The paper introduces Multi-View Aggregated Score Distillation (MV‑SDI), a training‑free sampler that replaces the single‑view per‑step gradient in score distillation with an average over K views while keeping the diffusion prior frozen. By averaging gradients from multiple views—especially antipodal pairs—MV‑SDI reduces per‑step variance by roughly 1/K, improves angular coverage, and cuts optimization steps while boosting CLIP R‑Precision and CLIP score on the SDI benchmark. The method achieves these gains without retraining or additional multi‑view data and is compatible with existing gradient‑based score‑distillation pipelines.
Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior work addresses this by retraining the diffusion prior on multi-view data; this improves consistency but makes the sampling contribution inseparable from prior quality.
arXiv:2610.20220v1 Announce Type: new Abstract: Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a b...
The paper introduces ReSeed, a lightweight post‑distillation technique that restores lost diversity in diffusion model distillation by adding a seed‑response bias adapter only to the first denoising step. By aligning the first step’s velocity with the teacher’s, ReSeed recovers most of the output diversity without altering later steps or adding target images. Experiments on SD3‑Medium, SD3.5‑Medium, FLUX.1‑dev, and Wan2.1‑T2V‑1.3B show a 48.3% increase in DINO diversity with negligible extra parameters and training data.
arXiv:2604. 16514v5 Announce Type: replace-cross Abstract: Autoregressive vision-language models (VLMs) deliver strong multimodal capability, but their token-by-token decoding imposes a fundamental inference bottleneck.
Autoregressive generation underlies real-time, causal video synthesis and is the backbone of video world models. Today's dominant approach distills a bidirectional diffusion model into a causal few-st...
arXiv:2610.19305v1 Announce Type: new Abstract: One-step diffusion distillation achieves strong performance on small datasets but remains insufficient for high-resolution or complex text-to-image set...
The paper introduces CP‑BG‑Bench, a paired‑view evaluation framework for Cell Painting vision encoders that fixes a central cell across four matched views (raw crop, segmented, and density‑augmented variants). Using this framework on three datasets and three encoders, the authors show that standard single‑metric rankings (e.g., replicate mAP) vary systematically across protocols, revealing disagreements along axes of cell versus background, morphology versus context, and within‑study versus across‑batch performance. The study demonstrates that segmented views can outperform crops in certain tasks and that background‑driven gains are largely determined by experimental design rather than encoder choice.
arXiv:2608. 13255v1 Announce Type: cross Abstract: Geometry-conditioned multi-view diffusion enables high-quality 3D texture generation, but its repeated per-view denoiser evaluations introduce substantial computational cost.
arXiv:2505. 06668v2 Announce Type: replace-cross Abstract: We present StableMotion, a novel framework that leverages geometric and content priors from pretrained large-scale image diffusion models for motion estimation in single-image rectification tasks such as Stitched Image Rectangling (SIR) and Rolling Shutter Correction (RSC).
CrossDistill is a trajectory-level hybrid few-step distillation framework for diffusion models that balances quality and diversity by splitting the sampling trajectory at a crossover point. The high-noise interval uses a trajectory-preserving objective to maintain global mode coverage, while the low-noise interval applies a distribution-matching objective to sharpen local details, with the two stages coupled through the crossover state. This noise-level scheduling policy, demonstrated on text-to-video and image-to-video diffusion models, expands the few-step quality-diversity frontier by preserving seed-level variation while achieving competitive visual fidelity.
arXiv:2610.17407v2 Announce Type: cross Abstract: Generating realistic time-series requires faithfully reproducing rare but high-impact extreme events. Existing approaches often rely on specialized r...
The paper introduces Probability‑Flow Distillation (PFD), a new method for matching parameter distributions in diffusion‑based models. It extends the particle variational inference framework of Variational Score Distillation to Score Distillation Sampling (SDS) and Score Distillation via Inversion (SDI), revealing that SDS focuses on mode collapse while SDI converges to a contracted distribution. By replacing a single Euler step in SDI with a full reverse probability‑flow ODE solve and simplifying the gradient, PFD achieves distribution matching with only a forward ODE solve, and experiments on synthetic data, CelebA, and text‑to‑3D tasks confirm its effectiveness.