The paper introduces a new object detection approach that protects sensitive visual data in test images. It is the first to apply perceptual encryption to object detection, leveraging the embedding structure of Vision Transformers and a key-based domain adaptation to maintain accuracy comparable to unprotected models. Experiments on ViTdet confirm the method’s effectiveness in both accuracy and visual protection.
By Homare Sueyoshi, Kiyoshi Nishikawa, Hitoshi Kiya
The paper shows that large language models (LLMs) naturally organize their hidden state manifolds into small‑world networks, enabling efficient multi‑hop reasoning. By converting similarity matrices into unweighted graphs, the authors trace connectivity between distant semantic anchors and find a sharp topological phase transition: deep reasoning layers compress conceptual distances into paths bounded by six semantic hops, while early syntactic layers remain fragmented. The framework is applied to zero‑shot hallucination detection in Retrieval‑Augmented Generation, revealing that factual generations preserve a ~3‑hop structure, whereas hallucinations collapse the topology.
By Md. Faiyaz Abdullah Sayeedi
StruProKGR is a Structural and Probabilistic framework designed for sparse Knowledge Graph (KG) reasoning. It reduces computational costs by using a distance‑guided path collection mechanism and improves interpretability by aggregating paths probabilistically to prioritize reinforcing paths. Experiments on five sparse KG benchmarks show that StruProKGR outperforms existing path‑based methods in both effectiveness and efficiency.
By Yucan Guo, Saiping Guan, Miao Su, Jiyao Wei, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
COEC (Calibrated Orthogonal-Equivalence Compensation) is a training‑free framework that improves structured pruning of large language models by applying alternating left and right orthogonal rotations to the retained weight matrix. The method optimizes the right rotation on a reduced Stiefel manifold, rescales singular values via generalized cross‑validation, tempers the calibration Gram matrix, and adds an alignment penalty to preserve geometric relations between attention projections. Experiments on Llama‑3, Llama‑3.1, and Qwen2.5 show that COEC consistently improves perplexity and zero‑shot accuracy across multiple sparsity levels, outperforming existing compensation techniques.
By Peiqi Yu, Nam Ling, Wei Wang, Wei Jiang
The paper defends the 'Whole Hog Thesis', arguing that sophisticated large language models such as ChatGPT are full linguistic and cognitive agents, possessing understanding, beliefs, desires, knowledge, and intentions. It rejects low‑level computational starting points and instead builds its case from high‑level behavioral observations, using Holistic Network Assumptions to link actions to mental states. The authors systematically rebut common objections—such as hallucinations and planning errors—by showing these resemble human fallibility and by challenging the necessity of traditional conditions like embodiment or semantic grounding.
By Herman Cappelen, Josh Dever
The study introduces PV‑SST, a peer‑voted social‑platform testbed, and conducts a preregistered matched‑exposure experiment across four topics, four seeds, four model families, and three larger variants, totaling 448 trials. Results show that feeding agents a ranked list of prior peer posts increases lexical similarity in both the core panel and larger variants, but does not produce a reliable advantage in opinion alignment or survival rates. The only robust finding is lexical convergence driven by the peer‑ranked feed, with no consistent coordination benefit across models or topics.
By Rana Muhammad Usman, Dominic Williamson
The paper discusses how large language models retrieve facts from their weights, proposing that this phenomenon reflects a broader operation termed feature recall. It argues that a linear projection can be interpreted as retrieving stored information scaled by input activations, and demonstrates that feature recall applies across various architectures, contrasting it with the traditional feature combination paradigm. The authors also explore potential mechanistic identification of feature recall cases and suggest new empirical directions for mechanistic interpretability research.
By Pierre Beckmann
The paper proposes a structured method for assessing the representativeness of Operational Design Domains (ODDs) in AI/ML-based aviation systems, focusing on safety assurance. It outlines a process flow from ODD definition to quantitative evaluation, recommending Kullback–Leibler divergence and Cramér’s V over chi‑squared tests for large datasets. The approach is illustrated with AI-based collision avoidance simulations, demonstrating how statistical distribution comparisons can support safety‑by‑design engineering aligned with EASA guidance.
By Thomas Stefani, Johann Maximilian Christensen, Elena Hoemann, Frank K\"oster, Sven Hallerbach
arXiv:2608.21175v1 Announce Type: cross
Abstract: Safe and efficient shape-aware navigation in heterogeneous crowds and robot fleets remains challenging. Traditional approaches often assume homogeneo...
By Ruihua Han, Rui Gao, Zhe Liu, Xinyi Wang, Chang Chen, Shuai Wang, Qi Hao, Jia Pan, Hengshuang Zhao
The paper introduces TSS (Triple-Stream Stress probe), a diagnostic framework that splits text into lexical, morpho-syntactic, and psycholinguistic style channels to analyze mental health NLP classifiers. Across four English datasets, TSS uncovers a lexical interference effect where adding lexical features harms performance on human-labeled data but not on auto-labeled data, and proposes the Degree of Divergence (DoD) statistic to audit label-source bias. The study demonstrates that style features largely remain effective even after masking content words, emphasizing that shortcut learning is label-source specific rather than clinically relevant.
By Moustafa Yehia Hassan
ReCurveflow is a flow‑matching framework that learns to predict transition state geometries by training on continuously curved reference paths derived from full NEB bands, rather than straight linear paths. It introduces an off‑path correction mechanism that generates corrective velocity fields when the model encounters geometries off the training path, improving resistance to exposure bias and TS prediction accuracy. Across multiple data splits and evaluation metrics, ReCurveflow outperforms seven baselines and produces reaction trajectories whose energy profiles closely follow the reference NEB path, aiding NEB optimization and demonstrating effective corrective behavior.
By Seungheun Baek, Mogan Gim, Jaewoo Kang
The paper introduces CTQW-GNN, a graph neural network that uses Continuous‑Time Quantum Walks (CTQW) to address two common GNN problems: low‑pass bias on heterophilic graphs and over‑smoothing with deep layers. By exploiting the unitary nature of the CTQW propagator, the model preserves high‑frequency signals and maintains feature norms across layers. Three aggregation modules—CTQW‑based, CTQW‑attention, and a low‑pass GAT branch—combine to handle both heterophilic and homophilic graph structures, supported by spectral‑gap analysis and a Lieb–Robinson‑type bound for walk‑time selection.
By Yuliang Zhan, Zefeng Gao, Jian Li, Yang Liu, Hao sun
RecGen3D is a framework that merges feed‑forward reconstruction and diffusion‑based generation to address the trade‑off between reconstruction fidelity and generative plausibility in sparse‑view 3D modeling. By aligning both models in a shared canonical space and using decoupled cooperative learning, the system stabilizes training and allows the reconstruction module to supply canonical geometric anchors while the diffusion generator refines and completes the structure. Experiments show that RecGen3D outperforms existing methods in producing complete and consistent 3D models from sparse observations.
By Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li, Wenping Wang
arXiv:2608.21133v1 Announce Type: new
Abstract: Medical image-text data can expose protected health information (PHI) through both visible image content as well as accompanying text, creating a barri...
By Shiva Shrestha, Zongxing Xie, Chen Zhao, Liran Ma, Zhipeng Cai, Honghui Xu
arXiv:2606.13971v3 Announce Type: replace
Abstract: While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current pr...
By Xiaomeng Yang, Yanyu Li, Gordon Guocheng Qian, Ivan Skorokhodov, Viacheslav Ivanov, Avalon Vinella, Xuan Zhang, Yanzhi Wang, Sergey Tulyakov, Anil Kag
Crane is a CLIP‑based framework for zero‑shot anomaly detection that enhances dense localization by adapting the vision encoder with a correlation‑based attention module and conditioning learnable prompts on global image context. It further fuses anomaly‑relevant patch features into the global representation for more sensitive image‑level detection, and a variant called Crane+ leverages DINOv2 spatial correlations for stronger pixel‑level performance. Across seven industrial benchmarks, Crane raises mean image‑level AP by 4.5% and Crane+ boosts mean pixel‑level AUPRO by 9.0%.
By Alireza Salehi, Mohammadreza Salehi, Reshad Hosseini, Cees G. M. Snoek, Makoto Yamada, Mohammad Sabokrou
RouteScan is a non‑intrusive auditing framework that detects harmful behavior in Mixture‑of‑Experts (MoE) large language models by analyzing expert‑routing telemetry captured from GPU execution. It uses the number of active GPU threads during the prefilling phase as a micro‑architectural fingerprint to isolate cross‑domain risk indicators and precisely identify malicious prompts. Evaluations on four open‑source MoE LLMs show strong generalization with AUROC > 0.91 on unseen harmful domains, while privacy tests indicate that full prompts cannot be reliably recovered from aggregated telemetry.
By Bo Lv, Zhiheng Xu, KeDong Xiu, Ruyi Ding, Tianhang Zheng, Zhibo Wang, Kui Ren
arXiv:2608.15698v2 Announce Type: replace
Abstract: Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from docume...
By Chunyi Peng, Zhipeng Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Sen Mei, Yubo Sun, Yongheng Zhang, Jie Zhou, Yu Gu, Ge Yu, Maosong Sun
arXiv:2411.02771v3 Announce Type: replace-cross
Abstract: Doubly robust estimators are widely used for estimating average treatment effects and other linear summaries of regression functions. While c...
By Lars van der Laan, Alex Luedtke, Marco Carone
MatMMExtract is an open‑source pipeline that disassembles compound scientific figures into individual sub‑panels and generates structured, grounded image‑text pairs using a large language model guided by a materials science taxonomy. Applied to 14,810 open‑access articles, it produced 391,606 panel‑level pairs with sub‑captions, a two‑level visualisation category (19 classes, 100+ subtypes), and scientific summaries. The project also introduces MaterialScope, a 2,811‑figure detection dataset, and demonstrates that Gemini 3.1 Flash Lite yields high‑quality annotations with low hallucination, while a dual‑encoder baseline outperforms zero‑shot CLIP on the resulting MatSciFig dataset.
By Subham Ghosh, Shubham Tiwari, Mohammad Ibrahim, Abhishek Tewari