leo's picture

Open to Collab

leo

duckking032

·

penguinmarket71

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 hour ago

From Context to Skills: Can Language Models Learn from Context Skillfully?

upvoted a paper about 8 hours ago

HRM-Text: Efficient Pretraining Beyond Scaling

upvoted a paper 1 day ago

δ-mem: Efficient Online Memory for Large Language Models

View all activity

Organizations

None yet

upvoted a paper about 1 hour ago

From Context to Skills: Can Language Models Learn from Context Skillfully?

Paper • 2604.27660 • Published 19 days ago • 161

upvoted a paper about 8 hours ago

HRM-Text: Efficient Pretraining Beyond Scaling

Paper • 2605.20613 • Published 1 day ago • 10

upvoted 2 papers 1 day ago

δ-mem: Efficient Online Memory for Large Language Models

Paper • 2605.12357 • Published 10 days ago • 120

MolmoAct2: Action Reasoning Models for Real-world Deployment

Paper • 2605.02881 • Published 18 days ago • 332

upvoted a paper 3 days ago

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Paper • 2605.13301 • Published 9 days ago • 154

liked a model 4 days ago

ai21labs/AI21-Jamba2-Mini

Text Generation • 52B • Updated Feb 16 • 969 • 53

upvoted a paper 4 days ago

SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer

Paper • 2605.15178 • Published 8 days ago • 80

liked 2 models 5 days ago

bartowski/ai21labs_AI21-Jamba2-Mini-GGUF

Text Generation • 52B • Updated Jan 8 • 831 • 1

bartowski/nvidia_Nemotron-H-47B-Reasoning-128K-GGUF

Text Generation • 47B • Updated Aug 29, 2025 • 863 • 4

liked a dataset 6 days ago

Modotte/CodeX-2M-Thinking

Viewer • Updated Feb 10 • 2.19M • 6.07k • 103

liked 4 models 6 days ago

unsloth/FLUX.2-dev-GGUF

Image-to-Image • 32B • Updated Dec 10, 2025 • 8.4k • 60

hexgrad/Kokoro-82M

Text-to-Speech • Updated Apr 10, 2025 • 10.4M • • 6.18k

NousResearch/Hermes-4.3-36B-GGUF

Text Generation • 36B • Updated Dec 3, 2025 • 4.45k • 52

Cactus-Compute/needle

Updated 8 days ago • 319 • 108

reacted to cesear64's post with 🔥 6 days ago

Post

4092

Just published: how we built production Sango (Central African Republic) translation without fine-tuning, parallel corpus, or training compute.

The method — vocabulary-augmented prompting with a 581-entry native-speaker-verified lexicon — generalizes to any of the ~2,000 African languages at the same data-poverty level. Recipe, dataset, and code template all included.

📄 Blog: https://huggingface.co/blog/MEYNG/sangoai
📦 Dataset: MEYNG/sango-vocabulary

Would especially value feedback from anyone working on other low-resource African languages — Ewondo, Lingala, Wolof next on our roadmap.

1 reply

·

liked 2 models 6 days ago

TencentARC/Pixal3D

Image-to-3D • Updated about 24 hours ago • 177

Jiunsong/supergemma4-26b-uncensored-gguf-v2

Text Generation • 25B • Updated Apr 12 • 244k • 642

liked a model 7 days ago

unsloth/Qwen3.6-27B-MTP-GGUF

Image-Text-to-Text • 27B • Updated 1 day ago • 478k • 364

liked a dataset 7 days ago

blanchon/opencs2_dataset

Viewer • Updated 17 days ago • 686k • 22.5k • 25

reacted to blanchon's post with ❤️ 7 days ago

Post

2469

I'm releasing OpenCS2 a 11TB dataset of around 5000 hours of counter strike gameplay recording.
- HD resolution - 1280×720 · 32 fps
- For each frame keyboard and mouse + world state (player position, velocity, weapon ...)
- HD Stereo audio
- All 10 players perspective

https://huggingface.co/collections/blanchon/opencs2

1 reply

·