arXiv:2606. 00140v3 Announce Type: replace-cross Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements.
arXiv:2606. 00140v1 Announce Type: cross Abstract: While the rapid adoption of multimodal generative models offers immense potential, it has also increased the risks of harmful content synthesis, deepfakes, and copyright infringements.
High-fidelity image generation faces a trade-off between speed and quality. Diffusion models produce strong visuals but require costly iterative sampling.
The paper compares diffusion and rectified flow objectives within the MotionGPT3 framework for text-driven motion generation. Experiments on HumanML3D show that rectified flow converges faster, achieves strong test performance earlier, and matches or exceeds diffusion quality while requiring fewer sampling steps. The study isolates the generative objective’s impact, demonstrating that rectified flow’s benefits transfer to continuous-latent motion generation.
Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields. While theoretical targets favor straight trajectories, empirical networks develop complex path deformations.
arXiv:2610.01969v1 Announce Type: new Abstract: Concept erasure aims to remove a target concept, such as a copyrighted style, a recognizable character, or unsafe content, from a pretrained text-to-im...
The paper introduces Flow Divergence Sampler (FDS), a training‑free method that refines intermediate states in flow‑matching models by using the divergence of the marginal velocity field to detect and correct misguidance toward low‑density regions. FDS operates during inference, requires no additional training, and can be applied as a plug‑and‑play module with standard solvers and existing flow backbones. Experiments show that FDS consistently improves fidelity in tasks such as text‑to‑image synthesis and inverse problems.
STAGE is a training‑free, closed‑form framework for concept erasure in native text‑to‑3D generators. It treats erasure as a stage‑aware editing problem, applying low‑dimensional affine corrections separately to the structural and appearance stages of the pipeline. Experiments on the TRELLIS generator show that STAGE outperforms adapted baselines, achieving a composite score of 66.7 versus 53.2 across 15 shape, material, and object concepts.
Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions.
In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising. Although prior work shows that these parameterizations lead to different empirical behaviors, the mechanisms underlying their respective advantages remain to be underexplored, and how to combine them effectively is still unclear.
arXiv:2607. 12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or the data endpoint, to perform denoising.
arXiv:2607. 12616v1 Announce Type: new Abstract: Continuous-time generative frameworks construct probability paths between base and target domains by optimizing time-dependent velocity fields.
TINA+ is a diffusion-consistent, text‑free inversion attack that probes residual visual knowledge in diffusion models after concept erasure. By using optimization‑based inversion and diffusion‑consistent trajectory regularization, it suppresses spurious trajectories that could falsely indicate retained concepts. Experiments across multiple erasure methods, tasks, and model architectures show that TINA+ reliably recovers erased concepts, revealing that many current techniques only sever text‑image links rather than eliminating underlying visual knowledge.