Xin Xie

Shelsin's activity

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

upvoted a paper 25 days ago

Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR

Paper • 2610.16105 • Published Oct 12 • 13

upvoted a paper about 1 month ago

ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience

Paper • 2610.05303 • Published Oct 4 • 20

upvoted a paper 8 months ago

Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation

Paper • 2506.19348 • Published Jun 24, 2025 • 1

authored 3 papers 8 months ago

Training-Free Motion Customization for Distilled Video Generators with Adaptive Test-Time Distillation

Paper • 2506.19348 • Published Jun 24, 2025 • 1

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

Paper • 2601.15968 • Published Jan 22 • 9

DyMO: Training-Free Diffusion Model Alignment with Dynamic Multi-Objective Scheduling

Paper • 2412.00759 • Published Dec 1, 2024

upvoted 2 papers 8 months ago

On Token's Dilemma: Dynamic MoE with Drift-Aware Token Assignment for Continual Learning of Large Vision Language Models

Paper • 2603.27481 • Published Mar 29 • 33

HyperAlign: Hypernetwork for Efficient Test-Time Alignment of Diffusion Models

Paper • 2601.15968 • Published Jan 22 • 9

upvoted a paper 12 months ago

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

Paper • 2512.03041 • Published Dec 2, 2025 • 64