SASATANI's picture

SASATANI PRO

sasa2000

·

jagaimo010

AI & ML interests

Modelscope:https://modelscope.ai/profile/SASATANI

Recent Activity

liked a model about 9 hours ago

zed-industries/zeta-2

liked a model about 10 hours ago

ricoh-ai/Qwen-3-VL-Ricoh-8B-20260227

updated a model 3 days ago

sasa2000/Cosmos-Reason2-2B-heretic

View all activity

Organizations

None yet

upvoted a collection 17 days ago

Qwen3.5-text-only

Qwen3.5-text-only • 4 items • Updated 18 days ago • 11

upvoted a paper 26 days ago

Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels

Paper • 2603.02573 • Published 28 days ago • 11

upvoted a collection 27 days ago

Deepseek Papers

Deepseek papers collection • 31 items • Updated about 20 hours ago • 335

upvoted a paper about 1 month ago

DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM Inference

Paper • 2602.21548 • Published Feb 25 • 49

upvoted a collection about 2 months ago

Micro-World

Action-controlled Interactive world model. • 3 items • Updated Feb 19 • 3

upvoted an article about 2 months ago

Article

The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+

Feb 3

•

52

upvoted a paper about 2 months ago

SWE-Universe: Scale Real-World Verifiable Environments to Millions

Paper • 2602.02361 • Published Feb 2 • 60

upvoted a collection 2 months ago

Falcon-H1-Tiny

A series of extremely small, yet powerful language models redefining capabilities at small scale • 19 items • Updated 29 days ago • 37

upvoted 5 collections 3 months ago

KVzap

6 items • Updated 6 days ago • 5

Open Korean LLM (MSIT 2025)

6 items • Updated Jan 2 • 16

Cosmos-Reason2

Cosmos Reason 2 is an open, customizable, reasoning vision language model (VLM) for physical AI and robotics • 2 items • Updated 6 days ago • 22

💧 LFM2

LFM2 is a new generation of hybrid models, designed for on-device deployment. • 28 items • Updated 16 days ago • 149

Hunyuan3D

28 items • Updated 21 days ago • 57

upvoted an article 3 months ago

Article

Codex is Open Sourcing AI models

Dec 11, 2025

•

80

upvoted 2 collections 3 months ago

Nemotron-Cascade

Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models • 14 items • Updated 6 days ago • 53

qqWen-Series

Based off the Qwen-2.5 Series - model finetuned for the Q programming language. • 14 items • Updated Feb 12 • 11

upvoted an article 4 months ago

Article

I Built a RAG System That Listens to Live BBC News and Answers Questions About "What Happened 10 Minutes Ago"

Dec 9, 2025

•

14

upvoted a collection 4 months ago

PaCoRe

Learning to Scale Test-Time Compute with Parallel Coordinated Reasoning • 4 items • Updated Jan 16 • 12

upvoted a paper 4 months ago

UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving

Paper • 2512.09864 • Published Dec 10, 2025 • 12

upvoted a collection 4 months ago

Ultra Quantization Hybrid Model.

These models are quantized in mixed precision that allows them to have a smaller footprint than fp8, but still high quality. • 15 items • Updated 3 days ago • 1