The paper introduces CADT, a Concept Attribution method through Dynamic Trajectories, which attributes diffusion model outputs by tracking factor-induced internal response trajectories rather than scalar responses. CADT constructs matched counterfactual pairs at identical noisy states to isolate factor-specific representation displacements and models their directional and magnitude evolution across denoising as dynamic attribution signatures. Experiments on multiple public datasets demonstrate consistent improvements over existing diffusion attribution baselines for hierarchical, compositional, and style attribution tasks.
arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.
The paper introduces a new method for training data attribution in diffusion models called TID, which uses a local score discrepancy measure and can be estimated without retraining. It further distills this approach into TIDE, a forward‑only student that reproduces the teacher’s rankings using internal activations, achieving comparable accuracy at dramatically lower query cost. Experiments on CIFAR‑10, ArtBench‑10, and MS‑COCO show that TID outperforms existing methods and TIDE attributes samples in milliseconds, faster than generation itself.
arXiv:2608.30081v1 Announce Type: new Abstract: Understanding which training samples influence a generated image is an important problem in generative modeling. In flow matching, training samples inf...
arXiv:2606. 03885v1 Announce Type: new Abstract: Feature attribution methods explain predictions by assigning importance scores to input features.
ORCA (Orthogonal Residual Compositional Alignment) is a method that improves text-to-image diffusion models by aligning the diffusion transformer’s latent space with a low‑rank target derived from a frozen visual encoder. It introduces an auxiliary loss that uses a predictor with an orthogonal basis parameterised by a learned residual between T5 and CLIP embeddings, providing a prompt‑dependent signal for selecting the visual readout subspace. Experiments on three diffusion‑transformer backbones show that ORCA improves FID and GenEval scores, especially on attribute binding, spatial relations, and multi‑object prompts, without adding inference‑time cost.
arXiv:2609.37974v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
arXiv:2610.14190v1 Announce Type: new Abstract: Explaining a vision--language model (VLM) prediction requires tracing training-example influence to the multimodal evidence that mediates it, yet exist...
arXiv:2605.27813v2 Announce Type: replace-cross Abstract: Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather th...
arXiv:2605. 23080v2 Announce Type: replace Abstract: Feature attribution methods promise to identify which input features matter for a model output.
arXiv:2601. 22276v2 Announce Type: replace Abstract: As Text-to-Image (T2I) diffusion models are increasingly used in real-world creative workflows, a principled framework for valuing contributors who provide a collection of data is essential for fair compensation and sustainable data marketplaces.
The paper argues that feature attribution scores for generative language models lack a fixed meaning because each generated token is both output and input, leading to multiple distinct explanatory questions. It introduces the Attribution Contract framework, which explicitly defines the model score, fixed variables, target output, generation process, and eligible features, showing how these choices affect attribution outcomes. Experiments demonstrate that different contracts (e.g., local next-token vs. prompt-level) and model architectures (mixture-of-experts vs. masked-diffusion) yield markedly different attribution distributions, highlighting the need for careful contract specification.
Diffusion Trajectory Modeling (DTM) treats the evolving feature maps of diffusion models as temporally structured trajectories rather than static snapshots. By interpreting each spatial patch’s progression across multiple timesteps as a trajectory, DTM captures semantic correspondence cues that prior methods miss. Experiments on SPair-71k, SPair-U, and AP-10K demonstrate that DTM achieves strong performance, highlighting the semantic value embedded in the diffusion process’s temporal axis.