Related papers: SAR3D: Autoregressive 3D Object Generation and Und…

Large Vision Language Models (LVLMs) have shown strong capabilities in understanding and analyzing visual scenes across various domains. However, in the context of autonomous driving, their limited comprehension of 3D environments restricts…

Open-set perception in complex traffic environments poses a critical challenge for autonomous driving systems, particularly in identifying previously unseen object categories, which is vital for ensuring safety. Visual Language Models…

Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used…

Visual autoregressive (AR) generation models have demonstrated strong potential for image generation, yet their next-token-prediction paradigm introduces considerable inference latency. Although speculative decoding (SD) has been proven…

3D fragment reassembly aims to recover the rigid poses of unordered fragment point clouds or meshes in a common object coordinate system to reconstruct the complete shape. The problem becomes particularly challenging as the number of…

Recent developments related to generative models have made it possible to generate diverse high-fidelity images. In particular, layout-to-image generation models have gained significant attention due to their capability to generate…

Without knowledge of specific pockets, generating ligands based on the global structure of a protein target plays a crucial role in drug discovery as it helps reduce the search space for potential drug-like candidates in the pipeline.…

Accurate, fast, and reliable 3D perception is essential for autonomous driving. Recently, bird's-eye view (BEV)-based perception approaches have emerged as superior alternatives to perspective-based solutions, offering enhanced spatial…

Visual AutoRegressive (VAR) modeling has garnered significant attention for its innovative next-scale prediction paradigm. However, mainstream VAR paradigms attend to all tokens across historical scales at each autoregressive step. As the…

In autoregressive (AR) image generation, models based on the 'next-token prediction' paradigm of LLMs have shown comparable performance to diffusion models by reducing inductive biases. However, directly applying LLMs to complex image…

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…

Recent text-to-3D generation approaches produce impressive 3D results but require time-consuming optimization that can take up to an hour per prompt. Amortized methods like ATT3D optimize multiple prompts simultaneously to improve…

Although Multimodal Large Language Models (MLLMs) have shown remarkable potential in Visual Document Retrieval (VDR) through generating high-quality multi-vector embeddings, the substantial storage overhead caused by representing a page…

Generating human motion from text has been dominated by denoising motion models either through diffusion or generative masking process. However, these models face great limitations in usability by requiring prior knowledge of the motion…

Generative models have emerged as powerful tools in medical imaging, enabling tasks such as segmentation, anomaly detection, and high-quality synthetic data generation. These models typically rely on learning meaningful latent…

Continuous visual autoregressive (AR) models have demonstrated promising performance in image generation. However, the heavy autoregressive inference burden imposes significant overhead. In Large Language Models (LLMs), speculative decoding…

Multi-modal large language models (MLLMs) have advanced general-purpose video understanding but struggle with long, high-resolution videos -- they process every pixel equally in their vision transformers (ViTs) or LLMs despite significant…

Recently, multi-view diffusion-based 3D generation methods have gained significant attention. However, these methods often suffer from shape and texture misalignment across generated multi-view images, leading to low-quality 3D generation…

It is desirable but challenging to generate content-rich long videos in the scale of minutes. Autoregressive large language models (LLMs) have achieved great success in generating coherent and long sequences of tokens in the domain of…