелось систематизировать свои знания по диффузионкам, и для этого хочу пописать серию постов. Начну с самой базы, дойду до SOTA, посмотрю как делают прикладные штуки, как дообучают и тд. Если вы не очень погружены, то, надеюсь, вам будет это интересно! А если вы все знаете лучше меня, то тогда поправьте меня плз, если я где-то ошибся! Diffusion Models Part 1: Idea and DDPM https://telegra.ph/Diffusion-M…
👍6🔥2
Photo, posted without a caption
Audio- and Gaze-driven Facial Animation of Codec Avatars 📝 arxiv.org/abs/2008.05023 (WACV 2021) 🌐 research.facebook.com/videos/audio-and-gaze-driven-facial-animation-of-codec-avatars Вообще стоило бы начать разбор с Expressive Telepresence via Modular Codec Avatars (ECCV 2020), но там про рендеринг, основанный на съемке на headset, а у админа ща арка про победу над липсинком. Так что читаем сразу липсинковую статью.…
В ише выше пишут, что > ICP between the surface of your mesh and the vertices of the provided mesh should give you a good enough alignment. ICP – это iterative closest point. Эта штука подбирает 4x4 трансформационную матрицу одного меша к другому, и после такого преобразования можно сделать маппинг из одной топологии к другой (просто смаппить ближайшие точки из двух мешей) Полезно, но для такого по-хорошему нужно и…
MeshTalk: 3D Face Animation from Speech using Cross-Modality Disentanglement 📝 arxiv.org/abs/2104.08223 (ICCV 2021) 🌐 github.com/facebookresearch/meshtalk Ребята придумали cross-modal loss, который позволяет разделять audio-correlated и audio-uncorrelated информацию. И победили VOCA in over 75% of cases по юзерстади. Итак, в чем была проблема. VOCA предсказывал дельты ко всем вершинам, включая глаза. Моргания глаз …
Showing the 12 most recent of 15 posts we hold for @vlivashkin_reads. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 9 August 2026 — this entry's latest reading, not the date you are reading this.
“vlivashkin reads” (@vlivashkin_reads), 80 subscribers as measured 9 August 2026. Telegram Register, tgregister.com/channel/vlivashkin_reads.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.