Causal-Adapter adapts frozen diffusion backbones via structural causal modeling, prompt-aligned injection, and conditioned token contrastive loss to achieve faithful counterfactual generation with strong attribute control and identity preservation.
hub
Gans trained by a two time-scale update rule converge to a local nash equilibrium
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
method 2
background 1
baseline 1
citation-polarity summary
representative citing papers
Guidance watermarking steers diffusion denoising steps via gradients from an off-the-shelf watermark decoder to embed marks during generation, converting post-hoc schemes into in-generation ones while remaining complementary to VAE modifications.
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
Derives closed-form optimal loss for unified diffusion models, provides variance-controlled estimators, and shows improved diagnosis, training schedules, and power-law scaling after subtracting the optimal value.
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
Hunyuan-DiT is a new multi-resolution diffusion transformer that achieves state-of-the-art Chinese text-to-image generation through custom architecture, data pipelines, and multimodal caption refinement.
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
BLIP3-o uses a diffusion transformer to generate CLIP image features and a sequential pretraining strategy to build open models that perform strongly on both image understanding and generation benchmarks.
ModelScopeT2V is a 1.7-billion-parameter text-to-video model built on Stable Diffusion that adds temporal modeling and outperforms prior methods on three evaluation metrics.
citing papers explorer
-
Causal-Adapter: Taming Text-to-Image Diffusion for Faithful Counterfactual Generation
Causal-Adapter adapts frozen diffusion backbones via structural causal modeling, prompt-aligned injection, and conditioned token contrastive loss to achieve faithful counterfactual generation with strong attribute control and identity preservation.
-
Guidance Watermarking for Diffusion Models
Guidance watermarking steers diffusion denoising steps via gradients from an off-the-shelf watermark decoder to embed marks during generation, converting post-hoc schemes into in-generation ones while remaining complementary to VAE modifications.
-
Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling
Geometry Forcing aligns video diffusion representations with geometric foundation model features via angular cosine and scale regression objectives to improve 3D consistency in generated videos.
-
2ndMatch: Finetuning Pruned Diffusion Models via Second-Order Jacobian Matching
2ndMatch finetunes pruned diffusion models via second-order Jacobian matching inspired by Finite-Time Lyapunov Exponents to reduce the quality gap with dense models on image generation tasks.
-
Emu3: Next-Token Prediction is All You Need
Emu3 shows that next-token prediction on a unified discrete token space for text, images, and video lets a single transformer outperform task-specific models such as SDXL and LLaVA-1.6 in multimodal generation and perception.
-
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Scaling an autoregressive Transformer to 20B parameters for text-to-image generation using image token sequences achieves new SOTA zero-shot FID of 7.23 and fine-tuned FID of 3.22 on MS-COCO.
-
Lossless Anti-Distillation Sampling
LADS is a sampling method that keeps benign user generations statistically identical to the original model while forcing correlated samples across a distiller's multiple accounts, provably worsening their generalization via uniform convergence bounds.
-
Reconstruction or Semantics? What Makes a Latent Space Useful for Robotic World Models
Semantic latent spaces from pretrained encoders outperform reconstruction-based spaces for robotic world models on planning and downstream policy performance.
-
ModelScope Text-to-Video Technical Report
ModelScopeT2V is a 1.7-billion-parameter text-to-video model built on Stable Diffusion that adds temporal modeling and outperforms prior methods on three evaluation metrics.