chengengliu
Follow
Starred repositories
Writing AI Conference Papers: A Handbook for Beginners
CVPR 2025 | Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond
SLIT-AI / ADPA
Forked from gaoshiping/ADPA[ICLR2025 Spotlight] Advantage-Guided Distillation for Preference Alignment in Small Language Models
The official implementation of "Cross-modal Causal Relation Alignment for Video Question Grounding. (CVPR 2025 Highlight)"
Bring background images to your vscode. vscode background 背景扩展插件。
✨First Open-Source R1-like Video-LLM [2025/02/18]
Fully open reproduction of DeepSeek-R1
The repo for "Distill Any Depth: Distillation Creates a Stronger Monocular Depth Estimator"
Download market data from Yahoo! Finance's API
User-friendly Desktop Client App for AI Models/LLMs (GPT, Claude, Gemini, Ollama...)
[ICLR 2023 Oral] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Unmixing Diffusion for Self-Supervised Hyperspectral Image Denoising
Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.
[ICLR'25] Official PyTorch implementation of "Framer: Interactive Frame Interpolation".
Example code for data-driven and physics-driven deep learning phase recovery
[CVPR 2024] Real-Time HDR Video Reconstruction
[CVPR2024 🏆 Best Paper Candidate] CorrMLP: Correlation-aware MLP-based networks for deformable medical image registration
🦦 Otter, a multi-modal model based on OpenFlamingo (open-sourced version of DeepMind's Flamingo), trained on MIMIC-IT and showcasing improved instruction-following and in-context learning ability.
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
Collection of AWESOME vision-language models for vision tasks
NeurIPS 2024: Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
MiniCPM4: Ultra-Efficient LLMs on End Devices, achieving 5+ speedup on typical end-side chips
[NeurIPS 2023] FouriDown: Factoring Down-Sampling into Shuffling and Superposing
