[ICML 2026] Alleviating Prompt Forgetting in Multimodal Diffusion Transformers
-
Updated
May 20, 2026 - Python
#
training-free-method
Here are 7 public repositories matching this topic...
[ACCV 2026 Oral] Official implementation of "REBASE: Reference-Background Subspace Elimination for Training-Free In-Context Segmentation".
computer-vision deep-learning sam image-segmentation foundation-models segment-anything dinov2 in-context-segmentation training-free-method
-
Updated
Oct 13, 2026
This is DARE, a two-separated-methods framework for robust tissue classfication !
-
Updated
Oct 15, 2026 - Python
[coming soon] The official implementation of the paper titled "Controllable Exaggeration for Generative Motion Models via Training-Time Adaptation and Inference-Time Guidance""
supervised-learning character-animation diffusion-models motion-generation generative-ai flow-matching character-motion-guide training-free-method animation-principle
-
Updated
Oct 9, 2026
Official code for "Where to Cut? Adaptive Thresholds for Density-Ratio Few-Shot Segmentation" — training-free FSS with frozen DINOv3 features.
-
Updated
Sep 2, 2026 - Python
Leveraging the powerful cross-lingual understanding capabilities of LLMs to obtain sentence representations, eliminate language-specific features from these representations, and thereby enhance their semantic characteristics.
-
Updated
May 26, 2026 - Python
The official implementation repository for our EMNLP 2025 paper, R-Bind: Unified Enhancement of Attribute and Relation Binding in Text-to-Image Diffusion Models.
-
Updated
Sep 12, 2026 - Python
Add this topic to your repo
To associate your repository with the training-free-method topic, visit your repo's landing page and select "manage topics."