Related papers: Towards Sequence Modeling Alignment between Tokeni…

Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make…

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…

Discrete diffusion models have recently become competitive with autoregressive models for language modeling, even outperforming them on reasoning tasks requiring planning and global coherence, but they require more computation at inference…

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

Class-conditional generative models have emerged as accurate and robust classifiers, with diffusion models demonstrating clear advantages over other visual generative paradigms, including autoregressive (AR) models. In this work, we revisit…

Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a…

We present TokenFlow, a novel unified image tokenizer that bridges the long-standing gap between multimodal understanding and generation. Prior research attempt to employ a single reconstruction-targeted Vector Quantization (VQ) encoder for…

We present UniFluid, a unified autoregressive framework for joint visual generation and understanding leveraging continuous visual tokens. Our unified autoregressive architecture processes multimodal image and text inputs, generating…

Autoregressive models have become the de facto choice for sequence generation tasks, but standard approaches treat digits as independent tokens and apply cross-entropy loss, overlooking the coherent structure of numerical sequences. This…

This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…

Recent studies have demonstrated the effectiveness of token-based methods for visual content generation. As a representative work, non-autoregressive Transformers (NATs) are able to synthesize images with decent quality in a small number of…

In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a…

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The…

Sequence-to-sequence vision-language models are showing promise, but their applicability is limited by their inference latency due to their autoregressive way of generating predictions. We propose a parallel decoding sequence-to-sequence…

The efficiency of large language models (LLMs) is fundamentally limited by their sequential, token-by-token generation process. We argue that overcoming this bottleneck requires a new design axis for LLM scaling: increasing the semantic…

Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…

Diffusion models have gained significant attention in the realm of image generation due to their exceptional performance. Their success has been recently expanded to text generation via generating all tokens within a sequence concurrently.…

Generative transformers have shown their superiority in synthesizing high-fidelity and high-resolution images, such as good diversity and training stability. However, they suffer from the problem of slow generation since they need to…

Transformer-based encoder-decoder models that generate outputs in a left-to-right fashion have become standard for sequence-to-sequence tasks. In this paper, we propose a framework for decoding that produces sequences from the "outside-in":…

The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern workloads. Existing autoscaling policies, often retrofitted from monolithic systems…