Muhammad Z. Ahmed @MoZayed007

Research Engineer @SprintsAi | Interested in R&D, On my journey of 10K hrs, Opinions are my own. linkedin.com/in/mozayed007 Giza, Egypt Joined October 2018

Tweets

596
Followers

196
Following

2K
Likes

6K

Kaiyue Wen @wen_kaiyue

4 days ago

Nice

11 77 374 134K 193

Download Image

0 0 0 43 0

Qwen @Alibaba_Qwen

3 days ago

chonky qwen is here❤️

46 140 1K 118K 236

0 0 0 51 0

Introducing EmbeddingGemma🎉 🔥With only 308M params, this is the top open model under 500M 🌏Trained on 100+ languages 🪆Flexible embeddings (768 to 128 dims) with Matryoshka 🤗Works with your favorite open tools 🤏Runs with as little as 200MB developers.googleblog.com/en/introducing…

27 156 1K 80K 544

Download Image

Luis @lusxvr

4 days ago

Today, we are releasing FineVision, a huge open-source dataset for training state-of-the-art Vision-Language Models: > 17.3M images > 24.3M samples > 88.9M turns > 9.5B answer tokens Here are my favourite findings:

19 214 1K 99K 908

Download Image

Alex Zhang @a1zhang

a week ago

All the recordings for the @GPU_MODE x @scaleml series are up as a playlist in case you missed it 😁 There's so much value in these ~8 hours of lectures, from proving quantization error bounds on a whiteboard to a deep-dive into GPU warp schedulers! Plz take advantage of it!

7 101 638 53K 692

Download Image

机器之心 JIQIZHIXIN @jiqizhixin

a week ago

What if foundation models weren’t just for language & vision—but also for structured data? 📊🤖 Stable AI & Tsinghua University introduce LimiX, the first large structured-data model (LDM), designed to handle any tabular task through query-based conditional prediction. Key…

7 64 277 22K 216

Download Image

机器之心 JIQIZHIXIN @jiqizhixin

2 weeks ago

How small can a BERT get without losing its power? 📱🤯 Meet EI-BERT: an ultra-compact framework for edge NLP that combines token pruning, cross-distillation, and quantization. ✅ Just 1.91 MB — smallest ever for Natural Language Understanding (NLU) tasks! It's already been…

6 81 479 30K 372

Download Image

merve @mervenoyann

2 weeks ago

first vision language model built off @OpenAI gpt-oss just dropped! 🔥 InternVL3.5 comes with 32 models 🤯 pre-trained, fine-tuned, aligned in various sizes comes with gpt-oss or Qwen3 for LLM part ⤵️

27 146 1K 186K 705

Download Image

You Jiacheng @YouJiacheng

2 weeks ago

btw it's possible to use mantissa-free weights. The Chief Scientist of NVIDIA had a keynote with content about it. nvidia.com/en-us/on-deman…

Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞) @teortaxesTex

2 weeks ago

btw it's possible to use mantissa-free weights. The Chief Scientist of NVIDIA had a keynote with content about it. nvidia.com/en-us/on-deman… https://t.co/5wIfpJ6Vk8

4 4 74 24K 31

Download Image

3 15 117 11K 79

Download Image

Jiawei Zhao @jiawzhao

2 weeks ago

Introducing DeepConf: Deep Think with Confidence 🚀 First method to achieve 99.9% on AIME 2025 with open-source models! Using GPT-OSS-120B even without tools, we reached this almost-perfect accuracy while saving up to 85% generated tokens. It also delivers many strong…

62 333 3K 446K 2K

Download Video

Guangxuan Xiao @Guangxuan_Xiao

2 weeks ago

Just wrote a post on my understanding of the statistics behind block sparse attention. My take is that it works by using the "learned similarity gap," which creates a simple SNR formula connecting retrieval quality with model architecture. Read more: guangxuanx.com/blog/block-spa…

5 46 385 33K 398

Zichen Liu @zzlccc

2 weeks ago

With just a few lines of code, Feng’s (@fengyao1909) suggested fix—applying importance sampling on the behavior policy—resolved the training instability in my case (oat). I believe the result can generalize to other RL frameworks as well. Great work, Feng!

7 54 473 44K 405

Download Image

Yacine Mahdid @yacinelearning

3 weeks ago

for all my toddlers out there that want to learn about muon I got you

20 60 1K 54K 830

Download Image

Google AI Developers @googleaidevs

3 weeks ago

Learning a specific speaking style and persona for an Alien NPC

1 2 92 18K 49

Download Video

Z.ai @Zai_org

3 weeks ago

Introducing ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. arxiv.org/abs/2508.14040 ComputerRL features the API-GUI paradigm, which unifies programmatic API calls and direct GUI interaction to…

10 103 579 69K 290

Download Image

Leandro von Werra @lvwerra

3 weeks ago

Excited to release: Jupyter Agent 2 The agent can load data, execute code, plot results inside Jupyter faster than you can scroll! 🤖 Powered by Qwen3-Coder ⚡️ Running on Cerebras ⚙️ Executed in E2B ↕️ Upload your files All videos are in *real time*! hf.co/spaces/lvwerra…

18 128 597 64K 510

Download Video

Lisan al Gaib @scaling01

3 weeks ago

DeepSeek V3.1 beats Claude 4 Opus on Aider Polyglot This makes it the best non-TTC coding model and all of that for ~$1

51 118 1K 286K 420

Download Image

Abhinav @Abhinavstwt

3 weeks ago

Here’s what I've received with my student ID : - Cursor pro @cursor_ai - Notion plus @NotionHQ - Perplexity pro @perplexity_ai - A free (.me) domain on @Namecheap - 60$ credits in @v0 - 50% off pro plan @lovable_dev - 50% off the annual plan for @HeyGen_Official

115 147 3K 448K 5K

Logan Kilpatrick @OfficialLoganK

3 weeks ago

Today we are making URL Context, my favorite Gemini API tool, ready for scaled production use 🔗 The model can now visit webpages, PDF's, images, and more when you provide the direct URL, and you simply pay for the tokens it processes, no additional tool cost!