Julius Duin

duinamit's activity

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

commented a paper 4 days ago

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Paper • 2504.13173 • Published 9 days ago • 17 •

3

upvoted a paper 4 days ago

It's All Connected: A Journey Through Test-Time Memorization, Attentional Bias, Retention, and Online Optimization

Paper • 2504.13173 • Published 9 days ago • 17

commented a paper 10 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 16 days ago • 19 •

6

upvoted 2 papers 11 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 16 days ago • 19

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published 15 days ago • 121

commented a paper 11 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 16 days ago • 19 •

6

upvoted 8 papers 18 days ago

Towards Physically Plausible Video Generation via VLM Planning

Paper • 2503.23368 • Published 27 days ago • 39

FreSca: Unveiling the Scaling Space in Diffusion Models

Paper • 2504.02154 • Published 24 days ago • 18

ZClip: Adaptive Spike Mitigation for LLM Pre-Training

Paper • 2504.02507 • Published 23 days ago • 76

MedSAM2: Segment Anything in 3D Medical Images and Videos

Paper • 2504.03600 • Published 22 days ago • 8

TransMamba: Flexibly Switching between Transformer and Mamba

Paper • 2503.24067 • Published 26 days ago • 20

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Paper • 2504.02605 • Published 23 days ago • 44

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published 19 days ago • 98

Gaussian Mixture Flow Matching Models

Paper • 2504.05304 • Published 19 days ago • 12

upvoted a paper 23 days ago

Multi-Token Attention

Paper • 2504.00927 • Published 25 days ago • 46

upvoted 5 papers about 1 month ago

Wan: Open and Advanced Large-Scale Video Generative Models

Paper • 2503.20314 • Published Mar 26 • 49

Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policy

Paper • 2503.19757 • Published Mar 25 • 50

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 37

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 160

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Paper • 2503.10772 • Published Mar 13 • 19