We present BDNet, a hierarchical image-classification backbone built around fast image features and slow statistical references. Its baseline deformation operator (BDO) transforms the deviation of a feature from a stage-specific reference through a low-rank projection and a learned channel scale. Rather than computing pairwise token similarity, the branch operates directly on baseline-relative residuals with complexity linear in the token count. Each of four reference buffers accumulates detached stage statistics during training and remains frozen at inference. A four-stage pyramid with depths $(2,2,6,2)$ and widths $(96,192,384,768)$ yields a 20.70M-parameter classifier at $224\times224$ resolution. We organize an ImageNet-1K study around clean classification, eight controlled ablations, and Gaussian-noise, contrast, and brightness perturbations. The central hypothesis is that a slow reference can improve the robustness of a compact representation while retaining a simple tensor implementation. We distinguish this training-time statistical mechanism from input-dependent attention and make its linear inference behavior explicit.
https://arxiv.org/abs/2610.41485
Integrated sensing and communication (ISAC) is a core design principle for sixth-generation (6G) wireless systems, yet fixed antenna geometry limits its performance. Pinching antenna systems (PASS) guide electromagnetic waves along dielectric waveguides and radiate them through position-adaptive antennas, allowing communication links and sensing observations to benefit from spatial reconfiguration. This article reviews PASS-enabled ISAC through single-waveguide, multi-waveguide, and segmented-waveguide architectures, comparing their feed structures, spatial degrees of freedom, operating protocols, and uplink/downlink support. We organize solution pathways around physics-consistent modeling, joint spatial-signal optimization, dynamic channel acquisition, and stable real-time control. A segmented waveguide-enabled pinching-antenna array (SWAN) case study demonstrates joint segment selection, antenna po?sitioning, and transmit beamforming using segment-hysteresis reinforcement learning. The results illustrate how waveguide loss and per-segment aperture gain create communication-sensing tradeoffs. We conclude with research directions in joint transmit?receive operation, measurement-calibrated digital twins, and trustworthy control.
https://arxiv.org/abs/2610.41380
Choosing among the hundreds of thousands of available large language models (LLMs) requires a thorough understanding of each candidate model's properties. In practice, each property is measured by its own benchmark suite, so profiling a model on many properties means paying for many separate evaluations. To address this, model embeddings compress each model into a fixed-length vector from which many properties can be predicted. Existing methods, such as EmbedLLM, build these vectors from correctness patterns and question features, and often need large probe batteries to do so. However, many behaviors that are important when choosing a model, such as its verbosity, safety and style, show up more in how it answers than in whether it is correct. We introduce BULLPEN (Behavioral Understanding of Large Language models via Profile ENcodings), a framework that extends EmbedLLM in three ways. First, BULLPEN organizes the downstream tasks that prior work uses and adds 20 task benchmarks we built on behavior, style and provenance. Second, it is the first framework to read a model's own answer text jointly with its correctness and the question text. Third, it encodes models from a few hundred questions instead of the full 24,118-question pool. Across 260 open-weight models, our answer-text encoder scores 0.48 +/- 0.10 on the new tasks against 0.35 +/- 0.10 for the best prior encoder. Our encoders that read answer text keep at least 91% of their full-pool skill from only 400 questions (1.3% of the inference compute of the full question pool), while a correctness-only baseline keeps 83% with the same 400 questions. Because these embeddings need only model outputs, they support behavioral auditing and low-cost profiling, and could extend to API-only models. Code and data: this https URL
https://arxiv.org/abs/2610.41375
Pre-trained models offer complementary strengths in CT organ segmentation, but their relative accuracy varies across organs and spatial regions. Multi-teacher knowledge distillation can combine these strengths in a single student, yet global or instance-level teacher weights overlook variation within a 3D volume. We propose Task-Performance Routing (TPR), which uses region-wise segmentation errors to determine teacher weights during training without learned routing parameters. In hard regions, TPR favors teachers with lower prediction errors; in easy regions, it uses uniform weights to combine their knowledge. A hierarchical spatial partition provides fine-grained routing in shallow encoder stages and coarse-grained routing in deep stages. Experiments on BTCV, MSD-Liver, and MSD-Pancreas with two teacher pairs and two backbone architectures show higher Dice scores than the individual teachers, adaptive ensembles, and evaluated multi-teacher distillation baselines. On MSD-Pancreas, TPR achieves Dice scores of 65.40% with SwinUNETR and 68.25% with U-Net, compared with 64.38% and 67.45% for the corresponding adaptive ensembles. Inference uses the student alone, with no routing or teacher overhead. Code is available at this https URL.
https://arxiv.org/abs/2610.41362
Generating small molecules to target protein-protein interactions (PPIs) remains one of the most challenging yet high-reward frontiers in drug discovery. Unlike traditional small-molecule drugs that bind to deep, well-defined pockets, PPI interfaces often comprise broad, shallow binding surfaces. A natural strategy is to leverage known peptide-target interactions, as peptide ligands provide rich interface-level constraints. However, a major algorithmic challenge is that rigid atom-level conditioning on peptide structures can over-constrain the generative space and exclude valid small-molecule solutions. To address this challenge, we present PIFT (Peptide InterFace Transfer), a novel framework that transfers peptide-target interaction patterns to small molecules through joint sampling-time guidance of masked discrete diffusion and continuous flow matching. PIFT first maps peptide-target and small-molecule-target interfaces into a shared, target-conditioned interaction space, capturing transferable interface information across molecular modalities. The resulting peptide-derived reference then jointly steers building-block logits and 3D coordinates toward peptide-compatible molecules while preserving a strong adapted molecular prior. Extensive experiments across diverse PPI targets show that the learned representation captures cross-modal interaction compatibility, while peptide guidance improves interface recovery and achieves strong docking performance and favorable molecular properties.
https://arxiv.org/abs/2610.41322
Human cognition flexibly draws on a shared perceptual foundation to understand environments, attend to referenced entities, reason about spatial relationships, and act. Endowing aerial robots with an analogous functional organization remains challenging, as existing systems are often specialized for individual capabilities, dependent on offboard computation, or unable to sustain closed-loop operation on resource-constrained platforms. We present OpenFlyV2, a unified onboard vision-language-action architecture that uses a shared vision-language representation to support semantic understanding, language-grounded perception, spatial reasoning, and continuous aerial control within a single model. A compact action expert converts the shared multimodal context into short-horizon flight waypoints, while motion-aware temporal memory and action priors reduce the computational cost of closed-loop execution. We construct \dataset{}, a simulation-based dataset comprising approximately 70,000 navigation trajectories and 60,000 vision-language instruction--response pairs. OpenFlyV2 generates action chunks, each comprising 12 waypoints, entirely onboard at 10 Hz using an NVIDIA Jetson Orin NX. It transfers zero-shot from simulation to physical quadrotor flight, achieving a 48\% navigation success rate across four real-world environments without real-world aerial training data. Extensive results demonstrate that broad vision-language competence and continuous closed-loop flight can coexist within a single model on a resource-constrained aerial platform. Code will be made publicly available at this https URL.
https://arxiv.org/abs/2610.39287
Scientific data selection is typically driven by relevance or utility scores, providing limited insight into why a document is retained. We introduce SciGraphSelect, a reference-grounded framework for auditable scientific data selection. SciGraphSelect organizes domain-specific knowledge, reusable reasoning operations, and reference-attested relations into a typed knowledge--reasoning graph, then scores candidate documents using concept coverage, relation and path co-support, and directional alignment. To avoid over-interpreting document embeddings, rich relational structure is preserved on the reference side while candidate-side evidence is treated conservatively without assuming relation entailment. By exposing the reference-grounded evidence behind each selection, SciGraphSelect brings traceability to the upstream construction of scientific training corpora and complements downstream scientific verification.
https://arxiv.org/abs/2610.41280
Existing sketch generation methods often rely on image guidance and are largely limited to individual objects or simplified scenes, leaving text-guided complex scene sketching underexplored. We present SketchDirector, an agentic framework that mimics the human sketching workflow for automatic multi-concept scene sketching. Given a scene-level text prompt, SketchDirector first employs a large language model~(LLM) to decompose the scene into multiple draft assets, where each is represented by a set of Bézier curves. Then, an agentic reasoning loop iteratively plans and executes their spatial arrangement, guided by self-evolving memory. Finally, a detail refinement module leverages diffusion priors to enhance sketch quality while preserving geometric structure. To support future research and applications in multi-concept scene sketch generation, we further introduce the \textit{MCSketch8K} dataset, comprising editable vector assets, compositional layouts, and object-level manipulation annotations. Extensive experiments show that SketchDirector outperforms state-of-the-art baselines in semantic and compositional quality while effectively preserving overall contour organization during refinement. The project page is: \href{this https URL}{this https URL}.
https://arxiv.org/abs/2610.41260
Although large language models have shown strong capabilities in domain-specific code generation, their performance in robotics software development, especially for the Robot Operating System (ROS), remains largely unexplored. ROS code generation presents distinctive challenges, including complex inter-node coordination, middleware configuration, and lifecycle semantics that go far beyond standard coding benchmarks, and many important correctness properties become observable only once migrated nodes are launched and communicate. We present ROSTrans, a benchmark for evaluating LLMs on ROS1-to-ROS2 code migration, a representative and practically important setting for ROS code generation. ROSTrans comprises 108 scaffolded completion tasks drawn from a diverse set of 70+ open-source ROS1 repositories and organized into a hierarchical taxonomy assessing interface-level, behavioral-level and system-level correctness. For every task we establish an executable reference: a verified ROS2 implementation, a runtime test suite that launches the nodes and exercises their topics, services, actions and parameters, and a container ensuring reproducibility. Candidates are scored by injecting only their target files into an otherwise fixed copy of the reference package, so a candidate can neither supply nor weaken the tests it is judged by. Evaluating six frontier LLMs over five stochastic generations per task, we find pass@1 below 10.9%, and that 56.5% of all samples build successfully and then fail at runtime,and 32.0% fail runtime assertions on the migrated interfaces, a class of error no compile-only oracle can detect. Execution-guided repair further improves task success, reaching 49.1% and 47.2% for Claude Opus 4.6 and GPT-5.5 after three rounds, respectively.
https://arxiv.org/abs/2610.41168
Synthesizing realistic tumors on medical images helps address data scarcity for clinical AI. Existing diffusion-based methods, however, lack fine-grained attribute-level controllability, closed-loop quality verification, and awareness of which morphological patterns are underrepresented in the target distribution. We present MATS, a multi-agent framework for text-controllable, cross-organ tumor synthesis. Given a target disease, MATS first profiles its morphological distribution over a fine-grained attribute space covering tumor geometry and appearance, and constructs a generation plan that amplifies underrepresented subtypes while keeping common ones dominant. It then localizes the target organ, proposes anatomically valid placement, and executes two-stage diffusion to produce the tumor mask and render texture, each conditioned on the corresponding attributes. A closed-loop reflective mechanism verifies attribute alignment at three checkpoints throughout synthesis and provides targeted feedback to guide re-generation when misalignment is detected. Trained exclusively on a single-source pancreatic neuroendocrine tumor dataset, MATS consistently improves downstream segmentation both in-domain and across LiTS, KiTS, and MSD-Pancreas benchmarks, whereas most prior generative augmentation methods fall below real-only training.
https://arxiv.org/abs/2610.41159
Computer vision models learn hand action only from its visual consequences, without access to the underlying embodied motor signals. We address this absence with MotorSense, the first large-scale paired egocentric video and surface electromyography (EMG) dataset. MotorSense pairs bimanual EMG bands with egocentric video and yields synchronized video, bimanual EMG and IMU, and audio across 100 hours of unscripted manipulation. EMG offers a powerful scalable alternative to manual annotation: it captures finger movement, hand configuration, and the forces exerted between hand and environment as a dense signal free of occlusion and labeler bias, whereas manual annotation is costly, subjective, and unreliable under occlusion. We use MotorSense to learn sensorimotor alignment, producing an organization of action that is shared across the visual and motoric spaces, through cross-modal pre-training between video and EMG. The resultant vision models are then transferred to downstream tasks that benefit from sensorimotor alignment: in this case, action recognition, 3D hand reconstruction, and 3D contact reconstruction. We further demonstrate a generative application in which EMG motor signals are used to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
https://arxiv.org/abs/2610.41127
Payroll-fraud screening requires finding hidden employee--payee links while distinguishing suspicious relationships from legitimate ones. We formulate this problem as inductive link prediction and entity ranking on synthetic human-resources and enterprise resource planning (HR/ERP) graphs, with unseen organizations and a matched benign twin for every planted case. An original study on 24 held-out organizations and a prospectively frozen extension compare analyst rules, explicit path features and graph neural networks (GNNs). A tuned gradient-boosted model on chained-join features achieved the highest overall link average precision (AP; 0.823), above the GraIL-style GNN (0.663); its 4-hop AP was 0.646 versus 0.272. Thus, the observed multi-hop gain is not specific to GNNs. On a new synthetic cohort with 2.0% positive entities, chained-join boosting again led (AP 0.798); the relational entity GNN also exceeded record-aware rules (0.707 versus 0.504). At a 2% review budget, their precision was 0.695 versus 0.602. Under 40% failed identifier joins, the entity GNN ranked above chained-join boosting (AP 0.712 versus 0.683, descriptively). Structure-only auditing exposed a shortcut in the initial generator; matched twins reduced the audited twin-pool AUROC to 0.493--0.514. These results separate multi-hop candidate discovery, record-based discrimination and review prioritization within an explicit synthetic evaluation design. Code and data are available from the authors on request.
https://arxiv.org/abs/2610.41085
An LLM agent that helps a patient get care must do two things. It must reach the correct outcome, and it must follow the necessary procedure. For example, the agent must get the patient's permission before it shares the patient's records. We introduce BABA-Bench, a benchmark of 47 interactive worlds. We built each world from a de-identified, real patient advocacy case that expert advocates reviewed. In each world, the agent must find hidden information and coordinate insurers, clinics, suppliers, pharmacies, and community organizations. The engine checks each action at the time the agent does it. It checks if the agent has permission, if the agent has evidence for the action, and if the action is prohibited. We evaluated 14 frontier models with three runs on each world, for a total of 1,974 runs. Agents often reached the correct outcome by an invalid route. Of the 921 runs that reached all required outcomes, 254 (28%) did not follow the necessary procedure. Claude Opus 5 reached all required outcomes in 81.6% of its runs, but only 52.5% of its runs passed all checks. When we gave two models a verified route, their pass rates increased from 29.8% to 91.5% and from 44.0% to 97.2%. For these models, the main problem is to find a route, not to execute it.
https://arxiv.org/abs/2610.41076
Background: Limited tumor annotations and incomplete labels across MRI datasets hinder unified segmentation of pancreatic tumors and organs at risk (OARs) for MRI-guided radiotherapy. Purpose: We propose Pancreas-MedNeXt, a unified model that segments the whole pancreas, its subregions, tumors, and surrounding OARs from one MRI volume. Methods: The model uses a shared MedNeXt encoder-decoder with supervised whole-pancreas and subregion pretraining, followed by multitask fine-tuning. Three output heads predict the pancreatic subregions, tumor, and OARs (stomach, duodenum, kidneys). An annotation-aware loss allows training on partially labeled data without treating unannotated structures as background. Pancreas and tumor were evaluated by three-fold cross-validation on 142 PANTHER patients (92 diagnostic, 50 MR-Linac), subregions and OARs on Cyst-X and AMOS test sets, and pancreas and OARs on 33 external T1-weighted TotalSegmentator scans. Comparisons with nnU-Net, MedNeXt, VISTA3D, and Swin UNETR used the Dice similarity coefficient (DSC) with paired bootstrap 95% CIs. Results: Pancreas-MedNeXt achieved the highest mean pancreas and tumor DSC on diagnostic and MR-Linac MRI. Tumor DSC was 58.41% and 42.55%, exceeding task-specific MedNeXt by 4.94 (95% CI: 0.28-9.45) and 5.89 (95% CI: 2.37-9.72) percentage points, respectively. Whole-pancreas DSC was 85.73% and 70.66%. Pretraining improved head, body, and tail DSC by 2.01, 3.00, and 3.78 percentage points over training from scratch. It also achieved the highest DSC for the pancreas, duodenum, and right kidney on AMOS, and for all five organs on external MRI, exceeding the next-best method by 4.92-8.85 percentage this http URL: A single Pancreas-MedNeXt model segments tumors, pancreatic subregions, and OARs on diagnostic and MR-Linac MRI, which could streamline contouring for pancreatic cancer radiotherapy.
https://arxiv.org/abs/2610.41063
We present FieldGuideRAG, a training-free GraphRAG method in which a vision-language model, or VLM, recognizes fine-grained species by comparing the query with real photographs stored on the nodes of a knowledge graph. Multimodal GraphRAG systems describe each entity in text, and text conveys little of the visual detail that separates look-alike species. Our graph stores one photograph on every species node and links each species to its relatives, its geographic range and its ecological facts. A frozen VLM verifies the query against the photograph of each candidate node. FieldGuideRAG fuses the verification scores with the range edge and answers questions about the organism from the fact edges of the verified species. On CUB-200, a Wikidata graph and four iNaturalist domains, the node photograph improves verification over the species name on every graph, while text descriptions add little. Verification of the candidate pool exceeds a SigLIP retriever by up to 16 points, the range edge adds 7 to 19 points on iNaturalist, and answering from fact edges is correct on up to 89.5% of 28,820 ecological questions. The verification scores also detect queries whose species is missing from the graph. Graphs, prompts and code will be released.
https://arxiv.org/abs/2610.40971
Digital agents can now gather and organize information, reason over it, and use tools to complete complex tasks. Forecasting puts all of these abilities to the test: it requires integrating incomplete evidence, inferring causal drivers, and committing to calibrated probabilistic judgments. Existing benchmarks are poorly suited to measuring and improving this ability. Live benchmarks provide feedback only after events resolve, so every evaluation cycle waits on the calendar; fixed-corpus evaluations return results immediately but confine research to pre-collected documents. We introduce FABench, a scalable backtesting environment for Forecasting Agents. An automated pipeline discovers events, generates questions, and resolves outcomes for any past forecast date, so the benchmark can be renewed to stay ahead of model training cutoffs; its first release poses 287 questions across nine domains. Agents research each question freely in an archive environment that combines an offline archive with live web search screened to prevent temporal leakage. Evaluating agents built on eight recent models, we find that retrieval improves the Brier score of all eight in every retrieval setting and lifts the leading agents to the market consensus on the 54 questions linked to Polymarket, with the best three scoring slightly above it. Research traces reveal recurring failures in how agents weigh and apply evidence, leaving ample room for improvement. We release our code, data, and archive environment as a foundation for community research on forecasting agents.
https://arxiv.org/abs/2610.40940
Training acceleration methods for diffusion transformers, such as REPA and dispersive regularization, are commonly explained by additional supervision, spatial-structure priors, or improved feature geometry. We revisit this view and uncover a striking internal change: the AdaLN-Zero residual gate $\alpha$, which directly controls how conditioned updates enter the residual stream, is substantially reorganized by these methods. This observation motivates our hypothesis that acceleration arises, at least in part, from reshaping the residual gating pathway rather than solely from the feature structures explicitly imposed by auxiliary objectives. Supporting this view, accelerated models are markedly more sensitive to perturbations of $\alpha$, and their gate geometry reflects semantic relationships among classes. We further introduce the normalized participation ratio (nPR) to characterize the channel-wise organization of the gates and find that, across REPA teachers, projector architectures, and radial-objective targets, broader gate participation accompanies better generation quality. Guided by this insight, we propose a simple teacher-free radial objective that promotes broader gate participation through feature-norm regularization, without pairwise feature comparisons. On ImageNet $256\times256$ with SiT-B/2, our method improves FID over dispersive loss while increasing mean gate participation over timesteps and classes, further supporting the link between gate organization and training acceleration. Our results identify residual-gate reorganization as a measurable axis of diffusion training acceleration and suggest a simple direction for further acceleration.
https://arxiv.org/abs/2610.40914
The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In unmanned aerial vehicle (UAV) scenes, small targets, subtle attributes, and changing viewpoints further complicate perception and understanding. Therefore, we introduce Drone-PUR, a dataset and benchmark organized around visual clue discovery, interpretation, and integration, corresponding to the three capability dimensions of perception, understanding, and reasoning. Reasoning samples are designed to require models to combine multiple visual clues to derive visually grounded conclusions. Its 11 tasks provide 175k training and 20k test samples spanning single images, image sequences, cross-modal images, and multiple viewpoints. All test samples undergo human review. Evaluating 22 general-purpose VLMs reveals persistent limitations in spatial judgment and cross-modal and cross-view reasoning. Across models, stronger perception is associated with better reasoning, while single-task fine-tuning further reveals selective bidirectional transfer between these capabilities. To examine domain adaptation, we develop UAV-PUR from Qwen3-VL through staged fine-tuning with auxiliary supervision. Its 4B and 8B variants improve overall multiple-choice accuracy by 18.33 and 17.52 percentage points over their pretrained counterparts, respectively. The dataset and project resources are available at this https URL.
https://arxiv.org/abs/2610.40801
The EGI Federation has provided federated e-infrastructure services to European and global science for over 15 years. We review EGI's early experiences with AI in the interTwin and iMagine Horizon Europe projects, which built digital twins in physics and environmental sciences and an image-analysis platform for aquatic research. We then examine how the AI landscape has changed since 2023 and argue that the focus of AI in science has shifted from model training to adapting and applying AI to specific domains, projects and questions. Building on these lessons, we present the AI strategy emerging from the EGI Federation Strategy 2026-2030, organised around three enablers: (1) an AI-ready infrastructure connecting compute, data and application resources across the continuum; (2) human skills to know what is possible with AI and how to implement it; and (3) trust, to run AI with confidence even in high-risk environments. We describe the projects implementing each enabler, including federated LLM inference, AI-ready data platforms and AI competence centres, and discuss a division of labour with EuroHPC's AI Factories, RAISE, research infrastructures and EOSC, in which EGI specialises in the customisation and long-term operation of AI for research.
https://arxiv.org/abs/2610.40494
Large language models support personalized tutoring, content generation, and adaptive learning paths. However, capability development requires these resources and interactions to form a coherent learning process that evolves with the learner. A central challenge is to align goals, activities, and assessment while using learning evidence to decide what should follow. We introduce Human-Participatory Multi-Agent Organization and instantiate it in Agentic University (AU). In AU, learners participate as organization members and work with specialized agents to maintain a revisable Capability Program. The program connects personal goals, learning activities across modalities, and layered assessment, while learner feedback and performance guide subsequent support. Our evaluation shows advantages in program organization, assessment design, and revision quality. Users achieved larger mean assessment gains (12.19 versus 5.61 points on a 50-point scale) and reported stronger cognitive support. This work contributes an organizational approach to adaptive learning that makes learner participation a continuing basis for multi-agent coordination. The Agentic University project is available at \href{this https URL}.
https://arxiv.org/abs/2610.40492