Related papers: HybriDLA: Hybrid Generation for Document Layout An…

We present LLaDA2.0-Uni, a unified discrete diffusion large language model (dLLM) that supports multimodal understanding and generation within a natively integrated framework. Its architecture combines a fully semantic discrete tokenizer, a…

Interior design is a complex and creative discipline involving aesthetics, functionality, ergonomics, and materials science. Effective solutions must meet diverse requirements, typically producing multiple deliverables such as renderings…

Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as confidence or entropy…

We present HySemRAG, a framework that combines Extract, Transform, Load (ETL) pipelines with Retrieval-Augmented Generation (RAG) to automate large-scale literature synthesis and identify methodological research gaps. The system addresses…

Although autoregressive models have dominated language modeling in recent years, there has been a growing interest in exploring alternative paradigms to the conventional next-token prediction framework. Diffusion-based language models have…

Multi-instance image generation (MIG) remains a significant challenge for modern diffusion models due to key limitations in achieving precise control over object layout and preserving the identity of multiple distinct subjects. To address…

The acquisition of large-scale and diverse demonstration data are essential for improving robotic imitation learning generalization. However, generating such data for complex manipulations is challenging in real-world settings. We introduce…

Hardware faults on the regular 2-D computing array of a typical deep learning accelerator (DLA) can lead to dramatic prediction accuracy loss. Prior redundancy design approaches typically have each homogeneous redundant processing element…

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…

Diffusion policies are a powerful paradigm for robot learning, but their training is often inefficient. A key reason is that networks must relearn fundamental spatial concepts, such as translations and rotations, from scratch for every new…

Document layout analysis is a key area in document research, involving techniques like text mining and visual analysis. Despite various methods developed to tackle layout analysis, a critical but frequently overlooked problem is the…

Recently, generative domain adaptation has achieved remarkable progress, enabling us to adapt a pre-trained generator to a new target domain. However, existing methods simply adapt the generator to a single target domain and are limited to…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

Controllable layout generation aims to create plausible visual arrangements of element bounding boxes within a graphic design according to certain optional constraints, such as the type or position of a specific component. While recent…

High Dynamic Range (HDR) generation remains challenging for generative models, which are largely limited to low dynamic range outputs. Recent diffusionbased approaches approximate HDR by generating multiple exposure-conditioned samples,…

Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs), typically from unstructured texts and structured graphs. While recent progress has advanced text-based RAG to multi-turn reasoning…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates…

Recently, large-scale diffusion models, e.g., Stable diffusion and DallE2, have shown remarkable results on image synthesis. On the other hand, large-scale cross-modal pre-trained models (e.g., CLIP, ALIGN, and FILIP) are competent for…