marinaretikof's picture

marinaretikof

marinaretik

·

AI & ML interests

None yet

Recent Activity

liked a model about 11 hours ago

llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF

liked a model about 11 hours ago

llmfan46/gemma-4-31B-it-uncensored-heretic

liked a model about 11 hours ago

llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF

View all activity

Organizations

None yet

upvoted a collection 4 days ago

Qwen-Scope

15 items • Updated 5 days ago • 50

upvoted a paper 5 days ago

Recursive Multi-Agent Systems

Paper • 2604.25917 • Published 7 days ago • 252

upvoted an article 8 days ago

Article

Norm-Preserving Biprojected Abliteration

Nov 6, 2025

•

77

upvoted a paper 14 days ago

DFlash: Block Diffusion for Flash Speculative Decoding

Paper • 2602.06036 • Published Feb 5 • 72

upvoted 3 papers 15 days ago

Can Large Language Models Reinvent Foundational Algorithms?

Paper • 2604.05716 • Published 28 days ago • 8

Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel Reasoning

Paper • 2604.16029 • Published 18 days ago • 23

Elucidating the SNR-t Bias of Diffusion Probabilistic Models

Paper • 2604.16044 • Published 18 days ago • 74

upvoted 2 collections 20 days ago

HLWQ Unified (Weights Q5 + KV Cache Q3)

Full-stack HLWQ: Q5 weights + torchao INT4 + Q3 KV cache · formerly PolarQuant Unified • 16 items • Updated 17 days ago • 3

HLWQ Models

Hadamard-Lloyd Weight Quantization · arXiv:2603.29078 · formerly PolarQuant • 26 items • Updated 17 days ago • 1

upvoted a collection 21 days ago

HLWQ Gemma Models

Google Gemma family quantized with HLWQ (Hadamard-Lloyd) · formerly PolarQuant Gemma • 5 items • Updated 22 days ago • 5

upvoted a collection 29 days ago

Gemma 4

Gemma 4 is Google's new model family including including E2B, E4B, 26B-A4B, and 31B. • 28 items • Updated 13 days ago • 171

upvoted a collection about 1 month ago

Qwen3.5-27B HLWQ

Qwen3.5-27B · HLWQ Q5 weight quantization · formerly PolarQuant • 1 item • Updated 22 days ago • 1

upvoted 4 papers about 1 month ago

MSA: Memory Sparse Attention for Efficient End-to-End Memory Model Scaling to 100M Tokens

Paper • 2603.23516 • Published Mar 6 • 49

Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration

Paper • 2603.24800 • Published Mar 25 • 68

Intern-S1-Pro: Scientific Multimodal Foundation Model at Trillion Scale

Paper • 2603.25040 • Published Mar 26 • 131

PEARL: Personalized Streaming Video Understanding Model

Paper • 2603.20422 • Published Mar 20 • 40

upvoted a paper about 2 months ago

Generation Models Know Space: Unleashing Implicit 3D Priors for Scene Understanding

Paper • 2603.19235 • Published Mar 19 • 95

upvoted a collection 2 months ago

Qwen3.5

21 items • Updated Mar 9 • 1.59k

upvoted a collection 7 months ago

Qwen3-Omni

6 items • Updated Dec 31, 2025 • 198

upvoted a collection 8 months ago

Qwen3-Next

4 items • Updated Dec 31, 2025 • 188