lnyan

lnyan

8 mesi fadiscuss

Can it detect when it itself is down

lnyan

anno scorsodiscuss

normalizing flow might be unpopular but definitely not a forgotten technique

lnyan

anno scorsodiscuss

Note that it's very likely that Veo models are based on "Flow Matching" [1]

[1] https://arxiv.org/abs/2210.02747

lnyan

anno scorsodiscuss

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

Submissions

Whole cross-sectional human ultrasound tomography

Midjourney Full Body Ultrasonic CT Scanner

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

PocketSSH: A pocket-sized ESP32-based SSH terminal

BabyVision: Visual Reasoning Beyond Language

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

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

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

Optimzing Our Jax LLM RL Pipeline

Walrus: A Cross-Domain Foundation Model for Continuum Dynamics

Multimodal Diffusion Language Models for Thinking-Aware Editing and Generation

NanoBoyAdvance: A cycle-accurate Nintendo Game Boy Advance emulator

Metalnes: Transistor Level NES Simulation

RND1: Simple, Scalable AR-to-Diffusion Conversion

Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers

Single-Step Diffusion Decoder for Efficient Image Tokenization

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

Skin-attached haptic patch for versatile and augmented tactile interaction

Optical Generative Models

Meta Announces a Partnership with Midjourney

comments