Ljubomir Josifovski

ljupco

https://ljubomirj.github.io/

AI & ML interests

Now - ML/AI, agents, forecasting, science & engineering. Previous - systematic trading, research & development. Previous^2 - speech recognition in noise, speech synthesis, machine learning.

Recent Activity

liked a model about 4 hours ago

kaitchup/MiniMax-M3-GGUF-MoQ

liked a model about 23 hours ago

sleepyeldrazi/deepseek-v4-flash-reap-k128-Q2-GGUF

upvoted a collection 1 day ago

Nemotron-TwoTower

View all activity

Organizations

None yet

upvoted a collection 1 day ago

Nemotron-TwoTower

Collection

Diffusion Language Modeling with Pretrained Autoregressive Nemotron 3 Models • 1 item • Updated 2 days ago • 4

upvoted a collection 2 days ago

Ornith-1.0

Collection

Ornith-1.0 is a family of open-source LLMs specialized for agentic coding. • 8 items • Updated about 9 hours ago • 167

upvoted a collection 3 days ago

Qwen-AgentWorld

Collection

3 items • Updated 3 days ago • 51

upvoted a paper 4 days ago

VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models

Paper • 2606.16140 • Published 12 days ago • 119

upvoted an article 10 days ago

Article

GLM-5.2: Built for Long-Horizon Tasks

zai-org

•

10 days ago

• 106

upvoted a collection 16 days ago

Apodex-1

Collection

4 items • Updated 19 days ago • 34

upvoted a paper 17 days ago

FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention

Paper • 2606.09079 • Published 19 days ago • 64

upvoted a collection 19 days ago

Gemma 4 QAT

Collection

Gemma 4 QAT (Quantization-Aware Training) for 3x less memory use and near original accuracy. • 16 items • Updated 12 days ago • 95

upvoted 2 collections 21 days ago

Domino

Collection

Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative Decoding • 3 items • Updated 5 days ago • 3

Mellum 2

Collection

Mellum2 model weights • 6 items • Updated 26 days ago • 123

upvoted a collection 25 days ago

Qwen 3.x MTP

Collection

MLX MTP drafter checkpoints for Qwen 3.x speculative decoding with mlx-vlm. • 12 items • Updated 26 days ago • 9

upvoted a paper 28 days ago

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 20

upvoted 2 papers about 1 month ago

Triplet-Block Diffusion RWKV

Paper • 2605.25969 • Published May 25 • 25

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

Paper • 2605.22138 • Published May 21 • 11

upvoted 3 collections about 1 month ago

upvoted a paper about 1 month ago

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

Paper • 2605.13301 • Published May 13 • 165

upvoted a collection about 2 months ago

SpecDrift

Collection

Models released as a part of Attention-Drift Paper, trained for deployment on production • 2 items • Updated May 10 • 2

upvoted an article about 2 months ago

Article

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

nvidia

•

Apr 28

• 62

Ljubomir Josifovski

AI & ML interests

Recent Activity

Organizations

ljupco's activity

GLM-5.2: Built for Long-Horizon Tasks

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents