Zhiyuan Ma PRO

ZhiyuanthePony's activity

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

upvoted 2 papers 3 days ago

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

Paper • 2604.14268 • Published 5 days ago • 89

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published 5 days ago • 140

upvoted a paper 4 days ago

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Paper • 2604.07429 • Published 12 days ago • 110

upvoted a paper 5 days ago

Lyra 2.0: Explorable Generative 3D Worlds

Paper • 2604.13036 • Published 6 days ago • 36

upvoted a paper 25 days ago

GameplayQA: A Benchmarking Framework for Decision-Dense POV-Synced Multi-Video Understanding of 3D Virtual Agents

Paper • 2603.24329 • Published 25 days ago • 28

upvoted a paper about 1 month ago

Attention Residuals

Paper • 2603.15031 • Published Mar 16 • 180

upvoted a paper about 2 months ago

CubeComposer: Spatio-Temporal Autoregressive 4K 360° Video Generation from Perspective Video

Paper • 2603.04291 • Published Mar 4 • 14

upvoted 2 papers 3 months ago

Advancing Open-source World Models

Paper • 2601.20540 • Published Jan 28 • 135

VerseCrafter: Dynamic Realistic Video World Model with 4D Geometric Control

Paper • 2601.05138 • Published Jan 8 • 18

upvoted 5 papers 5 months ago

Qwen3-VL Technical Report

Paper • 2511.21631 • Published Nov 26, 2025 • 161

DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

Paper • 2512.02556 • Published Dec 2, 2025 • 265

TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models

Paper • 2512.02014 • Published Dec 1, 2025 • 74

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

Paper • 2511.20714 • Published Nov 25, 2025 • 50

Kinematify: Open-Vocabulary Synthesis of High-DoF Articulated Objects

Paper • 2511.01294 • Published Nov 3, 2025 • 14

upvoted 6 papers 6 months ago

FullPart: Generating each 3D Part at Full Resolution

Paper • 2510.26140 • Published Oct 30, 2025 • 7

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 114

FlashWorld: High-quality 3D Scene Generation within Seconds

Paper • 2510.13678 • Published Oct 15, 2025 • 74

FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution

Paper • 2510.12747 • Published Oct 14, 2025 • 39

InfiniHuman: Infinite 3D Human Creation with Precise Control

Paper • 2510.11650 • Published Oct 13, 2025 • 6

Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation

Paper • 2510.08673 • Published Oct 9, 2025 • 127