HackerTrans
TopNewTrendsCommentsPastAskShowJobs

lnyan

no profile record

Submissions

Whole cross-sectional human ultrasound tomography

nature.com
112 points·by lnyan·26 дней назад·25 comments

Midjourney Full Body Ultrasonic CT Scanner

midjourney.com
83 points·by lnyan·26 дней назад·5 comments

See-Through: Single-Image Layer Decomposition for Anime Characters

github.com
1 points·by lnyan·3 месяца назад·0 comments

PocketSSH: A pocket-sized ESP32-based SSH terminal

github.com
2 points·by lnyan·4 месяца назад·0 comments

BabyVision: Visual Reasoning Beyond Language

unipat.ai
1 points·by lnyan·6 месяцев назад·0 comments

Digital Red Queen: Adversarial Program Evolution in Core War with LLMs

pub.sakana.ai
1 points·by lnyan·6 месяцев назад·1 comments

Designing Multispecies Worlds for Robots, Cats, and Humans (2024)

programs.sigchi.org
1 points·by lnyan·6 месяцев назад·0 comments

TMLR Beyond PDF:Journal of Machine Learning Research Now Accept HTML Submissions

tmlr-beyond-pdf.org
2 points·by lnyan·8 месяцев назад·0 comments

Optimzing Our Jax LLM RL Pipeline

notes.kvfrans.com
2 points·by lnyan·8 месяцев назад·0 comments

Walrus: A Cross-Domain Foundation Model for Continuum Dynamics

polymathic-ai.org
2 points·by lnyan·8 месяцев назад·0 comments

Multimodal Diffusion Language Models for Thinking-Aware Editing and Generation

github.com
136 points·by lnyan·8 месяцев назад·12 comments

NanoBoyAdvance: A cycle-accurate Nintendo Game Boy Advance emulator

github.com
2 points·by lnyan·8 месяцев назад·0 comments

Metalnes: Transistor Level NES Simulation

github.com
2 points·by lnyan·9 месяцев назад·0 comments

RND1: Simple, Scalable AR-to-Diffusion Conversion

radicalnumerics.ai
1 points·by lnyan·9 месяцев назад·0 comments

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

pixel-perfect-depth.github.io
1 points·by lnyan·9 месяцев назад·0 comments

Single-Step Diffusion Decoder for Efficient Image Tokenization

github.com
1 points·by lnyan·9 месяцев назад·0 comments

OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows

oneflow.framer.ai
1 points·by lnyan·9 месяцев назад·0 comments

Skin-attached haptic patch for versatile and augmented tactile interaction

science.org
2 points·by lnyan·10 месяцев назад·0 comments

Optical Generative Models

nature.com
2 points·by lnyan·10 месяцев назад·0 comments

Meta Announces a Partnership with Midjourney

twitter.com
5 points·by lnyan·11 месяцев назад·2 comments

comments

lnyan
·8 месяцев назад·discuss
Can it detect when it itself is down
lnyan
·в прошлом году·discuss
normalizing flow might be unpopular but definitely not a forgotten technique
lnyan
·в прошлом году·discuss
Note that it's very likely that Veo models are based on "Flow Matching" [1]

[1] https://arxiv.org/abs/2210.02747
lnyan
·в прошлом году·discuss
I just pre-ordered a Bigme 13-inch color e-ink monitor with a 30Hz refresh rate. At $499, it's much cheaper than the Dasung, though the quality and e-ink display algorithms might not be as good
lnyan
·2 года назад·discuss
I've been using a BOOX Tab Ultra C Pro (with the Kaleido 3 color e-ink) for a year. The colors are quite dim, to the point where I sometimes forget it's a color e-ink display. The Colorsoft display looks significantly better in comparison (even seems to have better contrast than ClearInk?), so I'm curious how it works.
lnyan
·2 года назад·discuss
Slightly off-topic: Is there a library in JAX that supports post-training quantization, similar to the one mentioned?