Marius Dinca

Puddings22's activity

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

commented a paper 2 days ago

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

Paper • 2609.19969 • Published 3 days ago • 126 •

3

upvoted a paper 2 days ago

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

Paper • 2609.19969 • Published 3 days ago • 126

upvoted a paper 3 days ago

Flattening Every Memory Peak in Long-Context Mixture-of-Experts Training

Paper • 2609.14306 • Published 7 days ago • 10

liked a model 10 days ago

deepseek-ai/DeepSeek-V4.1-Flash

Image-Text-to-Text • 763B • Updated 10 days ago • 497k • • 3.37k

updated a model 19 days ago

Puddings22/MIRAI-GlassBox-LLM

Text Generation • Updated 19 days ago • 391

published a model 19 days ago

Puddings22/MIRAI-GlassBox-LLM

Text Generation • Updated 19 days ago • 391

commented a paper 20 days ago

Puro-2B: Poor Lab's Qwen2-1.5B Trained on RTX 5090 within $5090

Paper • 2608.27370 • Published 24 days ago • 40 •

7

upvoted 2 papers about 1 month ago

Improving the matrix multiplication exponent with modern optimization and AlphaEvolve

Paper • 2608.16884 • Published Aug 17 • 19

BDH-CQ: In-Context Learning with Recurrent Latent Reasoning

Paper • 2608.09888 • Published Aug 10 • 784

liked a model about 2 months ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated 18 days ago • 2.01M • • 11.4k

upvoted 3 papers 4 months ago

Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

Paper • 2605.17423 • Published May 17 • 31

Generative Recursive Reasoning

Paper • 2605.19376 • Published May 20 • 31

WavFlow: Audio Generation in Waveform Space

Paper • 2605.18749 • Published May 18 • 9

commented a paper 4 months ago

Fast Byte Latent Transformer

Paper • 2605.08044 • Published May 8 • 11 •

3

upvoted a paper 4 months ago

Fast Byte Latent Transformer

Paper • 2605.08044 • Published May 8 • 11

upvoted 4 papers 5 months ago

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 171

Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning

Paper • 2604.12374 • Published Apr 14 • 39

Large Language Models Align with the Human Brain during Creative Thinking

Paper • 2604.03480 • Published Apr 3 • 7

Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models

Paper • 2604.02315 • Published Apr 3 • 5

updated a collection 6 months ago

interesting

Collection

3 items • Updated Apr 6