Proposes PerCo, an iterative diffusion-based image decoder, achieving ultra-low bitrate (0.003 bpp) with realistic reconstruction, surpassing state-of-the-art codecs.

Marlène Careil, Matthew J. Muckley, Jakob Verbeek et al.

Proposes a pseudo-generalized dynamic view synthesis method from monocular videos relying on geometry and temporal depth consistency, outperforming scene-specific approaches.

Xiaoming Zhao, Alex Colburn, Fangchang Ma et al.

OpenLEAF integrates LLMs and T2I models for high-quality image-text generation, enhancing consistency.

Jie An, Zhengyuan Yang, Linjie Li et al.

Uni3D employs end-to-end pretraining of a 2D ViT, scaled to 1 billion parameters, aligning 3D point clouds with image-text features, achieving state-of-the-art results.

Junsheng Zhou, Jinsheng Wang, Baorui Ma et al.

CoinSeg employs inter- and intra-class contrastive representations with multi-Gaussian modeling, achieving state-of-the-art performance on Pascal VOC and ADE20K, especially in long-term incremental scenarios.

Zekang Zhang, Guangyu Gao, Jianbo Jiao et al.

FLATTEN introduces flow-guided attention, significantly improving temporal consistency in text-to-video editing.

Yuren Cong, Mengmeng Xu, Christian Simon et al.

MAGVIT-v2 introduces a large-scale, shared vocabulary tokenizer with lookup-free quantization, surpassing diffusion models in image/video generation, compression, and recognition.

Lijun Yu, José Lezama, Nitesh B. Gundavarapu et al.

NOPE evaluates object hallucination in vision-language models, finding all models score below 10% accuracy on NegP datasets.

Holy Lovenia, Wenliang Dai, Samuel Cahyawijaya et al.

MagicDrive employs multi-view 3D geometry control with diffusion models, achieving high-fidelity street view synthesis for perception tasks.

Ruiyuan Gao, Kai Chen, Enze Xie et al.

Fine-tuning a viewpoint-aware diffusion model with coarse 3D priors achieves 85% consistency in text-to-3D generation, greatly reducing multi-view inconsistency.

Weiyu Li, Rui Chen, Xuelin Chen et al.

GPT-Driver transforms motion planning into a language modeling task using GPT-3.5, achieving 0.84m average L2 error on nuScenes, with high interpretability.

Jiageng Mao, Yuxi Qian, Junjie Ye et al.

DriveGPT4 leverages multimodal large language models for end-to-end interpretable autonomous driving, trained on BDD-X dataset, outperforming existing methods with significant improvements in control and explanation tasks.

Zhenhua Xu, Yujia Zhang, Enze Xie et al.

LVD leverages large language models to generate scene layouts guiding diffusion-based video synthesis, achieving high fidelity without training.

Long Lian, Baifeng Shi, Adam Yala et al.

Analyzed GPT-4V's multimodal capabilities, demonstrating superior performance in multi-domain tasks with visual marker understanding and prompting strategies.

Zhengyuan Yang, Linjie Li, Kevin Lin et al.

Introduces RIS-CQ benchmark and DUMOGA model, boosting complex semantic understanding and target localization by over 200%.

Wei Ji, Li Li, Hao Fei et al.

HoloAssist is a large-scale egocentric dataset combining multimodal data for training interactive AI assistants in real-world collaborative tasks.

Xin Wang, Taein Kwon, Mahdi Rad et al.

DreamGaussian uses generative Gaussian splatting to produce textured 3D meshes in 2 minutes, achieving 10x faster than prior methods.

Jiaxiang Tang, Jiawei Ren, Hang Zhou et al.

Show-1 combines pixel and latent diffusion models for efficient text-to-video generation, using only 15G GPU memory.

David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu et al.

TinyCLIP employs affinity mimicking and weight inheritance to compress CLIP by 50%, maintaining performance.

Kan Wu, Houwen Peng, Zhenghong Zhou et al.

Survey of multimodal foundation models evolving from specialized to general-purpose, covering vision and language capabilities.

Chunyuan Li, Zhe Gan, Zhengyuan Yang et al.