Harold Chen

Harold328's activity

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

upvoted a paper 19 days ago

Speed Always Wins: A Survey on Efficient Architectures for Large Language Models

Paper • 2508.09834 • Published 25 days ago • 52

upvoted a paper about 1 month ago

LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation

Paper • 2508.03694 • Published Aug 5 • 50

upvoted a paper about 2 months ago

StreamDiT: Real-Time Streaming Text-to-Video Generation

Paper • 2507.03745 • Published Jul 4 • 29

upvoted 3 papers 4 months ago

FinePhys: Fine-grained Human Action Generation by Explicitly Incorporating Physical Laws for Effective Skeletal Guidance

Paper • 2505.13437 • Published May 19 • 5

Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks

Paper • 2505.00234 • Published May 1 • 26

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Paper • 2505.00703 • Published May 1 • 45

upvoted 2 papers 5 months ago

Packing Input Frame Context in Next-Frame Prediction Models for Video Generation

Paper • 2504.12626 • Published Apr 17 • 52

VistaDPO: Video Hierarchical Spatial-Temporal Direct Preference Optimization for Large Video Models

Paper • 2504.13122 • Published Apr 17 • 21

upvoted 2 papers 6 months ago

Temporal Regularization Makes Your Video Generator Stronger

Paper • 2503.15417 • Published Mar 19 • 22

LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization

Paper • 2503.08619 • Published Mar 11 • 20

upvoted a paper 8 months ago

SeFAR: Semi-supervised Fine-grained Action Recognition with Temporal Perturbation and Learning Stabilization

Paper • 2501.01245 • Published Jan 2 • 5

upvoted 3 papers 9 months ago

VideoGen-of-Thought: A Collaborative Framework for Multi-Shot Video Generation

Paper • 2412.02259 • Published Dec 3, 2024 • 61

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

Paper • 2411.17440 • Published Nov 26, 2024 • 38

OmniCreator: Self-Supervised Unified Generation with Universal Editing

Paper • 2412.02114 • Published Dec 3, 2024 • 14