Lars Vagnes

larsh0103's activity

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

upvoted a paper about 16 hours ago

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

Paper • 2603.19227 • Published 1 day ago • 35

upvoted a paper about 22 hours ago

Matryoshka Gaussian Splatting

Paper • 2603.19234 • Published 1 day ago • 3

upvoted a paper 1 day ago

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

Paper • 2603.12789 • Published 8 days ago • 1

upvoted 2 papers 4 days ago

Learning Latent Proxies for Controllable Single-Image Relighting

Paper • 2603.15555 • Published 5 days ago • 8

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

Paper • 2603.15016 • Published 5 days ago • 10

upvoted a paper 12 days ago

WildActor: Unconstrained Identity-Preserving Video Generation

Paper • 2603.00586 • Published 21 days ago • 37

upvoted a paper 16 days ago

Helios: Real Real-Time Long Video Generation Model

Paper • 2603.04379 • Published 17 days ago • 172

upvoted a paper 17 days ago

Transformers converge to invariant algorithmic cores

Paper • 2602.22600 • Published 23 days ago • 3

upvoted a paper 19 days ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published 22 days ago • 58

upvoted a paper 22 days ago

EmbodMocap: In-the-Wild 4D Human-Scene Reconstruction for Embodied Agents

Paper • 2602.23205 • Published 23 days ago • 11

upvoted a paper 26 days ago

Generated Reality: Human-centric World Simulation using Interactive Video Generation with Hand and Camera Control

Paper • 2602.18422 • Published 29 days ago • 30

upvoted 5 papers about 1 month ago

UniWeTok: An Unified Binary Tokenizer with Codebook Size 2^{128} for Unified Multimodal Large Language Model

Paper • 2602.14178 • Published Feb 15 • 13

SemanticMoments: Training-Free Motion Similarity via Third Moment Features

Paper • 2602.09146 • Published Feb 9 • 21

OneVision-Encoder: Codec-Aligned Sparsity as a Foundational Principle for Multimodal Intelligence

Paper • 2602.08683 • Published Feb 9 • 52

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

Paper • 2602.07106 • Published Feb 6 • 11

Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging

Paper • 2602.04805 • Published Feb 4 • 6

upvoted 2 papers about 2 months ago

DreamActor-M2: Universal Character Image Animation via Spatiotemporal In-Context Learning

Paper • 2601.21716 • Published Jan 29 • 13

360Anything: Geometry-Free Lifting of Images and Videos to 360°

Paper • 2601.16192 • Published Jan 22 • 9

upvoted 2 papers 2 months ago

DualTalk: Dual-Speaker Interaction for 3D Talking Head Conversations

Paper • 2505.18096 • Published May 23, 2025 • 1

SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation

Paper • 2507.09862 • Published Jul 14, 2025 • 51