Embedding
-
Dense Representation Learning and Differentiable Shape Modeling for Spine Landmark Detection
2026-10-27 10:11:18Augustin Daridon, Sofiane Sifaoui, Ayman Assi, Mohamad Karam, Wafa Skalli, Elsa Angelini, Loic Le FolgocAbstract
Spine landmark detection from spinal X-ray is a key step for estimating spine deformation severity, for building biomechanical models, and for pre-operative planning. We reframe anatomical landmark detection as a pixel-level contrastive representation learning problem, matching dense pixel embeddings with landmark prototypes. Surprisingly, even with a generic U-Net backbone, this formulation results in more discriminative heatmaps compared to the traditional heatmap regression paradigm, leading to improved discrimination between vertebral corners on distinct vertebra. Furthermore, we combine the resulting heatmaps with learnable shape priors over the global configuration of spinal landmarks to resolve ambiguities in landmark locations, yielding a simple and practical approach to spinal landmark detection. Our approach is competitive, in terms of landmark accuracy and clinical parameter estimation, with the state-of-the-art on the public AASCE dataset and on two private spinal X-ray datasets. Our code and pre-trained weights are available at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36951
PDF
-
Nothing Left Behind: Finding Evidence from a Large Randomized Evaluation Corpus
2026-10-27 09:40:24Giuliano Martinelli, Abelardo Carlos Martinez Lorenzo, Satvik Garg, Linxi Wang, Riccardo Orlando, Piriyakorn Piriyatamwong, Samuel Paul FraibergerAbstract
Many AI systems need to find every relevant items in a large collection and then organize what they found. The standard way to do this is to tag each item with labels from a curated vocabulary and search on those labels. Those labels are useful for organizing results, but searching on them misses items that do not fit a label and returns too much when labels are broad. We compare this approach with an embedding-based approach: find candidates by meaning using text embeddings, then have a language model keep only the relevant ones. In a corpus of 7,354 randomized trials, label search found 45% of the evidence a systematic review would include, while the new approach found 92%, at a cost per query that rises with search depth. These results support a two-stage architecture that combines broad candidate retrieval with query-specific evidence filtering.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36910
PDF
-
GUI-JEPA: Candidate-Conditioned JEPA Latents as a Fast Action Policy for Mobile GUI Agents
2026-10-27 09:17:51Bingchao Wang, Yongcheng Jing, Shunyu Liu, Chengyu Wang, Jun Huang, Jie Yang, Wei Liu, Dacheng TaoAbstract
Mobile GUI agents are typically fine-tuned 7B-scale vision-language models (VLMs) that generate each action as text. However, these VLMs decode every action token by token, and even agents that score candidate actions keep a large language model or VLM in the loop, making them slow and memory-hungry. To address these issues, we propose GUI-JEPA, to our knowledge the first decoder-free GUI agent policy built on a Joint-Embedding Predictive Architecture (JEPA), which selects actions in the latent space of a JEPA encoder pretrained on unlabelled GUI screenshots. Its action- and region-conditioned latent predictor turns the screen latent into one latent per candidate action, letting lightweight heads score all candidates against the instruction in a single batched pass, without decoding a token. We further show that the scorer relies on this latent pathway and that the predictor is trained for the decision itself: a randomly initialised predictor does just as well as one pretrained on screen dynamics. On AndroidControl, GUI-JEPA is 2.8-4.0x faster on the same GPU than a Qwen2.5-VL-7B agent we fine-tune with the same inputs, while reaching 86-92% of its in-distribution accuracy with 6% of its parameters. Code is available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.36877
PDF
-
Evaluating AlphaEarth Embeddings for Crop Classification: Separability, Temporal Dynamics, and Cross-Regional Transferability
2026-10-27 08:53:02Priyanka Goyal, Maitreyee Sar, Adway Mitra, Manjira SinhaAbstract
Earth Observation (EO)-based agricultural monitoring is shifting from pixel-level spectral analysis toward representation-driven modeling, yet systematic evaluation of learned representations across spatial, temporal, and domain-generalization dimensions remains limited. Geospatial foundation models generate high-dimensional embeddings encoding spatio-temporal land-surface properties, but their utility for agricultural applications remains insufficiently understood. This study presents a representation-agnostic evaluation framework integrating geometric separability, temporal dynamics, spatial robustness, and cross-regional generalisation. A 64-dimensional AlphaEarth embedding space is benchmarked against Sentinel-2 reflectance, NDVI-derived phenology, and harmonic features using field-scale data from the Conterminous United States (CONUS; 2017-2023) and Northern India (2021). Traditional features achieve strong linear separability (Fisher ratio), while embeddings provide superior distribution-aware separation -- Bhattacharyya and Mahalanobis distances up to an order of magnitude higher for spectrally similar pairs (e.g. Corn/Soybeans: 3.9 vs. 0.10). Embeddings uniquely capture multi-year crop rotation dynamics, reaching a separability ratio of 1.784 versus a maximum of 1.003 across all engineered features, and exhibit lower residual spatial autocorrelation of errors (mean Moran's $I \approx 0.17$). However, harmonic and NDVI features show stronger cross-continental transferability (US $\to$ India Macro F1: 0.493 vs. 0.326 for embeddings), reflecting better distributional alignment. The combined feature space yields balanced performance, supporting hybrid modeling. These findings reveal a fundamental trade-off between representational richness and cross-region transferability, providing a structured framework for feature selection in large-scale crop classification.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36857
PDF
-
Personality Latents: Conditioning Frozen Language Models on Individuals from Their Own Writing
2026-10-27 08:08:06Gunhee Cho, Yun-Gyung CheongAbstract
Controlling the personality of a language model usually relies on written profiles or named trait categories, so it can only express what an author writes down or what a taxonomy names. We instead propose Personality Latents (PL), which learn a latent for each person from their own writing, with no personality labels and no authored profile, and inject it into a frozen language model as a soft prefix. Following generative latent optimization, each training person receives a free latent that is optimized through the frozen model itself, while an encoder learns to predict these latents so that a new person needs only one forward pass, with optional refinement at test time. We evaluate on held-out people by having the conditioned model answer neutral and interview questions and reading personality from its answers with scorers trained on real human writing. On the MBTI axes PL reaches an AUC of , ahead of persona embedding and prompt-based baselines under identical settings, and the ranking holds when the answers are scored in three different embedding spaces. A latent learned with Qwen2.5-3B-Instruct also transfers personality to Llama-3.1-8B-Instruct through a new adapter alone.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36805
PDF
-
CVBL-CCTV-Face Dataset for Real-World Face Enhancement and Recognition in Surveillance
2026-10-27 07:48:18Manish Das, Ajay Kumar Yadav, Shiv Ram Dubey, Satish Kumar SinghAbstract
In real-world surveillance settings, facial captures from closed-circuit television systems suffer from degradations such as low resolution, motion blur, noise, and occlusions, which undermine dependable face recognition. In this study, we propose a framework for super-resolution and identity recognition, aimed at surveillance applications. For this purpose, we present the CVBL-CCTV-Face Dataset which is a dataset of real-world images taken in an unpaired manner where each pair consists of a low-quality (LQ) image of a face captured by a 8MP IP Dome CCTV camera together with a high-quality (HQ) reference image that is taken in controlled settings. In order to cope with the various problems posed by such datasets, we construct a modular system that involves face detection, deep learning-based super-resolution of low-quality face images, and identity recognition through L2-normalized embeddings extracted by an embedding model. Enhancement models are trained and tested according to three different setups, and the system is deployed for identity verification in a real-time unconstrained environment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36781
PDF
-
Efficient Remote Sensing Image-Text Retrieval via Interaction-Free Recall and Text-Guided Reranking
2026-10-27 07:12:20Xi Chen, Xu Chen, Xiamgyang Jia, Wei Wang, Xu Zhang, Zhenyuan ShunAbstract
Remote sensing (RS) image-text retrieval plays a critical role in understanding massive RS imagery. However, the dense multi-object distribution and complex backgrounds in RS imagery make it difficult to simultaneously achieve fine-grained cross-modal alignment and efficient retrieval. Existing methods either rely on complex cross-modal interactions that lead to low retrieval efficiency, or depend on large-scale vision-language adaptation, which requires massive data and computational resources. To address these issues, we develop a fast-then-fine (FTF) retrieval framework centered on interaction-free multi-granular recall and parameter-free text-guided cross-modal reranking with the Balanced Text-guided Interaction Block (BTIB). Specifically, interaction-free multi-granular recall pre-computes gallery embeddings and matches them with the corresponding query embedding without full-gallery token-level text-image interaction, while text-guided cross-modal reranking with BTIB refines local semantic correspondence within the top-K candidate set. Furthermore, an inter- and intra-modal loss is designed to jointly optimize cross-modal alignment across multi-granular representations. Extensive experiments on public benchmarks demonstrate that the FTF achieves competitive retrieval accuracy while significantly improving retrieval efficiency compared with existing methods.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36756
PDF
-
SWIM: Learning What Matters from Behaviors for JEPA World Models
2026-10-27 05:28:28Jiaming Hu, Shi Bo, Yan Zheng, Tian Wang, Florian Dubost, Alejandro Mottini, Junze Liu, Arvind Srinivasan, Kai Zhong, Kun Qian, Sharon Gao, Vianne Gao, Houyu Zhang, Qingjun CuiAbstract
Joint-embedding predictive architectures (JEPAs) enable world models to plan from images by predicting future embeddings. However, their visual prediction objectives do not explicitly incorporate task-relevant state information, so the physical state that determines task progress may not be reliably captured in the latent space. Supervising world models with simulator state can make planning more informative, but it requires deciding which state features matter. Features are typically selected by hand or weighted uniformly, and a uniform weighting gives every standardized state feature equal influence, so redundant coordinates can overcount the same variation, while irrelevant ones can obscure task-relevant differences. To address this limitation, we propose SWIM (State Weighting with Inverse-Dynamics Model), which learns state weights from offline trajectories by predicting recorded actions from current states and observed future displacements. The learned weights quantify each feature's contribution to action prediction and define a weighted state metric for state-supervised training, which we demonstrate by aligning latent and state distances. The inverse-dynamics model is used only during training, so the resulting world model plans from images with no additional planning-time computation. Across five simulated robotic manipulation tasks, SWIM consistently improves planning success over uniform state weighting.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36662
PDF
-
MM-Net: A Multimodal Multi-Task Network for Sleep Staging and Sleep Apnea Assessment After Ischemic Stroke
2026-10-27 03:39:40Md Wahiduzzaman Suva, Esm E Moula Chowdhury Abha, Md Imtiaj Alam Sajin, Md Iftekharul Mobin, Jia UddinAbstract
Automated polysomnography after ischemic stroke is challenging because of altered sleep-related neural activity and concurrent respiratory disturbances. Existing stroke-specific approaches mainly address sleep-stage classification, leaving joint analysis of sleep architecture and respiratory events underexplored. Moreover, adapting pretrained EEG encoders introduces a representation inconsistency when downstream models are trained on embeddings from previously seen patients but evaluated on unseen individuals. We propose MM-Net, a multimodal multi-task framework that resolves this inconsistency through cross-fitting and ridge-based embedding alignment. Sleep-adapted EEG-EOG representations and engineered neural descriptors are fused with learned cardiorespiratory features through cross-attention and shared temporal modeling for simultaneous sleep staging and respiratory-event detection. On iSLEEPS (99 patients with subacute ischemic stroke), ten-fold patient-independent evaluation achieved 76.3% staging accuracy (Cohen's $\kappa$ = 0.656) and 0.825 respiratory-event AUC, outperforming the evaluated baselines under matched protocols. The sleep-adapted encoder improved the downstream model when its embeddings were aligned, raising staging accuracy by 1.4 percentage points over the frozen encoder ($p$ = 0.020) versus 0.2 points without alignment. MM-Net also achieved 86.4% staging accuracy on Sleep-EDF, above every single-EEG architecture reimplemented on the same recordings, and 80.3% staging accuracy with 0.889 respiratory AUC on ISRUC-I, exceeding its retrained staging baselines. Without retraining, the iSLEEPS-trained model retained respiratory AUCs of 0.833 on ISRUC-I and 0.841 on UCD. These findings support representation-consistent neural adaptation and joint physiological modeling across stroke, healthy-sleep, and sleep-disorder cohorts.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36583
PDF
-
AC-JEPA: Anchored Cross-Modal Joint Embedding Predictive Architecture for Visual-to-Symbolic Translation
2026-10-27 01:49:22Chaofei Hong, Ziyang Chen, Baochen Wang, Christina Yi Jin, Qing ZhangAbstract
Cross-modal translation requires models to capture shared semantics across modalities while preserving the fine-grained structure required by the target modality. Yet in real-world scientific domains, paired data are often imperfect, while obtaining clean pairs at scale is costly. Supervised fine-tuning (SFT) directly optimizes cross-modal translation through categorical token-level supervision, but this objective is sensitive to errors in the target sequences. JEPA offers a complementary representation-space objective, but most existing formulations focus on prediction within a modality rather than translation across modalities. We introduce Anchored Cross-Modal JEPA (AC-JEPA), an SFT-compatible plug-in that predicts masked intermediate states in both cross-modal directions using paired data. The joint-embedding objective targets cross-modal structure predictable from context, while the causal SFT path retains direct token-level supervision for the target sequence. During self-training, AC-JEPA learns from continuous latent targets derived from imperfect pseudo-labeled pairs, offering intrinsic tolerance to local data errors without promoting pseudo-tokens to hard categorical supervision. Using optical chemical structure recognition as a testbed, AC-JEPA trained on clean pairs achieves 76.07% accuracy on the Simple set of the WildMol benchmark, compared with 67.40% for SFT alone. Using the same pseudo-labeled data for both approaches, AC-JEPA-based self-training further raises accuracy to 80.23%, whereas accuracy under direct SFT drops from 67.40% to 63.47%. These results support SFT-anchored joint-embedding prediction as an effective strategy for cross-modal translation under both curated and imperfect supervision.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36493
PDF
-
Expert lithological labels do not improve learning when used to predict marine sediment properties
2026-10-26 23:43:29John M. Aiken, William Gilpin, Thorsten W. BeckerAbstract
Scientific drilling has produced large archives of physical, chemical and magnetic measurements linked to descriptions of the rock recovered. These archives are mostly incomplete: instruments sample at different intervals, recovery is partial, and destructive analyses preclude later measurement of the same material. We train an self-supervised embedding model on the LILY ocean drilling database using six routinely logged properties (bulk density, magnetic susceptibility, natural gamma radiation, and red, green and blue reflectance) across 236,963 observations from 296 boreholes, with a masked variational autoencoder that has a heteroscedastic Gaussian decoder and learnable mask tokens. The embeddings separate geologist-assigned lithologies as well as a variant trained with those labels, and increasing the weight on the labels degrades reconstruction while leaving classification unchanged. The labels are recoverable from the measurements geologists use to assign them, so training on them adds nothing. Lithological categories compress continuous measurements into classes, and compressing them discards what the measurements record about the processes that produced the rock. The embeddings also predict physical properties that were absent from training, on boreholes the model has never seen. While depth should account for this since sediments compact with burial, it does not. On held-out boreholes depth alone reaches a median $R^2$ of -0.02, against 0.20 for the embedding.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36410
PDF
-
TokenMinds: Pretrained User Tokens and Embeddings for User Understanding in Large Recommender Systems
2026-10-26 22:51:11Qingyun Liu, Bo Yan, Yang Liu, Yuji Roh, Ekansh Sharma, Likang Yin, Emma Olowo, Yuxuan Li, Yikun Jiang, Diego Uribe, Saksham Aggarwal, Siqi Wu, Yuan Hao, Vikas Kedigehalli, Min-hsuan Tsai, Lukasz Heldt, Lichan Hong, Li Wei, Xinyang YiAbstract
User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints due to fixed-dimensional vectors. As an emerging alternative for discrete user representation, LLM-generated natural-language user profiles often capture language semantics rather than sequential patterns in user behaviors. Meanwhile, Semantic ID (SID) is effective for item representation, yet existing discrete user representations remain largely confined to quantizing already-pooled user vectors, clustering historical watches, or predicting coarse topic clusters solely for candidate retrieval. We propose TokenMinds, an industrial system that extends the PLUM framework from SID-based item retrieval to generative sequential user modeling. Built on an encoder-decoder architecture adapted from pretrained LLMs, TokenMinds introduces a dual-output design: the encoder outputs a dense user embedding capturing a holistic user state, while the decoder generates discrete SID-based user tokens representing multi-faceted future interests. Grounded in item semantics, these tokens preserve distinct interests that a single pooled vector would average away. Additionally, a shared SID vocabulary across long- and short-form videos unifies cross-scenario behaviors into a single model, cutting upstream training and serving compute by 50% and 31%. Furthermore, leveraging the text vocabulary inherited from the pretrained LLM, TokenMinds interleaves textual search queries directly with watch histories to capture explicit user intent. We validate TokenMinds through offline evaluations and live A/B experiments across YouTube's primary ranking surfaces, serving billions of users asynchronously: SID-based user tokens are effective on their own, yield additive gains alongside dense embeddings, and together outperform the previous-generation, non-LLM user model in production.
Abstract (translated)
URL
https://arxiv.org/abs/2606.25147
PDF
-
Enhancing Clinical Classifier Robustness with Deep Representation Learning Based OOD Detection on DNA Methylation Data
2026-10-26 22:11:07Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar, Brent A. OrrAbstract
DNA methylation (DNAM) array-based tumor classification is a powerful clinical diagnostic tool, but models trained on fixed reference cohorts can produce faulty predictions for tumor types not represented in the training distribution. We propose an end-to-end deep representation learning-based out-of-distribution (OOD) detection framework for DNAm array data. Deep neural network (DNN) classifiers were trained on public sarcoma (SARC) (GSE140686) and brain tumor (BT) (GSE90496) cohorts, and feature vectors were extracted from bottleneck layers. Five OOD methods, including 1dimension (1D)-Subspace Analysis (1D-SSA), K-Nearest Neighbors (KNN), Ridge Regression, Mahalanobis Distance (MD), and Sum of Squared Distances (SSD), were explored with 200 and 500-dimensional embeddings. Spectral discrepancy was used to discriminate in-distribution (IND) from OOD samples. Performance was measured via cross-validation, holdout samples, and an independent clinical dataset. 1D-SSA was the most effective approach. In the sarcoma-IND/brain tumor-OOD setting, the framework achieved an AUROC of 0.975 and True Negative Rate (TNR)@95TPR of 0.930, and an AUROC of 0.9569 and TNR@95TPR of 0.8660 for the brain tumor-IND/sarcoma-OOD setting. On the independent clinical test set, the method yielded a mean AUROC of 0.976, a DE of 0.032, an FPR@95TPR of 0.065, and a TNR@95TPR of 0.935. These results show deep representation-based OOD detection as a practical quality-control layer for clinical-grade methylation-based tumor classification systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36344
PDF
-
BehaveRec: When Does Long-Term Behavioral History Help Sequential Recommendation? A Study with Session, History, and Community Signals
2026-10-26 20:15:26Aysenur Inan, Reza Yousefi Maragheh, Jayesh Uddhav Kudase, Selene Xu, Kaushiki Nag, Jianpeng Xu, Sushant KumarAbstract
Sequential recommendation models typically predict a user's next action from recent session interactions, which limits personalization when short-term signals are weak or ambiguous. Rather than assuming that incorporating longer-term history and community signals is universally beneficial, we study when it actually helps. We propose BehaveRec, a three-signal framework combining a causal session transformer, a bidirectional User History Encoder over a 90-day window, and a GraphSAGE module over a user-user graph built from behavioral embedding similarity rather than item co-occurrence; a learned gate blends the three signals per user. On an industrial dataset of 137M sequences from 12.6M users, BehaveRec improves R@5 by +3.2% over SASRec, with a larger-capacity SASRec baseline (more parameters than BehaveRec) still trailing by +2.5%, ruling out capacity as the explanation. More importantly, a user-level stratification by history length reveals a clear dose-response relationship: BehaveRec's advantage is negligible below roughly 10 interactions and grows monotonically with history richness, reaching +0.017 R@5 for users with 101+ events. This pattern is corroborated across one industrial and three public datasets spanning history-rich to history-sparse regimes, where session-only models remain preferable. These headline results, and the resulting deployment threshold, are established for category-level intent prediction; a preliminary, single-run check on the full item-level vocabulary yields a directionally mixed result and is scoped as an open question rather than a claim. We use these results to derive a practical deployment rule -- roughly 20 interactions per user -- for when long-term history and behavioral-graph signals are worth their added complexity. Despite this added complexity, BehaveRec remains lightweight: it uses 5.67M parameters and trains on a single GPU in under two days.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36239
PDF
-
Frankly Speaking: The Company Election Integrity Keeps in Congressional Communication
2026-10-26 19:22:29Michael A. Robinette, Christina Barsky, Amanda D. Clark, Helen Flannery, Juniper LovatoAbstract
Election integrity is a shared commitment in American politics, but Democrats and Republicans in Congress increasingly mean different things by it. Analyzing 10,420 congressional e-newsletters sent from 2010 to 2025, we examine how the two parties invoke election terms such as ``integrity,'' ``security,'' and ``fraud.'' Using diachronic word embeddings, which track semantic change through how words are used in context, we measure how differently each party uses each term, how much each party shifts, and whether they share nearest semantic neighbors. We show that members of Congress do not need different words to tell different stories about elections. They need only place those same words in different company. Across nearly every term and year, the two parties surround election-integrity vocabulary with entirely different words. That divergence is easy to miss, because most election vocabulary is no more divergent than other words used at roughly the same frequency, and neither party's usage shifted more than the other's. Only a subset of terms grew more divergent, most notably ``certification,'' while ``rigged'' and ``stolen'' entered election discourse after 2020 and polarized there. By 2024, Democrats surround ``voter,'' ``election,'' and ``integrity'' with the language of access and administration. Republicans surround the same terms with ``citizenship verification,'' ``noncitizen voting,'' and ``border security.'' For one party, integrity means protecting eligible voters' ability to cast a ballot. For the other, it means protecting the electoral process from illegitimate ballots. Election officials, who must administer a single system under both definitions, inherit this tension.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36187
PDF
-
Retriever-Free Retrieval: Navigating Documents with Decision Models
2026-10-26 17:59:44Chao Wan, Paul J\"unger, Beixi Du, Bodong Liu, Navaneetha Krishnan, Kilian Q. WeinbergerAbstract
While language models have become dramatically more capable, retrieval still largely relies on lexical matching or similarity in fixed embedding spaces. This creates a capability asymmetry: what the retriever fails to find, even the strongest generator cannot recover. We propose DecisionRAG, which brings the capabilities of pretrained language models to retrieval using decision models that jointly evaluate candidate branches in a single forward pass, without generating any tokens, and show that judging candidates in a shared context makes their relevance estimates comparable. Like a person browsing a library, DecisionRAG navigates the corpus's inherent structure from broad topics down to individual passages, deciding at each level which branches are worth exploring. Without task-specific training or a first-stage retriever, DecisionRAG outperforms dense retrieval with an 8B reranker by 13.8 R@1 points on MultiDoc2Dial and 17.4 Hit@1 points on Natural Questions. Across four benchmarks, including a corpus of 2.68 million Wikipedia paragraphs, retrieval takes just 0.7-1.8 seconds per query.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35868
PDF
-
Do vision models know that three is three?
2026-10-26 17:58:17Ankit Sonthalia, Arnas Uselis, Seong Joon OhAbstract
Do vision models encode the transition $2{\to}3$ the same way whether it appears in handwritten digits or in hand gestures, and do they "understand" that clean${\to}$dirty is the same transformation regardless of whether it is applied to a kitchen or a carpet? The linear representation hypothesis (LRH) answers this for language models: concept changes correspond to directions in (language) embedding space. In vision, the same concept can manifest in visually unrelated "regimes" that rarely co-occur: images of digits and hands do not share much in common in pixel space. To understand whether vision models still encode the underlying abstract concepts, we study 46 vision encoders across architectures, training objectives, and scales, on 10 concept families including numerosity, age, object identity, and MIT-States attributes. Within each regime, we find statistically significant concept directions near-universally across our tested models. However, two distinct regimes do not always share the same concept direction. Several models learn multiple linear structures for the same concept transition, split across regimes. We call this phenomenon "fragmented linearity": strong local linearity coexisting with near-absent global linearity. Fragmentation is, however, not fixed: models with stronger local linearity progressively escape it (local-global linearity correlated with $\tau \in [0.38, 0.89]$ across all concepts), and where global linearity does emerge, concept directions can transfer as linear probes across regimes.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35857
PDF
-
Explainable Multimodal AI Approach to Reduce Unnecessary Breast Biopsies
2026-10-26 16:29:09Sadam Hussain, Mansoor Ali, Daly Betzabeth Avenda\~no-Avalos, Jose Gerardo Tamez-Pe\~naAbstract
Recently, there has been rise in multimodal vision-language models for computer-aided diagnosis (CAD), yet their application in breast diagnosis, particularly for predicting biopsy outcomes remains limited. This study presents a multimodal vision-language approach, incorporating Grad-CAM as an Explainable AI (XAI) technique, to predict benign tumors in patients recommended for biopsy, especially those classified as BI-RADS 4 and 5. A novel multimodal framework was devel- oped using Vision Transformer (ViT) for imaging feature extraction and DeBERTa-V3-Large for textual embeddings. The model was trained and evaluated on a comprehensive in-house dataset comprising 1,632 patients, each with four mammography views and a corresponding radiology report. The features of both modalities were extracted independently and fused by late fusion before classification. Grad-CAM was used to generate visual explanations highlighting key regions influencing model predictions. The proposed model demonstrated high sensitivity 90%, 95%, 99%, and 100% with corresponding specificities of 40%, 36%, 18%, and 11%, respectively. The best AUC achieved was 0.72 by multimodal approach on the test set, outperforming the image only (0.66) and text-only (0.68) baselines. The proposed multimodal architecture, enhanced with Grad-CAM, demonstrates a strong potential to identify benign tumors among high-risk patients, offering interpretable insights and thereby helping reduce unnecessary biopsies, patient anxiety, and healthcare costs.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35704
PDF
-
Towards a Unified Framework of Optimal Input-Side Dimensional Configuration for Deep CTR Prediction
2026-10-26 16:24:11Chaohua Yang, Fuyuan Lyu, Xing Tang, Dugang Liu, Xiuqiang He, Zhong MingAbstract
Deep click-through rate (CTR) prediction has achieved substantial success through increasingly expressive feature interaction architectures. However, predictive performance also depends on how input-side information is configured before interaction modeling. Existing studies have shown that selecting informative samples, features, or embedding units can improve prediction accuracy. Nevertheless, they primarily optimize these selection mechanisms independently along a single input-side dimension, overlooking their shared basic form and the inherent dependencies across input levels, thereby limiting the effectiveness of input-side dimensional configuration. To address this issue, we propose OptIDC, a unified framework for Optimal Input-side Dimensional Configuration in deep CTR prediction. OptIDC jointly learns sample, feature, and embedding-unit level configurations within a unified framework by integrating their corresponding selection mechanisms. To explicitly coordinate selection decisions across different levels, OptIDC further introduces a selection-weighted Optimal Transport mechanism that aligns coarse- and fine-grained selections via transport over finite measures, thereby alleviating cross-level selection conflicts while preserving the semantics of each input level. Moreover, OptIDC is model-agnostic and can be seamlessly integrated into existing CTR models. Extensive experiments on four real-world benchmark datasets demonstrate that OptIDC consistently achieves higher AUC than existing input-side selection methods, validating the effectiveness of unified input-side dimensional configuration.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35695
PDF
-
Offline Language-Based Support System for Tactical Decision-Making in Air Combat Operations
Abstract
An offline language-based support tool is presented to assist pilot training and tactical decision-making in air combat operations. The system, named MATE (Mission Assistant for Training and Evaluation), applies retrieval-augmented generation (RAG) to answer natural language questions using content extracted from doctrinal and tactical manuals. Built entirely with open-source components, it performs text preprocessing, embedding generation, semantic search, and language generation locally, ensuring full offline functionality. The tool was evaluated by three Brazilian Air Force fighter pilots, who rated the answers produced with three open-weight language models (Llama 3.1 8B, Qwen 2.5 14B, and Mistral NeMo 12B) to five tactical questions derived from a publicly available air combat manual. Average ratings ranged from 4.00 to 4.40 on a five-point scale, with Mistral NeMo 12B obtaining the highest score, and the pilots rated the response time of the tool as fully adequate compared to manual search. The relevance of the retrieved content was identified as the main point for improvement. Potential applications are discussed in onboard mission systems, flight simulators, and training environments.
Abstract (translated)
URL
https://arxiv.org/abs/2610.35635
PDF
