# Research Papers — 2026-01 · bundle page 104 of 189

> Full-text markdown of papers #5151–5200 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/104
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/103.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/105.md)

### Your One-Stop Solution for AI-Generated Video Detection

Authors: Long Ma, Zihao Xue, Yan Wang, Zhiyuan Yan, Jin Xu, Xiaorui Jiang, Haiyang Yu, Yong Liao, Zhen Bi
Published: 2026-01-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.11035v1

Recent advances in generative modeling can create remarkably realistic synthetic videos, making it increasingly difficult for humans to distinguish them from real ones and necessitating reliable detection methods. However, two key limitations hinder the development of this field. \textbf{From the dataset perspective}, existing datasets are often limited in scale and constructed using outdated or narrowly scoped generative models, making it difficult to capture the diversity and rapid evolution of modern generative techniques. Moreover, the dataset construction process frequently prioritizes quantity over quality, neglecting essential aspects such as semantic diversity, scenario coverage, and technological representativeness. \textbf{From the benchmark perspective}, current benchmarks largely remain at the stage of dataset creation, leaving many fundamental issues and in-depth analysis yet to be systematically explored. Addressing this gap, we propose AIGVDBench, a benchmark designed to be comprehensive and representative, covering \textbf{31} state-of-the-art generation models and over \textbf{440,000} videos. By executing more than \textbf{1,500} evaluations on \textbf{33} existing detectors belonging to four distinct categories. This work presents \textbf{8 in-depth analyses} from multiple perspectives and identifies \textbf{4 novel findings} that offer valuable insights for future research. We hope this work provides a solid foundation for advancing the field of AI-generated video detection. Our benchmark is open-sourced at https://github.com/LongMa-2025/AIGVDBench.

---

### IDDR-NGP: Incorporating Detectors for Distractor Removal with Instant Neural Radiance Field

Authors: Xianliang Huang, Jiajie Gou, Shuhang Chen, Zhizhou Zhong, Jihong Guan, Shuigeng Zhou
Published: 2026-01-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.11030v1

This paper presents the first unified distractor removal method, named IDDR-NGP, which directly operates on Instant-NPG. The method is able to remove a wide range of distractors in 3D scenes, such as snowflakes, confetti, defoliation and petals, whereas existing methods usually focus on a specific type of distractors. By incorporating implicit 3D representations with 2D detectors, we demonstrate that it is possible to efficiently restore 3D scenes from multiple corrupted images. We design the learned perceptual image patch similarity~( LPIPS) loss and the multi-view compensation loss (MVCL) to jointly optimize the rendering results of IDDR-NGP, which could aggregate information from multi-view corrupted images. All of them can be trained in an end-to-end manner to synthesize high-quality 3D scenes. To support the research on distractors removal in implicit 3D representations, we build a new benchmark dataset that consists of both synthetic and real-world distractors. To validate the effectiveness and robustness of IDDR-NGP, we provide a wide range of distractors with corresponding annotated labels added to both realistic and synthetic scenes. Extensive experimental results demonstrate the effectiveness and robustness of IDDR-NGP in removing multiple types of distractors. In addition, our approach achieves results comparable with the existing SOTA desnow methods and is capable of accurately removing both realistic and synthetic distractors.

---

### A Quantum-Driven Evolutionary Framework for Solving High-Dimensional Sharpe Ratio Portfolio Optimization

Authors: Mingyang Yu, Jiaqi Zhang, Haorui Yang, Adam Slowik, Jun Zhang, Jing Xu
Published: 2026-01-16
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.11029v3

High-dimensional portfolio optimization faces significant computational challenges under complex constraints, with traditional optimization methods struggling to balance convergence speed and global exploration capability. To address this, firstly, we introduce an enhanced Sharpe ratio-based model that incorporates all constraints into the objective function using adaptive penalty terms, transforming the original constrained problem into an unconstrained single-objective formulation. This approach preserves financial interpretability while simplifying algorithmic implementation. To efficiently solve the resulting high-dimensional optimization problem, we develop a Quantum Hybrid Differential Evolution (QHDE) algorithm, which introduces a dynamic quantum tunneling mechanism that enables individuals to probabilistically escape local optima, dramatically enhancing global exploration and solution flexibility. To further improve performance, a good point set-chaos reverse learning strategy generates a well-dispersed initial population, providing a robust and diverse starting point. Meanwhile, a dynamic elite pool combined with Cauchy-Gaussian hybrid perturbations maintains population diversity and mitigates premature convergence, ensuring stable and high-quality solutions. Experimental validation on CEC benchmarks and real-world portfolios involving 20 to 80 assets demonstrates that QHDE's performance improves by up to 96.6%. It attains faster convergence, higher solution precision, and greater robustness than seven state-of-the-art counterparts, thereby confirming its suitability for complex, high-dimensional portfolio optimization.

---

### AVP-Pro: An Adaptive Multi-Modal Fusion and Contrastive Learning Approach for Comprehensive Two-Stage Antiviral Peptide Identification

Authors: Xinru Wen, Weizhong Lin, zi liu, Xuan Xiao
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.11028v1

The accurate identification of antiviral peptides (AVPs) is crucial for novel drug development. However, existing methods still have limitations in capturing complex sequence dependencies and distinguishing confusing samples with high similarity. To address these challenges, we propose AVP-Pro, a novel two-stage predictive framework that integrates adaptive feature fusion and contrastive learning. To comprehensively capture the physicochemical properties and deep-seated patterns of peptide sequences, we constructed a panoramic feature space encompassing 10 distinct descriptors and designed a hierarchical fusion architecture. This architecture integrates self-attention and adaptive gating mechanisms to dynamically modulate the weights of local motifs extracted by CNNs and global dependencies captured by BiLSTMs based on sequence context. Targeting the blurred decision boundary caused by the high similarity between positive and negative sample sequences, we adopted an Online Hard Example Mining (OHEM)-driven contrastive learning strategy enhanced by BLOSUM62. This approach significantly sharpened the model's discriminative power. Model evaluation results show that in the first stage of general AVP identification, the model achieved an accuracy of 0.9531 and an MCC of 0.9064, outperforming existing state-of-the-art (SOTA) methods. In the second stage of functional subtype prediction, combined with a transfer learning strategy, the model realized accurate classification of 6 viral families and 8 specific viruses under small-sample conditions. AVP-Pro provides a powerful and interpretable new tool for the high-throughput screening of antiviral drugs. To further enhance accessibility for users, we have developed a user-friendly web interface, which is available at https://wwwy1031-avp-pro.hf.space.

---

### Matching High-Dimensional Geometric Quantiles for Test-Time Adaptation of Transformers and Convolutional Networks Alike

Authors: Sravan Danda, Aditya Challa, Shlok Mehendale, Snehanshu Saha
Published: 2026-01-16
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2601.11022v1

Test-time adaptation (TTA) refers to adapting a classifier for the test data when the probability distribution of the test data slightly differs from that of the training data of the model. To the best of our knowledge, most of the existing TTA approaches modify the weights of the classifier relying heavily on the architecture. It is unclear as to how these approaches are extendable to generic architectures. In this article, we propose an architecture-agnostic approach to TTA by adding an adapter network pre-processing the input images suitable to the classifier. This adapter is trained using the proposed quantile loss. Unlike existing approaches, we correct for the distribution shift by matching high-dimensional geometric quantiles. We prove theoretically that under suitable conditions minimizing quantile loss can learn the optimal adapter. We validate our approach on CIFAR10-C, CIFAR100-C and TinyImageNet-C by training both classic convolutional and transformer networks on CIFAR10, CIFAR100 and TinyImageNet datasets.

---

### Combating Spurious Correlations in Graph Interpretability via Self-Reflection

Authors: Kecheng Cai, Chenyang Xu, Chao Peng, Jiafu Huang, Qiyuan Liang, Irene Zheng
Published: 2026-01-16
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.11021v2

Interpretable graph learning has recently emerged as a popular research topic in machine learning. The goal is to identify the important nodes and edges of an input graph that are crucial for performing a specific graph reasoning task. A number of studies have been conducted in this area, and various benchmark datasets have been proposed to facilitate evaluation. Among them, one of the most challenging is the Spurious-Motif benchmark, introduced at ICLR 2022. The datasets in this synthetic benchmark are deliberately designed to include spurious correlations, making it particularly difficult for models to distinguish truly relevant structures from misleading patterns. As a result, existing methods exhibit significantly worse performance on this benchmark compared to others. In this paper, we focus on improving interpretability on the challenging Spurious-Motif datasets. We demonstrate that the self-reflection technique, commonly used in large language models to tackle complex tasks, can also be effectively adapted to enhance interpretability in datasets with strong spurious correlations. Specifically, we propose a self-reflection framework that can be integrated with existing interpretable graph learning methods. When such a method produces importance scores for each node and edge, our framework feeds these predictions back into the original method to perform a second round of evaluation. This iterative process mirrors how large language models employ self-reflective prompting to reassess their previous outputs. We further analyze the reasons behind this improvement from the perspective of graph representation learning, which motivates us to propose a fine-tuning training method based on this feedback mechanism.

---

### From Interpretability to Performance: Optimizing Retrieval Heads for Long-Context Language Models

Authors: Youmi Ma, Naoaki Okazaki
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.11020v3

Advances in mechanistic interpretability have identified special attention heads, known as retrieval heads, that are responsible for retrieving information from the context. However, the role of these retrieval heads in improving model performance remains unexplored. This work investigates whether retrieval heads can be leveraged to enhance the long-context capabilities of LLMs. Specifically, we propose RetMask, a method that generates training signals by contrasting normal model outputs with those from an ablated variant in which the retrieval heads are masked. This mechanism-based approach achieves substantial improvements: +2.28 points on HELMET at 128K for Llama-3.1, with +70% gains on generation with citation and +32% on passage re-ranking, while preserving performance on general tasks. Experiments across four models in three families demonstrate that RetMask consistently improves long-context performance, where gains correlate with the sparsity of the retrieval score distribution: models with sparser distributions, where retrieval capabilities are concentrated in a small set of heads, respond more strongly, while those with less sparse distributions show more modest gains. These results validate the functional role of retrieval heads and show that mechanistic insights can be transformed into performance enhancements.

---

### Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs

Authors: Xinwei Wu, Heng Liu, Xiaohu Zhao, Yuqi Ren, Linlong Xu, Longyue Wang, Deyi Xiong, Weihua Luo, Kaifu Zhang
Published: 2026-01-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.11019v1

Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning. However, the internal mechanisms governing this innate capability remain largely opaque. To demystify this process, we leverage Sparse Autoencoders (SAEs) and introduce a novel framework for identifying task-specific features. Our method first recalls features that are frequently co-activated on translation inputs and then filters them for functional coherence using a PCA-based consistency metric. This framework successfully isolates a small set of **translation initiation** features. Causal interventions demonstrate that amplifying these features steers the model towards correct translation, while ablating them induces hallucinations and off-task outputs, confirming they represent a core component of the model's innate translation competency. Moving from analysis to application, we leverage this mechanistic insight to propose a new data selection strategy for efficient fine-tuning. Specifically, we prioritize training on **mechanistically hard** samples-those that fail to naturally activate the translation initiation features. Experiments show this approach significantly improves data efficiency and suppresses hallucinations. Furthermore, we find these mechanisms are transferable to larger models of the same family. Our work not only decodes a core component of the translation mechanism in LLMs but also provides a blueprint for using internal model mechanism to create more robust and efficient models. The codes are available at https://github.com/flamewei123/AAAI26-translation-Initiation-Features.

---

### KOCOBrain: Kuramoto-Guided Graph Network for Uncovering Structure-Function Coupling in Adolescent Prenatal Drug Exposure

Authors: Badhan Mazumder, Lei Wu, Sir-Lord Wiafe, Vince D. Calhoun, Dong Hye Ye
Published: 2026-01-16
Categories: q-bio.NC, cs.CV
arXiv: https://arxiv.org/abs/2601.11018v2

Exposure to psychoactive substances during pregnancy, such as cannabis, can disrupt neurodevelopment and alter large-scale brain networks, yet identifying their neural signatures remains challenging. We introduced KOCOBrain: KuramotO COupled Brain Graph Network; a unified graph neural network framework that integrates structural and functional connectomes via Kuramoto-based phase dynamics and cognition-aware attention. The Kuramoto layer models neural synchronization over anatomical connections, generating phase-informed embeddings that capture structure-function coupling, while cognitive scores modulate information routing in a subject-specific manner followed by a joint objective enhancing robustness under class imbalance scenario. Applied to the ABCD cohort, KOCOBrain improved prenatal drug exposure prediction over relevant baselines and revealed interpretable structure-function patterns that reflect disrupted brain network coordination associated with early exposure.

---

### Contextual Distributionally Robust Optimization with Causal and Continuous Structure

Authors: Fenglin Zhang, Jie Wang
Published: 2026-01-16
Categories: stat.ML, cs.AI, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.11016v3

We propose a framework for contextual distributionally robust optimization (DRO) that considers the causal and continuous structure of the underlying distribution, and we develop an interpretable and tractable decision rule. We first introduce the causal Sinkhorn discrepancy (CSD), an entropy-regularized causal Wasserstein distance that encourages continuous transport plans while preserving causal consistency. We then formulate a contextual DRO model with a CSD-based ambiguity set, termed Causal Sinkhorn DRO (Causal-SDRO), and derive its strong dual reformulation, where the worst-case distribution is characterized as a mixture of Gibbs distributions. To obtain an (infinite-dimensional) optimal policy, we propose a soft regression forest (SRF) decision rule: it preserves the interpretability of classical decision trees while being fully parametric, differentiable, and Lipschitz-smooth, enabling intrinsic interpretation from both global and local perspectives. To solve the Causal-SDRO with parametric decision rules, we develop an efficient stochastic compositional gradient algorithm that converges to an $\varepsilon$-stationary point at a rate of $\mathcal{O}(\varepsilon^{-4})$, matching that of standard stochastic gradient descent. Finally, we validate our method through numerical experiments on synthetic and real-world datasets, demonstrating its superior performance and interpretability.

---

### Efficient Protein Optimization via Structure-aware Hamiltonian Dynamics

Authors: Jiahao Wang, Shuangjia Zheng
Published: 2026-01-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.11012v1

The ability to engineer optimized protein variants has transformative potential for biotechnology and medicine. Prior sequence-based optimization methods struggle with the high-dimensional complexities due to the epistasis effect and the disregard for structural constraints. To address this, we propose HADES, a Bayesian optimization method utilizing Hamiltonian dynamics to efficiently sample from a structure-aware approximated posterior. Leveraging momentum and uncertainty in the simulated physical movements, HADES enables rapid transition of proposals toward promising areas. A position discretization procedure is introduced to propose discrete protein sequences from such a continuous state system. The posterior surrogate is powered by a two-stage encoder-decoder framework to determine the structure and function relationships between mutant neighbors, consequently learning a smoothed landscape to sample from. Extensive experiments demonstrate that our method outperforms state-of-the-art baselines in in-silico evaluations across most metrics. Remarkably, our approach offers a unique advantage by leveraging the mutual constraints between protein structure and sequence, facilitating the design of protein sequences with similar structures and optimized properties. The code and data are publicly available at https://github.com/GENTEL-lab/HADES.

---

### AdaMARP: An Adaptive Multi-Agent Interaction Framework for General Immersive Role-Playing

Authors: Zhenhua Xu, Dongsheng Chen, Shuo Wang, Jian Li, Chengjie Wang, Meng Han, Yabiao Wang
Published: 2026-01-16
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.11007v2

LLM role-playing aims to portray arbitrary characters in interactive narratives, yet existing systems often suffer from limited immersion and adaptability. They typically under-model dynamic environmental information and assume largely static scenes and casts, offering insufficient support for multi-character orchestration, scene transitions, and on-the-fly character introduction. We propose an adaptive multi-agent role-playing framework, AdaMARP, featuring an immersive message format that interleaves (Thought), (Action), <Environment>, and Speech, together with an explicit Scene Manager that governs role-playing through discrete actions (init_scene, pick_speaker, switch_scene, add_role, end) accompanied by rationales. To train these capabilities, we construct AdaRPSet for the Actor Model and AdaSMSet for supervising orchestration decisions, and introduce AdaptiveBench for trajectory-level evaluation. Experiments across multiple backbones and model scales demonstrate consistent improvements: AdaRPSet enhances character consistency, environment grounding, and narrative coherence, with an 8B actor outperforming several commercial LLMs, while AdaSMSet enables smoother scene transitions and more natural role introductions, surpassing Claude Sonnet 4.5 using only a 14B LLM.

---

### Backdoor Attacks on Multi-modal Contrastive Learning

Authors: Simi D Kuniyilh, Rita Machacy
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.11006v1

Contrastive learning has become a leading self- supervised approach to representation learning across domains, including vision, multimodal settings, graphs, and federated learning. However, recent studies have shown that contrastive learning is susceptible to backdoor and data poisoning attacks. In these attacks, adversaries can manipulate pretraining data or model updates to insert hidden malicious behavior. This paper offers a thorough and comparative review of backdoor attacks in contrastive learning. It analyzes threat models, attack methods, target domains, and available defenses. We summarize recent advancements in this area, underline the specific vulnerabilities inherent to contrastive learning, and discuss the challenges and future research directions. Our findings have significant implications for the secure deployment of systems in industrial and distributed environments.

---

### NOVA: NOise-aware Verbal Confidence CAlibration for Robust Large Language Models in RAG Systems

Authors: Jiayu Liu, Rui Wang, Qing Zong, Yumeng Wang, Cheng Qian, Qingcheng Zeng, Tianshi Zheng, Haochen Shi, Dadi Guo, Baixuan Xu, Chunyang Li, Yangqiu Song
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.11004v4

Accurately assessing model confidence is essential for deploying large language models (LLMs) in mission-critical factual domains. While retrieval-augmented generation (RAG) is widely adopted to improve grounding, confidence calibration in RAG settings remains poorly understood. We conduct a systematic study across four benchmarks, revealing that LLMs exhibit poor calibration performance especially when noisy contexts are retrieved. Specifically, contradictory or irrelevant evidence tends to exacerbate the model's overconfidence issue. To address this, we propose NOVA Rules (NOise-Aware Verbal Confidence CAlibration Rules) to provide a principled foundation for resolving overconfidence under noise. We further design NOVA, a noise-aware calibration framework that synthesizes supervision from ~2K HotpotQA examples guided by these rules. By performing supervised fine-tuning (SFT) with this data, NOVA equips models with intrinsic noise awareness without relying on stronger teacher models. Empirical results show that NOVA yields substantial gains, improving ECE scores by 10.9% in-domain and 8.0% out-of-domain. By bridging the gap between retrieval noise and verbal calibration, NOVA paves the way for both accurate and epistemically reliable LLMs.

---

### Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies

Authors: Qianen Zhang, Zeyu Yang, Satoshi Nakamura
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.11002v1

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four adaptive actions: Sentence_Cut, Drop, Partial_Summarization and Pronominalization, which enable real-time restructuring, omission, and simplification while preserving semantic fidelity. We adapt these actions in a large language model (LLM) framework and construct training references through action-aware prompting. To evaluate both quality and word-level monotonicity, we further develop a latency-aware TTS pipeline that maps textual outputs to speech with realistic timing. Experiments on the ACL60/60 English-Chinese, English-German and English-Japanese benchmarks show that our framework consistently improves semantic metrics and achieves lower delay compared to reference translations and salami-based baselines. Notably, combining Drop and Sentence_Cut leads to consistent improvements in the balance between fluency and latency. These results demonstrate that enriching the action space of LLM-based SiMT provides a promising direction for bridging the gap between human and machine interpretation.

---

### When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Authors: Zhongxiang Sun, Yi Zhan, Chenglei Shen, Weijie Yu, Xiao Zhang, Ming He, Jun Xu
Published: 2026-01-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.11000v1

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.

---

### Exact Constraint Enforcement in Physics-Informed Extreme Learning Machines using Null-Space Projection Framework

Authors: Rishi Mishra, Smriti, Balaji Srinivasan, Sundararajan Natarajan, Ganapathy Krishnamurthi
Published: 2026-01-16
Categories: math.NA, cs.LG
arXiv: https://arxiv.org/abs/2601.10999v2

Physics-informed extreme learning machines (PIELMs) typically impose boundary and initial conditions through penalty terms, yielding only approximate satisfaction that is sensitive to user-specified weights and can propagate errors into the interior solution. This work introduces Null-Space Projected PIELM (NP-PIELM), achieving exact constraint enforcement through algebraic projection in coefficient space. The method exploits the geometric structure of the admissible coefficient manifold, recognizing that it admits a decomposition through the null space of the boundary operator. By characterizing this manifold via a translation-invariant representation and projecting onto the kernel component, optimization is restricted to constraint-preserving directions, transforming the constrained problem into unconstrained least-squares where boundary conditions are satisfied exactly at discrete collocation points. This eliminates penalty coefficients, dual variables, and problem-specific constructions while preserving single-shot training efficiency. Numerical experiments on elliptic and parabolic problems including complex geometries and mixed boundary conditions validate the framework.

---

### Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detection

Authors: Minseo Kang, Seunghwan Park, Dongha Kim
Published: 2026-01-16
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.10993v2

Outlier detection (OD) aims to identify abnormal instances, known as outliers or anomalies, by learning typical patterns of normal data, or inliers. Performing OD under an unsupervised regime-without any information about anomalous instances in the training data-is challenging. A recently observed phenomenon, known as the inlier-memorization (IM) effect, where deep generative models (DGMs) tend to memorize inlier patterns during early training, provides a promising signal for distinguishing outliers. However, existing unsupervised approaches that rely solely on the IM effect still struggle when inliers and outliers are not well-separated or when outliers form dense clusters. To address these limitations, we incorporate active learning to selectively acquire informative labels, and propose IMBoost, a novel framework that explicitly reinforces the IM effect to improve outlier detection. Our method consists of two stages: 1) a warm-up phase that induces and promotes the IM effect, and 2) a polarization phase in which actively queried samples are used to maximize the discrepancy between inlier and outlier scores. In particular, we propose a novel query strategy and tailored loss function in the polarization phase to effectively identify informative samples and fully leverage the limited labeling budget. We provide a theoretical analysis showing that the IMBoost consistently decreases inlier risk while increasing outlier risk throughout training, thereby amplifying their separation. Extensive experiments on diverse benchmark datasets demonstrate that IMBoost not only significantly outperforms state-of-the-art active OD methods but also requires substantially less computational cost.

---

### Constant Metric Scaling in Riemannian Computation

Authors: Kisung You
Published: 2026-01-16
Categories: cs.LG, stat.CO
arXiv: https://arxiv.org/abs/2601.10992v2

Constant rescaling of a Riemannian metric appears in many computational settings, often through a global scale parameter that is introduced either explicitly or implicitly. Although this operation is elementary, its consequences are not always made clear in practice and may be confused with changes in curvature, manifold structure, or coordinate representation. In this note we provide a short, self-contained account of constant metric scaling on arbitrary Riemannian manifolds. We distinguish between quantities that change under such a scaling, including norms, distances, volume elements, and gradient magnitudes, and geometric objects that remain invariant, such as the Levi--Civita connection, geodesics, exponential and logarithmic maps, and parallel transport. We also discuss implications for Riemannian optimization, where constant metric scaling can often be interpreted as a global rescaling of step sizes rather than a modification of the underlying geometry. The goal of this note is purely expository and is intended to clarify how a global metric scale parameter can be introduced in Riemannian computation without altering the geometric structures on which these methods rely.

---

### Reasoning Distillation for Lightweight Automated Program Repair

Authors: Aanand Balasubramanian, Sashank Silwal
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10987v1

We study whether lightweight symbolic reasoning supervision can improve fix type classification in compact automated program repair models. Small code models are attractive for resource-constrained settings, but they typically produce only a single prediction, making it unclear whether they learn meaningful program structure or rely on shallow correlations. We propose a reasoning distillation approach in which a large teacher model provides structured symbolic reasoning tags alongside fix-type labels. These tags capture high-level causal properties of bugs without relying on free-form explanations. We train a CodeT5-based student model under label-only and reasoning-distilled settings on the IntroClass benchmark. Reasoning supervision consistently improves macro averaged performance, particularly on less frequent bug categories, without increasing model size or complexity. We further analyze the relationship between reasoning accuracy and fix-type prediction, showing that correct reasoning traces strongly correlate with correct predictions, while not fully determining them. Our results suggest that symbolic reasoning distillation is a practical way to improve interpretability and robustness in lightweight program repair models.

---

### ZPD Detector: Data Selection via Capability-Difficulty Alignment for Large Language Models

Authors: Bo Yang, Yunkui Chen, Lanfei Feng, Yu Zhang, Shijian Li
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10986v1

As the cost of training large language models continues to increase and high-quality training data become increasingly scarce, selecting high-value samples or synthesizing effective training data under limited data budgets has emerged as a critical research problem. Most existing data selection methods rely on static criteria, such as difficulty, uncertainty, or heuristics, and fail to model the evolving relationship between the model and the data. Inspired by the educational theory of the Zone of Proximal Development (ZPD), we propose ZPD Detector, a data selection framework that adopts a bidirectional perspective between models and data by explicitly modeling the alignment between sample difficulty and the model's current capability. ZPD Detector integrates difficulty calibration, model capability estimation based on Item Response Theory (IRT), and a capability-difficulty matching score to dynamically identify the most informative samples at each learning stage, improving data utilization efficiency; moreover, this dynamic matching strategy provides new insights into training strategy design. All code and data will be released after our work be accepted to support reproducible researc

---

### Toward Adaptive Grid Resilience: A Gradient-Free Meta-RL Framework for Critical Load Restoration

Authors: Zain ul Abdeen, Waris Gill, Ming Jin
Published: 2026-01-16
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2601.10973v1

Restoring critical loads after extreme events demands adaptive control to maintain distribution-grid resilience, yet uncertainty in renewable generation, limited dispatchable resources, and nonlinear dynamics make effective restoration difficult. Reinforcement learning (RL) can optimize sequential decisions under uncertainty, but standard RL often generalizes poorly and requires extensive retraining for new outage configurations or generation patterns. We propose a meta-guided gradient-free RL (MGF-RL) framework that learns a transferable initialization from historical outage experiences and rapidly adapts to unseen scenarios with minimal task-specific tuning. MGF-RL couples first-order meta-learning with evolutionary strategies, enabling scalable policy search without gradient computation while accommodating nonlinear, constrained distribution-system dynamics. Experiments on IEEE 13-bus and IEEE 123-bus test systems show that MGF-RL outperforms standard RL, MAML-based meta-RL, and model predictive control across reliability, restoration speed, and adaptation efficiency under renewable forecast errors. MGF-RL generalizes to unseen outages and renewable patterns while requiring substantially fewer fine-tuning episodes than conventional RL. We also provide sublinear regret bounds that relate adaptation efficiency to task similarity and environmental variation, supporting the empirical gains and motivating MGF-RL for real-time load restoration in renewable-rich distribution grids.

---

### AJAR: Adaptive Jailbreak Architecture for Red-teaming

Authors: Yipu Dou, Wang Yang
Published: 2026-01-16
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2601.10971v2

Large language model (LLM) safety evaluation is moving from content moderation to action security as modern systems gain persistent state, tool access, and autonomous control loops. Existing jailbreak frameworks still leave a gap between adaptive multi-turn attacks and agentic runtimes: attack algorithms are usually packaged as monolithic scripts, while agent harnesses rarely expose explicit abstractions for rollback, tool simulation, or strategy switching. We present AJAR, a red-teaming framework that exposes multi-turn jailbreak algorithms as callable MCP services and lets an Auditor Agent orchestrate them inside a tool-aware runtime built on Petri. AJAR integrates three representative attacks, namely Crescendo, ActorAttack, and X-Teaming, under a shared service interface for planning, prompt generation, optimization, evaluation, and context control. On 200 HarmBench validation behaviors, AJAR improves X-Teaming from 65.0% to 76.0% attack success rate (ASR), reaches 80% cumulative success one turn earlier than the native implementation, and reproduces Crescendo more effectively than PyRIT (91.0% vs. 87.5% ASR). Behavior-level analysis shows that these gains are concentrated in hard categories and frequently depend on rollback-enabled transcript repair. We further show that tool access reshapes rather than uniformly enlarges the attack surface: ActorAttack rises from 51.0% to 56.0% ASR with tools, whereas Crescendo drops from 91.0% to 78.0% and X-Teaming from 76.0% to 55.5%, with the sharpest declines appearing in categories that rely on long semantic buildup. These results position AJAR as a practical foundation for evaluating multi-turn jailbreaks under realistic agent constraints. Code and data are available at https://github.com/douyipu/ajar.

---

### Noise-Driven Exploration and Transient Freezing Select Flat Minima in Stochastic Gradient Descent

Authors: Ning Yang, Yikuan Zhang, Qi Ouyang, Chao Tang, Yuhai Tu
Published: 2026-01-16
Categories: cs.LG, cond-mat.dis-nn
arXiv: https://arxiv.org/abs/2601.10962v2

Stochastic gradient descent (SGD) is central to deep learning, yet the dynamical origin of its preference for flatter, more generalizable solutions remains unclear. Here, by analyzing SGD learning dynamics, we identify a nonequilibrium mechanism that governs solution selection during training. Numerical experiments reveal a transient exploratory phase in which SGD trajectories repeatedly escape sharp valleys and migrate toward flatter regions of the loss landscape before becoming confined to a final basin. Using a tractable physical model, we show that SGD noise reshapes the loss landscape into an effective potential that preferentially stabilizes flat solutions. We further uncover a transient freezing mechanism: as training progresses, the flattening landscape suppresses transitions between competing valleys. Stronger SGD noise delays this freezing transition, prolonging the exploratory phase and thereby increasing the probability of convergence to flatter minima. Together, these results provide a unified physical framework connecting learning dynamics, loss-landscape geometry, and generalization, and suggest guiding principles for the design of more effective optimization algorithms.

---

### Multivariate LSTM-Based Forecasting for Renewable Energy: Enhancing Climate Change Mitigation

Authors: Farshid Kamrani, Kristen Schell
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10961v1

The increasing integration of renewable energy sources (RESs) into modern power systems presents significant opportunities but also notable challenges, primarily due to the inherent variability of RES generation. Accurate forecasting of RES generation is crucial for maintaining the reliability, stability, and economic efficiency of power system operations. Traditional approaches, such as deterministic methods and stochastic programming, frequently depend on representative scenarios generated through clustering techniques like K-means. However, these methods may fail to fully capture the complex temporal dependencies and non-linear patterns within RES data. This paper introduces a multivariate Long Short-Term Memory (LSTM)-based network designed to forecast RESs generation using their real-world historical data. The proposed model effectively captures long-term dependencies and interactions between different RESs, utilizing historical data from both local and neighboring areas to enhance predictive accuracy. In the case study, we showed that the proposed forecasting approach results in lower CO2 emissions, and a more reliable supply of electric loads.

---

### Steering Language Models Before They Speak: Logit-Level Interventions

Authors: Hyeseon An, Shinwoo Park, Hyundong Jin, Yo-Sub Han
Published: 2026-01-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.10960v2

Controllable generation requires language models to realize output characteristics such as reading level, politeness, and toxicity. Existing steering methods are often indirect, require access to internal activations, or depend on auxiliary trained models. We propose SWAI, a training-free inference-time method that addresses these limitations by steering directly in logit space using corpus-derived token statistics. SWAI computes z-normalized one-vs-rest log-odds scores from labeled corpora and biases high-scoring tokens only within the model's top-K candidate set, allowing control to favor target-characteristic tokens while preserving contextually plausible choices. Across readability, politeness, and toxicity control, SWAI consistently improves over prompt-based and prior logit-level baselines without modifying model parameters, accessing internal layers, or training an auxiliary model. Selectivity and lookup-table ablations show that the gains come from target-specific statistical scores rather than generic logit perturbation. These results indicate that effective steering does not require learned controllers when the logit intervention is guided by target-specific statistics under high-probability candidates.

---

### Depression Detection Based on Electroencephalography Using a Hybrid Deep Neural Network CNN-GRU and MRMR Feature Selection

Authors: Mohammad Reza Yousefi, Hajar Ismail Al-Tamimi, Amin Dehghani
Published: 2026-01-16
Categories: q-bio.QM, cs.LG
arXiv: https://arxiv.org/abs/2601.10959v1

This study investigates the detection and classification of depressive and non-depressive states using deep learning approaches. Depression is a prevalent mental health disorder that substantially affects quality of life, and early diagnosis can greatly enhance treatment effectiveness and patient care. However, conventional diagnostic methods rely heavily on self-reported assessments, which are often subjective and may lack reliability. Consequently, there is a strong need for objective and accurate techniques to identify depressive states. In this work, a deep learning based framework is proposed for the early detection of depression using EEG signals. EEG data, which capture underlying brain activity and are not influenced by external behavioral factors, can reveal subtle neural changes associated with depression. The proposed approach combines convolutional neural networks (CNNs) and gated recurrent units (GRUs) to jointly extract spatial and temporal features from EEG recordings. The minimum redundancy maximum relevance (MRMR) algorithm is then applied to select the most informative features, followed by classification using a fully connected neural network. The results demonstrate that the proposed model achieves high performance in accurately identifying depressive states, with an overall accuracy of 98.74%. By effectively integrating temporal and spatial information and employing optimized feature selection, this method shows strong potential as a reliable tool for clinical applications. Overall, the proposed framework not only enables accurate early detection of depression but also has the potential to support improved treatment strategies and patient outcomes.

---

### Beyond Max Tokens: Stealthy Resource Amplification via Tool Calling Chains in LLM Agents

Authors: Kaiyu Zhou, Yongsen Zheng, Yicheng He, Meng Xue, Xueluan Gong, Yuji Wang, Xuanye Zhang, Kwok-Yan Lam
Published: 2026-01-16
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.10955v2

The agent--tool interaction loop is a critical attack surface for modern Large Language Model (LLM) agents. Existing denial-of-service (DoS) attacks typically function at the user-prompt or retrieval-augmented generation (RAG) context layer and are inherently single-turn in nature. This limitation restricts cost amplification and diminishes stealth in goal-oriented workflows. To address these issues, we proposed a stealthy, multi-turn economic DoS attack at the tool layer under the Model Context Protocol (MCP). By simply editing text-visible fields and implementing a template-driven return policy, our malicious server preserves function signatures and the terminal benign payload while steering agents into prolonged, verbose tool-calling chains. We optimize these text-only edits with Monte Carlo Tree Search (MCTS) to maximize cost under a task-success constraint. Across six LLMs on ToolBench and BFCL benchmarks, our attack yields trajectories over 60K tokens, increases per-query cost by up to 658 times, raises energy by 100 to 560 times, and pushes GPU key-value (KV) cache occupancy to 35--74%. Standard prompt filters and output trajectory monitors seldom detect these attacks, highlighting the need for defenses that safeguard agentic processes rather than focusing solely on final outcomes. We will release the code soon.

---

### Multi-Stage Patient Role-Playing Framework for Realistic Clinical Interactions

Authors: Shijie Jiang, Zefan Zhang, Kehua Zhu, Tian Bai, Ruihong Zhao
Published: 2026-01-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.10951v1

The simulation of realistic clinical interactions plays a pivotal role in advancing clinical Large Language Models (LLMs) and supporting medical diagnostic education. Existing approaches and benchmarks rely on generic or LLM-generated dialogue data, which limits the authenticity and diversity of doctor-patient interactions. In this work, we propose the first Chinese patient simulation dataset (Ch-PatientSim), constructed from realistic clinical interaction scenarios to comprehensively evaluate the performance of models in emulating patient behavior. Patients are simulated based on a five-dimensional persona structure. To address issues of the persona class imbalance, a portion of the dataset is augmented using few-shot generation, followed by manual verification. We evaluate various state-of-the-art LLMs and find that most produce overly formal responses that lack individual personality. To address this limitation, we propose a training-free Multi-Stage Patient Role-Playing (MSPRP) framework, which decomposes interactions into three stages to ensure both personalization and realism in model responses. Experimental results demonstrate that our approach significantly improves model performance across multiple dimensions of patient simulation.

---

### MMedExpert-R1: Strengthening Multimodal Medical Reasoning via Domain-Specific Adaptation and Clinical Guideline Reinforcement

Authors: Meidan Ding, Jipeng Zhang, Wenxuan Wang, Haiqin Zhong, Xiaoling Luo, Wenting Chen, Linlin Shen
Published: 2026-01-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.10949v2

Medical Vision-Language Models (MedVLMs) excel at perception tasks but struggle with complex clinical reasoning required in real-world scenarios. While reinforcement learning (RL) has been explored to enhance reasoning capabilities, existing approaches face critical mismatches: the scarcity of deep reasoning data, cold-start limits multi-specialty alignment, and standard RL algorithms fail to model clinical reasoning diversity. We propose MMedExpert-R1, a novel reasoning MedVLM that addresses these challenges through domain-specific adaptation and clinical guideline reinforcement. We construct MMedExpert, a high-quality dataset of 10K samples across four specialties with step-by-step reasoning traces. Our Domain-Specific Adaptation (DSA) creates specialty-specific LoRA modules to provide diverse initialization, while Guideline-Based Advantages (GBA) explicitly models different clinical reasoning perspectives to align with real-world diagnostic strategies. Conflict-Aware Capability Integration then merges these specialized experts into a unified agent, ensuring robust multi-specialty alignment. Comprehensive experiments demonstrate state-of-the-art performance, with our 7B model achieving 27.50 on MedXpert-MM and 83.03 on OmniMedVQA, establishing a robust foundation for reliable multimodal medical reasoning systems.

---

### PatientVLM Meets DocVLM: Pre-Consultation Dialogue Between Vision-Language Models for Efficient Diagnosis

Authors: K Lokesh, Abhirama Subramanyam Penamakuri, Uday Agarwal, Apoorva Challa, Shreya K Gowda, Somesh Gupta, Anand Mishra
Published: 2026-01-16
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.10945v1

Traditionally, AI research in medical diagnosis has largely centered on image analysis. While this has led to notable advancements, the absence of patient-reported symptoms continues to hinder diagnostic accuracy. To address this, we propose a Pre-Consultation Dialogue Framework (PCDF) that mimics real-world diagnostic procedures, where doctors iteratively query patients before reaching a conclusion. Specifically, we simulate diagnostic dialogues between two vision-language models (VLMs): a DocVLM, which generates follow-up questions based on the image and dialogue history, and a PatientVLM, which responds using a symptom profile derived from the ground-truth diagnosis. We additionally conducted a small-scale clinical validation of the synthetic symptoms generated by our framework, with licensed clinicians confirming their clinical relevance, symptom coverage, and overall realism. These findings indicate that the resulting DocVLM-PatientVLM interactions form coherent, multi-turn consultations paired with images and diagnoses, which we then use to fine-tune the DocVLM. This dialogue-based supervision leads to substantial gains over image-only training, highlighting the value of realistic symptom elicitation for diagnosis.

---

### HOSL: Hybrid-Order Split Learning for Memory-Constrained Edge Training

Authors: Aakriti Lnu, Zhe Li, Dandan Liang, Chao Huang, Rui Li, Haibo Yang
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10940v4

Split learning (SL) enables collaborative training of large language models (LLMs) between resource-constrained edge devices and compute-rich servers by partitioning model computation across the network boundary. However, existing SL systems predominantly rely on first-order (FO) optimization, which requires clients to store intermediate quantities such as activations for backpropagation. This results in substantial memory overhead, largely negating benefits of model partitioning. In contrast, zeroth-order (ZO) optimization eliminates backpropagation and significantly reduces memory usage, but often suffers from slow convergence and degraded performance. In this work, we propose HOSL, a novel Hybrid-Order Split Learning framework that addresses this fundamental trade-off between memory efficiency and optimization effectiveness by strategically integrating ZO optimization on the client side with FO optimization on the server side. By employing memory-efficient ZO gradient estimation at the client, HOSL eliminates backpropagation and activation storage, reducing client memory consumption. Meanwhile, server-side FO optimization ensures fast convergence and competitive performance. Theoretically, we show that HOSL achieves an $\mathcal{O}(\sqrt{d_c/TQ})$ rate, which depends on client-side model dimension $d_c$ rather than the full model dimension $d$, demonstrating that convergence improves as more computation is offloaded to the server. Extensive experiments on OPT models (125M and 1.3B parameters) across 6 tasks demonstrate that HOSL reduces client GPU memory by up to 3.7$\times$ compared to the FO method while achieving accuracy within 0.20%-4.23% of this baseline. Furthermore, HOSL outperforms the ZO baseline by up to 15.55%, validating the effectiveness of our hybrid strategy for memory-efficient training on edge devices.

---

### Sparse Data Tree Canopy Segmentation: Fine-Tuning Leading Pretrained Models on Only 150 Images

Authors: David Szczecina, Hudson Sun, Anthony Bertnyk, Niloofar Azad, Kyle Gao, Lincoln Linlin Xu
Published: 2026-01-16
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.10931v2

Tree canopy detection from aerial imagery is an important task for environmental monitoring, urban planning, and ecosystem analysis. Simulating real-life data annotation scarcity, the Solafune Tree Canopy Detection competition provides a small and imbalanced dataset of only 150 annotated images, posing significant challenges for training deep models without severe overfitting. In this work, we evaluate five representative architectures, YOLOv11, Mask R-CNN, DeepLabv3, Swin-UNet, and DINOv2, to assess their suitability for canopy segmentation under extreme data scarcity. Our experiments show that pretrained convolution-based models, particularly YOLOv11 and Mask R-CNN, generalize significantly better than pretrained transformer-based models. DeeplabV3, Swin-UNet and DINOv2 underperform likely due to differences between semantic and instance segmentation tasks, the high data requirements of Vision Transformers, and the lack of strong inductive biases. These findings confirm that transformer-based architectures struggle in low-data regimes without substantial pretraining or augmentation and that differences between semantic and instance segmentation further affect model performance. We provide a detailed analysis of training strategies, augmentation policies, and model behavior under the small-data constraint and demonstrate that lightweight CNN-based methods remain the most reliable for canopy detection on limited imagery.

---

### Selecting Language Models for Social Science: Start Small, Start Open, and Validate

Authors: Dustin S. Stoltz, Marshall A. Taylor, Sanuj Kumar
Published: 2026-01-16
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.10926v1

Currently, there are thousands of large pretrained language models (LLMs) available to social scientists. How do we select among them? Using validity, reliability, reproducibility, and replicability as guides, we explore the significance of: (1) model openness, (2) model footprint, (3) training data, and (4) model architectures and fine-tuning. While ex-ante tests of validity (i.e., benchmarks) are often privileged in these discussions, we argue that social scientists cannot altogether avoid validating computational measures (ex-post). Replicability, in particular, is a more pressing guide for selecting language models. Being able to reliably replicate a particular finding that entails the use of a language model necessitates reliably reproducing a task. To this end, we propose starting with smaller, open models, and constructing delimited benchmarks to demonstrate the validity of the entire computational pipeline.

---

### Massively Multilingual Joint Segmentation and Glossing

Authors: Michael Ginn, Lindia Tjuatja, Enora Rice, Ali Marashian, Maria Valentini, Jasmine Xu, Graham Neubig, Alexis Palmer
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10925v3

Automated interlinear gloss prediction with neural networks is a promising approach to accelerate language documentation efforts. However, while state-of-the-art models like GlossLM achieve high scores on glossing benchmarks, user studies with linguists have found critical barriers to the usefulness of such models in real-world scenarios. In particular, existing models typically generate morpheme-level glosses but assign them to whole words without predicting the actual morpheme boundaries, making the predictions less interpretable and thus untrustworthy to human annotators. We conduct the first study on neural models that jointly predict interlinear glosses and the corresponding morphological segmentation from raw text. We run experiments to determine the optimal way to train models that balance segmentation and glossing accuracy, as well as the alignment between the two tasks. We extend the training corpus of GlossLM and pretrain PolyGloss, a family of seq2seq multilingual models for joint segmentation and glossing that outperforms GlossLM on glossing and beats various open-source LLMs on segmentation, glossing, and alignment. In addition, we demonstrate that PolyGloss can be quickly adapted to a new dataset via low-rank adaptation.

---

### Data-Efficient Curation for Multimodal Reasoning under Fixed Training Protocols

Authors: Yosub Shin, Michael Buriek, Boris Sobolev, Pavel Bushuyeu, Vikas Kumar, Haoyang Xu, Samuel Watson, Igor Molybog
Published: 2026-01-16
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10922v2

We study data curation for multimodal reasoning in a fixed-protocol fine-tuning regime, where the base model, optimizer, training schedule, and evaluation pipeline are held constant and the main degree of freedom is the training data. Using the NeurIPS 2025 Data Curation for Vision--Language Reasoning (DCVLR) challenge as a controlled testbed, we analyze how source-dataset alignment, model-relative difficulty, dataset size, diversity heuristics, and rewritten synthetic mixtures affect downstream reasoning accuracy. Among the tested interventions, difficulty filtering on an aligned source corpus provides the strongest gains at matched scale. The effect is not explained only by LiveXivTQA weighting: a per-benchmark decomposition shows that much of the improvement over random sampling comes from OlympiadBench, the largest non-LiveXivTQA benchmark. Qwen-derived difficulty scores also transfer to some additional model families, though the benefit is architecture-dependent. In contrast, increasing dataset size beyond roughly 1k aligned examples mainly reduces run-to-run variance under the fixed recipe, while the diversity and rewritten CoSyn mixtures we tested do not improve over the difficulty-filtered baseline. These results provide a scoped empirical recipe for data-constrained multimodal reasoning fine-tuning, rather than a universal claim about data selection across all training regimes.

---

### RobuMTL: Enhancing Multi-Task Learning Robustness Against Weather Conditions

Authors: Tasneem Shaffee, Sherief Reda
Published: 2026-01-16
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.10921v1

Robust Multi-Task Learning (MTL) is crucial for autonomous systems operating in real-world environments, where adverse weather conditions can severely degrade model performance and reliability. In this paper, we introduce RobuMTL, a novel architecture designed to adaptively address visual degradation by dynamically selecting task-specific hierarchical Low-Rank Adaptation (LoRA) modules and a LoRA expert squad based on input perturbations in a mixture-of-experts fashion. Our framework enables adaptive specialization based on input characteristics, improving robustness across diverse real-world conditions. To validate our approach, we evaluated it on the PASCAL and NYUD-v2 datasets and compared it against single-task models, standard MTL baselines, and state-of-the-art methods. On the PASCAL benchmark, RobuMTL delivers a +2.8% average relative improvement under single perturbations and up to +44.4% under mixed weather conditions compared to the MTL baseline. On NYUD-v2, RobuMTL achieves a +9.7% average relative improvement across tasks. The code is available at GitHub.

---

### Neural Induction of Finite-State Transducers

Authors: Michael Ginn, Alexis Palmer, Mans Hulden
Published: 2026-01-16
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10918v3

Finite-State Transducers (FSTs) are effective models for string-to-string rewriting tasks, often providing the efficiency necessary for high-performance applications, but constructing transducers by hand is difficult. In this work, we propose a novel method for automatically constructing unweighted FSTs following the hidden state geometry learned by a recurrent neural network. We evaluate our methods on real-world datasets for morphological inflection, grapheme-to-phoneme prediction, and historical normalization, showing that the constructed FSTs are highly accurate and robust for many datasets, substantially outperforming classical transducer learning algorithms by up to 87% accuracy on held-out test sets.

---

### Self-learned representation-guided latent diffusion model for breast cancer classification in deep ultraviolet whole surface images

Authors: Pouya Afshin, David Helminiak, Tianling Niu, Julie M. Jorns, Tina Yen, Bing Yu, Dong Hye Ye
Published: 2026-01-16
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.10917v2

Breast-Conserving Surgery (BCS) requires precise intraoperative margin assessment to preserve healthy tissue. Deep Ultraviolet Fluorescence Scanning Microscopy (DUV-FSM) offers rapid, high-resolution surface imaging for this purpose; however, the scarcity of annotated DUV data hinders the training of robust deep learning models. To address this, we propose an Self-Supervised Learning (SSL)-guided Latent Diffusion Model (LDM) to generate high-quality synthetic training patches. By guiding the LDM with embeddings from a fine-tuned DINO teacher, we inject rich semantic details of cellular structures into the synthetic data. We combine real and synthetic patches to fine-tune a Vision Transformer (ViT), utilizing patch prediction aggregation for WSI-level classification. Experiments using 5-fold cross-validation demonstrate that our method achieves 96.47 % accuracy and reduces the FID score to 45.72, significantly outperforming class-conditioned baselines.

---

### A PAC-Bayesian Analysis of Channel-Induced Degradation in Edge Inference

Authors: Yangshuo He, Guanding Yu, Jingge Zhu
Published: 2026-01-16
Categories: cs.IT, cs.LG
arXiv: https://arxiv.org/abs/2601.10915v3

In the emerging paradigm of edge learning, neural networks (NNs) are partitioned across distributed edge devices that collaboratively perform inference via wireless transmission. However, deploying NNs for edge inference over wireless channels inevitably leads to performance degradation, as the exact channel realizations in the inference stage are not known in the training stage. In this paper, we establish a theoretical framework to evaluate and bound this performance degradation. Inspired by statistical learning theory, we define a wireless generalization error to characterize the gap between the empirical performance during training and the expected inference performance under the true stochastic channel. To enable theoretical analysis, we introduce an augmented NN model that incorporates channel statistics directly into the weight space. Leveraging the PAC-Bayesian framework, we derive a high-probability bound on this error, which provides theoretical guarantees for wireless inference performance. Furthermore, we propose a channel-aware training algorithm that minimizes a tractable surrogate objective based on the derived bound. Simulations demonstrate that the proposed algorithm effectively improves wireless inference performance and model robustness under various channel conditions.

---

### FAConvLSTM: Factorized-Attention ConvLSTM for Efficient Feature Extraction in Multivariate Climate Data

Authors: Francis Ndikum Nji, Jianwu Wang
Published: 2026-01-16
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10914v1

Learning physically meaningful spatiotemporal representations from high-resolution multivariate Earth observation data is challenging due to strong local dynamics, long-range teleconnections, multi-scale interactions, and nonstationarity. While ConvLSTM2D is a commonly used baseline, its dense convolutional gating incurs high computational cost and its strictly local receptive fields limit the modeling of long-range spatial structure and disentangled climate dynamics. To address these limitations, we propose FAConvLSTM, a Factorized-Attention ConvLSTM layer designed as a drop-in replacement for ConvLSTM2D that simultaneously improves efficiency, spatial expressiveness, and physical interpretability. FAConvLSTM factorizes recurrent gate computations using lightweight (1 times 1) bottlenecks and shared depthwise spatial mixing, substantially reducing channel complexity while preserving recurrent dynamics. Multi-scale dilated depthwise branches and squeeze-and-excitation recalibration enable efficient modeling of interacting physical processes across spatial scales, while peephole connections enhance temporal precision. To capture teleconnection-scale dependencies without incurring global attention cost, FAConvLSTM incorporates a lightweight axial spatial attention mechanism applied sparsely in time. A dedicated subspace head further produces compact per timestep embeddings refined through temporal self-attention with fixed seasonal positional encoding. Experiments on multivariate spatiotemporal climate data shows superiority demonstrating that FAConvLSTM yields more stable, interpretable, and robust latent representations than standard ConvLSTM, while significantly reducing computational overhead.

---

### Classification of Chest XRay Diseases through image processing and analysis techniques

Authors: Santiago Martínez Novoa, María Catalina Ibáñez, Lina Gómez Mesa, Jeremias Kramer
Published: 2026-01-16
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.10913v1

Multi-Classification Chest X-Ray Images are one of the most prevalent forms of radiological examination used for diagnosing thoracic diseases. In this study, we offer a concise overview of several methods employed for tackling this task, including DenseNet121. In addition, we deploy an open-source web-based application. In our study, we conduct tests to compare different methods and see how well they work. We also look closely at the weaknesses of the methods we propose and suggest ideas for making them better in the future. Our code is available at: https://github.com/AML4206-MINE20242/Proyecto_AML

---

### Slang Context-based Inference Enhancement via Greedy Search-Guided Chain-of-Thought Prompting

Authors: Jinghan Cao, Qingyang Ren, Xiangyun Chen, Xinjin Li, Haoxiang Gao, Yu Zhao
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.13230v1

Slang interpretation has been a challenging downstream task for Large Language Models (LLMs) as the expressions are inherently embedded in contextual, cultural, and linguistic frameworks. In the absence of domain-specific training data, it is difficult for LLMs to accurately interpret slang meaning based on lexical information. This paper attempts to investigate the challenges of slang inference using large LLMs and presents a greedy search-guided chain-of-thought framework for slang interpretation. Through our experiments, we conclude that the model size and temperature settings have limited impact on inference accuracy. Transformer-based models with larger active parameters do not generate higher accuracy than smaller models. Based on the results of the above empirical study, we integrate greedy search algorithms with chain-of-thought prompting for small language models to build a framework that improves the accuracy of slang interpretation. The experimental results indicate that our proposed framework demonstrates improved accuracy in slang meaning interpretation. These findings contribute to the understanding of context dependency in language models and provide a practical solution for enhancing slang comprehension through a structured reasoning prompting framework.

---

### Large Language Model (LLM)-enabled Reinforcement Learning for Wireless Network Optimization

Authors: Jie Zheng, Ruichen Zhang, Dusit Niyato, Haijun Zhang, Jiacheng Wang, Hongyang Du, Jiawen Kang, Zehui Xiong
Published: 2026-01-15
Categories: cs.NI, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.13210v1

Enhancing future wireless networks presents a significant challenge for networking systems due to diverse user demands and the emergence of 6G technology. While reinforcement learning (RL) is a powerful framework, it often encounters difficulties with high-dimensional state spaces and complex environments, leading to substantial computational demands, distributed intelligence, and potentially inconsistent outcomes. Large language models (LLMs), with their extensive pretrained knowledge and advanced reasoning capabilities, offer promising tools to enhance RL in optimizing 6G wireless networks. We explore RL models augmented by LLMs, emphasizing their roles and the potential benefits of their synergy in wireless network optimization. We then examine LLM-enabled RL across various protocol layers: physical, data link, network, transport, and application layers. Additionally, we propose an LLM-assisted state representation and semantic extraction to enhance the multi-agent reinforcement learning (MARL) framework. This approach is applied to service migration and request routing, as well as topology graph generation in unmanned aerial vehicle (UAV)-satellite networks. Through case studies, we demonstrate that our framework effectively performs optimization of wireless network. Finally, we outline prospective research directions for LLM-enabled RL in wireless network optimization.

---

### FeudalNav: A Simple Framework for Visual Navigation

Authors: Faith Johnson, Bryan Bo Cao, Shubham Jain, Ashwin Ashok, Kristin Dana
Published: 2026-01-15
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2602.06974v2

Visual navigation for robotics is inspired by the human ability to navigate environments using visual cues and memory, eliminating the need for detailed maps. In unseen, unmapped, or GPS-denied settings, traditional metric map-based methods fall short, prompting a shift toward learning-based approaches with minimal exploration. In this work, we develop a hierarchical framework that decomposes the navigation decision-making process into multiple levels. Our method learns to select subgoals through a simple, transferable waypoint selection network. A key component of the approach is a latent-space memory module organized solely by visual similarity, as a proxy for distance. This alternative to graph-based topological representations proves sufficient for navigation tasks, providing a compact, light-weight, simple-to-train navigator that can find its way to the goal in novel locations. We show competitive results with a suite of SOTA methods in Habitat AI environments without using any odometry in training or inference. An additional contribution leverages the interpretablility of the framework for interactive navigation. We consider the question: how much direction intervention/interaction is needed to achieve success in all trials? We demonstrate that even minimal human involvement can significantly enhance overall navigation performance.

---

### Deep g-Pricing for CSI 300 Index Options with Volatility Trajectories and Market Sentiment

Authors: Yilun Zhang, Zheng Tang, Hexiang Sun, Yufeng Shi
Published: 2026-01-15
Categories: q-fin.CP, cs.LG, math.PR, q-fin.PR
arXiv: https://arxiv.org/abs/2601.18804v1

Option pricing in real markets faces fundamental challenges. The Black--Scholes--Merton (BSM) model assumes constant volatility and uses a linear generator $g(t,x,y,z)=-ry$, while lacking explicit behavioral factors, resulting in systematic departures from observed dynamics. This paper extends the BSM model by learning a nonlinear generator within a deep Forward--Backward Stochastic Differential Equation (FBSDE) framework. We propose a dual-network architecture where the value network $u_θ$ learns option prices and the generator network $g_φ$ characterizes the pricing mechanism, with the hedging strategy $Z_t=σ_t X_t \nabla_x u_θ$ obtained via automatic differentiation. The framework adopts forward recursion from a learnable initial condition $Y_0=u_θ(0,\cdot)$, naturally accommodating volatility trajectory and sentiment features. Empirical results on CSI 300 index options show that our method reduces Mean Absolute Error (MAE) by 32.2\% and Mean Absolute Percentage Error (MAPE) by 35.3\% compared with BSM. Interpretability analysis indicates that architectural improvements are effective across all option types, while the information advantage is asymmetric between calls and puts. Specifically, call option improvements are primarily driven by sentiment features, whereas put options show more balanced contributions from volatility trajectory and sentiment features. This finding aligns with economic intuition regarding option pricing mechanisms.

---

### Latent Structural Similarity Networks for Unsupervised Discovery in Multivariate Time Series

Authors: Olusegun Owoeye
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18803v1

This paper proposes a task-agnostic discovery layer for multivariate time series that constructs a relational hypothesis graph over entities without assuming linearity, stationarity, or a downstream objective. The method learns window-level sequence representations using an unsupervised sequence-to-sequence autoencoder, aggregates these representations into entity-level embeddings, and induces a sparse similarity network by thresholding a latent-space similarity measure. This network is intended as an analyzable abstraction that compresses the pairwise search space and exposes candidate relationships for further investigation, rather than as a model optimized for prediction, trading, or any decision rule. The framework is demonstrated on a challenging real-world dataset of hourly cryptocurrency returns, illustrating how latent similarity induces coherent network structure; a classical econometric relation is also reported as an external diagnostic lens to contextualize discovered edges.

---

### How Do We Engage with Other Disciplines? A Framework to Study Meaningful Interdisciplinary Discourse in Scholarly Publications

Authors: Bagyasree Sudharsan, Alexandria Leto, Maria Leonor Pacheco
Published: 2026-01-15
Categories: cs.DL, cs.CL
arXiv: https://arxiv.org/abs/2601.17020v3

With the rising popularity of interdisciplinary work and increasing institutional incentives in this direction, there is a growing need to understand how resulting publications incorporate ideas from multiple disciplines. Existing computational approaches, such as affiliation diversity, keywords, and citation patterns, do not account for how individual citations are used to advance the citing work. Although, in line with addressing this gap, prior studies have proposed taxonomies to classify citation purpose, these frameworks are not well-suited to interdisciplinary research and do not provide quantitative measures of citation engagement quality. To address these limitations, we propose a framework for the evaluation of citation engagement in interdisciplinary Natural Language Processing (NLP) publications. Our approach introduces a citation purpose taxonomy tailored to interdisciplinary work, supported by an annotation study. We demonstrate the utility of this framework through a thorough analysis of publications at the intersection of NLP and Computational Social Science.

---

### Evaluating the Evolution of Critical Thinking, Creativity, Communication and Collaboration in Higher Education Courses

Authors: Margarida Romero
Published: 2026-01-15
Categories: cs.CY, cs.AI, cs.ET
arXiv: https://arxiv.org/abs/2601.17018v1

The development of Creativity, Communication, Critical Thinking, and Collaboration (the 4Cs) is a central objective of contemporary competency-based education. However, empirical evidence on how these competencies evolve across learning modules and instructional phases remains limited. This study evaluates the evolution of the 4Cs from pre-pilot to pilot implementation phases across three educational contexts, using the project's 4Cs theoretical framework as an analytical lens. The analysis of three pilot cases (IASIS, EASD, and UPATRAS) compares the 4Cs scores to identify patterns of growth, stagnation, or decline over time. Results indicate that communication and critical thinking showed the most consistent and substantial improvements, particularly in pilots with lower pre-pilot baselines, suggesting that structured pilot interventions effectively support cognitive and expressive competencies. In contrast, creativity exhibited context-dependent outcomes, while collaboration emerged as the most fragile competency, often stagnating or declining during scale-up. Interpreted through the theoretical framework, these findings suggest that competency evolution is strongly shaped by instructional design, assessment alignment, and learning activity structures rather than learner ability alone. The study contributes empirical validation to the 4Cs framework and highlights the need for differentiated, competency-sensitive design and evaluation strategies when scaling educational modules.

---

### Measuring Political Stance and Consistency in Large Language Models

Authors: Salah Feras Alali, Mohammad Nashat Maasfeh, Mucahid Kutlu, Saban Kardas
Published: 2026-01-15
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.17016v1

With the incredible advancements in Large Language Models (LLMs), many people have started using them to satisfy their information needs. However, utilizing LLMs might be problematic for political issues where disagreement is common and model outputs may reflect training-data biases or deliberate alignment choices. To better characterize such behavior, we assess the stances of nine LLMs on 24 politically sensitive issues using five prompting techniques. We find that models often adopt opposing stances on several issues; some positions are malleable under prompting, while others remain stable. Among the models examined, Grok-3-mini is the most persistent, whereas Mistral-7B is the least. For issues involving countries with different languages, models tend to support the side whose language is used in the prompt. Notably, no prompting technique alters model stances on the Qatar blockade or the oppression of Palestinians. We hope these findings raise user awareness when seeking political guidance from LLMs and encourage developers to address these concerns.

---