generation quality
The degree to which generated outputs (e.g., text, images) meet the desired criteria for relevance, coherence, and fidelity to the input or prompt.
- A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances
- Accelerating Parallel Diffusion Model Serving with Residual Compression
- BADiff: Bandwidth Adaptive Diffusion Model
- Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond
- DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
- Encoder-Decoder Diffusion Language Models for Efficient Training and Inference
- FAST: Foreground‑aware Diffusion with Accelerated Sampling Trajectory for Segmentation‑oriented Anomaly Synthesis
- GeoCAD: Local Geometry-Controllable CAD Generation with Large Language Models
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
- ImageSentinel: Protecting Visual Datasets from Unauthorized Retrieval-Augmented Image Generation
- Increasing the Utility of Synthetic Images through Chamfer Guidance
- LIFEBENCH: Evaluating Length Instruction Following in Large Language Models
- LeMiCa: Lexicographic Minimax Path Caching for Efficient Diffusion-Based Video Generation
- Learnable Sampler Distillation for Discrete Diffusion Models
- Learning Diffusion Models with Flexible Representation Guidance
- LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders
- Locality in Image Diffusion Models Emerges from Data Statistics
- On Inductive Biases That Enable Generalization in Diffusion Transformers
- OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps
- PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation
- Preventing Shortcuts in Adapter Training via Providing the Shortcuts
- RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers
- RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models
- Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation
- Theoretical Benefit and Limitation of Diffusion Language Model
- Towards Understanding the Mechanisms of Classifier-Free Guidance
- Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models
- U-REPA: Aligning Diffusion U-Nets to ViTs
- Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction