HelloZicky

[ICML 2026] Official implementation of "NaviCache: Test-Time Self-Calibration Caching for Video Generation".

ICML 2026 research code for NaviCache, a training-free method that speeds up AI video generation by skipping redundant computations when internal model states change very little between steps.

[WWW2023] PyTorch implementation of "DUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization".

[KDD2025] PyTorch implementation of "Collaboration of Large Language Models and Small Recommendation Models for Device-Cloud Recommendation".

[WWW2024 (Oral)] PyTorch implementation of "Intelligent Model Update Strategy for Sequential Recommendation".

[AAAI2025 (Oral)] PyTorch implementation of "Optimize Incompatible Parameters Through Compatibility-aware Knowledge Integration".

[MM2024] PyTorch implementation of "Semantic Codebook Learning for Dynamic Recommendation Models".

PyTorch implementation of Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion

AcadHomepage: A Modern and Responsive Academic Personal Homepage

No description.

Pytorch implementation of Detective

The fastest repo in history to surpass 50K stars ⭐, reaching the milestone in just 2 hours after publication. Better Harness Tools that make real things done. Now writing in Rust using oh-my-codex.

No description.