Ayman Mohammed's picture

Ayman Mohammed

Pegasus10

·

AI & ML interests

Interest in foundation, multimodal, LLMs , and ML, deep and reinforcement learning

Recent Activity

liked a dataset 2 days ago

microsoft/RHELM

liked a model 5 days ago

bageldotcom/paris2

upvoted an article 6 days ago

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

View all activity

Organizations

None yet

upvoted an article 6 days ago

Article

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

+6

aminediroHF, qgallouedec, kashif, lewtun, edbeeching, albertvillanova, lvwerra, sergiopaniego

•

8 days ago

• 39

upvoted a collection 6 days ago

Stable Audio 3

Stable Audio 3 Post-trained models • 3 items • Updated 15 days ago • 37

upvoted a collection 12 days ago

Nemotron-Labs-Diffusion

A Tri-Mode Language Model Family Unifying Autoregressive, Diffusion, and Self-Speculation Decoding • 7 items • Updated about 1 hour ago • 48

upvoted 2 articles 15 days ago

Article

Introducing the Ettin Reranker Family

tomaarsen

•

16 days ago

• 51

Article

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

nvidia

•

17 days ago

• 21

upvoted an article 20 days ago

Article

Unlocking asynchronicity in continuous batching

+1

ror, pcuenq, ariG23498

•

21 days ago

• 57

upvoted an article 21 days ago

Article

Building Blocks for Foundation Model Training and Inference on AWS

amazon

•

23 days ago

• 23

upvoted an article 23 days ago

Article

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

lablab-ai-amd-developer-hackathon

•

27 days ago

• 10

upvoted 2 collections about 1 month ago

Qwen-Scope

16 items • Updated 21 days ago • 68

Mistral Medium 3.5

Our first flaship models handling instruction-following, reasoning, and coding in a single set of opened-weights. • 2 items • Updated Apr 29 • 17

upvoted 2 articles about 1 month ago

Article

Granite 4.1 LLMs: How They’re Built

ibm-granite

•

Apr 29

• 77

Article

AI evals are becoming the new compute bottleneck

evaleval

•

Apr 29

• 28

upvoted a collection about 1 month ago

MOSS-Audio

An open-source audio understanding model supporting speech recognition, environmental sound analysis, music understanding, time-aware QA, and complex • 7 items • Updated May 2 • 63

upvoted an article about 1 month ago

Article

How to Use Transformers.js in a Chrome Extension

nico-martin

•

Apr 23

• 39

upvoted a paper about 1 month ago

Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond

Paper • 2604.22748 • Published Apr 24 • 227

upvoted a collection about 1 month ago

DeepSeek-V4

4 items • Updated Apr 24 • 670

upvoted an article about 1 month ago

Article

Building a Fast Multilingual OCR Model with Synthetic Data

nvidia

•

Apr 17

• 33

upvoted 3 articles about 2 months ago

Article

The PR you would have opened yourself

pcuenq, awni

•

Apr 16

• 72

Article

How we OCR'ed 30,000 papers using Codex, open OCR models and Jobs

nielsr

•

Apr 7

• 62

Article

Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents

ibm-research

•

Apr 15

• 28