172 citations · 1.2k across the 32 of their papers we have counts for
30 papers · 1 filter
PixWizard: Versatile Image-to-Image Visual Assistant with Open-Language Instructions
Weifeng Lin, Xinyu Wei, Renrui Zhang +8
This paper presents a versatile image-to-image visual assistant, PixWizard, designed for image generation, manipulation, and translation based on free-from language instructions. T…
Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
Peng Gao, Le Zhuo, Dongyang Liu +17
Sora unveils the potential of scaling Diffusion Transformer for generating photorealistic images and videos at arbitrary resolutions, aspect ratios, and durations, yet it still lac…
Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT
Le Zhuo, Ruoyi Du, Han Xiao +19
Lumina-T2X is a nascent family of Flow-based Large Diffusion Transformers that establishes a unified framework for transforming noise into various modalities, such as images and vi…
SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Models
Ziyi Lin, Chris Liu, Renrui Zhang +13
We present SPHINX, a versatile multi-modal large language model (MLLM) with a joint mixing of model weights, tuning tasks, and visual embeddings. First, for stronger vision-languag…
Meta-Transformer: A Unified Framework for Multimodal Learning
Yiyuan Zhang, Kaixiong Gong, Kaipeng Zhang +4
Multimodal learning aims to build models that can process and relate information from multiple modalities. Despite years of development in this field, it still remains challenging…
Retrieving-to-Answer: Zero-Shot Video Question Answering with Frozen Large Language Models
Junting Pan, Ziyi Lin, Yuying Ge +5
Video Question Answering (VideoQA) has been significantly advanced from the scaling of recent Large Language Models (LLMs). The key idea is to convert the visual information into t…
LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models
Peng Xu, Wenqi Shao, Kaipeng Zhang +7
Large Vision-Language Models (LVLMs) have recently played a dominant role in multimodal vision-language learning. Despite the great success, it lacks a holistic evaluation of their…
DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds
Tao Ma, Xuemeng Yang, Hongbin Zhou +9
Existing offboard 3D detectors always follow a modular pipeline design to take advantage of unlimited sequential point clouds. We have found that the full potential of offboard 3D…
DiffInDScene: Diffusion-based High-Quality 3D Indoor Scene Generation
Xiaoliang Ju, Zhaoyang Huang, Yijin Li +3
We present DiffInDScene, a novel framework for tackling the problem of high-quality 3D indoor scene generation, which is challenging due to the complexity and diversity of the indo…
Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation
Shilin Yan, Renrui Zhang, Ziyu Guo +7
Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challengin…
LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model
Peng Gao, Jiaming Han, Renrui Zhang +9
How to efficiently transform large language models (LLMs) into instruction followers is recently a popular research direction, while training LLM for multi-modal reasoning remains…
Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners
Renrui Zhang, Xiangfei Hu, Bohao Li +5
Visual recognition in low-data regimes requires deep neural networks to learn generalized representations from limited training samples. Recently, CLIP-based methods have shown pro…
LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention
Renrui Zhang, Jiaming Han, Chris Liu +7
We present LLaMA-Adapter, a lightweight adaption method to efficiently fine-tune LLaMA into an instruction-following model. Using 52K self-instruct demonstrations, LLaMA-Adapter on…
Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders
Renrui Zhang, Liuhui Wang, Yu Qiao +2
Pre-training by numerous image data has become de-facto for robust 2D representations. In contrast, due to the expensive data acquisition and annotation, a paucity of large-scale 3…
Stare at What You See: Masked Image Modeling without Reconstruction
Hongwei Xue, Peng Gao, Hongyang Li +4
Masked Autoencoders (MAE) have been prevailing paradigms for large-scale vision representation pre-training. By reconstructing masked image patches from a small portion of visible…
Recurrent Bilinear Optimization for Binary Neural Networks
Sheng Xu, Yanjing Li, Tiancheng Wang +6
Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an esse…
Collaboration of Pre-trained Models Makes Better Few-shot Learner
Renrui Zhang, Bohao Li, Wei Zhang +4
Few-shot classification requires deep neural networks to learn generalized representations only from limited training images, which is challenging but significant in low-data regim…
Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
Renrui Zhang, Zhang Wei, Rongyao Fang +5
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive per…
ConvMAE: Masked Convolution Meets Masked Autoencoders
Peng Gao, Teli Ma, Hongsheng Li +3
Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer…
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
Ziteng Cui, Kunchang Li, Lin Gu +5
Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision…
Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training
Renrui Zhang, Ziyu Guo, Rongyao Fang +5
Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for language and 2D image transformers. However, it still remains an open question on how to e…
POS-BERT: Point Cloud One-Stage BERT Pre-Training
Kexue Fu, Peng Gao, ShaoLei Liu +3
Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, dire…
MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection
Renrui Zhang, Han Qiu, Tai Wang +7
Monocular 3D object detection has long been a challenging task in autonomous driving. Most existing methods follow conventional 2D detectors to first localize object centers, and t…
Distillation with Contrast is All You Need for Self-Supervised Point Cloud Representation Learning
Kexue Fu, Peng Gao, Renrui Zhang +3
In this paper, we propose a simple and general framework for self-supervised point cloud representation learning. Human beings understand the 3D world by extracting two levels of i…