Tillmann Radmer

gruenebohne's activity

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

upvoted 3 papers 14 days ago

Next-Embedding Prediction Makes Strong Vision Learners

Paper • 2512.16922 • Published 18 days ago • 82

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

Paper • 2512.12602 • Published 22 days ago • 41

Both Semantics and Reconstruction Matter: Making Representation Encoders Ready for Text-to-Image Generation and Editing

Paper • 2512.17909 • Published 17 days ago • 36

upvoted a paper 19 days ago

Multiple Object Tracking as ID Prediction

Paper • 2403.16848 • Published Mar 25, 2024 • 3

upvoted 6 papers 7 months ago

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Paper • 2506.09350 • Published Jun 11, 2025 • 48

Sekai: A Video Dataset towards World Exploration

Paper • 2506.15675 • Published Jun 18, 2025 • 65

Video World Models with Long-term Spatial Memory

Paper • 2506.05284 • Published Jun 5, 2025 • 55

Magistral

Paper • 2506.10910 • Published Jun 12, 2025 • 66

Hidden in plain sight: VLMs overlook their visual representations

Paper • 2506.08008 • Published Jun 9, 2025 • 7

PlayerOne: Egocentric World Simulator

Paper • 2506.09995 • Published Jun 11, 2025 • 34

upvoted 5 papers about 1 year ago

SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation

Paper • 2410.23277 • Published Oct 30, 2024 • 9

ReferEverything: Towards Segmenting Everything We Can Speak of in Videos

Paper • 2410.23287 • Published Oct 30, 2024 • 19

Constant Acceleration Flow

Paper • 2411.00322 • Published Nov 1, 2024 • 24

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Video Generation

Paper • 2411.08380 • Published Nov 13, 2024 • 25

MagicDriveDiT: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control

Paper • 2411.13807 • Published Nov 21, 2024 • 11