Lars Vagnes

larsh0103's activity

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

upvoted 2 papers 1 day ago

PoseDreamer: Scalable and Photorealistic Human Data Generation Pipeline with Diffusion Models

Paper • 2603.28763 • Published 3 days ago • 4

Extend3D: Town-Scale 3D Generation

Paper • 2603.29387 • Published 3 days ago • 16

liked a dataset 1 day ago

prosperolo/PoseDreamer

Viewer • Updated 7 days ago • 500k • 257 • 10

upvoted 3 papers 1 day ago

MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation

Paper • 2603.29029 • Published 3 days ago • 8

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published 2 days ago • 39

VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward

Paper • 2603.26599 • Published 6 days ago • 47

upvoted 2 papers 6 days ago

AVControl: Efficient Framework for Training Audio-Visual Controls

Paper • 2603.24793 • Published 8 days ago • 25

Less Gaussians, Texture More: 4K Feed-Forward Textured Splatting

Paper • 2603.25745 • Published 7 days ago • 13

upvoted a paper 8 days ago

RealMaster: Lifting Rendered Scenes into Photorealistic Video

Paper • 2603.23462 • Published 9 days ago • 31

upvoted a paper 9 days ago

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Paper • 2603.21986 • Published 10 days ago • 120

upvoted a paper 10 days ago

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 16 days ago • 106

upvoted 2 papers 13 days ago

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Paper • 2603.19227 • Published 14 days ago • 42

Matryoshka Gaussian Splatting

Paper • 2603.19234 • Published 14 days ago • 11

upvoted a paper 14 days ago

Coherent Human-Scene Reconstruction from Multi-Person Multi-View Video in a Single Pass

Paper • 2603.12789 • Published 21 days ago • 3

upvoted 2 papers 16 days ago

Learning Latent Proxies for Controllable Single-Image Relighting

Paper • 2603.15555 • Published 17 days ago • 8

Riemannian Motion Generation: A Unified Framework for Human Motion Representation and Generation via Riemannian Flow Matching

Paper • 2603.15016 • Published 17 days ago • 10

upvoted a paper 24 days ago

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published Feb 28 • 37

upvoted a paper 28 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 29 days ago • 178

upvoted a paper 29 days ago

Transformers converge to invariant algorithmic cores

Paper • 2602.22600 • Published Feb 26 • 3

upvoted a paper about 1 month ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 58