2026-08-19

12 papers from arXiv

← Back to history

Memory Tree Guided Key Frame Querying for Efficient 3D Question Answering

Hsiang-Wei Huang, Fu-Chen Chen, Li-Wu Tsao, Cheng-Han Lee, Che-Chun Su et al.

Answering questions accurately and efficiently in embodied scenarios presents significant challenges due to limited computational and memory resources for Vision Language Model (VLM) inference. Existing methods adopt visual search key frame retrieval method to select critical question-related key frames for VLM input. However, visual search methods are inefficient because they require visual searc...

cs.CVECCV

Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment

Marko Haralovi, Zhiqi Miao, Alexander Machiel Bont, Jiapan Guo, Frans van Workum et al.

Surgical performance assessment in minimally invasive surgery largely relies on manual expert review, making it time-consuming, subjective, and difficult to scale. While existing surgical video understanding methods address tasks such as instrument segmentation, surgical phase recognition, and action recognition, they do not explicitly capture fine-grained tissue handling, a key indicator of surgi...

cs.CVECCV

DistillPath: An Efficient 22M Distilled Pathology Encoder Approaching Large Foundation Model Performance

Ramon Kaspar, Andrey Ignatov, Valentina Boeva

Many high-performing pathology tile encoders are now foundation models with hundreds of millions to over a billion parameters. Encoding and storing the thousands of tiles in each whole-slide image with such models is costly on commodity hardware, so compact encoders that retain useful downstream performance are a valuable alternative. We present DistillPath-KS16, which starts from the existing 22M...

cs.CVECCV

Scale Matters: Adaptive Granularity Selection for Cross-Species 3D Plant Organ Segmentation

Carla Salazar, Lazaros Nalpantidis

Recent 3D foundation models provide powerful feature representations for point cloud learning by controlling spatial granularity. However, relying on a fixed spatial granularity severely limits generalization in applications like plant phenotyping, where organ morphology and size vary substantially across species and growth stages. To address this, we propose AGS-PlantSeg, a few-shot 3D plant orga...

cs.CVPR

Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation

Zhikai Xu, Zhucun Xue, Teng Hu, Yabiao Wang, Yong Liu et al.

Academic surveys play a central role in organizing rapidly expanding scholarly literature, yet their construction requires extensive paper analysis, coherent knowledge organization, fine-grained citation support, and reliable manuscript assembly. Existing Deep Research and automated survey generation systems address parts of this process, but typically do not coordinate paper understanding, litera...

cs.CVPR

AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation

Haoran Qin, Zhengan Yan, Shikang Zheng, Xiaobing Tu, Jiacheng Liu et al.

Diffusion Transformers (DiTs) achieve high-quality generation but are costly due to iterative sampling. Dynamic-resolution sampling reduces early-stage cost by denoising at low resolution; however, uniformly upsampling all latent tokens at resolution transitions incurs redundant computation and may degrade fine-detail consistency. Existing partial upsampling strategies typically rely on local late...

cs.CVECCV

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

Jinshan Liu, Haoran Qin, Xiaobing Tu, Jiacheng Liu, Jiahui Hu et al.

Diffusion models have achieved remarkable success in image and video generation, yet the high computational cost of iterative sampling remains a critical bottleneck for practical deployment. Feature caching has emerged as a promising acceleration paradigm by reusing or predicting intermediate features across timesteps. However, existing training-free methods apply uniform prediction strategies tha...

cs.CVECCV

The Model's Tell: Measuring Context-Leakage Attack Signals with Behavior Gauges

Maosen Zhang, Jianshuo Dong, Boting Lu, Wenyue Li, Xiaoping Zhang et al.

LLMs increasingly rely on external contexts, such as pre-defined system prompts or retrieved documents, to improve generation quality. However, processing these contexts alongside user queries creates an attack surface: adversarial inputs can induce models to disclose them. Prior probing studies suggest that leakage-related signals emerge in hidden states, yet the need to extract these states pose...

cs.CRcs.AIPR

Training with synthetic data for drone detection in thermal imagery

Tanel Liiv, Sander Soodla, Nzamba Bignoumba, Alma M. Liezenga, Toomas Pruuden

Ground-to-Air (G2A) drone detection in medium- and long-wave infrared (MWIR/LWIR) imagery is challenging due to reduced texture information, sensor noise, weak thermal contrast, and the scarcity of annotated data. This work investigates a synthetic-first training strategy that combines synthetic scene generation with fine-tuning on real data. We show that synthetic data provides an effective basis...

cs.CVcs.AIcs.ETPR

Monitoring Pasture Restoration from Satellite Image Time Series: Caveats and Opportunities

Linnea Sartorius, Isak Randahl, Delia Fano Yela, Georg Andersson, Sadegh Jamali et al.

Monitoring nature restoration at scale is an important but difficult ecological problem. Deep learning methods to analyze satellite image time series (SITS) have been widely used for land surface monitoring. In semi-natural grasslands - the habitat type in focus in this work - restoration outcomes develop gradually, yet satellite observations are influenced by weather, acquisition conditions, and ...

cs.CVECCV

Conformal Prediction for Molecular Properties under Label Shift

Hyeonsu Lee, Juyeon Kim, Erkhembayar Jadamba, Seungjin Choi, Hyunjin Shin

Drug discovery and development underpins healthcare but remains costly and failure-prone. A critical bottleneck lies in predicting molecular properties such as solubility, potency, and toxicity, which directly determine whether a candidate can advance from preclinical to clinical trials. Artificial Intelligence (AI) has accelerated this process, yet its reliability is often undermined by distribut...

cs.LGNeurIPS

MSEditor: Toward Consistent Multi-Shot Video Editing

Kunyu Feng, Yue Ma, Bingyuan Wang, Yuefeng Wang, Zhiyuan Qin et al.

In this paper, we tackle the problem of performing consistent, unified modifications to a multi-shot video sequence. This task is particularly challenging because multi-shot videos consist of discontinuous temporal segments that vary significantly in viewpoint, camera scale, and subject pose, leading to severe identity drift and cumulative error propagation. Achieving coherent edits requires estab...

cs.CVECCV