📙 Nothing🙃

Starstrek

Stars321123

·

Stars321

AI & ML interests

AI

Recent Activity

liked a Space about 2 hours ago

AlexWortega/activation-oracle

upvoted a paper about 3 hours ago

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

liked a model about 4 hours ago

nvidia/NVIDIA-NemotronLabs-VoiceChat-11B

View all activity

Organizations

upvoted a paper about 3 hours ago

ODEWorld: A Continuous Predictive Architecture via Physical-Time Flow

Paper • 2607.27924 • Published 6 days ago • 11

upvoted an article about 5 hours ago

Article

The Fast Gemma Challenge: our verified-SOTA recipe, in full

FINAL-Bench

•

2 days ago

• 21

upvoted 2 papers about 5 hours ago

QQWorld: Quantile-Quantile Matching for World Model Regularization

Paper • 2607.28415 • Published 6 days ago • 28

Gemini Embedding: Generalizable Embeddings from Gemini

Paper • 2503.07891 • Published Mar 10, 2025 • 49

upvoted a collection about 5 hours ago

3D

65 items • Updated about 14 hours ago • 6

upvoted 2 papers about 5 hours ago

Meshy T2: Fast Native Mesh Generation with Flow Matching

Paper • 2607.28675 • Published 8 days ago • 48

Enhancing Rubric-based RL via Self-Distillation

Paper • 2607.18082 • Published 15 days ago • 22

upvoted 9 collections 1 day ago

Stable Diffusion official demos

All Stable Diffusion model demos • 3 items • Updated May 10, 2024 • 7

Awesome SDXL LoRAs

A curated set of amazing Stable Diffusion XL LoRAs (they power the LoRA the Explorer Space) • 36 items • Updated Jun 24, 2024 • 28

Perturbed Attention Guidance pipelines

Pipelines for Perturbed Attention Guidance with 🧨 library • 8 items • Updated Jun 26, 2024 • 7

Creative projects

2 items • Updated Dec 5, 2024 • 3

Wan 2.2

Wan 2.2 release collection • 5 items • Updated Jul 28, 2025 • 12

Base Models

Some of the relevant (July/2026) language base models on Hugging Face (meaning, LLMs trained on pure text, without Instruct/SFT/RLHF/RL tuning etc) • 23 items • Updated Jul 4 • 5

MiniMax H3

4 items • Updated 2 days ago • 5

MiniMax-M3

4 items • Updated Jul 1 • 19

MiniMax-H3

2 items • Updated 2 days ago • 12

upvoted 3 collections 2 days ago

Gemini Distills 1B to 32B - Reg and Uncensored

Qwen, Gemma, Mistral, Ernie, LFM, Llama fine tuned via Unsloth on Gemini dataset(s) to improve and/or add reasoning/thinking to the model.. • 20 items • Updated 29 days ago • 3

Dark Champion Collection MOE - Mixture Of Experts

Uncensored ; you can dial up/down the number of experts activated. 128 k context. • 8 items • Updated 29 days ago • 8

Heretic - Abliterated, Uncensored, Unrestricted POWER.

Models that have be abliterated using the HERETIC method. Done properly, this completely removed almost all censorship with no damage to the model. • 124 items • Updated 2 days ago • 135

upvoted a paper 4 days ago

DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence

Paper • 2606.19348 • Published Apr 26 • 26