Stars
DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data
Resources and paper list for "Thinking with Images for LVLMs". This repository accompanies our survey on how LVLMs can leverage visual information for complex reasoning, planning, and generation.
Official repository of the paper "A Glimpse to Compress: Dynamic Visual Token Pruning for Large Vision-Language Models"
Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment [ICCV 2025] - Official implementation
[CVPR 2025] DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation & [ICLR 2024] DFormer & [NeuriPS 2025] OmniSegmentor
[ICCV 2025] This is the official PyTorch codes for the paper: "DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"
Official Code for 'AR-1-to-3: Single Image to Consistent 3D Object Generation via Next-View Prediction' (ICCV 2025)
Official Code for 'TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction' (ICCV 2025)
Official Release of ICCV 2025 paper -- DiscretizedSDF
Awsome of VLM-CL. Continual Learning for VLMs: A Survey and Taxonomy Beyond Forgetting
A clean and simple data loading library for Continual Learning
[NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think
Official code for the paper: Depth Anything At Any Condition
This is the repo for "Adaptive Unimodal Regulation for Balanced Multimodal Information Acquisition", CVPR2025.
[CVPR2025] Iterative Predictor-Critic Code Decoding for Real-World Image Dehazing
[ICLR 2025 Oral🔥] SD-LoRA: Scalable Decoupled Low-Rank Adaptation for Class Incremental Learning
GET: Unlocking the Multi-modal Potential of CLIP for Generalized Category Discovery （CVPR2025）
Virtual whiteboard for sketching hand-drawn like diagrams
[ECCV 2024] Restore Anything with Masks: Leveraging Mask Image Modeling for Blind All-in-One Image Restoration
Generative Multi-modal Models are Good Class Incremental Learners, CVPR 2024 [PyTorch Code]
Official PyTorch implementation of our ECCV2024 paper “Rethinking Few-shot Class-incremental Learning: Learning from Yourself”
Official repository for "CLIP model is an Efficient Continual Learner".