Segment-Level Diffusion: A Framework for Controllable Long-Form Generation with Diffusion Language Models
Diffusion models have shown promise in text generation but often struggle with generating long, coherent, and contextually accurate text. Token-level diffusion overlooks word-order dependencies and enforces short output windows, while passage-level diffusion struggles with learning robust representation for long-form text. To address these challenges, we propose Segment-Level Diffusion (SLD), a framework that enhances diffusion-based text generation through text segmentation, robust representation training with adversarial and contrastive learning, and improved latent-space guidance. By segmenting long-form outputs into separate latent representations and decoding them with an autoregressive decoder, SLD simplifies diffusion predictions and improves scalability. Experiments on XSum, ROCStories, DialogSum, and DeliData demonstrate that SLD achieves competitive or superior performance in fluency, coherence, and contextual compatibility across automatic and human evaluation metrics comparing with other diffusion and autoregressive baselines. Ablation studies further validate the effectiveness of our segmentation and representation learning strategies.
Code (0)
등록된 구현이 없습니다.
Tasks
Contrastive LearningDecoderFormRepresentation LearningText GenerationText SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SALIENT: Frequency-Aware Paired Diffusion for Controllable Long-Tail CT Detection
Detection of rare lesions in whole-body CT is fundamentally limited by extreme class imbalance and low target-to-volume ratios, producing precision collapse despite high AUROC. Synthetic augmentation with diffusion model…
Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous Driving
Learning-based motion planners, despite recent progress, often suffer from temporal inconsistency. Small perturbations across frames can accumulate into unstable trajectories, degrading comfort and safety in closed-loop …
Autonomous DrivingCLE Diffusion: Controllable Light Enhancement Diffusion Model
Low light enhancement has gained increasing importance with the rapid development of visual creation and editing. However, most existing enhancement algorithms are designed to homogeneously increase the brightness of ima…
Low-Light Image EnhancementmodelCoSimGen: Controllable Diffusion Model for Simultaneous Image and Mask Generation
The acquisition of annotated datasets with paired images and segmentation masks is a critical challenge in domains such as medical imaging, remote sensing, and computer vision. Manual annotation demands significant resou…
TripletOmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding
In this paper, we propose a novel framework for controllable video diffusion, OmniVDiff, aiming to synthesize and comprehend multiple video visual content in a single diffusion model. To achieve this, OmniVDiff treats al…
Semantic SegmentationVideo GenerationVideo Understanding