VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain generalized object detection.
Deconstructing denoising diffusion models for self-supervised learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
representative citing papers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
A text-to-LiDAR diffusion model with self-conditioned reconstruction guidance, directional position encoding, and two >100K-pair benchmarks, supporting multiple conditioning modalities.
VRPO applies generative representation policy optimization to dynamically align diffusion features with pretrained visual encoders, claiming +1.8 FID gains and 2.3x faster training versus REPA.
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.
citing papers explorer
-
VFM$^{4}$SDG: Unveiling the Power of VFMs for Single-Domain Generalized Object Detection
VFM4SDG is a dual-prior framework that distills cross-domain stable relations from VFMs into DETR encoders and injects semantic-contextual priors into decoder queries to reduce missed detections in single-domain generalized object detection.
-
DiffusionBench: On Holistic Evaluation of Diffusion Transformers
NanoGen unifies DiT training on ImageNet and T2I, reveals negative Pearson correlations (-0.377 to -0.580) in method rankings across metrics from 21 models, and motivates DiffusionBench for holistic evaluation.
-
The two clocks and the innovation window: When and how generative models learn rules
Generative models learn rules before memorizing data, creating an innovation window whose width depends on dataset size and rule complexity, observed in both diffusion and autoregressive architectures.
-
Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think
Aligning noisy hidden states in diffusion transformers to clean features from pretrained visual encoders speeds up training over 17x and reaches FID 1.42.
-
T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
A text-to-LiDAR diffusion model with self-conditioned reconstruction guidance, directional position encoding, and two >100K-pair benchmarks, supporting multiple conditioning modalities.
-
Improving Visual Representation Alignment Generation with GRPO
VRPO applies generative representation policy optimization to dynamically align diffusion features with pretrained visual encoders, claiming +1.8 FID gains and 2.3x faster training versus REPA.
-
Semantic Generative Tuning for Unified Multimodal Models
Semantic Generative Tuning applies segmentation-based generative proxies during post-training to align and improve both understanding and generation in unified multimodal models.