arXiv AI
Jun 2
E4GEN: Event-level Explainable Extreme-Enhanced Time-series Generation
arXiv:2606. 01634v1 Announce Type: cross Abstract: Generating realistic time series is essential for scientific research and real-world applications.
Cross-View Time-Frequency Diffusion for Extreme-Aware Time-Series Generation
Related stories
arXiv Machine Learning
Jun 16
Towards a Unified Generative Model for Scarce Time Series with Domain Experts
arXiv:2606. 15172v1 Announce Type: new Abstract: Synthesizing realistic time series with generative models has wide-ranging applications in real-world scenarios.
arXiv AI
Aug 6
Seeking Physics in Diffusion Noise
arXiv:2603. 14294v3 Announce Type: replace-cross Abstract: Do video diffusion models encode signals predictive of physical plausibility?
arXiv Machine Learning
Oct 22
DriftNeRF: Cross-Ray Density Drifting for Sparse-View Neural Radiance Fields
DriftNeRF introduces a regularizer that addresses cross‑ray density disagreement in Neural Radiance Fields, a defect that causes poor performance when only a few views are available. By aggregating densities from nearby points on other rays into a stop‑gradient consensus target, DriftNeRF penalizes unsupported disagreement while preserving agreed boundaries. The method improves 3‑view PSNR by 0.42–0.65 dB on NeRF‑Synthetic, DTU, and LLFF datasets and remains competitive with sparse‑view Gaussian pipelines without requiring additional geometry or preprocessing.
arXiv Machine Learning
Aug 4
DAVET: Denoising-Aware Visual Evidence Trajectory Allocation for Diffusion Vision-Language Models
arXiv:2608. 01821v1 Announce Type: cross Abstract: Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial recurring inference cost.
arXiv AI
Jul 1
FMA-Net++: Motion- and Exposure-Aware Joint Video Super-Resolution and Deblurring
arXiv:2512. 04390v2 Announce Type: replace-cross Abstract: Joint video super-resolution and deblurring (VSRDB) requires both efficient long-range temporal modeling and robustness to frame-wise exposure-duration variation, which changes the extent of motion blur across video frames.
arXiv AI
Aug 11
HEART: Exploiting Head Heterogeneity in Sparse Attention for Video Diffusion
arXiv:2605. 14513v2 Announce Type: replace-cross Abstract: Sparse attention accelerates video diffusion by allowing each attention head to focus on only a small subset of interactions.
arXiv Computer Vision
Aug 31
Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation
The paper introduces Relax Forcing, a training‑free memory mechanism for autoregressive video diffusion that structures temporal context into Sink, Tail, and History frames. By selecting History frames with a relaxation criterion, the method reduces error accumulation and attention overhead while preserving motion dynamics. Experiments on VBench‑Long demonstrate that this structured memory improves long‑video generation quality over existing baselines.
arXiv Computer Vision
Sep 22
GAPS: Generative Active Pseudo-view Selection for Sparse-View 3D Gaussian Splatting
arXiv:2609.23436v1 Announce Type: new Abstract: Novel view synthesis from sparse observations is severely under-constrained. Although 3D Gaussian Splatting (3DGS) enables real-time rendering, it prod...
arXiv Computer Vision
Oct 9
Stratified Multi-View Aggregation for Score Distillation
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.
arXiv Computer Vision
Sep 18
Recency Forcing: Bridging the Long-Horizon Gap in Autoregressive Video Generation
The paper introduces Recency Forcing, a technique that addresses the long‑horizon degradation in autoregressive video generation caused by KV eviction mismatch. By applying a timestep‑dependent bias—Temporal Response Bias—derived from a positional response measure, the method reduces the influence of distant frames during inference without altering context length or training objectives. An exact reformulation, Biased Attention Reparameterization, enables this bias to be applied as a standard FlashAttention call with zero overhead, achieving state‑of‑the‑art long‑horizon generation quality on VBench datasets.
arXiv Machine Learning
Jul 10
Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning
arXiv:2603. 12478v2 Announce Type: replace-cross Abstract: Multimodal instruction tuning is often compute-inefficient because training budgets are spread across large mixed image-video pools whose utility is highly uneven.