Haoge Deng

Bitterdhg's activity

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

authored a paper 3 days ago

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

Paper • 2604.18518 • Published 18 days ago • 7

liked 2 models 3 days ago

Yovecents/URSA-1.7B-IBQ512-UDMGRPO-PickScore

Text-to-Image • Updated 16 days ago • 59 • 2

Yovecents/URSA-1.7B-IBQ512-UDMGRPO-GenEval

Text-to-Image • Updated 16 days ago • 26 • 2

upvoted a paper 3 days ago

UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models

Paper • 2604.18518 • Published 18 days ago • 7

upvoted a paper 3 months ago

FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation

Paper • 2601.13976 • Published Jan 20 • 22

upvoted a paper 5 months ago

The Prism Hypothesis: Harmonizing Semantic and Pixel Representations via Unified Autoencoding

Paper • 2512.19693 • Published Dec 22, 2025 • 68

authored a paper 6 months ago

Emu3.5: Native Multimodal Models are World Learners

Paper • 2510.26583 • Published Oct 30, 2025 • 115

liked 4 models 6 months ago

BAAI/URSA-0.6B-IBQ1024

Text-to-Image • Updated Nov 2, 2025 • 519 • 6

BAAI/URSA-0.6B-FSQ320

Text-to-Video • Updated Nov 2, 2025 • 20 • 5

BAAI/URSA-1.7B-IBQ1024

Text-to-Image • Updated Oct 30, 2025 • 148 • 5

BAAI/URSA-1.7B-FSQ320

Text-to-Video • Updated Oct 29, 2025 • 539 • 9

liked a Space 6 months ago

Runtime error

Agents

22

URSA-1.7B-FSQ320

🎞

22

URSA Text-to-Image-to-Video

liked 3 models 6 months ago

BAAI/Emu3.5-VisionTokenizer

0.5B • Updated Jan 4 • 1.2k • 26

BAAI/Emu3.5

Any-to-Any • Updated Dec 25, 2025 • 677 • 171

BAAI/Emu3.5-Image

Image-Text-to-Image • 34B • Updated Dec 25, 2025 • 323 • 75

upvoted 2 collections 6 months ago

🐻 URSA

Collection

URSA: Uniform Discrete Diffusion with Metric Path for Video Generation • 8 items • Updated 15 days ago • 9

Emu3.5

Collection

Native Multimodal Models are World Learners 🌍 • 4 items • Updated Feb 4 • 77

authored 3 papers 6 months ago

EVEv2: Improved Baselines for Encoder-Free Vision-Language Models

Paper • 2502.06788 • Published Feb 10, 2025 • 14

OmniGen2: Exploration to Advanced Multimodal Generation

Paper • 2506.18871 • Published Jun 23, 2025 • 78

CI-VID: A Coherent Interleaved Text-Video Dataset

Paper • 2507.01938 • Published Jul 2, 2025 • 1