Related papers: Beyond Next-Token: Next-X Prediction for Autoregre…

Image tokenization plays a critical role in reducing the computational demands of modeling high-resolution images, significantly improving the efficiency of image and multimodal understanding and generation. Recent advances in 1D latent…

Large language models display remarkable capabilities in logical and mathematical reasoning, allowing them to solve complex tasks. Interestingly, these abilities emerge in networks trained on the simple task of next-token prediction. In…

Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…

While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited…

Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…

Autoregressive large language models (LLMs) scale well by expressing diverse tasks as sequences of discrete natural-language tokens and training with next-token prediction, which unifies comprehension and generation under self-supervision.…

3D structure modeling is essential across scales, enabling applications from fluid simulation and 3D reconstruction to protein folding and molecular docking. Yet, despite shared 3D spatial patterns, current approaches remain fragmented,…

Generative Retrieval introduces a new approach to Information Retrieval by reframing it as a constrained generation task, leveraging recent advancements in Autoregressive (AR) language models. However, AR-based Generative Retrieval methods…

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

While deep learning has significantly advanced medical image segmentation, most existing methods still struggle with handling complex anatomical regions. Cascaded or deep supervision-based approaches attempt to address this challenge…

This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum Description Length principle, we reinterpret image tokens as…

Autoregressive (AR) video generative models rely on video tokenizers that compress pixels into discrete token sequences. The length of these token sequences is crucial for balancing reconstruction quality against downstream generation…

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…

Recent advances in pretraining general foundation models have significantly improved performance across diverse downstream tasks. While autoregressive (AR) generative models like GPT have revolutionized NLP, most visual generative…

The tokenizer, as one of the fundamental components of large models, has long been overlooked or even misunderstood in visual tasks. One key factor of the great comprehension power of the large language model is that natural language…

Autoregressive (AR) models are promising for image generation, yet continuous-token AR variants often trail latent diffusion and masked-generation models. The core issue is heterogeneous variance in VAE latents, which is amplified during AR…

Visual autoregressive (VAR) models have recently emerged as a promising family of generative models, enabling a wide range of downstream vision tasks such as text-guided image editing. By shifting the editing paradigm from noise…

While deep learning models have demonstrated remarkable success in numerous domains, their black-box nature remains a significant limitation, especially in critical fields such as medical image analysis and inference. Existing…

Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…

Autoregressive (AR) language models have emerged as powerful solutions for zero-shot text-to-speech (TTS) synthesis, capable of generating natural speech from a few seconds of audio prompts. However, conventional AR-based TTS systems…