Related papers: LADR: Locality-Aware Dynamic Rescue for Efficient …

Discrete Diffusion Language Models (DLMs) offer a promising non-autoregressive alternative for text generation, yet effective mechanisms for inference-time control remain relatively underexplored. Existing approaches include sampling-level…

Autoregressive (AR) models have garnered significant attention in image generation for their ability to effectively capture both local and global structures within visual data. However, prevalent AR models predominantly rely on the…

Diffusion models are the main driver of progress in image and video synthesis, but suffer from slow inference speed. Distillation methods, like the recently introduced adversarial diffusion distillation (ADD) aim to shift the model from…

Most multi-agent systems rely exclusively on autoregressive language models (ARMs) that are based on sequential generation. Although effective for fluent text, ARMs limit global reasoning and plan revision. On the other hand, Discrete…

Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding excessive compute demands by training a diffusion model in a compressed lower-dimensional latent space. Here, we apply the LDM paradigm to high-resolution…

Autoregressive decoding in Large Language Models (LLMs) generates one token per step, causing high inference latency. Speculative decoding (SD) mitigates this through a guess-and-verify strategy, but existing training-free variants face…

In this paper, we show that the performance of a learnt generative model is closely related to the model's ability to accurately represent the inferred \textbf{latent data distribution}, i.e. its topology and structural properties. We…

Ensuring both safety and efficiency in decision-making for autonomous driving systems remains a fundamental challenge. Traditional Deep Reinforcement Learning (DRL) suffers from unsafe random exploration and slow convergence, while Large…

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…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

Diffusion language models (DLMs) are emerging as a compelling alternative to the dominant autoregressive paradigm, offering inherent advantages in parallel generation and bidirectional context modeling. However, for the tasks with strict…

The evolution of Diffusion Models has dramatically improved image generation quality, making it increasingly difficult to differentiate between real and generated images. This development, while impressive, also raises significant privacy…

Deep Reinforcement Learning (DRL) has demonstrated strong performance in robotic control but remains susceptible to out-of-distribution (OOD) states, often resulting in unreliable actions and task failure. While previous methods have…

Retrieval-augmented generation (RAG) incorporates external knowledge into large language models (LLMs), improving their adaptability to downstream tasks and enabling information updates. Surprisingly, recent empirical evidence demonstrates…

Thanks to the rapid development of diffusion models, unprecedented progress has been witnessed in image synthesis. Prior works mostly rely on pre-trained linguistic models, but a text is often too abstract to properly specify all the…

Traditional point-based image editing methods rely on iterative latent optimization or geometric transformations, which are either inefficient in their processing or fail to capture the semantic relationships within the image. These methods…

With the dramatic increase of dimensions in the data representation, extracting latent low-dimensional features becomes of the utmost importance for efficient classification. Aiming at the problems of unclear margin representation and…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs…

In spite of the rapidly evolving landscape of text-to-image generation, the synthesis and manipulation of multiple entities while adhering to specific relational constraints pose enduring challenges. This paper introduces an innovative…

Ensuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial…