Josh Ause

joshause

2 24 77

AI & ML interests

None yet

Recent Activity

liked a Space 8 days ago

joelniklaus/harness-optimization

liked a model 8 days ago

Harahan/QVGen-CogVideoX-2B-W4A4

liked a Space 15 days ago

justforkicks/sae-gpu-backend

View all activity

Organizations

liked a Space 8 days ago

Don't Train the Model, Evolve the Harness

🌿

Evolving an agent's harness, not its model, on Harvey's LAB

liked a model 8 days ago

Harahan/QVGen-CogVideoX-2B-W4A4

Text-to-Video • Updated Feb 2 • 25 • 2

liked a Space 15 days ago

GPU SAE Service

🧠

Analyze transformer model features for any prompt

liked 2 models 15 days ago

google/gemma-4-E4B-it

Any-to-Any • 8B • Updated 1 day ago • 5.86M • 1.36k

Qwen/Qwen3-VL-4B-Instruct

Image-Text-to-Text • 4B • Updated Oct 15, 2025 • 3.62M • • 411

liked 4 Spaces 15 days ago

Gemma 3 12b It

🔥

165

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

Gemma 4 12B IT

⚡

102

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

PROMETHEUS v1.0 — World Model Interactive Demo

🔥

World-first embodied AI world model

WORLD MODEL Leaderboard

💻

WORLD MODEL Bench

liked 2 Spaces 16 days ago

DVD-JEPA

📺

A browser JEPA world model of a bouncing DVD logo

Wan2.2 14B Fast Preview

🐌

2.02k

generate a video from an image with a text prompt

upvoted a paper 18 days ago

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

Paper • 2606.16140 • Published 26 days ago • 122

liked a model 18 days ago

WeiboAI/VibeThinker-3B

Text Generation • 3B • Updated 11 days ago • 84.2k • • 788

liked a Space 18 days ago

VibeThinker 3B

😻

Generate detailed answers with step‑by‑step reasoning

liked a model 19 days ago

openbmb/MiniCPM-o-4_5

Any-to-Any • 9B • Updated 5 days ago • 446k • 1.42k

upvoted 2 papers 19 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 19 days ago

Library

Collection

High Low Media's AI/ML bookshelf • 9 items • Updated 19 days ago

upvoted a paper 19 days ago

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

Paper • 2603.22281 • Published Mar 23 • 20

liked a Space 19 days ago

World Tracing Demo

🌍

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