arXiv:2607. 06856v1 Announce Type: cross Abstract: Prior work suggests that diffusion representations capture low-level geometry but struggle with high-level semantics.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.
arXiv:2609.21379v1 Announce Type: new Abstract: Accurate traffic forecasting requires both understanding scene dynamics and synthesizing realistic future observations. Recent diffusion-based video ge...
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
arXiv:2512.07480v2 Announce Type: replace Abstract: While traditional and neural video codecs (NVCs) have achieved remarkable rate-distortion performance, improving perceptual quality at low bitrates...
ContextAnyone is a context‑aware diffusion framework that treats a reference image as an explicitly preserved appearance anchor rather than a simple conditioning signal. By jointly reconstructing the reference image and generating the target video within a shared diffusion transformer, it provides direct supervision for maintaining identity and fine‑grained appearance throughout denoising. The method introduces asymmetric information flow and Gap‑RoPE positional representations to keep the reference stable while allowing selective access by video tokens, and demonstrates improved identity and appearance consistency on an OpenVid‑HD benchmark.
The article surveys how diffusion and flow-based generative models learn rich visual representations and how these representations can be used to improve generation and other perception tasks. It introduces a three-tier framework that categorizes work into improving generative quality via representation learning, extracting representations for perception, and developing unified applications. The survey covers downstream tasks such as image classification, dense prediction, instance-level perception, and annotation-scarce scenarios, offering a taxonomy and highlighting future research directions.
arXiv:2608.20515v1 Announce Type: new Abstract: Generative video compression can recover rich visual details at low bitrates, but simultaneously achieving high temporal consistency and low inference...