Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
hub
LCM-LoRA: A universal stable-diffusion acceleration module.arXiv preprint arXiv:2311.05556
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.
Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.
Asymmetric CUDA-stream pipelining, a compile-friendly LLLite reformulation, and periodic conditioning refresh sustain 27-30 fps video stylization on a consumer GPU with a 2.13B MLLM text encoder and 0.39B distilled U-Net.
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
ActWorld extends navigation-centric world models to support mid-rollout object interactions via chunk-autoregressive generation, action-aware memory routing, and a persistent memory bank, backed by a 100K annotated interaction dataset.
SAWR applies stain-aware multi-level wavelet regularization to purify adversarial perturbations in histopathology images, claiming up to 10.69% robustness gain while preserving texture and spectral properties.
A privacy-preserving thermal-only crowd counting framework extracts enhanced features from thermal images via single-step LCM denoising in a depth-to-RGB diffusion model and matches RGB-T fusion performance without RGB input at inference.
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
A compact Chinese-native T2I U-Net (~0.387B) trained on Sugon K100, distilled to 4 steps, reports GenEval 0.69 and ~1.6–4.5s offline mobile generation.
Frozen multimodal encoders enable robust AI-generated image detection via linear classification on a 10K-image curated training set that improves generalization over larger datasets.
Systematic benchmarking of diffusion model optimizations on Apple M3 Ultra produces 22.7 FPS real-time img2img at 512x512 and demonstrates that CUDA-derived techniques do not transfer directly to Apple Silicon.
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
citing papers explorer
-
Beyond Trajectory Matching: Reflow with Marginal Distribution Alignment
Introduces a marginal-alignment regularizer for reflow distillation of diffusion models that aligns endpoint marginals, supported by a telescoping TV bound and benchmark experiments.
-
Semantic Browsing: Controllable Diversity for Image Generation
A technique for controllable diversity in text-to-image generation by inducing structured semantic variations at the prompt level via VLM and agentic workflow.
-
Timage: A Generative Text-in-Image Paradigm for Fine-Tuning Vision-Language Models
Timage generates text query overlays on images via Constrained Schrödinger Bridge to boost fine-grained spatial reasoning in vision-language models, outperforming larger systems on VMCBench with a 7B backbone.
-
Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU
Asymmetric CUDA-stream pipelining, a compile-friendly LLLite reformulation, and periodic conditioning refresh sustain 27-30 fps video stylization on a consumer GPU with a 2.13B MLLM text encoder and 0.39B distilled U-Net.
-
ORBIS: Output-Guided Token Reduction with Distribution-Aware Matching for Video Diffusion Acceleration
ORBIS uses output-guided token reduction and DATM to achieve 2x higher token reduction than AsymRnR, with up to 4.5x speedup and 79.3% energy savings versus A100 GPU for video DiT models.
-
LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation
LongLive-2.0 delivers an NVFP4 parallel infrastructure that enables direct training of long multi-shot autoregressive diffusion video models and achieves up to 2.15x training and 1.84x inference speedups on Blackwell and other GPUs.
-
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
ActWorld extends navigation-centric world models to support mid-rollout object interactions via chunk-autoregressive generation, action-aware memory routing, and a persistent memory bank, backed by a 100K annotated interaction dataset.
-
Stain-Aware Wavelet Regularization for Instant Adversarial Purification in Histopathology
SAWR applies stain-aware multi-level wavelet regularization to purify adversarial perturbations in histopathology images, claiming up to 10.69% robustness gain while preserving texture and spectral properties.
-
Thermal-Only Crowd Counting with Deployment-Time Privacy Protection
A privacy-preserving thermal-only crowd counting framework extracts enhanced features from thermal images via single-step LCM denoising in a depth-to-RGB diffusion model and matches RGB-T fusion performance without RGB input at inference.
-
RAVEN: Real-time Autoregressive Video Extrapolation with Consistency-model GRPO
RAVEN aligns training and inference for causal autoregressive video diffusion via interleaved rollout repacking and introduces CM-GRPO for direct RL on consistency-model kernels, claiming better quality than recent baselines.
-
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
DP-DMD preserves sample diversity in few-step image synthesis by applying a teacher-derived target-prediction objective to the first distillation step and standard DMD loss to the rest.
-
Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.
-
JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Accelerators
A compact Chinese-native T2I U-Net (~0.387B) trained on Sugon K100, distilled to 4 steps, reports GenEval 0.69 and ~1.6–4.5s offline mobile generation.
-
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Frozen multimodal encoders enable robust AI-generated image detection via linear classification on a 10K-image curated training set that improves generalization over larger datasets.
-
Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra
Systematic benchmarking of diffusion model optimizations on Apple M3 Ultra produces 22.7 FPS real-time img2img at 512x512 and demonstrates that CUDA-derived techniques do not transfer directly to Apple Silicon.
-
Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
- Teacher-Feature Drifting: One-Step Diffusion Distillation with Pretrained Diffusion Representations
- Adversarial Concept Distillation for One-Step Diffusion Personalization