849 citations · 2.4k across the 172 of their papers we have counts for
88 papers · 1 filter
The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation
Guannan Lai, Da-Wei Zhou, Zhenguo Li +1
Continual Test-Time Adaptation (CTTA) aims to enable models to adapt online to unlabeled data streams under distribution shift without accessing source data. Existing CTTA methods…
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
Yao Teng, Fuyun Wang, Xian Liu +7
As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requir…
Reasoning-Aligned Perception Decoupling for Scalable Multi-modal Reasoning
Yunhao Gou, Kai Chen, Zhili Liu +5
Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, h…
FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities
Jin Wang, Yao Lai, Aoxue Li +6
The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation with…
Adding Additional Control to One-Step Diffusion with Joint Distribution Matching
Yihong Luo, Tianyang Hu, Yifan Song +3
While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as nove…
Empowering Sparse-Input Neural Radiance Fields with Dual-Level Semantic Guidance from Dense Novel Views
Yingji Zhong, Kaichen Zhou, Zhihao Li +3
Neural Radiance Fields (NeRF) have shown remarkable capabilities for photorealistic novel view synthesis. One major deficiency of NeRF is that dense inputs are typically required,…
Corrupted but Not Broken: Understanding and Mitigating the Negative Impacts of Corrupted Data in Visual Instruction Tuning
Yunhao Gou, Hansi Yang, Zhili Liu +8
Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), yet its effectiveness is often compromised by corrupted datasets with issues such as hallu…
LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation
Jiahao Wang, Ning Kang, Lewei Yao +12
In this paper, we investigate how to convert a pre-trained Diffusion Transformer (DiT) into a linear DiT, as its simplicity, parallelism, and efficiency for image generation. Throu…
Efficient Multi-modal Large Language Models via Visual Token Grouping
Minbin Huang, Runhui Huang, Han Shi +6
The development of Multi-modal Large Language Models (MLLMs) enhances Large Language Models (LLMs) with the ability to perceive data formats beyond text, significantly advancing a…
MagicDrive-V2: High-Resolution Long Video Generation for Autonomous Driving with Adaptive Control
Ruiyuan Gao, Kai Chen, Bo Xiao +3
The rapid advancement of diffusion models has greatly improved video synthesis, especially in controllable video generation, which is vital for applications like autonomous driving…
Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
Yao Teng, Han Shi, Xian Liu +5
The current large auto-regressive models can generate high-quality, high-resolution images, but these models require hundreds or even thousands of steps of next-token prediction du…
EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions
Kai Chen, Yunhao Gou, Runhui Huang +28
GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language…
T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation
Kaiyue Sun, Kaiyi Huang, Xian Liu +4
Text-to-video (T2V) generative models have advanced significantly, yet their ability to compose different objects, attributes, actions, and motions into a video remains unexplored.…
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
Mingyang Yi, Aoxue Li, Yi Xin +1
Recently, the strong latent Diffusion Probabilistic Model (DPM) has been applied to high-quality Text-to-Image (T2I) generation (e.g., Stable Diffusion), by injecting the encoded t…
Enhancing Text-to-Image Editing via Hybrid Mask-Informed Fusion
Aoxue Li, Mingyang Yi, Zhenguo Li
Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the exp…
MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes
Ruiyuan Gao, Kai Chen, Zhihao Li +3
Controllable generative models for images and videos have seen significant success, yet 3D scene generation, especially in unbounded scenarios like autonomous driving, remains unde…
DiM: Diffusion Mamba for Efficient High-Resolution Image Synthesis
Yao Teng, Yue Wu, Han Shi +5
Diffusion models have achieved great success in image generation, with the backbone evolving from U-Net to Vision Transformers. However, the computational cost of Transformers is q…
DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection
Lewei Yao, Renjie Pi, Jianhua Han +5
Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introd…
Automated Evaluation of Large Vision-Language Models on Self-driving Corner Cases
Kai Chen, Yanze Li, Wenhua Zhang +10
Large Vision-Language Models (LVLMs) have received widespread attention for advancing the interpretable self-driving. Existing evaluations of LVLMs primarily focus on multi-faceted…
CVT-xRF: Contrastive In-Voxel Transformer for 3D Consistent Radiance Fields from Sparse Inputs
Yingji Zhong, Lanqing Hong, Zhenguo Li +1
Neural Radiance Fields (NeRF) have shown impressive capabilities for photorealistic novel view synthesis when trained on dense inputs. However, when trained on sparse inputs, NeRF…
Editing Massive Concepts in Text-to-Image Diffusion Models
Tianwei Xiong, Yue Wu, Enze Xie +2
Text-to-image diffusion models suffer from the risk of generating outdated, copyrighted, incorrect, and biased content. While previous methods have mitigated the issues on a small…
DetDiffusion: Synergizing Generative and Perceptive Models for Enhanced Data Generation and Perception
Yibo Wang, Ruiyuan Gao, Kai Chen +8
Current perceptive models heavily depend on resource-intensive datasets, prompting the need for innovative solutions. Leveraging recent advances in diffusion models, synthetic data…
PixArt-Σ: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation
Junsong Chen, Chongjian Ge, Enze Xie +7
In this paper, we introduce PixArt-Σ, a Diffusion Transformer model~(DiT) capable of directly generating images at 4K resolution. PixArt-Σrepresents a significant advancement over…
Open-Vocabulary Object Detection with Meta Prompt Representation and Instance Contrastive Optimization
Zhao Wang, Aoxue Li, Fengwei Zhou +2
Classical object detectors are incapable of detecting novel class objects that are not encountered before. Regarding this issue, Open-Vocabulary Object Detection (OVOD) is proposed…