knightnemo's picture

2 48 3

knightnemo

knightnemo

·

https://knightnemo.github.io

AI & ML interests

World Models, Generative Models, VLA Models, Reinforcement Learning

Recent Activity

published a model 6 days ago

knightnemo/dummy_repo_id

published a model 8 days ago

thuml/Vid2World-RT1-Shift

published a model 8 days ago

thuml/Vid2World-RT1-Masked

View all activity

Organizations

upvoted a paper 24 days ago

Generative Neural Video Compression via Video Diffusion Prior

Paper • 2512.05016 • Published 26 days ago • 9

upvoted a paper 28 days ago

What about gravity in video generation? Post-Training Newton's Laws with Verifiable Rewards

Paper • 2512.00425 • Published about 1 month ago • 49

upvoted 11 papers about 1 month ago

First Frame Is the Place to Go for Video Content Customization

Paper • 2511.15700 • Published Nov 19 • 52

WorldGen: From Text to Traversable and Interactive 3D Worlds

Paper • 2511.16825 • Published Nov 20 • 23

RynnVLA-002: A Unified Vision-Language-Action and World Model

Paper • 2511.17502 • Published Nov 21 • 25

SAM 3: Segment Anything with Concepts

Paper • 2511.16719 • Published Nov 20 • 122

HunyuanVideo 1.5 Technical Report

Paper • 2511.18870 • Published Nov 24 • 23

GigaWorld-0: World Models as Data Engine to Empower Embodied AI

Paper • 2511.19861 • Published Nov 25 • 30

Terminal Velocity Matching

Paper • 2511.19797 • Published Nov 24 • 12

Inferix: A Block-Diffusion based Next-Generation Inference Engine for World Simulation

Paper • 2511.20714 • Published Nov 25 • 47

P1: Mastering Physics Olympiads with Reinforcement Learning

Paper • 2511.13612 • Published Nov 17 • 133

Depth Anything 3: Recovering the Visual Space from Any Views

Paper • 2511.10647 • Published Nov 13 • 95

One Small Step in Latent, One Giant Leap for Pixels: Fast Latent Upscale Adapter for Your Diffusion Models

Paper • 2511.10629 • Published Nov 13 • 123

upvoted a paper about 2 months ago

PAN: A World Model for General, Interactable, and Long-Horizon World Simulation

Paper • 2511.09057 • Published Nov 12 • 76

upvoted a paper 2 months ago

VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

Paper • 2510.14902 • Published Oct 16 • 15

upvoted 5 papers 3 months ago

Diffusion Transformers with Representation Autoencoders

Paper • 2510.11690 • Published Oct 13 • 165

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

Paper • 2509.26633 • Published Sep 30 • 5

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6 • 500

LongLive: Real-time Interactive Long Video Generation

Paper • 2509.22622 • Published Sep 26 • 184

Video models are zero-shot learners and reasoners

Paper • 2509.20328 • Published Sep 24 • 98