相关论文: LARP: Tokenizing Videos with a Learned Autoregress…

How to improve discriminative feature learning is central in classification. Existing works address this problem by explicitly increasing inter-class separability and intra-class similarity, whether by constructing positive and negative…

Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis, but they suffer from high computational cost. We study how to design compute-efficient linear…

We introduce RandAR, a decoder-only visual autoregressive (AR) model capable of generating images in arbitrary token orders. Unlike previous decoder-only AR models that rely on a predefined generation order, RandAR removes this inductive…

Historically, LLMs have been trained using either autoregressive (AR) or masked language modeling (MLM) objectives, with AR models gaining dominance in recent years. However, AR models are inherently incapable of masked infilling, which is…

Fine-tuning pre-trained generative models with Reinforcement Learning (RL) has emerged as an effective approach for aligning outputs more closely with nuanced human preferences. In this paper, we investigate the application of Group…

Intelligent agents can learn to represent the action spaces of other agents simply by observing them act. Such representations help agents quickly learn to predict the effects of their own actions on the environment and to plan complex…

Audio-Visual Video Parsing (AVVP) task aims to detect and temporally locate events within audio and visual modalities. Multiple events can overlap in the timeline, making identification challenging. While traditional methods usually focus…

Most existing image tokenizers encode images into a fixed number of tokens or patches, overlooking the inherent variability in image complexity. To address this, we introduce Content-Adaptive Tokenizer (CAT), which dynamically adjusts…

Prompt learning has proven effective in adapting vision language models for downstream tasks. However, existing methods usually append learnable prompt tokens solely with the category names to obtain textual features, which fails to fully…

Autoregressive~(AR) generation almost dominates sequence generation for its efficacy. Recently, non-autoregressive~(NAR) generation gains increasing popularity for its efficiency and growing efficacy. However, its efficiency is still…

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…

Deep networks are able to learn highly predictive models of video data. Due to video length, a common strategy is to train them on small video snippets. We apply the deep Taylor / LRP technique to understand the deep network's…

Autoregressive (AR) models have demonstrated significant success in the realm of text-to-image generation. However, they usually face two major challenges. Firstly, the generated images may not always meet the quality standards expected by…

Large pretrained vision-language models like CLIP have shown promising generalization capability, but may struggle in specialized domains (e.g., satellite imagery) or fine-grained classification (e.g., car models) where the visual concepts…

Contrastive Language-Image Pre-training (CLIP) has significantly improved performance in various vision-language tasks by expanding the dataset with image-text pairs obtained from websites. This paper further explores CLIP from the…

Diffusion Large Language Models (DLLMs) have emerged as a powerful alternative to autoregressive models, enabling parallel token generation across multiple positions. However, preference alignment of DLLMs remains challenging due to high…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

Autoregressive (AR) approaches, which represent images as sequences of discrete tokens from a finite codebook, have achieved remarkable success in image generation. However, the quantization process and the limited codebook size inevitably…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…

Finding compact representation of videos is an essential component in almost every problem related to video processing or understanding. In this paper, we propose a generative model to learn compact latent codes that can efficiently…