Liu Songhua

Huage001's activity

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

upvoted 2 papers 11 days ago

ShotPlan: Cinematic Video Generation with Learnable Planning Token

Paper • 2607.17675 • Published 13 days ago • 6

DiFA: Inference-Time Forward-Process Alignment for Diffusion Models

Paper • 2607.17972 • Published 13 days ago • 7

upvoted 4 papers 19 days ago

Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator

Paper • 2607.05765 • Published 26 days ago • 3

CineMobile: On-Device Image-to-Video Diffusion for Cinematic Camera Motion Generation

Paper • 2607.03803 • Published 29 days ago • 19

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 26 days ago • 95

Unified Audio Intelligence Without Regressing on Text Intelligence

Paper • 2607.05196 • Published 27 days ago • 23

upvoted 2 papers 24 days ago

Flex-Forcing: Towards a Unified Autoregressive and Bidirectional Video Diffusion Model

Paper • 2607.03509 • Published 30 days ago • 14

Infinite Worlds with Versatile Interactions

Paper • 2607.07534 • Published 25 days ago • 46

upvoted a paper about 2 months ago

Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models

Paper • 2606.03988 • Published Jun 3 • 126

upvoted a paper 2 months ago

Unified Panoramic Geometry Estimation via Multi-View Foundation Models

Paper • 2605.26368 • Published May 25 • 4

upvoted a paper 3 months ago

Continuous Latent Diffusion Language Model

Paper • 2605.06548 • Published May 7 • 87

upvoted a paper 5 months ago

ViFeEdit: A Video-Free Tuner of Your Video Diffusion Transformer

Paper • 2603.15478 • Published Mar 16 • 24

upvoted 2 papers 6 months ago

VideoAR: Autoregressive Video Generation via Next-Frame & Scale Prediction

Paper • 2601.05966 • Published Jan 9 • 23

CoDance: An Unbind-Rebind Paradigm for Robust Multi-Subject Animation

Paper • 2601.11096 • Published Jan 16 • 8

upvoted 6 papers 7 months ago

Knot Forcing: Taming Autoregressive Video Diffusion Models for Real-time Infinite Interactive Portrait Animation

Paper • 2512.21734 • Published Dec 25, 2025 • 5

SpotEdit: Selective Region Editing in Diffusion Transformers

Paper • 2512.22323 • Published Dec 26, 2025 • 39

Streaming Video Instruction Tuning

Paper • 2512.21334 • Published Dec 24, 2025 • 11

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Paper • 2512.21004 • Published Dec 24, 2025 • 13

Region-Constraint In-Context Generation for Instructional Video Editing

Paper • 2512.17650 • Published Dec 19, 2025 • 53

TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times

Paper • 2512.16093 • Published Dec 18, 2025 • 96