rotem israeli

irotem98's activity

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

upvoted a paper about 15 hours ago

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 2 days ago • 62

upvoted 3 papers 4 days ago

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper • 2609.13356 • Published 8 days ago • 249

Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation

Paper • 2609.11638 • Published 9 days ago • 684

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Paper • 2609.04010 • Published 16 days ago • 111

liked 2 models 5 days ago

ukisai/Swift-Qwen3.8-27b

Image-Text-to-Text • 28B • Updated 3 days ago • 6.29k • 446

ukisai/Swift-Qwen3.8-27B-NVFP4

Image-Text-to-Text • 18B • Updated 3 days ago • 4.31k • 31

upvoted 6 papers 14 days ago

Editable Visual Design

Paper • 2609.04034 • Published 16 days ago • 43

Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States

Paper • 2609.04196 • Published 16 days ago • 69

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 16 days ago • 98

Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM

Paper • 2609.04098 • Published 16 days ago • 83

Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning

Paper • 2609.03430 • Published 16 days ago • 186

LatentPress: Context Compression Beyond Text and Vision

Paper • 2609.01507 • Published 18 days ago • 118

liked a Space 17 days ago

Running on CPU Upgrade

Featured

138

H3 Acceleration Arena

🥇

138

Blind A/B ranking of MiniMax-H3 acceleration variants

liked a model 17 days ago

Boogu/Boogu-Image-0.1-Edit-Turbo

Image-to-Image • 10B • Updated Jul 24 • 300 • 54

upvoted 3 papers 17 days ago

H3-World: Turning Language Understanding into World Control

Paper • 2609.01560 • Published 18 days ago • 51

SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers

Paper • 2609.01343 • Published 18 days ago • 89

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 18 days ago • 333

upvoted 3 papers 18 days ago

On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability

Paper • 2608.30320 • Published 19 days ago • 59

SHAPE of Chain-of-Thought in Math Reasoning

Paper • 2608.28600 • Published Jun 28 • 31

Normalized Low-Rank Adaptation

Paper • 2608.31036 • Published 19 days ago • 54