XinXia

XiaXin-Aloys's activity

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

upvoted 2 papers 6 months ago

Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals

Paper • 2510.27684 • Published Oct 31, 2025 • 23

Attention Sinks in Diffusion Language Models

Paper • 2510.15731 • Published Oct 17, 2025 • 50

upvoted 2 papers 7 months ago

Seedream 4.0: Toward Next-generation Multimodal Image Generation

Paper • 2509.20427 • Published Sep 24, 2025 • 84

Hyper-Bagel: A Unified Acceleration Framework for Multimodal Understanding and Generation

Paper • 2509.18824 • Published Sep 23, 2025 • 23

upvoted a paper 9 months ago

Qwen-Image Technical Report

Paper • 2508.02324 • Published Aug 4, 2025 • 274

upvoted 2 papers 11 months ago

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Paper • 2505.11594 • Published May 16, 2025 • 75

Emerging Properties in Unified Multimodal Pretraining

Paper • 2505.14683 • Published May 20, 2025 • 134

upvoted 2 papers 12 months ago

Seed1.5-VL Technical Report

Paper • 2505.07062 • Published May 11, 2025 • 157

Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities

Paper • 2505.02567 • Published May 5, 2025 • 82

upvoted 3 papers about 1 year ago

Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model

Paper • 2504.08685 • Published Apr 11, 2025 • 130

Training-free Diffusion Acceleration with Bottleneck Sampling

Paper • 2503.18940 • Published Mar 24, 2025 • 12

RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories

Paper • 2503.07699 • Published Mar 10, 2025 • 5

upvoted a paper over 1 year ago

Diffusion Adversarial Post-Training for One-Step Video Generation

Paper • 2501.08316 • Published Jan 14, 2025 • 36

upvoted a paper almost 2 years ago

Photorealistic Video Generation with Diffusion Models

Paper • 2312.06662 • Published Dec 11, 2023 • 24

upvoted a paper about 2 years ago

Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis

Paper • 2404.13686 • Published Apr 21, 2024 • 29