Julius Duin

duinamit's activity

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

commented a paper 16 days ago

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

Paper • 2504.13173 • Published 21 days ago • 18 •

3

upvoted a paper 16 days ago

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

Paper • 2504.13173 • Published 21 days ago • 18

commented a paper 22 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 28 days ago • 19 •

6

upvoted 2 papers 23 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 28 days ago • 19

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

Paper • 2504.08685 • Published 27 days ago • 123

commented a paper 23 days ago

PixelFlow: Pixel-Space Generative Models with Flow

Paper • 2504.07963 • Published 28 days ago • 19 •

6

upvoted 14 papers about 1 month ago

Towards Physically Plausible Video Generation via VLM Planning

Paper • 2503.23368 • Published Mar 30 • 40

FreSca: Unveiling the Scaling Space in Diffusion Models

Paper • 2504.02154 • Published Apr 2 • 19

ZClip: Adaptive Spike Mitigation for LLM Pre-Training

Paper • 2504.02507 • Published Apr 3 • 78

MedSAM2: Segment Anything in 3D Medical Images and Videos

Paper • 2504.03600 • Published Apr 4 • 8

TransMamba: Flexibly Switching between Transformer and Mamba

Paper • 2503.24067 • Published Mar 31 • 20

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

Paper • 2504.02605 • Published Apr 3 • 45

One-Minute Video Generation with Test-Time Training

Paper • 2504.05298 • Published about 1 month ago • 102

Gaussian Mixture Flow Matching Models

Paper • 2504.05304 • Published about 1 month ago • 12

Multi-Token Attention

Paper • 2504.00927 • Published Apr 1 • 49

Wan: Open and Advanced Large-Scale Video Generative Models

Paper • 2503.20314 • Published Mar 26 • 51

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 • 38

Transformers without Normalization

Paper • 2503.10622 • Published Mar 13 • 162

FlowTok: Flowing Seamlessly Across Text and Image Tokens

Paper • 2503.10772 • Published Mar 13 • 19