# Research Papers — 2026-01 · bundle page 78 of 189 > Full-text markdown of papers #3851–3900 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2026-01/page/78 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/77.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/79.md) ### Transfer Learning from One Cancer to Another via Deep Learning Domain Adaptation Authors: Justin Cheung, Samuel Savine, Calvin Nguyen, Lin Lu, Alhassan S. Yasin Published: 2026-01-21 Categories: cs.CV, cs.AI, cs.LG, cs.NE, q-bio.TO arXiv: https://arxiv.org/abs/2601.14678v1 Supervised deep learning models often achieve excellent performance within their training distribution but struggle to generalize beyond it. In cancer histopathology, for example, a convolutional neural network (CNN) may classify cancer severity accurately for cancer types represented in its training data, yet fail on related but unseen types. Although adenocarcinomas from different organs share morphological features that might support limited cross-domain generalization, addressing domain shift directly is necessary for robust performance. Domain adaptation offers a way to transfer knowledge from labeled data in one cancer type to unlabeled data in another, helping mitigate the scarcity of annotated medical images. This work evaluates cross-domain classification performance among lung, colon, breast, and kidney adenocarcinomas. A ResNet50 trained on any single adenocarcinoma achieves over 98% accuracy on its own domain but shows minimal generalization to others. Ensembling multiple supervised models does not resolve this limitation. In contrast, converting the ResNet50 into a domain adversarial neural network (DANN) substantially improves performance on unlabeled target domains. A DANN trained on labeled breast and colon data and adapted to unlabeled lung data reaches 95.56% accuracy. We also examine the impact of stain normalization on domain adaptation. Its effects vary by target domain: for lung, accuracy drops from 95.56% to 66.60%, while for breast and colon targets, stain normalization boosts accuracy from 49.22% to 81.29% and from 78.48% to 83.36%, respectively. Finally, using Integrated Gradients reveals that DANNs consistently attribute importance to biologically meaningful regions such as densely packed nuclei, indicating that the model learns clinically relevant features and can apply them to unlabeled cancer types. --- ### A comprehensive overview of deep learning models for object detection from videos/images Authors: Sukana Zulfqar, Sadia Saeed, M. Azam Zia, Anjum Ali, Faisal Mehmood, Abid Ali Published: 2026-01-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.14677v1 Object detection in video and image surveillance is a well-established yet rapidly evolving task, strongly influenced by recent deep learning advancements. This review summarises modern techniques by examining architectural innovations, generative model integration, and the use of temporal information to enhance robustness and accuracy. Unlike earlier surveys, it classifies methods based on core architectures, data processing strategies, and surveillance specific challenges such as dynamic environments, occlusions, lighting variations, and real-time requirements. The primary goal is to evaluate the current effectiveness of semantic object detection, while secondary aims include analysing deep learning models and their practical applications. The review covers CNN-based detectors, GAN-assisted approaches, and temporal fusion methods, highlighting how generative models support tasks such as reconstructing missing frames, reducing occlusions, and normalising illumination. It also outlines preprocessing pipelines, feature extraction progress, benchmarking datasets, and comparative evaluations. Finally, emerging trends in low-latency, efficient, and spatiotemporal learning approaches are identified for future research. --- ### LaVR: Scene Latent Conditioned Generative Video Trajectory Re-Rendering using Large 4D Reconstruction Models Authors: Mingyang Xie, Numair Khan, Tianfu Wang, Naina Dhingra, Seonghyeon Nam, Haitao Yang, Zhuo Hui, Christopher Metzler, Andrea Vedaldi, Hamed Pirsiavash, Lei Luo Published: 2026-01-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.14674v2 Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to drift and deformation under viewpoint changes. On the other hand, geometrically-conditioned models depend on estimated depth and explicit reconstruction, making them susceptible to depth inaccuracies and calibration errors. We propose to address these challenges by using the implicit geometric knowledge embedded in the latent space of a large 4D reconstruction model to condition the video generation process. These latents capture scene structure in a continuous space without explicit reconstruction. Therefore, they provide a flexible representation that allows the pretrained diffusion prior to regularize errors more effectively. By jointly conditioning on these latents and source camera poses, we demonstrate that our model achieves state-of-the-art results on the video re-rendering task. Project webpage is https://lavr-4d-scene-rerender.github.io/. --- ### Efficient reformulations of ReLU deep neural networks for surrogate modelling in power system optimisation Authors: Yogesh Pipada Sunil Kumar, S. Ali Pourmousavi, Jon A. R. Liisberg, Julian Lesmos-Vinasco Published: 2026-01-21 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2601.14673v1 The ongoing decarbonisation of power systems is driving an increasing reliance on distributed energy resources, which introduces complex and nonlinear interactions that are difficult to capture in conventional optimisation models. As a result, machine learning based surrogate modelling has emerged as a promising approach, but integrating machine learning models such as ReLU deep neural networks (DNNs) directly into optimisation often results in nonconvex and computationally intractable formulations. This paper proposes a linear programming (LP) reformulation for a class of convexified ReLU DNNs with non-negative weight matrices beyond the first layer, enabling a tight and tractable embedding of learned surrogate models in optimisation. We evaluate the method using a case study on learning the prosumer's responsiveness within an aggregator bidding problem in the Danish tertiary capacity market. The proposed reformulation is benchmarked against state-of-the-art alternatives, including piecewise linearisation (PWL), MIP-based embedding, and other LP relaxations. Across multiple neural network architectures and market scenarios, the convexified ReLU DNN achieves solution quality comparable to PWL and MIP-based reformulations while significantly improving computational performance and preserving model fidelity, unlike penalty-based reformulations. The results demonstrate that convexified ReLU DNNs offer a scalable and reliable methodology for integrating learned surrogate models in optimisation, with applicability to a wide range of emerging power system applications. --- ### GEGO: A Hybrid Golden Eagle and Genetic Optimization Algorithm for Efficient Hyperparameter Tuning in Resource-Constrained Environments Authors: Amaras Nazarians, Sachin Kumar Published: 2026-01-21 Categories: cs.NE, cs.AI arXiv: https://arxiv.org/abs/2601.14672v1 Hyperparameter tuning is a critical yet computationally expensive step in training neural networks, particularly when the search space is high dimensional and nonconvex. Metaheuristic optimization algorithms are often used for this purpose due to their derivative free nature and robustness against local optima. In this work, we propose Golden Eagle Genetic Optimization (GEGO), a hybrid metaheuristic that integrates the population movement strategy of Golden Eagle Optimization with the genetic operators of selection, crossover, and mutation. The main novelty of GEGO lies in embedding genetic operators directly into the iterative search process of GEO, rather than applying them as a separate evolutionary stage. This design improves population diversity during search and reduces premature convergence while preserving the exploration behavior of GEO. GEGO is evaluated on standard unimodal, multimodal, and composite benchmark functions from the CEC2017 suite, where it consistently outperforms its constituent algorithms and several classical metaheuristics in terms of solution quality and robustness. The algorithm is further applied to hyperparameter tuning of artificial neural networks on the MNIST dataset, where GEGO achieves improved classification accuracy and more stable convergence compared to GEO and GA. These results indicate that GEGO provides a balanced exploration-exploitation tradeoff and is well suited for hyperparameter optimization under constrained computational settings. --- ### Mirai: Autoregressive Visual Generation Needs Foresight Authors: Yonghao Yu, Lang Huang, Zerun Wang, Runyi Li, Toshihiko Yamasaki Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14671v2 Autoregressive (AR) visual generators model images as sequences of discrete tokens and are trained with a next-token likelihood objective. This strict causal supervision optimizes each step based only on the immediate next token, which can weaken global coherence and slow convergence. We investigate whether foresight, training signals that originate from later tokens, can improve autoregressive visual generation. We conduct a series of controlled diagnostics along the injection level, foresight layout, and foresight source axes, revealing a key insight: aligning foresight with AR models' internal representations on the 2D image grid improves causal modeling. We formulate this insight with Mirai (meaning "future" in Japanese), a general framework that injects future information into AR training with no architecture change and no extra inference overhead: Mirai-E uses explicit foresight from multiple future positions of unidirectional representations, whereas Mirai-I leverages implicit foresight from matched bidirectional representations. Extensive experiments show that Mirai significantly accelerates convergence and improves generation quality. For instance, Mirai can speed up LlamaGen-B's convergence by up to 10$\times$ and reduce the generation FID from 5.34 to 4.34 on the ImageNet class-condition image generation benchmark. Our study highlights that visual autoregressive models need foresight. --- ### INFA-Guard: Mitigating Malicious Propagation via Infection-Aware Safeguarding in LLM-Based Multi-Agent Systems Authors: Yijin Zhou, Xiaoya Lu, Dongrui Liu, Junchi Yan, Jing Shao Published: 2026-01-21 Categories: cs.MA, cs.AI arXiv: https://arxiv.org/abs/2601.14667v1 The rapid advancement of Large Language Model (LLM)-based Multi-Agent Systems (MAS) has introduced significant security vulnerabilities, where malicious influence can propagate virally through inter-agent communication. Conventional safeguards often rely on a binary paradigm that strictly distinguishes between benign and attack agents, failing to account for infected agents i.e., benign entities converted by attack agents. In this paper, we propose Infection-Aware Guard, INFA-Guard, a novel defense framework that explicitly identifies and addresses infected agents as a distinct threat category. By leveraging infection-aware detection and topological constraints, INFA-Guard accurately localizes attack sources and infected ranges. During remediation, INFA-Guard replaces attackers and rehabilitates infected ones, avoiding malicious propagation while preserving topological integrity. Extensive experiments demonstrate that INFA-Guard achieves state-of-the-art performance, reducing the Attack Success Rate (ASR) by an average of 33%, while exhibiting cross-model robustness, superior topological generalization, and high cost-effectiveness. --- ### Calibrated uncertainty quantification for prosumer flexibility aggregation in ancillary service markets Authors: Yogesh Pipada Sunil Kumar, S. Ali Pourmousavi, Jon A. R. Liisberg, Julian Lesmos-Vinasco Published: 2026-01-21 Categories: eess.SY, cs.AI arXiv: https://arxiv.org/abs/2601.14663v1 Reliable forecasting of prosumer flexibility is critical for demand response aggregators participating in frequency controlled ancillary services market, where strict reliability requirements such as the P90 standard are enforced. Limited historical data, dependence on exogeneous factors, and heterogenous prosumer behaviour introduce significant epistemic uncertainty, making deterministic or poorly calibrated probabilistic models unsuitable for market bidding. This paper proposes the use of scalable uncertainty quantification framework that integrates Monte Carlo dropout (MCD) with conformal prediction (CP) to produce calibrated, finite sample prediction intervals for aggregated prosumer flexibility. The proposed framework is applied to a behind-the-meter aggregator participating in the Danish manual frequency restoration reserve capacity market. A large-scale synthetic dataset is generated using a modified industry-grade home energy management system, combined with publicly available load, solar, price, activation and device-level data. The resulting machine learning surrogate model captures aggregate prosumer price responsiveness and provides uncertainty-aware estimates suitable for market bidding. Multiple multivariate CP strategies are evaluated and benchmarked against conventional MCD-based methods. Results show that standalone MCD systematically overestimates available flexibility and violates P90 compliance, whereas the proposed MCD-CP framework achieves reliable coverage with controlled conservatism. When embedded in aggregator bidding model, conformalised methods substantially reduce overbidding risk and achieve upto 70% of perfect-information profit while satisfying regulatory reliability constraints, providing practical, computationally efficient, and market-compliant solution for aggregator flexibility forecasting under uncertainty. --- ### Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems Authors: Shuhua Yang, Jiahao Zhang, Yilong Wang, Dongwon Lee, Suhang Wang Published: 2026-01-21 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.14662v2 Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning. While prior work shows that GraphRAG responses may leak retrieved subgraphs, the feasibility of query-efficient reconstruction of the hidden graph structure remains unexplored under realistic query budgets. We study a budget-constrained black-box setting where an adversary adaptively queries the system to steal its latent entity-relation graph. We propose AGEA (Agentic Graph Extraction Attack), a framework that leverages a novelty-guided exploration-exploitation strategy, external graph memory modules, and a two-stage graph extraction pipeline combining lightweight discovery with LLM-based filtering. We evaluate AGEA on medical, agriculture, and literary datasets across Microsoft-GraphRAG and LightRAG systems. Under identical query budgets, AGEA significantly outperforms prior attack baselines, recovering up to 90% of entities and relationships while maintaining high precision. These results demonstrate that modern GraphRAG systems are highly vulnerable to structured, agentic extraction attacks, even under strict query limits. The code is available at https://github.com/shuashua0608/AGEA. --- ### NeuroFilter: Activation-Based Guardrails for Privacy-Conscious LLM Agents Authors: Saswat Das, Ferdinando Fioretto Published: 2026-01-21 Categories: cs.CR, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.14660v2 Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling transformative applications in domains spanning from personal assistant, financial, and legal domains. While these systems can substantially improve productivity and service quality, effective agency typically requires access to sensitive personal or organizational information. However, this access introduces critical inference-time privacy risks, specifically regarding contextually appropriate information disclosure. While recent studies highlight the inability of agentic LLMs to consistently adhere to privacy norms, existing defenses often rely on auxiliary LLM-based monitors. However, these defenses are expensive and offer limited protection against attacks that are robust to semantic censorship. To contrast this background, this paper proposes a notion of privacy filters based on activation probing. We show that these filters are both computationally efficient and effective for both single-turn and multi-turn conversational settings. Furthermore, this work provides the first systematic investigation into probing model internals across a conversation trajectory, moving beyond static, single-prompt analysis to capture the evolving state of privacy-sensitive interactions. --- ### Say Anything but This: When Tokenizer Betrays Reasoning in LLMs Authors: Navid Ayoobi, Marcus I Armstrong, Arjun Mukherjee Published: 2026-01-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.14658v1 Large language models (LLMs) reason over discrete token ID sequences, yet modern subword tokenizers routinely produce non-unique encodings: multiple token ID sequences can detokenize to identical surface strings. This representational mismatch creates an unmeasured fragility wherein reasoning processes can fail. LLMs may treat two internal representations as distinct "words" even when they are semantically identical at the text level. In this work, we show that tokenization can betray LLM reasoning through one-to-many token ID mappings. We introduce a tokenization-consistency probe that requires models to replace designated target words in context while leaving all other content unchanged. The task is intentionally simple at the surface level, enabling us to attribute failures to tokenizer-detokenizer artifacts rather than to knowledge gaps or parameter limitations. Through analysis of over 11000 replacement trials across state-of-the-art open-source LLMs, we find a non-trivial rate of outputs exhibit phantom edits: cases where models operate under the illusion of correct reasoning, a phenomenon arising from tokenizer-induced representational defects. We further analyze these cases and provide a taxonomy of eight systematic tokenizer artifacts, including whitespace-boundary shifts and intra-word resegmentation. These findings indicate that part of apparent reasoning deficiency originates in the tokenizer layer, motivating tokenizer-level remedies before incurring the cost of training ever-larger models on ever-larger corpora. --- ### Efficient Imputation for Patch-based Missing Single-cell Data via Cluster-regularized Optimal Transport Authors: Yuyu Liu, Jiannan Yang, Ziyang Yu, Weishen Pan, Fei Wang, Tengfei Ma Published: 2026-01-21 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2601.14653v3 Missing data in single-cell sequencing datasets poses significant challenges for extracting meaningful biological insights. However, existing imputation approaches, which often assume uniformity and data completeness, struggle to address cases with large patches of missing data. In this paper, we present CROT (Cluster-Regularized Optimal Transport), an optimal transport-based imputation algorithm designed to handle patch-based missing data in tabular formats. Our approach effectively captures the underlying data structure in the presence of significant missingness. Notably, it achieves superior imputation accuracy while significantly reducing runtime, demonstrating its scalability and efficiency for large-scale datasets. This work introduces a robust solution for imputation in heterogeneous, high-dimensional datasets with structured data absence, addressing critical challenges in both biological and clinical data analysis. Our code is available on GitHub, https://github.com/yuyuliu11037/CROT. --- ### MAS-Orchestra: Understanding and Improving Multi-Agent Reasoning Through Holistic Orchestration and Controlled Benchmarks Authors: Zixuan Ke, Yifei Ming, Austin Xu, Ryan Chin, Xuan-Phi Nguyen, Prathyusha Jwalapuram, Jiayu Wang, Semih Yavuz, Caiming Xiong, Shafiq Joty Published: 2026-01-21 Categories: cs.AI, cs.CL, cs.MA arXiv: https://arxiv.org/abs/2601.14652v5 While multi-agent systems (MAS) promise elevated intelligence through coordination of agents, current approaches to automatic MAS design under-deliver. Such shortcomings stem from two key factors: (1) methodological complexity - agent orchestration is performed using sequential, code-level execution that limits global system-level holistic reasoning and scales poorly with agent complexity - and (2) efficacy uncertainty - MAS are deployed without understanding if there are tangible benefits compared to single-agent systems (SAS). We propose MASOrchestra, a training-time framework that formulates MAS orchestration as a function-calling reinforcement learning problem with holistic orchestration, generating an entire MAS at once. In MAS-Orchestra, complex, goal-oriented subagents are abstracted as callable functions, enabling global reasoning over system structure while hiding internal execution details. To rigorously study when and why MAS are beneficial, we introduce MASBENCH, a controlled benchmark that characterizes tasks along five axes: Depth, Horizon, Breadth, Parallel, and Robustness. Our analysis reveals that MAS gains depend critically on task structure, verification protocols, and the capabilities of both orchestrator and subagents, rather than holding universally. Guided by these insights, MAS-Orchestra achieves consistent improvements on public benchmarks including mathematical reasoning, multi-hop QA, and search-based QA, while achieving more than 10x efficiency over strong baselines. Together, MAS-Orchestra and MASBENCH enable better training and understanding of MAS in the pursuit of multi-agent intelligence. --- ### READ-Net: Clarifying Emotional Ambiguity via Adaptive Feature Recalibration for Audio-Visual Depression Detection Authors: Chenglizhao Chen, Boze Li, Mengke Song, Dehao Feng, Xinyu Liu, Shanchen Pang, Jufeng Yang, Hui Yu Published: 2026-01-21 Categories: cs.CV, cs.MM, cs.SD arXiv: https://arxiv.org/abs/2601.14651v1 Depression is a severe global mental health issue that impairs daily functioning and overall quality of life. Although recent audio-visual approaches have improved automatic depression detection, methods that ignore emotional cues often fail to capture subtle depressive signals hidden within emotional expressions. Conversely, those incorporating emotions frequently confuse transient emotional expressions with stable depressive symptoms in feature representations, a phenomenon termed \emph{Emotional Ambiguity}, thereby leading to detection errors. To address this critical issue, we propose READ-Net, the first audio-visual depression detection framework explicitly designed to resolve Emotional Ambiguity through Adaptive Feature Recalibration (AFR). The core insight of AFR is to dynamically adjust the weights of emotional features to enhance depression-related signals. Rather than merely overlooking or naively combining emotional information, READ-Net innovatively identifies and preserves depressive-relevant cues within emotional features, while adaptively filtering out irrelevant emotional noise. This recalibration strategy significantly clarifies feature representations, and effectively mitigates the persistent challenge of emotional interference. Additionally, READ-Net can be easily integrated into existing frameworks for improved performance. Extensive evaluations on three publicly available datasets show that READ-Net outperforms state-of-the-art methods, with average gains of 4.55\% in accuracy and 1.26\% in F1-score, demonstrating its robustness to emotional disturbances and improving audio-visual depression detection. --- ### TRSVR: An Adaptive Stochastic Trust-Region Method with Variance Reduction Authors: Yuchen Fang, Xinshou Zheng, Javad Lavaei Published: 2026-01-21 Categories: math.OC, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.14647v1 We propose a stochastic trust-region method for unconstrained nonconvex optimization that incorporates stochastic variance-reduced gradients (SVRG) to accelerate convergence. Unlike classical trust-region methods, the proposed algorithm relies solely on stochastic gradient information and does not require function value evaluations. The trust-region radius is adaptively adjusted based on a radius-control parameter and the stochastic gradient estimate. Under mild assumptions, we establish that the algorithm converges in expectation to a first-order stationary point. Moreover, the method achieves iteration and sample complexity bounds that match those of SVRG-based first-order methods, while allowing stochastic and potentially gradient-dependent second-order information. Extensive numerical experiments demonstrate that incorporating SVRG accelerates convergence, and that the use of trust-region methods and Hessian information further improves performance. We also highlight the impact of batch size and inner-loop length on efficiency, and show that the proposed method outperforms SGD and Adam on several machine learning tasks. --- ### Forest-Chat: Adapting Vision-Language Agents for Interactive Forest Change Analysis Authors: James Brock, Ce Zhang, Nantheera Anantrasirichai Published: 2026-01-21 Categories: cs.CV, cs.AI, cs.CL, cs.HC arXiv: https://arxiv.org/abs/2601.14637v2 The increasing availability of high-resolution satellite imagery, together with advances in deep learning, creates new opportunities for forest monitoring workflows. Two central challenges in this domain are pixel-level change detection and semantic change interpretation, particularly for complex forest dynamics. While large language models (LLMs) are increasingly adopted for data exploration, their integration with vision-language models (VLMs) for remote sensing image change interpretation (RSICI) remains underexplored, especially beyond urban environments. This paper introduces Forest-Chat, an LLM-driven agent for forest change analysis, enabling natural language querying across multiple RSICI tasks, including change detection and captioning, object counting, deforestation characterisation, and change reasoning. Forest-Chat builds upon a multi-level change interpretation (MCI) vision-language backbone with LLM-based orchestration, incorporating zero-shot change detection via AnyChange and multimodal LLM-based zero-shot change captioning and refinement. To support adaptation and evaluation in forest environments, we introduce the Forest-Change dataset, comprising bi-temporal satellite imagery, pixel-level change masks, and semantic change captions via human annotation and rule-based methods. Forest-Chat achieves mIoU and BLEU-4 scores of 67.10% and 40.17% on Forest-Change, and 88.13% and 34.41% on LEVIR-MCI-Trees, a tree-focused subset of LEVIR-MCI. In a zero-shot capacity, it achieves 60.15% and 34.00% on Forest-Change, and 47.32% and 18.23% on LEVIR-MCI-Trees. Further experiments demonstrate the value of caption refinement for injecting geographic domain knowledge into supervised captions, and the system's limited label domain transfer onto JL1-CD-Trees. These findings demonstrate that interactive, LLM-driven systems can support accessible and interpretable forest change analysis. --- ### Relational Graph Modeling for Credit Default Prediction: Heterogeneous GNNs and Hybrid Ensemble Learning Authors: Yvonne Yang, Eranki Vasistha Published: 2026-01-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14633v1 Credit default risk arises from complex interactions among borrowers, financial institutions, and transaction-level behaviors. While strong tabular models remain highly competitive in credit scoring, they may fail to explicitly capture cross-entity dependencies embedded in multi-table financial histories. In this work, we construct a massive-scale heterogeneous graph containing over 31 million nodes and more than 50 million edges, integrating borrower attributes with granular transaction-level entities such as installment payments, POS cash balances, and credit card histories. We evaluate heterogeneous graph neural networks (GNNs), including heterogeneous GraphSAGE and a relation-aware attentive heterogeneous GNN, against strong tabular baselines. We find that standalone GNNs provide limited lift over a competitive gradient-boosted tree baseline, while a hybrid ensemble that augments tabular features with GNN-derived customer embeddings achieves the best overall performance, improving both ROC-AUC and PR-AUC. We further observe that contrastive pretraining can improve optimization stability but yields limited downstream gains under generic graph augmentations. Finally, we conduct structured explainability and fairness analyses to characterize how relational signals affect subgroup behavior and screening-oriented outcomes. --- ### Semi-Supervised Mixture Models under the Concept of Missing at Radom with Margin Confidence and Aranda Ordaz Function Authors: Jinyang Liao, Ziyang Lyu Published: 2026-01-21 Categories: stat.ML, cs.LG, stat.CO, stat.ME arXiv: https://arxiv.org/abs/2601.14631v1 This paper presents a semi-supervised learning framework for Gaussian mixture modelling under a Missing at Random (MAR) mechanism. The method explicitly parameterizes the missingness mechanism by modelling the probability of missingness as a function of classification uncertainty. To quantify classification uncertainty, we introduce margin confidence and incorporate the Aranda Ordaz (AO) link function to flexibly capture the asymmetric relationships between uncertainty and missing probability. Based on this formulation, we develop an efficient Expectation Conditional Maximization (ECM) algorithm that jointly estimates all parameters appearing in both the Gaussian mixture model (GMM) and the missingness mechanism, and subsequently imputes the missing labels by a Bayesian classifier derived from the fitted mixture model. This method effectively alleviates the bias induced by ignoring the missingness mechanism while enhancing the robustness of semi-supervised learning. The resulting uncertainty-aware framework delivers reliable classification performance in realistic MAR scenarios with substantial proportions of missing labels. --- ### Online Linear Programming with Replenishment Authors: Yuze Chen, Yuan Zhou, Baichuan Mo, Jie Ying, Yufei Ruan, Zhou Ye Published: 2026-01-21 Categories: math.OC, cs.DS, cs.LG arXiv: https://arxiv.org/abs/2601.14629v1 We study an online linear programming (OLP) model in which inventory is not provided upfront but instead arrives gradually through an exogenous stochastic replenishment process. This replenishment-based formulation captures operational settings, such as e-commerce fulfillment, perishable supply chains, and renewable-powered systems, where resources are accumulated gradually and initial inventories are small or zero. The introduction of dispersed, uncertain replenishment fundamentally alters the structure of classical OLPs, creating persistent stockout risk and eliminating advance knowledge of the total budget. We develop new algorithms and regret analyses for three major distributional regimes studied in the OLP literature: bounded distributions, finite-support distributions, and continuous-support distributions with a non-degeneracy condition. For bounded distributions, we design an algorithm that achieves $\widetilde{\mathcal{O}}(\sqrt{T})$ regret. For finite-support distributions with a non-degenerate induced LP, we obtain $\mathcal{O}(\log T)$ regret, and we establish an $Ω(\sqrt{T})$ lower bound for degenerate instances, demonstrating a sharp separation from the classical setting where $\mathcal{O}(1)$ regret is achievable. For continuous-support, non-degenerate distributions, we develop a two-stage accumulate-then-convert algorithm that achieves $\mathcal{O}(\log^2 T)$ regret, comparable to the $\mathcal{O}(\log T)$ regret in classical OLPs. Together, these results provide a near-complete characterization of the optimal regret achievable in OLP with replenishment. Finally, we empirically evaluate our algorithms and demonstrate their advantages over natural adaptations of classical OLP methods in the replenishment setting. --- ### A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control Authors: Weiyu Guo, He Zhang, Pengteng Li, Tiefu Cai, Ziyang Chen, Yandong Guo, Xiao He, Yongkui Yang, Ying Sun, Hui Xiong Published: 2026-01-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.14628v1 Recent advances in embodied intelligence have leveraged massive scaling of data and model parameters to master natural-language command following and multi-task control. In contrast, biological systems demonstrate an innate ability to acquire skills rapidly from sparse experience. Crucially, current robotic policies struggle to replicate the dynamic stability, reflexive responsiveness, and temporal memory inherent in biological motion. Here we present Neuromorphic Vision-Language-Action (NeuroVLA), a framework that mimics the structural organization of the bio-nervous system between the cortex, cerebellum, and spinal cord. We adopt a system-level bio-inspired design: a high-level model plans goals, an adaptive cerebellum module stabilizes motion using high-frequency sensors feedback, and a bio-inspired spinal layer executes lightning-fast actions generation. NeuroVLA represents the first deployment of a neuromorphic VLA on physical robotics, achieving state-of-the-art performance. We observe the emergence of biological motor characteristics without additional data or special guidance: it stops the shaking in robotic arms, saves significant energy(only 0.4w on Neuromorphic Processor), shows temporal memory ability and triggers safety reflexes in less than 20 milliseconds. --- ### Diffusion Epistemic Uncertainty with Asymmetric Learning for Diffusion-Generated Image Detection Authors: Yingsong Huang, Hui Guo, Jing Huang, Bing Bai, Qi Xiong Published: 2026-01-21 Categories: cs.CV, stat.ML arXiv: https://arxiv.org/abs/2601.14625v1 The rapid progress of diffusion models highlights the growing need for detecting generated images. Previous research demonstrates that incorporating diffusion-based measurements, such as reconstruction error, can enhance the generalizability of detectors. However, ignoring the differing impacts of aleatoric and epistemic uncertainty on reconstruction error can undermine detection performance. Aleatoric uncertainty, arising from inherent data noise, creates ambiguity that impedes accurate detection of generated images. As it reflects random variations within the data (e.g., noise in natural textures), it does not help distinguish generated images. In contrast, epistemic uncertainty, which represents the model's lack of knowledge about unfamiliar patterns, supports detection. In this paper, we propose a novel framework, Diffusion Epistemic Uncertainty with Asymmetric Learning~(DEUA), for detecting diffusion-generated images. We introduce Diffusion Epistemic Uncertainty~(DEU) estimation via the Laplace approximation to assess the proximity of data to the manifold of diffusion-generated samples. Additionally, an asymmetric loss function is introduced to train a balanced classifier with larger margins, further enhancing generalizability. Extensive experiments on large-scale benchmarks validate the state-of-the-art performance of our method. --- ### Scaling Ambiguity: Augmenting Human Annotation in Speech Emotion Recognition with Audio-Language Models Authors: Wenda Zhang, Hongyu Jin, Siyi Wang, Zhiqiang Wei, Ting Dang Published: 2026-01-21 Categories: eess.AS, cs.AI, cs.LG, cs.SD arXiv: https://arxiv.org/abs/2601.14620v1 Speech Emotion Recognition models typically use single categorical labels, overlooking the inherent ambiguity of human emotions. Ambiguous Emotion Recognition addresses this by representing emotions as probability distributions, but progress is limited by unreliable ground-truth distributions inferred from sparse human annotations. This paper explores whether Large Audio-Language Models (ALMs) can mitigate the annotation bottleneck by generating high-quality synthetic annotations. We introduce a framework leveraging ALMs to create Synthetic Perceptual Proxies, augmenting human annotations to improve ground-truth distribution reliability. We validate these proxies through statistical analysis of their alignment with human distributions and evaluate their impact by fine-tuning ALMs with the augmented emotion distributions. Furthermore, to address class imbalance and enable unbiased evaluation, we propose DiME-Aug, a Distribution-aware Multimodal Emotion Augmentation strategy. Experiments on IEMOCAP and MSP-Podcast show that synthetic annotations enhance emotion distribution, especially in low-ambiguity regions where annotation agreement is high. However, benefits diminish for highly ambiguous emotions with greater human disagreement. This work provides the first evidence that ALMs could address annotation scarcity in ambiguous emotion recognition, but highlights the need for more advanced prompting or generation strategies to handle highly ambiguous cases. --- ### SearchGym: Bootstrapping Real-World Search Agents via Cost-Effective and High-Fidelity Environment Simulation Authors: Xichen Zhang, Ziyi He, Yinghao Zhu, Sitong Wu, Shaozuo Yu, Meng Chu, Wenhu Zhang, Haoru Tan, Jiaya Jia Published: 2026-01-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.14615v1 Search agents have emerged as a pivotal paradigm for solving open-ended, knowledge-intensive reasoning tasks. However, training these agents via Reinforcement Learning (RL) faces a critical dilemma: interacting with live commercial Web APIs is prohibitively expensive, while relying on static data snapshots often introduces noise due to data misalignment. This misalignment generates corrupted reward signals that destabilize training by penalizing correct reasoning or rewarding hallucination. To address this, we propose SearchGym, a simulation environment designed to bootstrap robust search agents. SearchGym employs a rigorous generative pipeline to construct a verifiable knowledge graph and an aligned document corpus, ensuring that every reasoning task is factually grounded and strictly solvable. Building on this controllable environment, we introduce SearchGym-RL, a curriculum learning methodology that progressively optimizes agent policies through purified feedback, evolving from basic interactions to complex, long-horizon planning. Extensive experiments across the Llama and Qwen families demonstrate strong Sim-to-Real generalization. Notably, our Qwen2.5-7B-Base model trained within SearchGym surpasses the web-enhanced ASearcher baseline across nine diverse benchmarks by an average relative margin of 10.6%. Our results validate that high-fidelity simulation serves as a scalable and highly cost-effective methodology for developing capable search agents. --- ### Learning Consistent Taxonomic Classification through Hierarchical Reasoning Authors: Zhenghong Li, Kecheng Zheng, Haibin Ling Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14610v1 While Vision-Language Models (VLMs) excel at visual understanding, they often fail to grasp hierarchical knowledge. This leads to common errors where VLMs misclassify coarser taxonomic levels even when correctly identifying the most specific level (leaf level). Existing approaches largely overlook this issue by failing to model hierarchical reasoning. To address this gap, we propose VL-Taxon, a two-stage, hierarchy-based reasoning framework designed to improve both leaf-level accuracy and hierarchical consistency in taxonomic classification. The first stage employs a top-down process to enhance leaf-level classification accuracy. The second stage then leverages this accurate leaf-level output to ensure consistency throughout the entire taxonomic hierarchy. Each stage is initially trained with supervised fine-tuning to instill taxonomy knowledge, followed by reinforcement learning to refine the model's reasoning and generalization capabilities. Extensive experiments reveal a remarkable result: our VL-Taxon framework, implemented on the Qwen2.5-VL-7B model, outperforms its original 72B counterpart by over 10% in both leaf-level and hierarchical consistency accuracy on average on the iNaturalist-2021 dataset. Notably, this significant gain was achieved by fine-tuning on just a small subset of data, without relying on any examples generated by other VLMs. --- ### Communication-efficient distributed hazard difference estimation for heterogeneous multi-site survival data Authors: Ziwen Wang, Siqi Li, Marcus Eng Hock Ong, Nan Liu Published: 2026-01-21 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.14609v2 Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block patient-level data sharing and the persistent server connections required by iterative federated methods. We present DiSAH (\underline{\textbf{Di}}stributed \underline{\textbf{S}}urvival via \underline{\textbf{A}}dditive \underline{\textbf{H}}azards), a federated algorithm for time-to-event analysis whose closed-form, non-iterative structure removes the need for a dedicated central server. Coordination requires only aggregation of summary statistics, which any site can perform, with no patient-level data leaving the site. DiSAH is the first federated method to estimate hazard differences, the absolute change in event rate attributable to each risk factor, providing an actionable scale for triage, resource allocation, and health-economic evaluation. Across simulations and 47,778 emergency-department patients from the United States and Singapore, DiSAH matches centralized analysis in accuracy and discrimination, recovers mortality risk factors no individual site was powered to detect, and outperforms meta-analysis and local models. --- ### U-Harmony: Enhancing Joint Training for Segmentation Models with Universal Harmonization Authors: Weiwei Ma, Xiaobing Yu, Peijie Qiu, Jin Yang, Pan Xiao, Xiaoqi Zhao, Xiaofeng Liu, Tomo Miyazaki, Shinichiro Omachi, Yongsong Huang Published: 2026-01-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.14605v1 In clinical practice, medical segmentation datasets are often limited and heterogeneous, with variations in modalities, protocols, and anatomical targets across institutions. Existing deep learning models struggle to jointly learn from such diverse data, often sacrificing either generalization or domain-specific knowledge. To overcome these challenges, we propose a joint training method called Universal Harmonization (U-Harmony), which can be integrated into deep learning-based architectures with a domain-gated head, enabling a single segmentation model to learn from heterogeneous datasets simultaneously. By integrating U-Harmony, our approach sequentially normalizes and then denormalizes feature distributions to mitigate domain-specific variations while preserving original dataset-specific knowledge. More appealingly, our framework also supports universal modality adaptation, allowing the seamless learning of new imaging modalities and anatomical classes. Extensive experiments on cross-institutional brain lesion datasets demonstrate the effectiveness of our approach, establishing a new benchmark for robust and adaptable 3D medical image segmentation models in real-world clinical settings. --- ### Variance-Adaptive Muon: Pre-Orthogonalization Variance Modulation for Efficient Language Model Pretraining Authors: Jingru Li, Yibo Fan, Huan Li Published: 2026-01-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14603v2 Optimizer design plays a central role in efficient language model pretraining, directly affecting optimization dynamics, convergence speed, and compute cost under fixed training budgets. Muon has emerged as a strong optimizer by orthogonalizing momentum updates, yielding a matrix-valued analogue of sign-based normalization. However, unlike Adam-style methods, Muon does not explicitly incorporate gradient-variance information into its updates. Motivated by Adam's variance-adaptive interpretation, we propose Muon-NSR and Muon-VS, two variance-adaptive Muon variants for language model pretraining. Muon-NSR applies noise-to-signal ratio (NSR) modulation before Newton--Schulz orthogonalization, whereas Muon-VS uses variance scaling (VS) without introducing any additional hyperparameters beyond those of Muon. Both methods preserve Muon's spectral normalization structure while requiring only one additional variance buffer. Experiments on Llama-style and GPT-2 pretraining across model scales from 125M to 1.2B parameters show that our methods improve over well-tuned Muon baselines and remain competitive with representative adaptive Muon-family baselines. On Llama-1.2B, Muon-VS achieves a 1.33$\times$ step-to-target speedup over a well-tuned Muon baseline, with Muon's final validation loss as the target. These results indicate that variance-adaptive modulation is a simple and effective mechanism for improving Muon-style optimizers in language model pretraining. --- ### 3D Space as a Scratchpad for Editable Text-to-Image Generation Authors: Oindrila Saha, Vojtech Krs, Radomir Mech, Subhransu Maji, Matheus Gadelha, Kevin Blackburn-Matzen Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14602v1 Recent progress in large language models (LLMs) has shown that reasoning improves when intermediate thoughts are externalized into explicit workspaces, such as chain-of-thought traces or tool-augmented reasoning. Yet, visual language models (VLMs) lack an analogous mechanism for spatial reasoning, limiting their ability to generate images that accurately reflect geometric relations, object identities, and compositional intent. We introduce the concept of a spatial scratchpad -- a 3D reasoning substrate that bridges linguistic intent and image synthesis. Given a text prompt, our framework parses subjects and background elements, instantiates them as editable 3D meshes, and employs agentic scene planning for placement, orientation, and viewpoint selection. The resulting 3D arrangement is rendered back into the image domain with identity-preserving cues, enabling the VLM to generate spatially consistent and visually coherent outputs. Unlike prior 2D layout-based methods, our approach supports intuitive 3D edits that propagate reliably into final images. Empirically, it achieves a 32% improvement in text alignment on GenAI-Bench, demonstrating the benefit of explicit 3D reasoning for precise, controllable image generation. Our results highlight a new paradigm for vision-language models that deliberate not only in language, but also in space. Code and visualizations at https://oindrilasaha.github.io/3DScratchpad/ --- ### Rethinking Reinforcement fine-tuning of LLMs: A Multi-armed Bandit Learning Perspective Authors: Xiao Hu, Hong Xie, Tao Tan, Defu Lian, Jianyu Han Published: 2026-01-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.14599v1 A large number of heuristics have been proposed to optimize the reinforcement fine-tuning of LLMs. However, inconsistent claims are made from time to time, making this area elusive. Reflecting on this situation, two fundamental questions still lack a clear understanding: 1) what is the role of each optimizing choice? 2) which ones are the bottlenecks? This paper aims to shed light on them, and it faces the challenge of several entangled confounding factors in the fine-tuning process. To tackle this challenge, we propose a bottom-up experiment pipeline. The bottom layer is composed of a minimalist configuration: one training data, one rollout per round and the reward directly serve as the learning signal without advantage function design. This minimalist configuration connects to multi-armed bandit learning with extremely large discrete action space, which offers theories to corroborate the experiment findings. The up procedure of the experiment pipeline expanding the minimalist configuration layer by layer, examining the role of each design choice. Experimental results on three LLMs and two reasoning datasets not only reveal new understanding of the design choice but also yield essential insights to shape the area. --- ### HELIOS: Hierarchical Graph Abstraction for Structure-Aware LLM Decompilation Authors: Yonatan Gizachew Achamyeleh, Harsh Thomare, Mohammad Abdullah Al Faruque Published: 2026-01-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.14598v2 Large language models (LLMs) have recently been applied to binary decompilation, yet they still treat code as plain text and ignore the graphs that govern program control flow. This limitation often yields syntactically fragile and logically inconsistent output, especially for optimized binaries. This paper presents \textsc{HELIOS}, a framework that reframes LLM-based decompilation as a structured reasoning task. \textsc{HELIOS} summarizes a binary's control flow and function calls into a hierarchical text representation that spells out basic blocks, their successors, and high-level patterns such as loops and conditionals. This representation is supplied to a general-purpose LLM, along with raw decompiler output, optionally combined with a compiler-in-the-loop that returns error messages when the generated code fails to build. On HumanEval-Decompile for \texttt{x86\_64}, \textsc{HELIOS} raises average object file compilability from 45.0\% to 85.2\% for Gemini~2.0 and from 71.4\% to 89.6\% for GPT-4.1~Mini. With compiler feedback, compilability exceeds 94\% and functional correctness improves by up to 5.6 percentage points over text-only prompting. Across six architectures drawn from x86, ARM, and MIPS, \textsc{HELIOS} reduces the spread in functional correctness while keeping syntactic correctness consistently high, all without fine-tuning. These properties make \textsc{HELIOS} a practical building block for reverse engineering workflows in security settings where analysts need recompilable, semantically faithful code across diverse hardware targets. --- ### Optimality of Staircase Mechanisms for Vector Queries under Differential Privacy Authors: James Melbourne, Mario Diaz, Shahab Asoodeh Published: 2026-01-21 Categories: cs.IT, cs.AI, cs.CR, stat.ML arXiv: https://arxiv.org/abs/2601.14597v1 We study the optimal design of additive mechanisms for vector-valued queries under $ε$-differential privacy (DP). Given only the sensitivity of a query and a norm-monotone cost function measuring utility loss, we ask which noise distribution minimizes expected cost among all additive $ε$-DP mechanisms. Using convex rearrangement theory, we show that this infinite-dimensional optimization problem admits a reduction to a one-dimensional compact and convex family of radially symmetric distributions whose extreme points are the staircase distributions. As a consequence, we prove that for any dimension, any norm, and any norm-monotone cost function, there exists an $ε$-DP staircase mechanism that is optimal among all additive mechanisms. This result resolves a conjecture of Geng, Kairouz, Oh, and Viswanath, and provides a geometric explanation for the emergence of staircase mechanisms as extremal solutions in differential privacy. --- ### IntelliSA: An Intelligent Static Analyzer for IaC Security Smell Detection Using Symbolic Rules and Neural Inference Authors: Qiyue Mei, Michael Fu Published: 2026-01-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.14595v1 Infrastructure as Code (IaC) enables automated provisioning of large-scale cloud and on-premise environments, reducing the need for repetitive manual setup. However, this automation is a double-edged sword: a single misconfiguration in IaC scripts can propagate widely, leading to severe system downtime and security risks. Prior studies have shown that IaC scripts often contain security smells--bad coding patterns that may introduce vulnerabilities--and have proposed static analyzers based on symbolic rules to detect them. Yet, our preliminary analysis reveals that rule-based detection alone tends to over-approximate, producing excessive false positives and increasing the burden of manual inspection. In this paper, we present IntelliSA, an intelligent static analyzer for IaC security smell detection that integrates symbolic rules with neural inference. IntelliSA applies symbolic rules to over-approximate potential smells for broad coverage, then employs neural inference to filter false positives. While an LLM can effectively perform this filtering, reliance on LLM APIs introduces high cost and latency, raises data governance concerns, and limits reproducibility and offline deployment. To address the challenges, we adopt a knowledge distillation approach: an LLM teacher generates pseudo-labels to train a compact student model--over 500x smaller--that learns from the teacher's knowledge and efficiently classifies false positives. We evaluate IntelliSA against two static analyzers and three LLM baselines (Claude-4, Grok-4, and GPT-5) using a human-labeled dataset including 241 security smells across 11,814 lines of real-world IaC code. Experimental results show that IntelliSA achieves the highest F1 score (83%), outperforming baselines by 7-42%. Moreover, IntelliSA demonstrates the best cost-effectiveness, detecting 60% of security smells while inspecting less than 2% of the codebase. --- ### LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning Authors: Lianying Chao, Linfeng Yin, Peiyu Ren, Yifan Jiang, Qiaoyu Ren, Dingcheng Shan, Jing-cheng Pang, Sijie Wu, Xubin Li, Kai Zhang, Xin Chen Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14594v2 Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal temporal coverage while ignoring the uneven events distribution. This motivates a Learnable Frame Selector (LFS) that selects temporally diverse and event-relevant frames. LFS explicitly models temporal importance to balance temporal diversity and event relevance, and employs a stratified strategy to ensure temporal coverage while avoiding clustering. Crucially, LFS leverages caption feedback from frozen video-LLMs to learn frame selection that directly optimizes downstream caption quality. Additionally, we identify the gap between existing benchmark and human's cognition. Thus, we introduce ICH-CC built from carefully designed questions by annotators that reflect human-consistent understanding of video. Experiments indicate that LFS consistently improves detailed video captioning across two representative community benchmarks and ICH-CC, achieving up to 2.0% gains on VDC and over 4% gains on ICH-CC. Moreover, we observe that enhanced captions with LFS leads to improved performance on video question answering. Overall, LFS provides an effective and easy-to-integrate solution for detailed video captioning. --- ### From Volumes to Slices: Computationally Efficient Contrastive Learning for Sequential Abdominal CT Analysis Authors: Po-Kai Chiu, Hung-Hsuan Chen Published: 2026-01-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.14593v1 The requirement for expert annotations limits the effectiveness of deep learning for medical image analysis. Although 3D self-supervised methods like volume contrast learning (VoCo) are powerful and partially address the labeling scarcity issue, their high computational cost and memory consumption are barriers. We propose 2D-VoCo, an efficient adaptation of the VoCo framework for slice-level self-supervised pre-training that learns spatial-semantic features from unlabeled 2D CT slices via contrastive learning. The pre-trained CNN backbone is then integrated into a CNN-LSTM architecture to classify multi-organ injuries. In the RSNA 2023 Abdominal Trauma dataset, 2D-VoCo pre-training significantly improves mAP, precision, recall, and RSNA score over training from scratch. Our framework provides a practical method to reduce the dependency on labeled data and enhance model performance in clinical CT analysis. We release the code for reproducibility. https://github.com/tkz05/2D-VoCo-CT-Classifier --- ### Counterfactual Modeling with Fine-Tuned LLMs for Health Intervention Design and Sensor Data Augmentation Authors: Shovito Barua Soumma, Asiful Arefeen, Stephanie M. Carpenter, Melanie Hingle, Hassan Ghasemzadeh Published: 2026-01-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14590v3 Counterfactual explanations (CFEs) provide human-centric interpretability by identifying the minimal, actionable changes required to alter a machine learning model's prediction. Therefore, CFs can be used as (i) interventions for abnormality prevention and (ii) augmented data for training robust models. We conduct a comprehensive evaluation of CF generation using large language models (LLMs), including GPT-4 (zero-shot and few-shot) and two open-source models-BioMistral-7B and LLaMA-3.1-8B, in both pretrained and fine-tuned configurations. Using the multimodal AI-READI clinical dataset, we assess CFs across three dimensions: intervention quality, feature diversity, and augmentation effectiveness. Fine-tuned LLMs, particularly LLaMA-3.1-8B, produce CFs with high plausibility (up to 99%), strong validity (up to 0.99), and realistic, behaviorally modifiable feature adjustments. When used for data augmentation under controlled label-scarcity settings, LLM-generated CFs substantially restore classifier performance, yielding an average 20% F1 recovery across three scarcity scenarios. Compared with optimization-based baselines such as DiCE, CFNOW, and NICE, LLMs offer a flexible, model-agnostic approach that generates more clinically actionable and semantically coherent counterfactuals. Overall, this work demonstrates the promise of LLM-driven counterfactuals for both interpretable intervention design and data-efficient model training in sensor-based digital health. Impact: SenseCF fine-tunes an LLM to generate valid, representative counterfactual explanations and supplement minority class in an imbalanced dataset for improving model training and boosting model robustness and predictive performance --- ### Designing KRIYA: An AI Companion for Wellbeing Self-Reflection Authors: Shanshan Zhu, Wenxuan Song, Jiayue Melissa Shi, Dong Whi Yoo, Karthik S. Bhat, Koustuv Saha Published: 2026-01-21 Categories: cs.HC, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2601.14589v1 Most personal wellbeing apps present summative dashboards of health and physical activity metrics, yet many users struggle to translate this information into meaningful understanding. These apps commonly support engagement through goals, reminders, and structured targets, which can reinforce comparison, judgment, and performance anxiety. To explore a complementary approach that prioritizes self-reflection, we design KRIYA, an AI wellbeing companion that supports co-interpretive engagement with personal wellbeing data. KRIYA aims to collaborate with users to explore questions, explanations, and future scenarios through features such as Comfort Zone, Detective Mode, and What-If Planning. We conducted semi-structured interviews with 18 college students interacting with a KRIYA prototype using hypothetical data. Our findings show that through KRIYA interaction, users framed engaging with wellbeing data as interpretation rather than performance, experienced reflection as supportive or pressuring depending on emotional framing, and developed trust through transparency. We discuss design implications for AI companions that support curiosity, self-compassion, and reflective sensemaking of personal health data. --- ### Anatomically Guided Latent Diffusion for Brain MRI Progression Modeling Authors: Cheng Wan, Bahram Jafrasteh, Ehsan Adeli, Miaomiao Zhang, Qingyu Zhao Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14584v2 Accurately modeling longitudinal brain MRI progression is crucial for understanding neurodegenerative diseases and predicting individualized structural changes. Existing state-of-the-art approaches, such as Brain Latent Progression (BrLP), often use multi-stage training pipelines with auxiliary conditioning modules but suffer from architectural complexity, suboptimal use of conditional clinical covariates, and limited guarantees of anatomical consistency. We propose Anatomically Guided Latent Diffusion Model (AG-LDM), a segmentation-guided framework that enforces anatomically consistent progression while substantially simplifying the training pipeline. AG-LDM conditions latent diffusion by directly fusing baseline anatomy, noisy follow-up states, and clinical covariates at the input level, a strategy that avoids auxiliary control networks by learning a unified, end-to-end model that represents both anatomy and progression. A lightweight 3D tissue segmentation model (WarpSeg) provides explicit anatomical supervision during both autoencoder fine-tuning and diffusion model training, ensuring consistent brain tissue boundaries and morphometric fidelity. Experiments on 31,713 ADNI longitudinal pairs and zero-shot evaluation on OASIS-3 demonstrate that AG-LDM matches or surpasses more complex diffusion models, achieving highly competitive image quality and 15-20% reduction in volumetric errors in generated images. AG-LDM also exhibits markedly stronger utilization of temporal and clinical covariates (3.5-31.5x higher covariate sensitivity than BrLP) and generates biologically plausible counterfactual trajectories, accurately capturing hallmarks of Alzheimer's progression such as limbic atrophy and ventricular expansion. These results highlight AG-LDM as an efficient, anatomically grounded framework for reliable brain MRI progression modeling. --- ### Place with Intention: An Empirical Attendance Predictive Study of Expo 2025 Osaka, Kansai, Japan Authors: Xiaojie Yang, Dizhi Huang, Hangli Ge, Masahiro Sano, Takeaki Ohdake, Kazuma Hatano, Noboru Koshizuka Published: 2026-01-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14570v1 Accurate forecasting of daily attendance is vital for managing transportation, crowd flows, and services at large-scale international events such as Expo 2025 Osaka, Kansai, Japan. However, existing approaches often rely on multi-source external data (such as weather, traffic, and social media) to improve accuracy, which can lead to unreliable results when historical data are insufficient. To address these challenges, we propose a Transformer-based framework that leverages reservation dynamics, i.e., ticket bookings and subsequent updates within a time window, as a proxy for visitors' attendance intentions, under the assumption that such intentions are eventually reflected in reservation patterns. This design avoids the complexity of multi-source integration while still capturing external influences like weather and promotions implicitly embedded in reservation dynamics. We construct a dataset combining entrance records and reservation dynamics and evaluate the model under both single-channel (total attendance) and two-channel (separated by East and West gates) settings. Results show that separately modeling East and West gates consistently improves accuracy, particularly for short- and medium-term horizons. Ablation studies further confirm the importance of the encoder-decoder structure, inverse-style embedding, and adaptive fusion module. Overall, our findings indicate that reservation dynamics offer a practical and informative foundation for attendance forecasting in large-scale international events. --- ### Social Caption: Evaluating Social Understanding in Multimodal Models Authors: Leena Mathur, Bhaavanaa Thumu, Youssouf Kebe, Louis-Philippe Morency Published: 2026-01-21 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.14569v3 Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL CAPTION, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding. --- ### Breaking the accuracy-resource dilemma: a lightweight adaptive video inference enhancement Authors: Wei Ma, Shaowu Chen, Junjie Ye, Peichang Zhang, Lei Huang Published: 2026-01-21 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.14568v2 Existing video inference (VI) enhancement methods typically aim to improve performance by scaling up model sizes and employing sophisticated network architectures. While these approaches demonstrated state-of-the-art performance, they often overlooked the trade-off of resource efficiency and inference effectiveness, leading to inefficient resource utilization and suboptimal inference performance. To address this problem, a fuzzy controller (FC-r) is developed based on key system parameters and inference-related metrics. Guided by the FC-r, a VI enhancement framework is proposed, where the spatiotemporal correlation of targets across adjacent video frames is leveraged. Given the real-time resource conditions of the target device, the framework can dynamically switch between models of varying scales during VI. Experimental results demonstrate that the proposed method effectively achieves a balance between resource utilization and inference performance. --- ### Scribble-Supervised Medical Image Segmentation with Dynamic Teacher Switching and Hierarchical Consistency Authors: Thanh-Huy Nguyen, Hoang-Loc Cao, Dat T. Chung, Mai-Anh Vu, Thanh-Minh Nguyen, Minh Le, Phat K. Huynh, Ulas Bagci Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.14563v3 Scribble-supervised methods have emerged to mitigate the prohibitive annotation burden in medical image segmentation. However, the inherent sparsity of these annotations introduces significant ambiguity, which results in noisy pseudo-label propagation and hinders the learning of robust anatomical boundaries. To address this challenge, we propose SDT-Net, a novel dual-teacher, single-student framework designed to maximize supervision quality from these weak signals. Our method features a Dynamic Teacher Switching (DTS) module to adaptively select the most reliable teacher. This selected teacher then guides the student via two synergistic mechanisms: high-confidence pseudo-labels, refined by a Pick Reliable Pixels (PRP) mechanism, and multi-level feature alignment, enforced by a Hierarchical Consistency (HiCo) module. Extensive experiments on the ACDC and MSCMRseg datasets demonstrate that SDT-Net achieves state-of-the-art performance, producing more accurate and anatomically plausible segmentation. --- ### Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education Authors: Unggi Lee, Jiyeong Bae, Jaehyeon Park, Haeun Park, Taejun Park, Younghoon Jeon, Sungmin Cho, Junbo Koh, Yeil Jeong, Gyeonggeon Lee Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.14560v1 Large language models (LLMs) are increasingly deployed as intelligent tutoring systems, yet research on optimizing LLMs specifically for educational contexts remains limited. Recent works have proposed reinforcement learning approaches for training LLM tutors, but these methods focus solely on optimizing visible responses while neglecting the model's internal thinking process. We introduce PedagogicalRL-Thinking, a framework that extends pedagogical alignment to reasoning LLMs in education through two novel approaches: (1) Pedagogical Reasoning Prompting, which guides internal reasoning using domain-specific educational theory rather than generic instructions; and (2) Thinking Reward, which explicitly evaluates and reinforces the pedagogical quality of the model's reasoning traces. Our experiments reveal that domain-specific, theory-grounded prompting outperforms generic prompting, and that Thinking Reward is most effective when combined with pedagogical prompting. Furthermore, models trained only on mathematics tutoring dialogues show improved performance on educational benchmarks not seen during training, while preserving the base model's factual knowledge. Our quantitative and qualitative analyses reveal that pedagogical thinking reward produces systematic reasoning trace changes, with increased pedagogical reasoning and more structured instructional decision-making in the tutor's thinking process. --- ### Constructing Multi-label Hierarchical Classification Models for MITRE ATT&CK Text Tagging Authors: Andrew Crossman, Jonah Dodd, Viralam Ramamurthy Chaithanya Kumar, Riyaz Mohammed, Andrew R. Plummer, Chandra Sekharudu, Deepak Warrier, Mohammad Yekrangian Published: 2026-01-21 Categories: cs.LG, cs.CR arXiv: https://arxiv.org/abs/2601.14556v1 MITRE ATT&CK is a cybersecurity knowledge base that organizes threat actor and cyber-attack information into a set of tactics describing the reasons and goals threat actors have for carrying out attacks, with each tactic having a set of techniques that describe the potential methods used in these attacks. One major application of ATT&CK is the use of its tactic and technique hierarchy by security specialists as a framework for annotating cyber-threat intelligence reports, vulnerability descriptions, threat scenarios, inter alia, to facilitate downstream analyses. To date, the tagging process is still largely done manually. In this technical note, we provide a stratified "task space" characterization of the MITRE ATT&CK text tagging task for organizing previous efforts toward automation using AIML methods, while also clarifying pathways for constructing new methods. To illustrate one of the pathways, we use the task space strata to stage-wise construct our own multi-label hierarchical classification models for the text tagging task via experimentation over general cyber-threat intelligence text -- using shareable computational tools and publicly releasing the models to the security community (via https://github.com/jpmorganchase/MITRE_models). Our multi-label hierarchical approach yields accuracy scores of roughly 94% at the tactic level, as well as accuracy scores of roughly 82% at the technique level. The models also meet or surpass state-of-the-art performance while relying only on classical machine learning methods -- removing any dependence on LLMs, RAG, agents, or more complex hierarchical approaches. Moreover, we show that GPT-4o model performance at the tactic level is significantly lower (roughly 60% accuracy) than our own approach. We also extend our baseline model to a corpus of threat scenarios for financial applications produced by subject matter experts. --- ### Self-Blinding and Counterfactual Self-Simulation Mitigate Biases and Sycophancy in Large Language Models Authors: Brian Christian, Matan Mazor Published: 2026-01-21 Categories: cs.CL, cs.AI, cs.CY arXiv: https://arxiv.org/abs/2601.14553v1 Fair decisions require ignoring irrelevant, potentially biasing, information. To achieve this, decision-makers need to approximate what decision they would have made had they not known certain facts, such as the gender or race of a job candidate. This counterfactual self-simulation is notoriously hard for humans, leading to biased judgments even by well-meaning actors. Here we show that large language models (LLMs) suffer from similar limitations in their ability to approximate what decisions they would make under counterfactual knowledge in offsetting gender and race biases and overcoming sycophancy. We show that prompting models to ignore or pretend not to know biasing information fails to offset these biases and occasionally backfires. However, unlike humans, LLMs can be given access to a ground-truth model of their own counterfactual cognition -- their own API. We show that this access to the responses of a blinded replica enables fairer decisions, while providing greater transparency to distinguish implicit from intentionally biased behavior. --- ### QMC: Efficient SLM Edge Inference via Outlier-Aware Quantization and Emergent Memories Co-Design Authors: Nilesh Prasad Pandey, Jangseon Park, Onat Gungor, Flavio Ponzina, Tajana Rosing Published: 2026-01-21 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.14549v1 Deploying Small Language Models (SLMs) on edge platforms is critical for real-time, privacy-sensitive generative AI, yet constrained by memory, latency, and energy budgets. Quantization reduces model size and cost but suffers from device noise in emerging non-volatile memories, while conventional memory hierarchies further limit efficiency. SRAM provides fast access but has low density, DRAM must simultaneously accommodate static weights and dynamic KV caches, which creates bandwidth contention, and Flash, although dense, is primarily used for initialization and remains inactive during inference. These limitations highlight the need for hybrid memory organizations tailored to LLM inference. We propose Outlier-aware Quantization with Memory Co-design (QMC), a retraining-free quantization with a novel heterogeneous memory architecture. QMC identifies inlier and outlier weights in SLMs, storing inlier weights in compact multi-level Resistive-RAM (ReRAM) while preserving critical outliers in high-precision on-chip Magnetoresistive-RAM (MRAM), mitigating noise-induced degradation. On language modeling and reasoning benchmarks, QMC outperforms and matches state-of-the-art quantization methods using advanced algorithms and hybrid data formats, while achieving greater compression under both algorithm-only evaluation and realistic deployment settings. Specifically, compared against SoTA quantization methods on the latest edge AI platform, QMC reduces memory usage by 6.3x-7.3x, external data transfers by 7.6x, energy by 11.7x, and latency by 12.5x when compared to FP16, establishing QMC as a scalable, deployment-ready co-design for efficient on-device inference. --- ### Translational Gaps in Graph Transformers for Longitudinal EHR Prediction: A Critical Appraisal of GT-BEHRT Authors: Krish Tadigotla Published: 2026-01-20 Categories: cs.LG, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2603.13231v1 Transformer-based models have improved predictive modeling on longitudinal electronic health records through large-scale self-supervised pretraining. However, most EHR transformer architectures treat each clinical encounter as an unordered collection of codes, which limits their ability to capture meaningful relationships within a visit. Graph-transformer approaches aim to address this limitation by modeling visit-level structure while retaining the ability to learn long-term temporal patterns. This paper provides a critical review of GT-BEHRT, a graph-transformer architecture evaluated on MIMIC-IV intensive care outcomes and heart failure prediction in the All of Us Research Program. We examine whether the reported performance gains reflect genuine architectural benefits and whether the evaluation methodology supports claims of robustness and clinical relevance. We analyze GT-BEHRT across seven dimensions relevant to modern machine learning systems, including representation design, pretraining strategy, cohort construction transparency, evaluation beyond discrimination, fairness assessment, reproducibility, and deployment feasibility. GT-BEHRT reports strong discrimination for heart failure prediction within 365 days, with AUROC 94.37 +/- 0.20, AUPRC 73.96 +/- 0.83, and F1 64.70 +/- 0.85. Despite these results, we identify several important gaps, including the lack of calibration analysis, incomplete fairness evaluation, sensitivity to cohort selection, limited analysis across phenotypes and prediction horizons, and limited discussion of practical deployment considerations. Overall, GT-BEHRT represents a meaningful architectural advance in EHR representation learning, but more rigorous evaluation focused on calibration, fairness, and deployment is needed before such models can reliably support clinical decision-making. --- ### Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark Authors: Daniel Dobriy, Frederik Bauer, Amr Azzam, Debayan Banerjee, Axel Polleres Published: 2026-01-20 Categories: cs.IR, cs.AI, cs.MA arXiv: https://arxiv.org/abs/2603.06582v2 Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted "agentic" AI applications, which, powered by LLMs' planning capabilities, promise to solve complex tasks with the access of external tools and data sources. In this context, publicly available SPARQL endpoints offer a natural connection to combine various data sources through MCP by (a) implementing a standardised protocol and query language, (b) standardised metadata formats, and (c) the native capability to federate queries. In the present paper, we explore the potential of SPARQL-MCP-based intelligent agents to facilitate federated SPARQL querying: firstly, we discuss how to extend an existing Knowledge Graph Question Answering benchmark towards agentic federated Knowledge Graph Question Answering (FKGQA); secondly, we implement and evaluate the ability of integrating SPARQL federation with LLM agents via MCP (incl. endpoint discovery/source selection, schema exploration, and query formulation), comparing different architectural options against the extended benchmark. Our work complements and extends prior work on automated SPARQL query federation towards fruitful combinations with agentic AI. --- ### What Do LLMs Know About Alzheimer's Disease? Multi-loss Fine-Tuning and Probing for AD Detection Authors: Lei Jiang, Yue Zhou, Natalie Parde Published: 2026-01-20 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2602.11177v2 Reliable early detection of Alzheimer's disease (AD) is challenging, particularly due to the limited availability of labeled data. While large language models (LLMs) have shown strong transfer capabilities across do mains, adapting them to the AD domain through supervised fine-tuning remains largely unexplored. In this work, we empirically evaluate various model architectures across three heterogeneous transcript corpora (Pitt, CCC, ADRC) to investigate their effectiveness for text-based AD detection and analyze how task-relevant information is encoded within their internal representations. To the best of our knowledge, our fine-tuned BERT and T5 models establish a new state-of-the-art on the Pitt and CCC datasets, while achieving strong performance on ADRC. In parallel, the decoder-only Llama-1B achieves highly competitive results comparable to BERT and T5 across all three corpora, highlighting its effectiveness for AD detection. We further conduct a comprehensive evaluation of the Llama-1B backbone, analyzing cross-corpus transferability, optimal input chunk-size granularity, and the impact of clinical transcript markers. Also, we use linear probing to empirically show that fine-tuning shifts the representations of individual tokens, both linguistic markers and content words, in ways that reflect AD-related signal. --- ### Evaluating Few-Shot Temporal Reasoning of LLMs for Human Activity Prediction in Smart Environments Authors: Maral Doctorarastoo, Katherine A. Flanigan, Mario Bergés, Christopher McComb Published: 2026-01-20 Categories: cs.CL, cs.AI, cs.CE, cs.LG arXiv: https://arxiv.org/abs/2602.11176v1 Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration, where adaptive systems must respond to human activities. Existing data-driven agent-based models--from rule-based to deep learning--struggle in low-data environments, limiting their practicality. This paper investigates whether large language models, pre-trained on broad human knowledge, can fill this gap by reasoning about everyday activities from compact contextual cues. We adopt a retrieval-augmented prompting strategy that integrates four sources of context--temporal, spatial, behavioral history, and persona--and evaluate it on the CASAS Aruba smart-home dataset. The evaluation spans two complementary tasks: next-activity prediction with duration estimation, and multi-step daily sequence generation, each tested with various numbers of few-shot examples provided in the prompt. Analyzing few-shot effects reveals how much contextual supervision is sufficient to balance data efficiency and predictive accuracy, particularly in low-data environments. Results show that large language models exhibit strong inherent temporal understanding of human behavior: even in zero-shot settings, they produce coherent daily activity predictions, while adding one or two demonstrations further refines duration calibration and categorical accuracy. Beyond a few examples, performance saturates, indicating diminishing returns. Sequence-level evaluation confirms consistent temporal alignment across few-shot conditions. These findings suggest that pre-trained language models can serve as promising temporal reasoners, capturing both recurring routines and context-dependent behavioral variations, thereby strengthening the behavioral modules of agent-based models. --- ### Sparse Adapter Fusion for Continual Learning in NLP Authors: Min Zeng, Xi Chen, Haiqin Yang, Yike Guo Published: 2026-01-20 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2602.02502v1 Continual learning in natural language processing plays a crucial role in adapting to evolving data and preventing catastrophic forgetting. Despite significant progress, existing methods still face challenges, such as inefficient parameter reuse across tasks, risking catastrophic forgetting when tasks are dissimilar, and the unnecessary introduction of new parameters for each task, which hampers knowledge sharing among similar tasks. To tackle these issues, we propose a Sparse Adapter Fusion Method (SAFM), which dynamically fuses old and new adapters to address these challenges. SAFM operates in two stages: the decision stage and the tuning stage. In the decision stage, SAFM determines whether to incorporate a new adapter, reuse an existing one, or add an empty adapter. The architecture search procedure, designed to prioritize reusing or adding empty adapters, minimizes parameter consumption and maximizes reuse. In the tuning stage, SAFM especially facilitates a layer-wise loss to encourage differentiation between adapters, effectively capturing knowledge within the same task. Experimental results consistently show that SAFM outperforms state-of-the-art (SOTA) methods, achieving comparable performance while utilizing less than 60% of the parameters. ---