Zach Mustafa's picture

Zach Mustafa PRO

Zmu

·

AI & ML interests

None yet

Recent Activity

upvoted an article about 14 hours ago

Introducing Daggr: Chain apps programmatically, inspect visually

liked a Space 4 days ago

merve/daggr-image-to-3d

liked a Space 4 days ago

insomnia7/SAMTok

View all activity

Organizations

upvoted an article about 14 hours ago

Article

Introducing Daggr: Chain apps programmatically, inspect visually

+3

6 days ago

•

78

upvoted a collection 11 days ago

VibeVoice

Frontier Text-to-Speech Models https://microsoft.github.io/VibeVoice/ • 9 items • Updated 13 days ago • 206

upvoted a collection 12 days ago

Qwen3-TTS

7 items • Updated 12 days ago • 275

upvoted a collection 22 days ago

DroPE

Extending the Context of Pretrained LLMs by Dropping Their Positional Embedding (https://www.arxiv.org/abs/2512.12167) • 1 item • Updated 23 days ago • 1

upvoted a collection about 1 month ago

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 181

upvoted an article about 2 months ago

Article

New in llama.cpp: Model Management

Dec 11, 2025

•

116

upvoted 2 articles 2 months ago

Article

Transformers v5: Simple model definitions powering the AI ecosystem

+2

Dec 1, 2025

•

289

Article

Continuous batching from first principles

+1

Nov 25, 2025

•

316

upvoted a collection 2 months ago

Olmo 3

Artifacts for the Olmo 3 release. • 9 items • Updated Dec 23, 2025 • 163

upvoted 2 collections 3 months ago

V-JEPA 2

A frontier video understanding model developed by FAIR, Meta, which extends the pretraining objectives of https://ai.meta.com/blog/v-jepa-yann • 8 items • Updated Jun 13, 2025 • 191

ViDoRe Benchmark V3

ViDoRe V3 is our latest benchmark, engineered to set a new industry gold standard for multi-modal, enterprise document retrieval evaluation. • 8 items • Updated 20 days ago • 18

upvoted a paper 5 months ago

zELO: ELO-inspired Training Method for Rerankers and Embedding Models

Paper • 2509.12541 • Published Sep 16, 2025 • 5

upvoted a collection 5 months ago

OpenVision

27 items • Updated Aug 15, 2025 • 33

upvoted a collection 6 months ago

DINOv3

DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21, 2025 • 474

upvoted 3 collections 7 months ago

Qwen3

Qwen's new Qwen3 models. In Unsloth Dynamic 2.0, GGUF, 4-bit and 16-bit Safetensor formats. Includes 128K Context Length variants. • 79 items • Updated 12 days ago • 260

🧠 SmolLM3

Smol, multilingual, long-context reasoner • 14 items • Updated Oct 9, 2025 • 96

Gemma 3n

4 items • Updated Jul 10, 2025 • 262

upvoted an article 8 months ago

Article

Accelerating LLM Code Generation Through Mask Store Streamlining

Jan 17, 2025

•

3

upvoted a collection 8 months ago

Qwen3

84 items • Updated Dec 31, 2025 • 1.63k

upvoted an article 8 months ago

Article

KV Cache from scratch in nanoVLM

+3

Jun 4, 2025

•

109