Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gaussian frameworks are often bottlenecked by restrictive multiview capture requirements, costly scene-specific optimization, and the massive memory overhead of storing dense language features.
Long-horizon steel-equipment inspection requires reasoning over heterogeneous records accumulated across repeated inspection cycles. Existing retrieval-augmented generation systems treat historical logs as a static corpus and retain records without estimating their diagnostic value, failing to report early risk.
Objective evaluation of expressive MIDI piano performances typically relies on attribute statistics such as timing, velocity, and duration of individual notes. However, these methods often disregard dependencies between notes, which poses a potential limitation in assessing the similarity between two sets of performances.
Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances.
Remote sensing images acquired by unmanned aerial vehicles (UAVs) and satellites are often degraded by adverse weather, illumination variation, and imaging artifacts, which may co-occur and jointly induce global distribution shifts and local structural corruption. Although All-in-One image restoration offers an appealing unified alternative to task-specific pipelines, existing methods still suffer from weak or implicit degradation cues and parameter redundancy caused by full-rank multi-expert designs with overlapping restoration behaviors.
LLM agents increasingly rely on long-term memory to support multi-session interaction and personalization. However, existing agent memory systems are designed around forward-only evolution, continuously accumulating, consolidating, and overwriting knowledge, with no principled mechanism to inspect, version, or revert prior states.
We describe the DS@GT submissions to the ImageCLEFmedical Caption 2026 challenge, which continues a long-running benchmark on the ROCOv2 dataset with two tracks: Concept Detection (Task 1), assigning UMLS Concept Unique Identifiers (CUIs) to radiology images, and Caption Prediction (Task 2), generating natural-language captions. For Task 1, our primary submission was a three-way late-fusion ensemble of ConvNeXt-V2, BiomedCLIP ViT-B/16, and DenseNet-169 with a regularized ''Honest Threshold Tuning'' procedure designed to avoid validation overfitting on rare concepts; this submission ranked first on the official submission with a primary $F_1$ of $0.
Event analysis is an essential and fundamental direction of information extraction, involving various event-centric tasks at different granularity of documents. While large language models (LLMs) have preliminarily achieved promising performance in part of these tasks individually, their capability in event analysis still lacks comprehensive understanding due to restricted document granularity, task designs, and data source of existing benchmarks.
arXiv:2607. 26631v1 Announce Type: new Abstract: Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments.
By Hansi Karunarathna, Nirhoshan Sivaroopan, Chamara Madarasingha, Anura Jayasumana, Kanchana Thilakarathna
arXiv:2603. 21033v3 Announce Type: replace-cross Abstract: Geotechnical site characterisation relies on sparse, heterogeneous borehole data, where uncertainty quantification and interpretability matter as much as predictive accuracy.
By Taiga Saito, Yu Otake, Daijiro Mizutani, Stephen Wu
arXiv:2605. 08810v2 Announce Type: replace Abstract: We propose \textbf{Compressed Video Aggregator} (CVA), a lightweight micro-video recommendation module that decouples video information from preference learning.
By Yang Xiao, Huiyuan Chen, Kaiyuan Deng, Chao Jiang, Zinan Ling, Ruimeng Ye, Fei Wang, Xiaolong Ma, Bo Hui
arXiv:2605. 24033v2 Announce Type: replace Abstract: Mechanistic interpretability typically discovers circuits and then argues what they do from examples and ablations.
By Neel Somani
arXiv:2607. 26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning: maliciously injected passages that manipulate retrieved evidence.
By Pushkal Kumar, Tucker Nielson, Tanish Kolhe, Shubham Zala, Vincent Li
arXiv:2605. 11759v2 Announce Type: replace-cross Abstract: Dimensionality reduction is essential in simulation-based shape design, where high-dimensional parameterizations hinder optimization, surrogate modeling, and systematic design-space exploration.
By Andrea Serani, Giorgio Palma, Matteo Diez
arXiv:2607. 25132v2 Announce Type: replace Abstract: A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior.
By Shiwei Tan, Yusong Zhao, Weiyi Qin, Wentian Wang, Jacob Feldman, Lazaros K. Gallos, Paul B. Kantor, Vladimir Menkov, Hao Wang
arXiv:2607. 27090v1 Announce Type: cross Abstract: Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histories, that is shared across a user's many requests.
By Peter Li, Prashant Pandey
arXiv:2607. 26988v1 Announce Type: cross Abstract: What types of decision problems can a causally masked, finite-precision transformer solve for inputs of arbitrary length?
By Franz Nowak, Ryan Cotterell, Reda Boumasmoud
arXiv:2607. 27078v1 Announce Type: cross Abstract: In this paper, we formulate three communication tasks for empirical optimal transport: distributed coupling sampling, cost-evaluable coupling output, and scalar value-certified sampling.
By Hung Mai, Hai Nguyen, Luong Doan, Ngoc Vu, Khanh Nguyen, Nhung Duong, Tuan Do
arXiv:2607. 26278v1 Announce Type: new Abstract: It is common for two-dimensional embeddings of high-dimensional data to be read far beyond what they can support.
By Abdallah Baraka, Daniel Probst
arXiv:2603. 15384v2 Announce Type: replace-cross Abstract: We improve and extend persistence spheres, introduced in~\cite{pegoraro2025persistence}.
By Matteo Pegoraro