As the development of Large Language Models (LLMs) shifts from parameter scaling to inference-time collaboration, the Mixture-of-Agents (MoA) framework has emerged as a general paradigm to harness collective intelligence by layering diverse models. While recent MoA variants have introduced dynamic routing and residual connections to improve efficiency, these methods often fail to facilitate deep semantic interaction between agents, limiting the system's ability to actively correct hallucinations and refine logic. In this paper, we introduce Attention-MoA, a novel MoA-based framework that redefines collaboration through Inter-agent Semantic Attention. Complemented by an Inter-layer Residual Module with Adaptive Early Stopping Mechanism, our architecture mitigates information degradation in deep layers while improving computational efficiency. Extensive evaluations across AlpacaEval 2.0, MT-Bench, and FLASK demonstrate that Attention-MoA significantly outperforms state-of-the-art baselines, achieving a 91.15% Length-Controlled Win Rate on AlpacaEval 2.0 and dominating in 10 out of 12 capabilities on FLASK. Notably, Attention-MoA enables an ensemble of small open-source models to outperform massive proprietary models like Claude-4.5-Sonnet and GPT-4.1, achieving an MT-Bench score of 8.83 and an AlpacaEval 2.0 LC Win Rate of 77.36%.

Train delays result from complex interactions between operational, technical, and environmental factors. While weather impacts railway reliability, particularly in Nordic regions, existing datasets rarely integrate meteorological information with operational train data. This study presents the first publicly available dataset combining Finnish railway operations with synchronized meteorological observations from 2018-2024. The dataset integrates operational metrics from Finland Digitraffic Railway Traffic Service with weather measurements from 209 environmental monitoring stations, using spatial-temporal alignment via Haversine distance. It encompasses 28 engineered features across operational variables and meteorological measurements, covering approximately 38.5 million observations from Finland's 5,915-kilometer rail network. Preprocessing includes strategic missing data handling through spatial fallback algorithms, cyclical encoding of temporal features, and robust scaling of weather data to address sensor outliers. Analysis reveals distinct seasonal patterns, with winter months exhibiting delay rates exceeding 25\% and geographic clustering of high-delay corridors in central and northern Finland. Furthermore, the work demonstrates applications of the data set in analysing the reliability of railway traffic in Finland. A baseline experiment using XGBoost regression achieved a Mean Absolute Error of 2.73 minutes for predicting station-specific delays, demonstrating the dataset's utility for machine learning applications. The dataset enables diverse applications, including train delay prediction, weather impact assessment, and infrastructure vulnerability mapping, providing researchers with a flexible resource for machine learning applications in railway operations research.

Composed Video Retrieval (CoVR) facilitates video retrieval by combining visual and textual queries. However, existing CoVR frameworks typically fuse multimodal inputs in a single stage, achieving only marginal gains over initial baseline. To address this, we propose a novel CoVR framework that leverages the representational power of Vision Language Models (VLMs). Our framework incorporates a novel cross-attention module X-Aligner, composed of cross-attention layers that progressively fuse visual and textual inputs and align their multimodal representation with that of the target video. To further enhance the representation of the multimodal query, we incorporate the caption of the visual query as an additional input. The framework is trained in two stages to preserve the pretrained VLM representation. In the first stage, only the newly introduced module is trained, while in the second stage, the textual query encoder is also fine-tuned. We implement our framework on top of BLIP-family architecture, namely BLIP and BLIP-2, and train it on the Webvid-CoVR data set. In addition to in-domain evaluation on Webvid-CoVR-Test, we perform zero-shot evaluations on the Composed Image Retrieval (CIR) data sets CIRCO and Fashion-IQ. Our framework achieves state-of-the-art performance on CoVR obtaining a Recall@1 of 63.93% on Webvid-CoVR-Test, and demonstrates strong zero-shot generalization on CIR tasks.

Remote sensing change detection (RSCD) aims to identify the spatio-temporal changes of land cover, providing critical support for multi-disciplinary applications (e.g., environmental monitoring, disaster assessment, and climate change studies). Existing methods focus either on extracting features from localized patches, or pursue processing entire images holistically, which leads to the cross temporal feature matching deviation and exhibiting sensitivity to radiometric and geometric noise. Following the above issues, we propose a dual-module collaboration guided hierarchical adaptive aggregation framework, namely HA2F, which consists of dynamic hierarchical feature calibration module (DHFCM) and noise-adaptive feature refinement module (NAFRM). The former dynamically fuses adjacent-level features through perceptual feature selection, suppressing irrelevant discrepancies to address multi-temporal feature alignment deviations. The NAFRM utilizes the dual feature selection mechanism to highlight the change sensitive regions and generate spatial masks, suppressing the interference of irrelevant regions or shadows. Extensive experiments verify the effectiveness of the proposed HA2F, which achieves state-of-the-art performance on LEVIR-CD, WHU-CD, and SYSU-CD datasets, surpassing existing comparative methods in terms of both precision metrics and computational efficiency. In addition, ablation experiments show that DHFCM and NAFRM are effective. \href{https://huggingface.co/InPeerReview/RemoteSensingChangeDetection-RSCD.HA2F}{HA2F Official Code is Available Here!}

This work proposes neural training as a \emph{process tensor}: a multi-time map that takes a sequence of controllable instruments (batch choices, augmentations, optimizer micro-steps) and returns an observable of the trained model. Building on this operational lens, we introduce a simple, model-agnostic witness of training memory based on \emph{back-flow of distinguishability}. In a controlled two-step protocol, we compare outcome distributions after one intervention versus two; the increase $Δ_{\mathrm{BF}} = D_2 - D_1>0$ (with $D\in\{\mathrm{TV}, \mathrm{JS}, \mathrm{H}\}$ measured on softmax predictions over a fixed probe set) certifies non-Markovianity. We observe consistent positive back-flow with tight bootstrap confidence intervals, amplification under higher momentum, larger batch overlap, and more micro-steps, and collapse under a \emph{causal break} (resetting optimizer state), directly attributing the effect to optimizer/data-state memory. The witness is robust across TV/JS/Hellinger, inexpensive to compute, and requires no architectural changes. We position this as a \emph{measurement} contribution: a principled diagnostic and empirical evidence that practical SGD deviates from the Markov idealization. An exploratory case study illustrates how the micro-level signal can inform curriculum orderings. "Data order matters" turns into a testable operator with confidence bounds, our framework offers a common stage to compare optimizers, curricula, and schedules through their induced training memory.

Fact-checking aims to verify the truthfulness of a claim based on the retrieved evidence. Existing methods typically follow a decomposition paradigm, in which a claim is broken down into sub-claims that are individually verified. However, the decomposition paradigm may introduce noise to the verification process due to irrelevant entities or evidence, ultimately degrading verification accuracy. To address this problem, we propose a Retrieve-Refine-Calibrate (RRC) framework based on large language models (LLMs). Specifically, the framework first identifies the entities mentioned in the claim and retrieves evidence relevant to them. Then, it refines the retrieved evidence based on the claim to reduce irrelevant information. Finally, it calibrates the verification process by re-evaluating low-confidence predictions. Experiments on two popular fact-checking datasets (HOVER and FEVEROUS-S) demonstrate that our framework achieves superior performance compared with competitive baselines.

Nonlinear dimensionality reduction techniques, particularly UMAP, are widely used for visualizing high-dimensional data. However, UMAP's local Euclidean distance assumption often fails to capture intrinsic manifold geometry, leading to topological tearing and structural collapse. We identify UMAP's sensitivity to the k-nearest neighbor graph as a key cause. To address this, we introduce Ollivier-Ricci curvature as a geometric prior, reinforcing edges at geometric bottlenecks and reducing redundant links. Since curvature estimation is noise-sensitive, we also incorporate a topological prior using Jaccard similarity to ensure neighborhood consistency. The resulting method, JORC-UMAP, better distinguishes true manifold structure from spurious connections. Experiments on synthetic and real-world datasets show that JORC-UMAP reduces tearing and collapse more effectively than standard UMAP and other DR methods, as measured by SVM accuracy and triplet preservation scores, while maintaining computational efficiency. This work offers a geometry-aware enhancement to UMAP for more faithful data visualization.

The combination of multimodal Vision-Language Models (VLMs) and Large Language Models (LLMs) opens up new possibilities for medical classification. This work offers a rigorous, unified benchmark by using four publicly available datasets covering text and image modalities (binary and multiclass complexity) that contrasts traditional Machine Learning (ML) with contemporary transformer-based techniques. We evaluated three model classes for each task: Classical ML (LR, LightGBM, ResNet-50), Prompt-Based LLMs/VLMs (Gemini 2.5), and Fine-Tuned PEFT Models (LoRA-adapted Gemma3 variants). All experiments used consistent data splits and aligned metrics. According to our results, traditional machine learning (ML) models set a high standard by consistently achieving the best overall performance across most medical categorization tasks. This was especially true for structured text-based datasets, where the classical models performed exceptionally well. In stark contrast, the LoRA-tuned Gemma variants consistently showed the worst performance across all text and image experiments, failing to generalize from the minimal fine-tuning provided. However, the zero-shot LLM/VLM pipelines (Gemini 2.5) had mixed results; they performed poorly on text-based tasks, but demonstrated competitive performance on the multiclass image task, matching the classical ResNet-50 baseline. These results demonstrate that in many medical categorization scenarios, established machine learning models continue to be the most reliable option. The experiment suggests that foundation models are not universally superior and that the effectiveness of Parameter-Efficient Fine-Tuning (PEFT) is highly dependent on the adaptation strategy, as minimal fine-tuning proved detrimental in this study.

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio-text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

Hierarchical open-set classification handles previously unseen classes by assigning them to the most appropriate high-level category in a class taxonomy. We extend this paradigm to the semi-supervised setting, enabling the use of large-scale, uncurated datasets containing a mixture of known and unknown classes to improve the hierarchical open-set performance. To this end, we propose a teacher-student framework based on pseudo-labeling. Two key components are introduced: 1) subtree pseudo-labels, which provide reliable supervision in the presence of unknown data, and 2) age-gating, a mechanism that mitigates overconfidence in pseudo-labels. Experiments show that our framework outperforms self-supervised pretraining followed by supervised adaptation, and even matches the fully supervised counterpart when using only 20 labeled samples per class on the iNaturalist19 benchmark. Our code is available at https://github.com/walline/semihoc.

Large language models (LLMs) and high-capacity encoders have advanced zero and few-shot classification, but their inference cost and latency limit practical deployment. We propose training lightweight text classifiers using dynamically generated supervision from an LLM. Our method employs an iterative, agentic loop in which the LLM curates training data, analyzes model successes and failures, and synthesizes targeted examples to address observed errors. This closed-loop generation and evaluation process progressively improves data quality and adapts it to the downstream classifier and task. Across four widely used benchmarks, our approach consistently outperforms standard zero and few-shot baselines. These results indicate that LLMs can serve effectively as data curators, enabling accurate and efficient classification without the operational cost of large-model deployment.

Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual recognition and semantic understanding. Nevertheless, their ability to perform precise compositional spatial reasoning remains largely unexplored. Existing benchmarks often involve relatively simple tasks and rely on semantic approximations or coarse relative positioning, while their evaluation metrics are typically limited and lack rigorous mathematical formulations. To bridge this gap, we introduce TangramPuzzle, a geometry-grounded benchmark designed to evaluate compositional spatial reasoning through the lens of the classic Tangram game. We propose the Tangram Construction Expression (TCE), a symbolic geometric framework that grounds tangram assemblies in exact, machine-verifiable coordinate specifications, to mitigate the ambiguity of visual approximation. We design two complementary tasks: Outline Prediction, which demands inferring global shapes from local components, and End-to-End Code Generation, which requires solving inverse geometric assembly problems. We conduct extensive evaluation experiments on advanced open-source and proprietary models, revealing an interesting insight: MLLMs tend to prioritize matching the target silhouette while neglecting geometric constraints, leading to distortions or deformations of the pieces.

Federated graph learning (FGL) enables collaborative training on graph data across multiple clients. With the rise of large language models (LLMs), textual attributes in FGL graphs are gaining attention. Text-attributed graph federated learning (TAG-FGL) improves FGL by explicitly leveraging LLMs to process and integrate these textual features. However, current TAG-FGL methods face three main challenges: \textbf{(1) Overhead.} LLMs for processing long texts incur high token and computation costs. To make TAG-FGL practical, we introduce graph condensation (GC) to reduce computation load, but this choice also brings new issues. \textbf{(2) Suboptimal.} To reduce LLM overhead, we introduce GC into TAG-FGL by compressing multi-hop texts/neighborhoods into a condensed core with fixed LLM surrogates. However, this one-shot condensation is often not client-adaptive, leading to suboptimal performance. \textbf{(3) Interpretability.} LLM-based condensation further introduces a black-box bottleneck: summaries lack faithful attribution and clear grounding to specific source spans, making local inspection and auditing difficult. To address the above issues, we propose \textbf{DANCE}, a new TAG-FGL paradigm with GC. To improve \textbf{suboptimal} performance, DANCE performs round-wise, model-in-the-loop condensation refresh using the latest global model. To enhance \textbf{interpretability}, DANCE preserves provenance by storing locally inspectable evidence packs that trace predictions to selected neighbors and source text spans. Across 8 TAG datasets, DANCE improves accuracy by \textbf{2.33\%} at an \textbf{8\%} condensation ratio, with \textbf{33.42\%} fewer tokens than baselines.

With the advent of large language models (LLMs), it has become common practice for users to draft text and utilize LLMs to enhance its quality through paraphrasing. However, this process can sometimes result in the loss or distortion of the original intended meaning. Due to the human-like quality of LLM-generated text, traditional detection methods often fail, particularly when text is paraphrased to closely mimic original content. In response to these challenges, we propose a novel approach named SearchLLM, designed to identify LLM-paraphrased text by leveraging search engine capabilities to locate potential original text sources. By analyzing similarities between the input and regenerated versions of candidate sources, SearchLLM effectively distinguishes LLM-paraphrased content. SearchLLM is designed as a proxy layer, allowing seamless integration with existing detectors to enhance their performance. Experimental results across various LLMs demonstrate that SearchLLM consistently enhances the accuracy of recent detectors in detecting LLM-paraphrased text that closely mimics original content. Furthermore, SearchLLM also helps the detectors prevent paraphrasing attacks.

Single-prompt evaluations dominate current LLM benchmarking, yet they fail to capture the conversational dynamics where real-world harm occurs. In this study, we examined whether conversation length affects response veracity by evaluating LLM performance on the BoolQ dataset under varying length and scaffolding conditions. Our results across three distinct LLMs revealed model-specific vulnerabilities that are invisible under single-turn testing. The length-dependent and scaffold-specific effects we observed demonstrate a fundamental limitation of static evaluations, as deployment-relevant vulnerabilities could only be spotted in a multi-turn conversational setting.

Accurate fine-grained tree species classification is critical for forest inventory and biodiversity monitoring. Existing methods predominantly focus on designing complex architectures to fit local data distributions. However, they often overlook the long-tailed distributions and high inter-class similarity inherent in limited data, thereby struggling to distinguish between few-shot or confusing categories. In the process of knowledge dissemination in the human world, individuals will actively seek expert assistance to transcend the limitations of local thinking. Inspired by this, we introduce an external "Domain Expert" and propose an Expert Knowledge-Guided Classification Decision Calibration Network (EKDC-Net) to overcome these challenges. Our framework addresses two core issues: expert knowledge extraction and utilization. Specifically, we first develop a Local Prior Guided Knowledge Extraction Module (LPKEM). By leveraging Class Activation Map (CAM) analysis, LPKEM guides the domain expert to focus exclusively on discriminative features essential for classification. Subsequently, to effectively integrate this knowledge, we design an Uncertainty-Guided Decision Calibration Module (UDCM). This module dynamically corrects the local model's decisions by considering both overall category uncertainty and instance-level prediction uncertainty. Furthermore, we present a large-scale classification dataset covering 102 tree species, named CU-Tree102 to address the issue of scarce diversity in current benchmarks. Experiments on three benchmark datasets demonstrate that our approach achieves state-of-the-art performance. Crucially, as a lightweight plug-and-play module, EKDC-Net improves backbone accuracy by 6.42% and precision by 11.46% using only 0.08M additional learnable parameters. The dataset, code, and pre-trained models are available at https://github.com/WHU-USI3DV/TreeCLS.

Federated graph learning (FGL) enables collaborative training of graph neural networks (GNNs) across decentralized subgraphs without exposing raw data. While existing FGL methods often achieve high overall accuracy, we show that this average performance can conceal severe degradation on disadvantaged node groups. From a fairness perspective, these disparities arise systematically from three coupled sources: label skew toward majority patterns, topology confounding in message propagation, and aggregation dilution of updates from hard clients. To address this, we propose \textbf{BoostFGL}, a boosting-style framework for fairness-aware FGL. BoostFGL introduces three coordinated mechanisms: \ding{182} \emph{Client-side node boosting}, which reshapes local training signals to emphasize systematically under-served nodes; \ding{183} \emph{Client-side topology boosting}, which reallocates propagation emphasis toward reliable yet underused structures and attenuates misleading neighborhoods; and \ding{184} \emph{Server-side model boosting}, which performs difficulty- and reliability-aware aggregation to preserve informative updates from hard clients while stabilizing the global model. Extensive experiments on 9 datasets show that BoostFGL delivers substantial fairness gains, improving Overall-F1 by 8.43\%, while preserving competitive overall performance against strong FGL baselines.

Data set composed of categorical features is very common in big data analysis tasks. Since categorical features are usually with a limited number of qualitative possible values, the nested granular cluster effect is prevalent in the implicit discrete distance space of categorical data. That is, data objects frequently overlap in space or subspace to form small compact clusters, and similar small clusters often form larger clusters. However, the distance space cannot be well-defined like the Euclidean distance due to the qualitative categorical data values, which brings great challenges to the cluster analysis of categorical data. In view of this, we design a Multi-Granular Competitive Penalization Learning (MGCPL) algorithm to allow potential clusters to interactively tune themselves and converge in stages with different numbers of naturally compact clusters. To leverage MGCPL, we also propose a Cluster Aggregation strategy based on MGCPL Encoding (CAME) to first encode the data objects according to the learned multi-granular distributions, and then perform final clustering on the embeddings. It turns out that the proposed MGCPL-guided Categorical Data Clustering (MCDC) approach is competent in automatically exploring the nested distribution of multi-granular clusters and highly robust to categorical data sets from various domains. Benefiting from its linear time complexity, MCDC is scalable to large-scale data sets and promising in pre-partitioning data sets or compute nodes for boosting distributed computing. Extensive experiments with statistical evidence demonstrate its superiority compared to state-of-the-art counterparts on various real public data sets.

Wound care is often challenged by the economic and logistical burdens that consistently afflict patients and hospitals worldwide. In recent decades, healthcare professionals have sought support from computer vision and machine learning algorithms. In particular, wound segmentation has gained interest due to its ability to provide professionals with fast, automatic tissue assessment from standard RGB images. Some approaches have extended segmentation to 3D, enabling more complete and precise healing progress tracking. However, inferring multi-view consistent 3D structures from 2D images remains a challenge. In this paper, we evaluate WoundNeRF, a NeRF SDF-based method for estimating robust wound segmentations from automatically generated annotations. We demonstrate the potential of this paradigm in recovering accurate segmentations by comparing it against state-of-the-art Vision Transformer networks and conventional rasterisation-based algorithms. The code will be released to facilitate further development in this promising paradigm.

As large language models (LLMs) increasingly tackle complex reasoning tasks, test-time scaling has become critical for enhancing capabilities. However, in agentic scenarios with frequent tool calls, the traditional generation-length-based definition breaks down: tool latency decouples inference time from generation length. We propose Timely Machine, redefining test-time as wall-clock time, where models dynamically adjust strategies based on time budgets. We introduce Timely-Eval, a benchmark spanning high-frequency tool calls, low-frequency tool calls, and time-constrained reasoning. By varying tool latency, we find smaller models excel with fast feedback through more interactions, while larger models dominate high-latency settings via superior interaction quality. Moreover, existing models fail to adapt reasoning to time budgets. We propose Timely-RL to address this gap. After cold-start supervised fine-tuning, we use reinforcement learning to enhance temporal planning. Timely-RL improves time budget awareness and consistently boosts performance across Timely-Eval. We hope our work offers a new perspective on test-time scaling for the agentic era.

Large language models have demonstrated strong reasoning capabilities in complex tasks through tool integration, which is typically framed as a Markov Decision Process and optimized with trajectory-level RL algorithms such as GRPO. However, a common class of reasoning tasks, iterative optimization, presents distinct challenges: the agent interacts with the same underlying environment state across turns, and the value of a trajectory is determined by the best turn-level reward rather than cumulative returns. Existing GRPO-based methods cannot perform fine-grained, turn-level optimization in such settings, while black-box optimization methods discard prior knowledge and reasoning capabilities. To address this gap, we propose Turn-Level GRPO (TL-GRPO), a lightweight RL algorithm that performs turn-level group sampling for fine-grained optimization. We evaluate TL-GRPO on analog circuit sizing (ACS), a challenging scientific optimization task requiring multiple simulations and domain expertise. Results show that TL-GRPO outperforms standard GRPO and Bayesian optimization methods across various specifications. Furthermore, our 30B model trained with TL-GRPO achieves state-of-the-art performance on ACS tasks under same simulation budget, demonstrating both strong generalization and practical utility.

While Large Language Models (LLMs) demonstrate remarkable proficiency in semantic understanding, they often struggle to ensure structural consistency and reasoning reliability in complex decision-making tasks that demand rigorous logic. Although classical decision theories, such as the Analytic Hierarchy Process (AHP), offer systematic rational frameworks, their construction relies heavily on labor-intensive domain expertise, creating an "expert bottleneck" that hinders scalability in general scenarios. To bridge the gap between the generalization capabilities of LLMs and the rigor of decision theory, we propose Doc2AHP, a novel structured inference framework guided by AHP principles. Eliminating the need for extensive annotated data or manual intervention, our approach leverages the structural principles of AHP as constraints to direct the LLM in a constrained search within the unstructured document space, thereby enforcing the logical entailment between parent and child nodes. Furthermore, we introduce a multi-agent weighting mechanism coupled with an adaptive consistency optimization strategy to ensure the numerical consistency of weight allocation. Empirical results demonstrate that Doc2AHP not only empowers non-expert users to construct high-quality decision models from scratch but also significantly outperforms direct generative baselines in both logical completeness and downstream task accuracy.

With the rapid growth of scientific literature, scientific question answering (SciQA) has become increasingly critical for exploring and utilizing scientific knowledge. Retrieval-Augmented Generation (RAG) enhances LLMs by incorporating knowledge from external sources, thereby providing credible evidence for scientific question answering. But existing retrieval and reranking methods remain vulnerable to passages that are semantically similar but logically irrelevant, often reducing factual reliability and amplifying hallucinations.To address this challenge, we propose a Deep Evidence Reranking Agent (DeepEra) that integrates step-by-step reasoning, enabling more precise evaluation of candidate passages beyond surface-level semantics. To support systematic evaluation, we construct SciRAG-SSLI (Scientific RAG - Semantically Similar but Logically Irrelevant), a large-scale dataset comprising about 300K SciQA instances across 10 subjects, constructed from 10M scientific corpus. The dataset combines naturally retrieved contexts with systematically generated distractors to test logical robustness and factual grounding. Comprehensive evaluations confirm that our approach achieves superior retrieval performance compared to leading rerankers. To our knowledge, this work is the first to comprehensively study and empirically validate innegligible SSLI issues in two-stage RAG frameworks.

Discovery of sensitive and biologically grounded biomarkers is essential for early detection and monitoring of Alzheimer's disease (AD). Structural MRI is widely available but typically relies on hand-crafted features such as cortical thickness or volume. We ask whether self-supervised learning (SSL) can uncover more powerful biomarkers from the same data. Existing SSL methods underperform FreeSurfer-derived features in disease classification, conversion prediction, and amyloid status prediction. We introduce Residual Noise Contrastive Estimation (R-NCE), a new SSL framework that integrates auxiliary FreeSurfer features while maximizing additional augmentation-invariant information. R-NCE outperforms traditional features and existing SSL methods across multiple benchmarks, including AD conversion prediction. To assess biological relevance, we derive Brain Age Gap (BAG) measures and perform genome-wide association studies. R-NCE-BAG shows high heritability and associations with MAPT and IRAG1, with enrichment in astrocytes and oligodendrocytes, indicating sensitivity to neurodegenerative and cerebrovascular processes.

Large Language Models (LLMs) are increasingly deployed in domains such as education, mental health and customer support, where stable and consistent personas are critical for reliability. Yet, existing studies focus on narrative or role-playing tasks and overlook how adversarial conversational history alone can reshape induced personas. Black-box persona manipulation remains unexplored, raising concerns for robustness in realistic interactions. In response, we introduce the task of persona editing, which adversarially steers LLM traits through user-side inputs under a black-box, inference-only setting. To this end, we propose PHISH (Persona Hijacking via Implicit Steering in History), the first framework to expose a new vulnerability in LLM safety that embeds semantically loaded cues into user queries to gradually induce reverse personas. We also define a metric to quantify attack success. Across 3 benchmarks and 8 LLMs, PHISH predictably shifts personas, triggers collateral changes in correlated traits, and exhibits stronger effects in multi-turn settings. In high-risk domains mental health, tutoring, and customer support, PHISH reliably manipulates personas, validated by both human and LLM-as-Judge evaluations. Importantly, PHISH causes only a small reduction in reasoning benchmark performance, leaving overall utility largely intact while still enabling significant persona manipulation. While current guardrails offer partial protection, they remain brittle under sustained attack. Our findings expose new vulnerabilities in personas and highlight the need for context-resilient persona in LLMs. Our codebase and dataset is available at: https://github.com/Jivnesh/PHISH

Adversarial robustness refers to a model's ability to resist perturbation of inputs, while distribution robustness evaluates the performance of the model under data shifts. Although both aim to ensure reliable performance, prior work has revealed a tradeoff in distribution and adversarial robustness. Specifically, adversarial training might increase reliance on spurious features, which can harm distribution robustness, especially the performance on some underrepresented subgroups. We present a theoretical analysis of adversarial and distribution robustness that provides a tractable surrogate for per-step adversarial training by studying models trained on perturbed data. In addition to the tradeoff, our work further identified a nuanced phenomenon that $\ell_\infty$ perturbations on data with moderate bias can yield an increase in distribution robustness. Moreover, the gain in distribution robustness remains on highly skewed data when simplicity bias induces reliance on the core feature, characterized as greater feature separability. Our theoretical analysis extends the understanding of the tradeoff by highlighting the interplay of the tradeoff and the feature separability. Despite the tradeoff that persists in many cases, overlooking the role of feature separability may lead to misleading conclusions about robustness.

Accurate semantic segmentation for histopathology image is crucial for quantitative tissue analysis and downstream clinical modeling. Recent segmentation foundation models have improved generalization through large-scale pretraining, yet remain poorly aligned with pathology because they treat segmentation as a static visual prediction task. Here we present VISTA-PATH, an interactive, class-aware pathology segmentation foundation model designed to resolve heterogeneous structures, incorporate expert feedback, and produce pixel-level segmentation that are directly meaningful for clinical interpretation. VISTA-PATH jointly conditions segmentation on visual context, semantic tissue descriptions, and optional expert-provided spatial prompts, enabling precise multi-class segmentation across heterogeneous pathology images. To support this paradigm, we curate VISTA-PATH Data, a large-scale pathology segmentation corpus comprising over 1.6 million image-mask-text triplets spanning 9 organs and 93 tissue classes. Across extensive held-out and external benchmarks, VISTA-PATH consistently outperforms existing segmentation foundation models. Importantly, VISTA-PATH supports dynamic human-in-the-loop refinement by propagating sparse, patch-level bounding-box annotation feedback into whole-slide segmentation. Finally, we show that the high-fidelity, class-aware segmentation produced by VISTA-PATH is a preferred model for computational pathology. It improve tissue microenvironment analysis through proposed Tumor Interaction Score (TIS), which exhibits strong and significant associations with patient survival. Together, these results establish VISTA-PATH as a foundation model that elevates pathology image segmentation from a static prediction to an interactive and clinically grounded representation for digital pathology. Source code and demo can be found at https://github.com/zhihuanglab/VISTA-PATH.

The study on the expressive power of transformers shows that transformers are permutation equivariant, and they can approximate all permutation-equivariant continuous functions on a compact domain. However, these results are derived under real parameters and exact operations, while real implementations on computers can only use a finite set of numbers and inexact machine operations with round-off errors. In this work, we investigate the representability of floating-point transformers that use floating-point parameters and floating-point operations. Unlike existing results under exact operations, we first show that floating-point transformers can represent a class of non-permutation-equivariant functions even without positional encoding. Furthermore, we prove that floating-point transformers can represent all permutation-equivariant functions when the sequence length is bounded, but they cannot when the sequence length is large. We also found the minimal equivariance structure in floating-point transformers, and show that all non-trivial additive positional encoding can harm the representability of floating-point transformers.

Large language models (LLMs) have demonstrated exceptional performance in reasoning tasks such as mathematics and coding, matching or surpassing human capabilities. However, these impressive reasoning abilities face significant challenges in specialized domains. Taking Go as an example, although AlphaGo has established the high performance ceiling of AI systems in Go, mainstream LLMs still struggle to reach even beginner-level proficiency, let alone perform natural language reasoning. This performance gap between general-purpose LLMs and domain experts is significantly limiting the application of LLMs on a wider range of domain-specific tasks. In this work, we aim to bridge the divide between LLMs' general reasoning capabilities and expert knowledge in domain-specific tasks. We perform mixed fine-tuning with structured Go expertise and general long Chain-of-Thought (CoT) reasoning data as a cold start, followed by reinforcement learning to integrate expert knowledge in Go with general reasoning capabilities. Through this methodology, we present \textbf{LoGos}, a powerful LLM that not only maintains outstanding general reasoning abilities, but also conducts Go gameplay in natural language, demonstrating effective strategic reasoning and accurate next-move prediction. LoGos achieves performance comparable to human professional players, substantially surpassing all existing LLMs. Through this work, we aim to contribute insights on applying general LLM reasoning capabilities to specialized domains. We will release the first large-scale Go dataset for LLM training, the first LLM Go evaluation benchmark, and the first general LLM that reaches human professional-level performance in Go at: https://github.com/Entarochuan/LoGos.

Deep learning models are effective for sequential data modeling, yet commonly used activation functions such as ReLU, LeakyReLU, and PReLU often exhibit gradient instability when applied to noisy, non-stationary financial time series. This study introduces BrownianReLU, a stochastic activation function induced by Brownian motion that enhances gradient propagation and learning stability in Long Short-Term Memory (LSTM) networks. Using Monte Carlo simulation, BrownianReLU provides a smooth, adaptive response for negative inputs, mitigating the dying ReLU problem. The proposed activation is evaluated on financial time series from Apple, GCB, and the S&P 500, as well as LendingClub loan data for classification. Results show consistently lower Mean Squared Error and higher $R^2$ values, indicating improved predictive accuracy and generalization. Although ROC-AUC metric is limited in classification tasks, activation choice significantly affects the trade-off between accuracy and sensitivity, with Brownian ReLU and the selected activation functions yielding practically meaningful performance.