Deyuan Liu PRO

SempraETY's activity

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

upvoted 8 papers 1 day ago

Agents' Last Exam

Paper • 2606.05405 • Published 25 days ago • 366

Looped World Models

Paper • 2606.18208 • Published 12 days ago • 466

Qwen-Image-Agent: Bridging the Context Gap in Real-World Image Generation

Paper • 2606.26907 • Published 3 days ago • 39

Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models

Paper • 2606.25473 • Published 4 days ago • 22

Unlimited OCR Works

Paper • 2606.23050 • Published 6 days ago • 37

Wan-Streamer v0.1: End-to-end Real-time Interactive Foundation Models

Paper • 2606.25041 • Published 5 days ago • 87

Qwen-AgentWorld: Language World Models for General Agents

Paper • 2606.24597 • Published 5 days ago • 133

DanceOPD: On-Policy Generative Field Distillation

Paper • 2606.27377 • Published 3 days ago • 64

upvoted an article 26 days ago

view article

Article

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

• 

nvidia

•

27 days ago

• 83

upvoted a paper about 1 month ago

Causal Forcing++: Scalable Few-Step Autoregressive Diffusion Distillation for Real-Time Interactive Video Generation

Paper • 2605.15141 • Published May 14 • 96

upvoted 3 papers 2 months ago

LLaDA2.0-Uni: Unifying Multimodal Understanding and Generation with Diffusion Large Language Model

Paper • 2604.20796 • Published Apr 22 • 244

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published Apr 15 • 167

Self-Adversarial One Step Generation via Condition Shifting

Paper • 2604.12322 • Published Apr 14 • 13

upvoted a paper 3 months ago

Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training

Paper • 2603.16139 • Published Mar 17 • 33

upvoted an article 4 months ago

view article

Article

NEO-unify: Building Native Multimodal Unified Models End to End

• 

sensenova

•

Mar 5

• 167

upvoted a paper 6 months ago

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

Paper • 2601.07832 • Published Jan 12 • 53

upvoted a collection 6 months ago

TwinFlow

Collection

A collection of TwinFlow-accelerated diffusion models • 4 items • Updated 12 days ago • 7

upvoted 2 papers 7 months ago

Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

Paper • 2512.08765 • Published Dec 9, 2025 • 134

TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows

Paper • 2512.05150 • Published Dec 3, 2025 • 77

upvoted a paper about 1 year ago

Model Merging in Pre-training of Large Language Models

Paper • 2505.12082 • Published May 17, 2025 • 40