rotem israeli

irotem98's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted an article about 2 hours ago

view article

Article

Kog Laneformer 2B: The Latency-First Model Behind Kog Inference Engine

• 

kogai

•

about 16 hours ago

• 22

upvoted 2 papers 3 days ago

BrainG3N: A Dual-Purpose Tokenizer for Controllable 3D Brain MRI Generation

Paper • 2606.19651 • Published 8 days ago • 9

PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models

Paper • 2606.19534 • Published 8 days ago • 60

upvoted a paper 6 days ago

Moebius: 0.2B Lightweight Image Inpainting Framework with 10B-Level Performance

Paper • 2606.19195 • Published 8 days ago • 133

upvoted 2 papers 14 days ago

Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings

Paper • 2606.07502 • Published 20 days ago • 97

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published 20 days ago • 119

upvoted 2 papers 23 days ago

NITP: Next Implicit Token Prediction for LLM Pre-training

Paper • 2605.24956 • Published May 24 • 35

Draft-OPD: On-Policy Distillation for Speculative Draft Models

Paper • 2605.29343 • Published 28 days ago • 36

upvoted an article about 1 month ago

view article

Article

OpenReasoning-Nemotron: A Family of State-of-the-Art Distilled Reasoning Models

• 

nvidia

•

Jul 18, 2025

• 51

upvoted a collection about 2 months ago

Gemma 4

Collection

15 items • Updated 14 days ago • 990

upvoted a paper 2 months ago

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published Apr 9 • 103

upvoted 2 papers 3 months ago

Think Anywhere in Code Generation

Paper • 2603.29957 • Published Mar 31 • 26

Attend Before Attention: Efficient and Scalable Video Understanding via Autoregressive Gazing

Paper • 2603.12254 • Published Mar 12 • 23

upvoted 2 collections 4 months ago

Qwen3.5

Collection

Qwen3.5 is Qwen's new model family including Qwen3.5 Small: 0.8B, 2B, 4B, 9B and Qwen3.5 Medium: 35B-A3B, 27B, 122B-A10B and 397B-A17B. • 25 items • Updated 10 days ago • 161

Qwen3-Embedding

Collection

6 items • Updated Dec 31, 2025 • 173

upvoted 3 papers 4 months ago

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Paper • 2602.20161 • Published Feb 23 • 23

SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models

Paper • 2602.18993 • Published Feb 22 • 4

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Paper • 2602.12205 • Published Feb 13 • 83

upvoted a collection 4 months ago

timm DINOv3

Collection

Meta AI's DINOv3 weights in timm. ViTs with `qkvb` have a zero QV bias present, otherwise bias is disabled. QKV bias are all 0 in original weights. • 18 items • Updated Sep 19, 2025 • 37

upvoted a paper 5 months ago

Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel Generations

Paper • 2602.05885 • Published Feb 5 • 28