Related papers: Autoregressive Model Beats Diffusion: Llama for Sc…

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either…

Research in vision-language models has seen rapid developments off-late, enabling natural language-based interfaces for image generation and manipulation. Many existing text guided manipulation techniques are restricted to specific classes…

In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-token, parallel…

Diffusion-based decoding has recently emerged as an appealing alternative to autoregressive (AR) generation, offering the potential to update multiple tokens in parallel and reduce latency. However, diffusion vision language models (dVLMs)…

Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) to achieve performance on par with closed-source systems like GPT-4V. However, deploying these models in real-world scenarios, particularly on…

Diffusion models have achieved success in high-fidelity data synthesis, yet their capacity for more complex, structured reasoning like text following tasks remains constrained. While advances in language models have leveraged strategies…

Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in aligning visual inputs with natural language outputs. Yet, the extent to which generated tokens depend on visual modalities remains poorly understood,…

Recently, large multimodal models (LMMs) have achieved significant advancements. When dealing with high-resolution images, dominant LMMs typically divide them into multiple local images and a global image, leading to a large number of…

Image rescaling aims to learn the optimal low-resolution (LR) image that can be accurately reconstructed to its original high-resolution (HR) counterpart, providing an efficient image processing and storage method for ultra-high definition…

Recent advances in large language models (LLMs) have spurred interests in encoding images as discrete tokens and leveraging autoregressive (AR) frameworks for visual generation. However, the quantization process in AR-based visual…

This paper presents an in-depth survey on the use of multimodal Generative Artificial Intelligence (GenAI) and autoregressive Large Language Models (LLMs) for human motion understanding and generation, offering insights into emerging…

Despite the crucial importance of accelerating text generation in large language models (LLMs) for efficiently producing content, the sequential nature of this process often leads to high inference latency, posing challenges for real-time…

Modern Latent Diffusion Models (LDMs) typically operate in low-level Variational Autoencoder (VAE) latent spaces that are primarily optimized for pixel-level reconstruction. To unify vision generation and understanding, a burgeoning trend…

Recent advances in text-to-image generation have primarily relied on extensive datasets and parameter-heavy architectures. These requirements severely limit accessibility for researchers and practitioners who lack substantial computational…

Autoregressive (AR) models remain the standard for natural language generation but still suffer from high latency due to strictly sequential decoding. Recent diffusion-inspired approaches, such as LlaDA and Dream, mitigate this by…

While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems…

A fundamental objective of manipulation policy design is to endow robots to comprehend human instructions, reason about scene cues, and execute generalized actions in dynamic environments. Recent autoregressive vision-language-action (VLA)…

Tokenization is a central component of natural language processing in current large language models (LLMs), enabling models to convert raw text into processable units. Although learned tokenizers are widely adopted, they exhibit notable…

Recent advances in large language models (LLMs) have inspired new paradigms for document reranking. While this paradigm better exploits the reasoning and contextual understanding capabilities of LLMs, most existing LLM-based rerankers rely…

Utilization of classification latent space information for downstream reconstruction and generation is an intriguing and a relatively unexplored area. In general, discriminative representations are rich in class-specific features but are…