Josh Ause

joshause's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked a Space 2 days ago

Paused

Agents

1

GPU SAE Service

🧠

1

Analyze transformer model features for any prompt

liked 2 models 2 days ago

google/gemma-4-E4B-it

Any-to-Any • 8B • Updated 25 days ago • 5.68M • 1.3k

Qwen/Qwen3-VL-4B-Instruct

Image-Text-to-Text • 4B • Updated Oct 15, 2025 • 4.05M • 403

liked 2 Spaces 2 days ago

Running on Zero

Agents

165

Gemma 3 12b It

🔥

165

Chat with an AI that understands text, images, and videos

Running on Zero

Agents

Featured

84

Gemma 4 12B IT

⚡

84

Chat with an AI using text, images, audio, or video

liked 3 Spaces 3 days ago

Running on T4

Agents

Featured

57

PROMETHEUS v1.0 — World Model Interactive Demo

🔥

57

World-first embodied AI world model

Running

Agents

25

WORLD MODEL Leaderboard

💻

25

WORLD MODEL Bench

Running

2

DVD-JEPA

📺

2

A browser JEPA world model of a bouncing DVD logo

liked a Space 4 days ago

Running on Zero

MCP

1.89k

Wan2.2 14B Fast Preview

🐌

1.89k

generate a video from an image with a text prompt

upvoted a paper 6 days ago

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

Paper • 2606.16140 • Published 14 days ago • 119

liked a model 6 days ago

WeiboAI/VibeThinker-3B

Text Generation • 3B • Updated 9 days ago • 59.3k • • 742

liked a Space 6 days ago

Running on Zero

Agents

4

VibeThinker 3B

😻

4

Generate detailed answers with step‑by‑step reasoning

liked a model 6 days ago

openbmb/MiniCPM-o-4_5

Any-to-Any • 9B • Updated May 19 • 369k • 1.4k

upvoted 2 papers 6 days ago

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

Paper • 2603.19312 • Published Mar 13 • 50

Causal-JEPA: Learning World Models through Object-Level Latent Interventions

Paper • 2602.11389 • Published Feb 11 • 11

updated a collection 6 days ago

Library

Collection

High Low Media's AI/ML bookshelf • 9 items • Updated 6 days ago

upvoted a paper 6 days ago

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

Paper • 2603.22281 • Published Mar 23 • 19

liked a Space 6 days ago

Running on Zero

Agents

17

World Tracing Demo

🌍

17

Multilayer-geometry 3D from a single image or 16-frame clip

upvoted a paper 6 days ago

World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible

Paper • 2606.13652 • Published 18 days ago • 15

liked a model 6 days ago

wassemgtk/jepa_llm_prototypes

Updated Jan 24 • 4