hypedarhypedar
feedtrendsdiscovershowcasearchive
login
login
login
FeedTrendsDiscoverShowcaseArchiveDashboard
Submit Showcase

Trending now

Discussion + Ethics50Kernel + Hardware40Sociology + Ethics40
View all trends →

hypedar

AI trend radar for developers. Catch emerging papers, repos, and discussions before the hype peaks.

AboutGitHubDiscord

By the makers of hypedar

Codepawl

Open-source tools for developers.

Explore our tools →
AboutPrivacyTermsX

© 2026 Codepawl

Built by Codepawl·© 2026

About·Terms·Privacy·Security

GitHub·Discord·X

feedtrendsdiscovershowcasearchive
← trends

Diffusion + Inference + Multimodal

30.0

Provide a clean, plug-and-play PyTorch implementation of Fleming-Viot resampling for existing stable diffusion or flux pipelines. This helps maintain sample diversity during long sampling processes.

+0
emergingimplementation gap
diffusioninferencerlreasoningmultimodalimage-generation

Signals (10)

arXiv1d ago

$S^3$: Stratified Scaling Search for Test-Time in Diffusion Language Models

arXiv3d ago

Rethinking Token Prediction: Tree-Structured Diffusion Language Model

OpenAI21h ago

Creating images with ChatGPT

HuggingFace1d ago

Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs

GitHub19h ago

z-lab/dflash

arXiv4d ago

Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language Models

arXiv17h ago

FVD: Inference-Time Alignment of Diffusion Models via Fleming-Viot Resampling

GitHub19h ago

OpenBMB/VoxCPM

arXiv4d ago

Dependency-Guided Parallel Decoding in Discrete Diffusion Language Models

arXiv3d ago

Noise Steering for Controlled Text Generation: Improving Diversity and Reading-Level Fidelity in Arabic Educational Story Generation