172 citations · 1.2k across the 42 of their papers we have counts for
41 papers · 1 filter
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…
MChat: Empowering VLM for Multimodal LLM Interleaved Text-Image Generation
Xiaowei Chi, Junbo Qi, Rongyu Zhang +3
While current LLM chatbots like GPT-4V bridge the gap between human instructions and visual representations to enable text-image generations, they still lack efficient alignment me…
Improving Compositional Text-to-image Generation with Large Vision-Language Models
Song Wen, Guian Fang, Renrui Zhang +3
Recent advancements in text-to-image models, particularly diffusion models, have shown significant promise. However, compositional text-to-image models frequently encounter difficu…
NTO3D: Neural Target Object 3D Reconstruction with Segment Anything
Xiaobao Wei, Renrui Zhang, Jiarui Wu +4
Neural 3D reconstruction from multi-view images has recently attracted increasing attention from the community. Existing methods normally learn a neural field for the whole scene,…
RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
Mingjie Pan, Jiaming Liu, Renrui Zhang +6
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels. Recent…
Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following
Ziyu Guo, Renrui Zhang, Xiangyang Zhu +8
We introduce Point-Bind, a 3D multi-modality model aligning point clouds with 2D image, language, audio, and video. Guided by ImageBind, we construct a joint embedding space betwee…
Revisiting Event-based Video Frame Interpolation
Jiaben Chen, Yichen Zhu, Dongze Lian +7
Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining bot…
JourneyDB: A Benchmark for Generative Image Understanding
Keqiang Sun, Junting Pan, Yuying Ge +11
While recent advancements in vision-language models have had a transformative impact on multi-modal comprehension, the extent to which these models possess the ability to comprehen…
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…
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…
Personalize Segment Anything Model with One Shot
Renrui Zhang, Zhengkai Jiang, Ziyu Guo +6
Driven by large-data pre-training, Segment Anything Model (SAM) has been demonstrated as a powerful and promptable framework, revolutionizing the segmentation models. Despite the g…
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…
Not All Features Matter: Enhancing Few-shot CLIP with Adaptive Prior Refinement
Xiangyang Zhu, Renrui Zhang, Bowei He +4
The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-…
PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
Anthony Chen, Kevin Zhang, Renrui Zhang +4
Masked Autoencoders learn strong visual representations and achieve state-of-the-art results in several independent modalities, yet very few works have addressed their capabilities…
Mimic before Reconstruct: Enhancing Masked Autoencoders with Feature Mimicking
Peng Gao, Renrui Zhang, Rongyao Fang +4
Masked Autoencoders (MAE) have been popular paradigms for large-scale vision representation pre-training. However, MAE solely reconstructs the low-level RGB signals after the decod…
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…
ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance
Zoey Guo, Yiwen Tang, Ray Zhang +4
Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view c…
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…
Parameter is Not All You Need: Starting from Non-Parametric Networks for 3D Point Cloud Analysis
Renrui Zhang, Liuhui Wang, Ziyu Guo +4
We present a Non-parametric Network for 3D point cloud analysis, Point-NN, which consists of purely non-learnable components: farthest point sampling (FPS), k-nearest neighbors (k-…
Nearest Neighbors Meet Deep Neural Networks for Point Cloud Analysis
Renrui Zhang, Liuhui Wang, Ziyu Guo +1
Performances on standard 3D point cloud benchmarks have plateaued, resulting in oversized models and complex network design to make a fractional improvement. We present an alternat…
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning
Peixiang Huang, Li Liu, Renrui Zhang +4
To achieve accurate and low-cost 3D object detection, existing methods propose to benefit camera-based multi-view detectors with spatial cues provided by the LiDAR modality, e.g.,…
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…
iQuery: Instruments as Queries for Audio-Visual Sound Separation
Jiaben Chen, Renrui Zhang, Dongze Lian +3
Current audio-visual separation methods share a standard architecture design where an audio encoder-decoder network is fused with visual encoding features at the encoder bottleneck…
Decorate the Newcomers: Visual Domain Prompt for Continual Test Time Adaptation
Yulu Gan, Yan Bai, Yihang Lou +4
Continual Test-Time Adaptation (CTTA) aims to adapt the source model to continually changing unlabeled target domains without access to the source data. Existing methods mainly foc…