The paper introduces GeoPatch, a fixed‑scaffold patch encoder that decouples token support from signal geometry for time‑warp robust sequence retrieval. By using geometry‑derived descriptors (slope, curvature, acceleration, affine‑residual, confidence) as continuous conditioning variables, GeoPatch prevents patch boundary drift while still allowing geometry to modulate embeddings. Experiments on ECG, speech, and multivariate time‑series data show that GeoPatch improves early‑rank retrieval under timing variation and highlights a trade‑off between local surface matching and strict non‑overlap retrieval.
arXiv:2608. 12695v1 Announce Type: new Abstract: Self-supervised electrocardiogram (ECG) models are often trained on a few seconds of ECG signal and, increasingly, on discretized token sequences.
arXiv:2608. 02044v1 Announce Type: cross Abstract: Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut.
arXiv:2606.06158v2 Announce Type: replace Abstract: Adaptive video tokenisation seeks to dynamically allocate token budgets based on the underlying visual complexity of a sequence. Current continuous...
arXiv:2608. 13741v1 Announce Type: cross Abstract: Synthesizing time series from natural language is emerging as the most expressive form of controllable time series generation.
arXiv:2603.12916v4 Announce Type: replace-cross Abstract: Multivariate time series anomalies often manifest as shifts in cross-channel dependencies rather than simple amplitude excursions. In autonom...
The paper introduces TEMPS, a modular temporal branch that enhances semantic retrievers by adding a temporal scoring component. TEMPS resolves anchored temporal expressions into intervals, matches them to Gaussian distributions, and trains an anchor-date-conditioned encoder using grounding supervision without hand‑labeled data. On three temporal benchmarks, TEMPS improves MRR across all tested backbones and raises R@1 from 19.92 to 25.39 on the TS‑Retriever, surpassing prior temporal state‑of‑the‑art methods.
arXiv:2605. 16366v2 Announce Type: replace-cross Abstract: Video MLLMs face a persistent tension between spatial fidelity and temporal coverage: preserving fine-grained visual details requires many spatial tokens, while capturing short-lived events requires dense temporal sampling.
PAGER is a label‑free adaptation method that aligns partial, viewpoint‑dependent 3D observations with a frozen global semantic space. It uses matched‑point feature alignment and relational supervision to anchor partial features to their global counterparts while preserving similarity structure, all without altering the pretrained encoder or global probe. Experiments show PAGER outperforms label‑supervised PEFT on Sonata and Concerto, and achieves superior zero‑shot transfer from ScanNet to ScanNet++ compared to fully fine‑tuned Sonata.
arXiv:2606. 01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos.
arXiv:2609.10224v1 Announce Type: new Abstract: Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing acc...
arXiv:2608. 19297v1 Announce Type: new Abstract: While multimodal large language models (MLLMs) excel in medical applications, most of them favor static images or short-term signals.
arXiv:2605. 21028v2 Announce Type: replace-cross Abstract: Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors.