# Research Papers — 2026-01 · bundle page 138 of 189 > Full-text markdown of papers #6851–6900 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/138 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/137.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/139.md) ### Gecko: An Efficient Neural Architecture Inherently Processing Sequences with Arbitrary Lengths Authors: Xuezhe Ma, Shicheng Wen, Linghao Jin, Bilge Acun, Ruihang Lai, Bohan Hou, Will Lin, Hao Zhang, Songlin Yang, Ryan Lee, Mengxi Wu, Jonathan May et al. Published: 2026-01-10 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.06463v1 Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The design choices in Transformer, including quadratic complexity and weak length extrapolation, have limited their ability to scale to long sequences. In this work, we propose Gecko, a neural architecture that inherits the design of Mega and Megalodon (exponential moving average with gated attention), and further introduces multiple technical components to improve its capability to capture long range dependencies, including timestep decay normalization, sliding chunk attention mechanism, and adaptive working memory. In a controlled pretraining comparison with Llama2 and Megalodon in the scale of 7 billion parameters and 2 trillion training tokens, Gecko achieves better efficiency and long-context scalability. Gecko reaches a training loss of 1.68, significantly outperforming Llama2-7B (1.75) and Megalodon-7B (1.70), and landing close to Llama2-13B (1.67). Notably, without relying on any context-extension techniques, Gecko exhibits inherent long-context processing and retrieval capabilities, stably handling sequences of up to 4 million tokens and retrieving information from contexts up to $4\times$ longer than its attention window. Code: https://github.com/XuezheMax/gecko-llm --- ### Physics-informed Gaussian Process Regression in Solving Eigenvalue Problem of Linear Operators Authors: Tianming Bai, Jiannan Yang Published: 2026-01-10 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2601.06462v1 Applying Physics-Informed Gaussian Process Regression to the eigenvalue problem $(\mathcal{L}-λ)u = 0$ poses a fundamental challenge, where the null source term results in a trivial predictive mean and a degenerate marginal likelihood. Drawing inspiration from system identification, we construct a transfer function-type indicator for the unknown eigenvalue/eigenfunction using the physics-informed Gaussian Process posterior. We demonstrate that the posterior covariance is only non-trivial when $λ$ corresponds to an eigenvalue of the partial differential operator $\mathcal{L}$, reflecting the existence of a non-trivial eigenspace, and any sample from the posterior lies in the eigenspace of the linear operator. We demonstrate the effectiveness of the proposed approach through several numerical examples with both linear and non-linear eigenvalue problems. --- ### VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference Authors: Minfeng Qi, Dongyang He, Qin Wang, Lefeng Zhang Published: 2026-01-10 Categories: cs.CR, cs.CV, cs.ET arXiv: https://arxiv.org/abs/2601.06461v1 Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes, and spatial relations. They are increasingly deployed as a primary defense against automated bots. Existing solvers fall into two paradigms: vision-centric, which rely on template-specific detectors but fail on novel layouts, and reasoning-centric, which leverage LLMs but struggle with fine-grained visual perception. Both lack the generality needed to handle heterogeneous VRC deployments. We present ViPer, a unified attack framework that integrates structured multi-object visual perception with adaptive LLM-based reasoning. ViPer parses visual layouts, grounds attributes to question semantics, and infers target coordinates within a modular pipeline. Evaluated on six major VRC providers (VTT, Geetest, NetEase, Dingxiang, Shumei, Xiaodun), ViPer achieves up to 93.2% success, approaching human-level performance across multiple benchmarks. Compared to prior solvers, GraphNet (83.2%), Oedipus (65.8%), and the Holistic approach (89.5%), ViPer consistently outperforms all baselines. The framework further maintains robustness across alternative LLM backbones (GPT, Grok, DeepSeek, Kimi), sustaining accuracy above 90%. To anticipate defense, we further introduce Template-Space Randomization (TSR), a lightweight strategy that perturbs linguistic templates without altering task semantics. TSR measurably reduces solver (i.e., attacker) performance. Our proposed design suggests directions for human-solvable but machine-resistant CAPTCHAs. --- ### Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs Authors: Weihao Hong, Zhiyuan Jiang, Bingyu Shen, Xinlei Guan, Yangyi Feng, Meng Xu, Boyang Li Published: 2026-01-10 Categories: cs.CV, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06460v1 Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are not present in the image to satisfy user prompts. While recent datasets and benchmarks have been introduced to evaluate systematic hallucinations in VLMs, many hallucination behaviors remain insufficiently characterized. In particular, prior work primarily focuses on object presence or absence, leaving it unclear how prompt phrasing and structural constraints can systematically induce hallucinations. In this paper, we investigate how different forms of prompt pressure influence hallucination behavior. We introduce Ghost-100, a procedurally generated dataset of synthetic scenes in which key visual details are deliberately removed, enabling controlled analysis of absence-based hallucinations. Using a structured 5-Level Prompt Intensity Framework, we vary prompts from neutral queries to toxic demands and rigid formatting constraints. We evaluate three representative open-weight VLMs: MiniCPM-V 2.6-8B, Qwen2-VL-7B, and Qwen3-VL-8B. Across all three models, hallucination rates do not increase monotonically with prompt intensity. All models exhibit reductions at higher intensity levels at different thresholds, though not all show sustained reduction under maximum coercion. These results suggest that current safety alignment is more effective at detecting semantic hostility than structural coercion, revealing model-specific limitations in handling compliance pressure. Our dataset is available at: https://github.com/bli1/tone-matters --- ### PixRec: Leveraging Visual Context for Next-Item Prediction in Sequential Recommendation Authors: Sayak Chakrabarty, Souradip Pal Published: 2026-01-10 Categories: cs.IR, cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.06458v1 Large Language Models (LLMs) have recently shown strong potential for usage in sequential recommendation tasks through text-only models, which combine advanced prompt design, contrastive alignment, and fine-tuning on downstream domain-specific data. While effective, these approaches overlook the rich visual information present in many real-world recommendation scenarios, particularly in e-commerce. This paper proposes PixRec - a vision-language framework that incorporates both textual attributes and product images into the recommendation pipeline. Our architecture leverages a vision-language model backbone capable of jointly processing image-text sequences, maintaining a dual-tower structure and mixed training objective while aligning multi-modal feature projections for both item-item and user-item interactions. Using the Amazon Reviews dataset augmented with product images, our experiments demonstrate $3\times$ and 40% improvements in top-rank and top-10 rank accuracy over text-only recommenders respectively, indicating that visual features can help distinguish items with similar textual descriptions. Our work outlines future directions for scaling multi-modal recommenders training, enhancing visual-text feature fusion, and evaluating inference-time performance. This work takes a step toward building software systems utilizing visual information in sequential recommendation for real-world applications like e-commerce. --- ### ConSensus: Multi-Agent Collaboration for Multimodal Sensing Authors: Hyungjun Yoon, Mohammad Malekzadeh, Sung-Ju Lee, Fahim Kawsar, Lorena Qendro Published: 2026-01-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06453v2 Large language models (LLMs) are increasingly grounded in sensor data to perceive and reason about human physiology and the physical world. However, accurately interpreting heterogeneous multimodal sensor data remains a fundamental challenge. We show that a single monolithic LLM often fails to reason coherently across modalities, leading to incomplete interpretations and prior-knowledge bias. We introduce ConSensus, a training-free multi-agent collaboration framework that decomposes multimodal sensing tasks into specialized, modality-aware agents. To aggregate agent-level interpretations, we propose a hybrid fusion mechanism that balances semantic aggregation, which enables cross-modal reasoning and contextual understanding, with statistical consensus, which provides robustness through agreement across modalities. While each approach has complementary failure modes, their combination enables reliable inference under sensor noise and missing data. We evaluate ConSensus on five diverse multimodal sensing benchmarks, demonstrating an average accuracy improvement of 7.1% over the single-agent baseline. Furthermore, ConSensus matches or exceeds the performance of iterative multi-agent debate methods while achieving a 12.7 times reduction in average fusion token cost through a single-round hybrid fusion protocol, yielding a robust and efficient solution for real-world multimodal sensing tasks. The source code is available at https://github.com/nokia/multi-agent-collaboration-for-multimodal-sensing. --- ### CulinaryCut-VLAP: A Vision-Language-Action-Physics Framework for Food Cutting via a Force-Aware Material Point Method Authors: Hyunseo Koh, Chang-Yong Song, Youngjae Choi, Misa Viveiros, David Hyde, Heewon Kim Published: 2026-01-10 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2601.06451v1 Food cutting is a highly practical yet underexplored application at the intersection of vision and robotic manipulation. The task remains challenging because interactions between the knife and deformable materials are highly nonlinear and often entail large deformations, frequent contact, and topological change, which in turn hinder stable and safe large-scale data collection. To address these challenges, we propose a unified framework that couples a vision-language-action (VLA) dataset with a physically realistic cutting simulator built on the material point method (MPM). Our simulator adopts MLS-MPM as its computational core, reducing numerical dissipation and energy drift while preserving rotational and shear responses even under topology-changing cuts. During cutting, forces and stress distributions are estimated from impulse exchanges between particles and the grid, enabling stable tracking of transient contact forces and energy transfer. We also provide a benchmark dataset that integrates diverse cutting trajectories, multi-view visual observations, and fine-grained language instructions, together with force--torque and tool--pose labels to provide physically consistent training signals. These components realize a learning--evaluation loop that respects the core physics of cutting and establishes a safe, reproducible, and scalable foundation for advancing VLA models in deformable object manipulation. --- ### LitVISTA: A Benchmark for Narrative Orchestration in Literary Text Authors: Mingzhe Lu, Yiwen Wang, Yanbing Liu, Qi You, Chong Liu, Ruize Qin, Haoyu Dong, Wenyu Zhang, Jiarui Zhang, Yue Hu, Yunpeng Li Published: 2026-01-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06445v2 Computational narrative analysis aims to capture rhythm, tension, and emotional dynamics in literary texts. Existing large language models can generate long stories but overly focus on causal coherence, neglecting the complex story arcs and orchestration inherent in human narratives. This suggests a structural misalignment between model- and human-generated narratives. We therefore position narrative analysis as a diagnostic proxy for generation and propose VISTA Space, a high-dimensional framework for narrative orchestration that unifies human and model perspectives while jointly characterizing narrative function and structure in a common space. We further introduce LitVISTA, a structurally annotated benchmark grounded in literary texts, which operationalizes VISTA Space for systematic evaluation of models' narrative orchestration capabilities. Under an oracle setting with gold event anchors, we evaluate frontier LLMs including GPT, Claude, Grok, and Gemini. Results reveal systematic deficiencies, as current models struggle to jointly capture narrative function and structure and fail to form an integrated global view of literary narrative orchestration. End-to-end analysis further shows that failures are dominated by anchor identification and localization errors. Even advanced thinking modes yield mixed and often limited gains for literary narrative understanding. --- ### Physics-Informed Tree Search for High-Dimensional Computational Design Authors: Suvo Banik, Troy D. Loeffler, Henry Chan, Sukriti Manna, Orcun Yildiz, Tom Peterka, Subramanian Sankaranarayanan Published: 2026-01-10 Categories: cs.LG, cond-mat.mtrl-sci, physics.comp-ph, physics.data-an arXiv: https://arxiv.org/abs/2601.06444v1 High-dimensional design spaces underpin a wide range of physics-based modeling and computational design tasks in science and engineering. These problems are commonly formulated as constrained black-box searches over rugged objective landscapes, where function evaluations are expensive, and gradients are unavailable or unreliable. Conventional global search engines and optimizers struggle in such settings due to the exponential scaling of design spaces, the presence of multiple local basins, and the absence of physical guidance in sampling. We present a physics-informed Monte Carlo Tree Search (MCTS) framework that extends policy-driven tree-based reinforcement concepts to continuous, high-dimensional scientific optimization. Our method integrates population-level decision trees with surrogate-guided directional sampling, reward shaping, and hierarchical switching between global exploration and local exploitation. These ingredients allow efficient traversal of non-convex, multimodal landscapes where physically meaningful optima are sparse. We benchmark our approach against standard global optimization baselines on a suite of canonical test functions, demonstrating superior or comparable performance in terms of convergence, robustness, and generalization. Beyond synthetic tests, we demonstrate physics-consistent applicability to (i) crystal structure optimization from clusters to bulk, (ii) fitting of classical interatomic potentials, and (iii) constrained engineering design problems. Across all cases, the method converges with high fidelity and evaluation efficiency while preserving physical constraints. Overall, our work establishes physics-informed tree search as a scalable and interpretable paradigm for computational design and high-dimensional scientific optimization, bridging discrete decision-making frameworks with continuous search in scientific design workflows. --- ### How to Build Robust, Scalable Models for GSV-Based Indicators in Neighborhood Research Authors: Xiaoya Tang, Xiaohe Yue, Heran Mane, Dapeng Li, Quynh Nguyen, Tolga Tasdizen Published: 2026-01-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06443v1 A substantial body of health research demonstrates a strong link between neighborhood environments and health outcomes. Recently, there has been increasing interest in leveraging advances in computer vision to enable large-scale, systematic characterization of neighborhood built environments. However, the generalizability of vision models across fundamentally different domains remains uncertain, for example, transferring knowledge from ImageNet to the distinct visual characteristics of Google Street View (GSV) imagery. In applied fields such as social health research, several critical questions arise: which models are most appropriate, whether to adopt unsupervised training strategies, what training scale is feasible under computational constraints, and how much such strategies benefit downstream performance. These decisions are often costly and require specialized expertise. In this paper, we answer these questions through empirical analysis and provide practical insights into how to select and adapt foundation models for datasets with limited size and labels, while leveraging larger, unlabeled datasets through unsupervised training. Our study includes comprehensive quantitative and visual analyses comparing model performance before and after unsupervised adaptation. --- ### WHU-PCPR: A cross-platform heterogeneous point cloud dataset for place recognition in complex urban scenes Authors: Xianghong Zou, Jianping Li, Yandi Yang, Weitong Wu, Yuan Wang, Qiegen Liu, Zhen Dong Published: 2026-01-10 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.06442v2 Point Cloud-based Place Recognition (PCPR) demonstrates considerable potential in applications such as autonomous driving, robot localization and navigation, and map update. In practical applications, point clouds used for place recognition are often acquired from different platforms and LiDARs across varying scene. However, existing PCPR datasets lack diversity in scenes, platforms, and sensors, which limits the effective development of related research. To address this gap, we establish WHU-PCPR, a cross-platform heterogeneous point cloud dataset designed for place recognition. The dataset differentiates itself from existing datasets through its distinctive characteristics: 1) cross-platform heterogeneous point clouds: collected from survey-grade vehicle-mounted Mobile Laser Scanning (MLS) systems and low-cost Portable helmet-mounted Laser Scanning (PLS) systems, each equipped with distinct mechanical and solid-state LiDAR sensors. 2) Complex localization scenes: encompassing real-time and long-term changes in both urban and campus road scenes. 3) Large-scale spatial coverage: featuring 82.3 km of trajectory over a 60-month period and an unrepeated route of approximately 30 km. Based on WHU-PCPR, we conduct extensive evaluation and in-depth analysis of several representative PCPR methods, and provide a concise discussion of key challenges and future research directions. The dataset and benchmark code are available at https://github.com/zouxianghong/WHU-PCPR. --- ### FlexAct: Why Learn when you can Pick? Authors: Ramnath Kumar, Kyle Ritscher, Junmin Judy, Lawrence Liu, Cho-Jui Hsieh Published: 2026-01-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06441v2 Learning activation functions has emerged as a promising direction in deep learning, allowing networks to adapt activation mechanisms to task-specific demands. In this work, we introduce a novel framework that employs the Gumbel-Softmax trick to enable discrete yet differentiable selection among a predefined set of activation functions during training. Our method dynamically learns the optimal activation function independently of the input, thereby enhancing both predictive accuracy and architectural flexibility. Experiments on synthetic datasets show that our model consistently selects the most suitable activation function, underscoring its effectiveness. These results connect theoretical advances with practical utility, paving the way for more adaptive and modular neural architectures in complex learning scenarios. --- ### Time Travel Engine: A Shared Latent Chronological Manifold Enables Historical Navigation in Large Language Models Authors: Jingmin An, Wei Liu, Qian Wang, Fang Fang Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06437v1 Time functions as a fundamental dimension of human cognition, yet the mechanisms by which Large Language Models (LLMs) encode chronological progression remain opaque. We demonstrate that temporal information in their latent space is organized not as discrete clusters but as a continuous, traversable geometry. We introduce the Time Travel Engine (TTE), an interpretability-driven framework that projects diachronic linguistic patterns onto a shared chronological manifold. Unlike surface-level prompting, TTE directly modulates latent representations to induce coherent stylistic, lexical, and conceptual shifts aligned with target eras. By parameterizing diachronic evolution as a continuous manifold within the residual stream, TTE enables fluid navigation through period-specific "zeitgeists" while restricting access to future knowledge. Furthermore, experiments across diverse architectures reveal topological isomorphism between the temporal subspaces of Chinese and English-indicating that distinct languages share a universal geometric logic of historical evolution. These findings bridge historical linguistics with mechanistic interpretability, offering a novel paradigm for controlling temporal reasoning in neural networks. --- ### Certified Unlearning in Decentralized Federated Learning Authors: Hengliang Wu, Youming Tao, Anhao Zhou, Shuzhen Chen, Falko Dressler, Dongxiao Yu Published: 2026-01-10 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.06436v1 Driven by the right to be forgotten (RTBF), machine unlearning has become an essential requirement for privacy-preserving machine learning. However, its realization in decentralized federated learning (DFL) remains largely unexplored. In DFL, clients exchange local updates only with neighbors, causing model information to propagate and mix across the network. As a result, when a client requests data deletion, its influence is implicitly embedded throughout the system, making removal difficult without centralized coordination. We propose a novel certified unlearning framework for DFL based on Newton-style updates. Our approach first quantifies how a client's data influence propagates during training. Leveraging curvature information of the loss with respect to the target data, we then construct corrective updates using Newton-style approximations. To ensure scalability, we approximate second-order information via Fisher information matrices. The resulting updates are perturbed with calibrated noise and broadcast through the network to eliminate residual influence across clients. We theoretically prove that our approach satisfies the formal definition of certified unlearning, ensuring that the unlearned model is difficult to distinguish from a retrained model without the deleted data. We also establish utility bounds showing that the unlearned model remains close to retraining from scratch. Extensive experiments across diverse decentralized settings demonstrate the effectiveness and efficiency of our framework. --- ### On a Gradient Approach to Chebyshev Center Problems with Applications to Function Learning Authors: Abhinav Raghuvanshi, Mayank Baranwal, Debasish Chatterjee Published: 2026-01-10 Categories: math.OC, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.06434v1 We introduce $\textsf{gradOL}$, the first gradient-based optimization framework for solving Chebyshev center problems, a fundamental challenge in optimal function learning and geometric optimization. $\textsf{gradOL}$ hinges on reformulating the semi-infinite problem as a finitary max-min optimization, making it amenable to gradient-based techniques. By leveraging automatic differentiation for precise numerical gradient computation, $\textsf{gradOL}$ ensures numerical stability and scalability, making it suitable for large-scale settings. Under strong convexity of the ambient norm, $\textsf{gradOL}$ provably recovers optimal Chebyshev centers while directly computing the associated radius. This addresses a key bottleneck in constructing stable optimal interpolants. Empirically, $\textsf{gradOL}$ achieves significant improvements in accuracy and efficiency on 34 benchmark Chebyshev center problems from a benchmark $\textsf{CSIP}$ library. Moreover, we extend $\textsf{gradOL}$ to general convex semi-infinite programming (CSIP), attaining up to $4000\times$ speedups over the state-of-the-art $\texttt{SIPAMPL}$ solver tested on the indicated $\textsf{CSIP}$ library containing 67 benchmark problems. Furthermore, we provide the first theoretical foundation for applying gradient-based methods to Chebyshev center problems, bridging rigorous analysis with practical algorithms. $\textsf{gradOL}$ thus offers a unified solution framework for Chebyshev centers and broader CSIPs. --- ### LsrIF: Enhancing Logic-Structured Instruction Following of Large Language Models Authors: Qingyu Ren, Qianyu He, Jingwen Chang, Geng Zhang, Jiajie Zhu, Xingzhou Chen, Zhuofei Shi, Jiaqing Liang, Yanghua Xiao, Han Xia, Zeye Sun, Fei Yu Published: 2026-01-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06431v3 Instruction following is critical for large language models, yet real-world instructions often involve multiple constraints with logical structures, such as parallel composition, sequential dependencies, and conditional branching. Existing methods typically construct data by simply combining constraints and aggregate rewards by averaging individual constraint scores during training, overlooking logical dependencies and introducing noisy signals. We propose LsrIF, a training framework for logic-structured instruction following. LsrIF constructs data by organizing atomic constraints into parallel, sequential, conditional, and nested structures, and applies structure-aware reward aggregation aligned with their execution semantics: averaging rewards for parallel constraints, decaying later rewards after early failures in sequential structures, and rewarding only active branches in conditional structures. Experiments show that LsrIF improves instruction following in both in-domain and out-of-domain settings while also benefiting logic reasoning. Further analysis indicates that logic-structured training increases attention to constraint-related tokens and logical connectors, suggesting improved modeling of instruction logic. We will release our data and code for future research. --- ### A Unified Shape-Aware Foundation Model for Time Series Classification Authors: Zhen Liu, Yucheng Wang, Boyuan Li, Junhao Zheng, Emadeldeen Eldele, Min Wu, Qianli Ma Published: 2026-01-10 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.06429v1 Foundation models pre-trained on large-scale source datasets are reshaping the traditional training paradigm for time series classification. However, existing time series foundation models primarily focus on forecasting tasks and often overlook classification-specific challenges, such as modeling interpretable shapelets that capture class-discriminative temporal features. To bridge this gap, we propose UniShape, a unified shape-aware foundation model designed for time series classification. UniShape incorporates a shape-aware adapter that adaptively aggregates multiscale discriminative subsequences (shapes) into class tokens, effectively selecting the most relevant subsequence scales to enhance model interpretability. Meanwhile, a prototype-based pretraining module is introduced to jointly learn instance- and shape-level representations, enabling the capture of transferable shape patterns. Pre-trained on a large-scale multi-domain time series dataset comprising 1.89 million samples, UniShape exhibits superior generalization across diverse target domains. Experiments on 128 UCR datasets and 30 additional time series datasets demonstrate that UniShape achieves state-of-the-art classification performance, with interpretability and ablation analyses further validating its effectiveness. --- ### BackPlay: Head-Only Look-Back Self-Correction for Diffusion Language Models Authors: Liming Liu, Binxuan Huang, Zixuan Zhang, Xin Liu, Bing Yin, Tuo Zhao Published: 2026-01-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06428v3 Diffusion Language Models (DLMs) decode multiple tokens in parallel, but aggressive multi-token decoding amplifies cross-token dependency errors and can sharply degrade generation quality. We propose BackPlay, a frozen-backbone self-correction framework that trains only a lightweight correction head on a finetuned DLM without updating any backbone or adapter parameters. Because the head is trained on errors produced by the same frozen generator used at inference time, its training distribution aligns with the error patterns of the deployed model. We further introduce Look-back Correction, a training mechanism that injects predictions from earlier, more corrupted denoising states into later, richer contexts, enabling the head to leverage later context to detect mistakes made in earlier generation steps. During inference, BackPlay periodically revisits previously generated tokens through selective remasking and regeneration to limit error accumulation. Across mathematical reasoning and code generation benchmarks, BackPlay improves the speed--quality trade-off of the underlying DLM under multi-token decoding. --- ### NC-Bench: An LLM Benchmark for Evaluating Conversational Competence Authors: Robert J. Moore, Sungeun An, Farhan Ahmed, Jay Pankaj Gala Published: 2026-01-10 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.06426v3 Existing LLM benchmarks evaluate what models say, such as whether answers are correct, faithful, or helpful, but they do not test whether models produce the right type of conversational action at the right point in an interaction. The Natural Conversation Benchmark (NC-Bench) fills this gap by evaluating conversational competence: the ability to perform structurally appropriate actions such as repairing, closing, or refusing, as defined by conversation science. Grounded in the Natural Conversation Framework (NCF), NC-Bench comprises three sets: (1) the basic set evaluates fundamental sequence management practices, such as answering inquiries, repairing responses, and closing conversational pairs; (2) the retrieval-augmented generation (RAG) set applies the same patterns but incorporates information-seeking via RAG; (3) the complex request set extends to requests involving more intricate sequence management. Each set tests a model's ability to produce contextually appropriate conversational actions in response to characteristic interaction patterns. Evaluations across six open-source models and one closed-source model on 14 interaction patterns reveal quantifiable shortcomings in conversational competence present in current models. By operationalizing fundamental principles of human conversation, NC-Bench provides a lightweight, extensible, and theory-grounded framework for identifying specific conversational action gaps in LLMs beyond topical or task-specific benchmarks. --- ### HiDVFS: Hierarchical Multi-Agent DVFS for Real-Time OpenMP DAG Workloads Authors: Mohammad Pivezhandi, Abusayeed Saifullah, Ali Jannesari Published: 2026-01-10 Categories: cs.DC, cs.AI arXiv: https://arxiv.org/abs/2601.06425v2 Leakage power in multicore embedded systems now rivals dynamic power, so DVFS schedulers must respect deadlines and thermal limits, not just average makespan. Existing heuristics lack per-core, temperature-aware control and overlook the irregular execution of OpenMP DAGs. We propose HiDVFS, a general, extensible hierarchical multi-agent DVFS scheduler: a profiler agent selects cores and frequencies, a thermal agent groups cores by temperature, and a priority agent orders tasks under contention, all trained with a makespan-focused reward using short-horizon future-state shaping for sample efficiency. Deadlines are soft, derived from a measured reference cost; a federated schedulability gate keeps operating points feasible, and a calibrated split-conformal shield bounds each action's predicted response time. On Jetson TX2 with multi-seed validation, HiDVFS attains a 4.16+/-0.58 s L10 makespan, a 2.83x speedup and 32.9% energy reduction over a fairness-corrected GearDVFS port, and a 4.62x average speedup with 55.7% energy reduction across all 12 BOTS benchmarks. Cross-platform results on TX2, Orin NX, and RubikPi show deadline-aware DVFS cuts energy 15 to 18% versus pinning the maximum frequency, and a measured mixed-criticality study shows cluster-aware reservation is required to keep a high-criticality task's deadline-miss ratio at zero. --- ### Can a Unimodal Language Agent Provide Preferences to Tune a Multimodal Vision-Language Model? Authors: Sazia Tabasum Mim, Jack Morris, Manish Dhakal, Yanming Xiu, Maria Gorlatova, Yi Ding Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06424v1 To explore a more scalable path for adding multimodal capabilities to existing LLMs, this paper addresses a fundamental question: Can a unimodal LLM, relying solely on text, reason about its own informational needs and provide effective feedback to optimize a multimodal model? To answer this, we propose a method that enables a language agent to give feedback to a vision-language model (VLM) to adapt text generation to the agent's preferences. Our results from different experiments affirm this hypothesis, showing that LLM preference feedback significantly enhances VLM descriptions. Using our proposed method, we find that the VLM can generate multimodal scene descriptions to help the LLM better understand multimodal context, leading to improvements of maximum 13% in absolute accuracy compared to the baseline multimodal approach. Furthermore, a human study validated our AI-driven feedback, showing a 64.6% preference alignment rate between the LLM's choices and human judgments. Extensive experiments provide insights on how and why the method works and its limitations. --- ### Does Inference Scaling Improve Reasoning Faithfulness? A Multi-Model Analysis of Self-Consistency Tradeoffs Authors: Deep Mehta Published: 2026-01-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06423v1 Self-consistency has emerged as a popular technique for improving large language model accuracy on reasoning tasks. The approach is straightforward: generate multiple reasoning paths and select the most common answer through majority voting. While this reliably boosts accuracy, it remains unclear whether these gains reflect genuine improvements in reasoning quality. We investigate a fundamental question that has not been studied before: does inference scaling improve reasoning faithfulness? We conduct a comprehensive empirical study across four frontier models (GPT-5.2, Claude Opus 4.5, Gemini-3-flash-preview, and DeepSeek-v3.2) on 100 GSM8K mathematical reasoning problems. Our analysis employs bootstrap confidence intervals, McNemar's tests for paired comparisons, and Cohen's d effect sizes to quantify the effects rigorously. The results reveal striking differences across models that challenge common assumptions about self-consistency. GPT-5.2 shows the expected pattern: accuracy improves from 78% to 90% at N=5, with faithfulness remaining relatively stable (0.540 to 0.510). Claude Opus 4.5 tells a completely different story. Its accuracy actually drops from 78% to 74.3% while faithfulness jumps dramatically from 0.270 to 0.891 at N=5. DeepSeek-v3.2, already at 98% accuracy, shows ceiling effects with modest faithfulness gains (0.440 to 0.541). Gemini-3-flash improves from 81% to 86% accuracy with a slight faithfulness decrease (0.260 to 0.212). Problem difficulty analysis reveals that GPT-5.2 solves 82% of hard problems while breaking only 13% of easy ones. Claude, in contrast, breaks 23% of easy problems, explaining its accuracy decrease. These findings matter for practitioners: self-consistency is not universally beneficial, and teams should test their specific models before deployment. We release our code and provide practical recommendations for navigating these tradeoffs. --- ### Semantic Enrichment of CAD-Based Industrial Environments via Scene Graphs for Simulation and Reasoning Authors: Nathan Pascal Walus, Ranulfo Bezerra, Shotaro Kojima, Tsige Tadesse Alemayoh, Satoshi Tadokoro, Kazunori Ohno Published: 2026-01-10 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.06415v1 Utilizing functional elements in an industrial environment, such as displays and interactive valves, provide effective possibilities for robot training. When preparing simulations for robots or applications that involve high-level scene understanding, the simulation environment must be equally detailed. Although CAD files for such environments deliver an exact description of the geometry and visuals, they usually lack semantic, relational and functional information, thus limiting the simulation and training possibilities. A 3D scene graph can organize semantic, spatial and functional information by enriching the environment through a Large Vision-Language Model (LVLM). In this paper we present an offline approach to creating detailed 3D scene graphs from CAD environments. This will serve as a foundation to include the relations of functional and actionable elements, which then can be used for dynamic simulation and reasoning. Key results of this research include both quantitative results of the generated semantic labels as well as qualitative results of the scene graph, especially in hindsight of pipe structures and identified functional relations. All code, results and the environment will be made available at https://cad-scenegraph.github.io --- ### GlobalPaint: Spatiotemporal Coherent Video Outpainting with Global Feature Guidance Authors: Yueming Pan, Ruoyu Feng, Jianmin Bao, Chong Luo, Nanning Zheng Published: 2026-01-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06413v1 Video outpainting extends a video beyond its original boundaries by synthesizing missing border content. Compared with image outpainting, it requires not only per-frame spatial plausibility but also long-range temporal coherence, especially when outpainted content becomes visible across time under camera or object motion. We propose GlobalPaint, a diffusion-based framework for spatiotemporal coherent video outpainting. Our approach adopts a hierarchical pipeline that first outpaints key frames and then completes intermediate frames via an interpolation model conditioned on the completed boundaries, reducing error accumulation in sequential processing. At the model level, we augment a pretrained image inpainting backbone with (i) an Enhanced Spatial-Temporal module featuring 3D windowed attention for stronger spatiotemporal interaction, and (ii) global feature guidance that distills OpenCLIP features from observed regions across all frames into compact global tokens using a dedicated extractor. Comprehensive evaluations on benchmark datasets demonstrate improved reconstruction quality and more natural motion compared to prior methods. Our demo page is https://yuemingpan.github.io/GlobalPaint/ --- ### Structured Episodic Event Memory Authors: Zhengxuan Lu, Dongfang Li, Yukun Shi, Beilun Wang, Longyue Wang, Baotian Hu Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06411v2 Current approaches to memory in Large Language Models (LLMs) predominantly rely on static Retrieval-Augmented Generation (RAG), which often results in scattered retrieval and fails to capture the structural dependencies required for complex reasoning. For autonomous agents, these passive and flat architectures lack the cognitive organization necessary to model the dynamic and associative nature of long-term interaction. To address this, we propose Structured Episodic Event Memory (SEEM), a hierarchical framework that synergizes a graph memory layer for relational facts with a dynamic episodic memory layer for narrative progression. Grounded in cognitive frame theory, SEEM transforms interaction streams into structured Episodic Event Frames (EEFs) anchored by precise provenance pointers. Furthermore, we introduce an agentic associative fusion and Reverse Provenance Expansion (RPE) mechanism to reconstruct coherent narrative contexts from fragmented evidence. Experimental results on the LoCoMo and LongMemEval benchmarks demonstrate that SEEM significantly outperforms baselines, enabling agents to maintain superior narrative coherence and logical consistency. --- ### Value of Information: A Framework for Human-Agent Communication Authors: Yijiang River Dong, Tiancheng Hu, Zheng Hui, Caiqi Zhang, Ivan Vulić, Andreea Bobu, Nigel Collier Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06407v1 Large Language Model (LLM) agents deployed for real-world tasks face a fundamental dilemma: user requests are underspecified, yet agents must decide whether to act on incomplete information or interrupt users for clarification. Existing approaches either rely on brittle confidence thresholds that require task-specific tuning, or fail to account for the varying stakes of different decisions. We introduce a decision-theoretic framework that resolves this trade-off through the Value of Information (VoI), enabling agents to dynamically weigh the expected utility gain from asking questions against the cognitive cost imposed on users. Our inference-time method requires no hyperparameter tuning and adapts seamlessly across contexts-from casual games to medical diagnosis. Experiments across four diverse domains (20 Questions, medical diagnosis, flight booking, and e-commerce) show that VoI consistently matches or exceeds the best manually-tuned baselines, achieving up to 1.36 utility points higher in high-cost settings. This work provides a parameter-free framework for adaptive agent communication that explicitly balances task risk, query ambiguity, and user effort. --- ### Stitch the Fragments: One-Shot Hierarchical Federated Clustering Authors: Shenghong Cai, Zihua Yang, Yang Lu, Mengke Li, Yuzhu Ji, Yiqun Zhang, Yiu-Ming Cheung Published: 2026-01-10 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.06404v2 Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incomplete, multi-granular unlabeled ``clusterlets'' distributed across Non-IID clients. Although hierarchical clustering is theoretically well-suited to model such nested distributions, its recursive nature strictly relies on multi-round communication, introducing prohibitive computational overhead and severe privacy vulnerabilities. This paper, therefore, proposes a novel one-shot hierarchical federated clustering framework designed to seamlessly ``stitch'' the fragmented local clusterlets into a holistic global distribution. Our approach enables clients to perform autonomous fine-grained distribution exploration, uploading prototype-level knowledge via a dynamic parameter-interleaving mechanism to scramble transmission trajectories, which effectively prevents the server from tracing individual client data distributions. Subsequently, a multi-granular learning mechanism at the server fuses these granularly inconsistent local clusterlets, reconstructing a coherent global hierarchy for ultimate clustering. Extensive experiments on real benchmark datasets illustrate the superiority of the proposed approach, which effectively bridges the granularity gap among heterogeneous clients while minimizing privacy exposure risks via anonymized informative one-shot communication. --- ### Steer Model beyond Assistant: Controlling System Prompt Strength via Contrastive Decoding Authors: Yijiang River Dong, Tiancheng Hu, Zheng Hui, Nigel Collier Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06403v1 Large language models excel at complex instructions yet struggle to deviate from their helpful assistant persona, as post-training instills strong priors that resist conflicting instructions. We introduce system prompt strength, a training-free method that treats prompt adherence as a continuous control. By contrasting logits from target and default system prompts, we isolate and amplify the behavioral signal unique to the target persona by a scalar factor alpha. Across five diverse benchmarks spanning constraint satisfaction, behavioral control, pluralistic alignment, capability modulation, and stylistic control, our method yields substantial improvements: up to +8.5 strict accuracy on IFEval, +45pp refusal rate on OffTopicEval, and +13% steerability on Prompt-Steering. Our approach enables practitioners to modulate system prompt strength, providing dynamic control over model behavior without retraining. --- ### BizFinBench.v2: Towards Reliable LLMs in Finance via Real-User Data and Offline/Online Bilingual Evaluation Authors: Xin Guo, Rongjunchen Zhang, Guilong Lu, Xuntao Guo, Shuai Jia, Zhi Yang, Liwen Zhang Published: 2026-01-10 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.06401v2 Large language models are becoming increasingly significant in financial applications. Nevertheless, prevailing benchmarks are largely dependent on simulated or generic data, which leads to a significant gap between reported performance and actual efficacy in real-world scenarios. To tackle this challenge, we present BizFinBench.v2, the first integrated offline and online benchmark built upon authentic user query-response data from both Chinese and U.S. equity markets. It comprises 28,860 questions across eight offline and two online tasks. Experimental results show that GPT-5 achieves a mere 61.5% accuracy, still failing to meet the practical business requirement (84.8%). Among the evaluated commercial models, DeepSeek-R1 exhibits superior investment efficacy. Error analysis grounded in real financial practice reveals persistent limitations in existing models. By overcoming the constraints of prior benchmarks, BizFinBench.v2 provides a substantiated foundation for advancing LLM deployment in the financial sector. Our data and code are available at https://github.com/HiThink-Research/BizFinBench.v2. --- ### MITRA: A Large-Scale Parallel Corpus and Multilingual Pretrained Language Model for Machine Translation and Semantic Retrieval for Pāli, Sanskrit, Buddhist Chinese, and Tibetan Authors: Sebastian Nehrdich, Kurt Keutzer Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06400v1 Ancient Buddhist literature features frequent, yet often unannotated, textual parallels spread across diverse languages: Sanskrit, Pāli, Buddhist Chinese, Tibetan, and more. The scale of this material makes manual examination prohibitive. We present the MITRA framework, which consists of a novel pipeline for multilingual parallel passage mining, MITRA-parallel, a large-scale corpus of 1.74 million parallel sentence pairs between Sanskrit, Chinese, and Tibetan, and the development of the domain-specific pretrained language model Gemma 2 MITRA. We present Gemma 2 MITRA-MT, a version of this base model fine-tuned on machine translation tasks, reaching state-of-the-art performance for machine translation of these languages into English and outperforming even much larger open-source models. We also present Gemma 2 MITRA-E, a semantic embedding model that shows state-of-the-art performance on a novel, detailed semantic embedding benchmark. We make the parallel dataset, model weights, and semantic similarity benchmark openly available to aid both NLP research and philological studies in Buddhist and classical Asian literature. --- ### AfriqueLLM: How Data Mixing and Model Architecture Impact Continued Pre-training for African Languages Authors: Hao Yu, Tianyi Xu, Michael A. Hedderich, Wassim Hamidouche, Syed Waqas Zamir, David Ifeoluwa Adelani Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06395v3 Large language models (LLMs) are increasingly multilingual, yet open models continue to underperform relative to proprietary systems, with the gap most pronounced for African languages. Continued pre-training (CPT) offers a practical route to language adaptation, but improvements on demanding capabilities such as mathematical reasoning often remain limited. This limitation is driven in part by the uneven domain coverage and missing task-relevant knowledge that characterize many low-resource language corpora. We present \texttt{AfriqueLLM}, a suite of open LLMs adapted to 20 African languages through CPT on 26B tokens. We perform a comprehensive empirical study across five base models spanning sizes and architectures, including Llama 3.1, Gemma 3, and Qwen 3, and systematically analyze how CPT data composition shapes downstream performance. In particular, we vary mixtures that include math, code, and synthetic translated data, and evaluate the resulting models on a range of multilingual benchmarks. Our results identify data composition as the primary driver of CPT gains. Adding math, code, and synthetic translated data yields consistent improvements, including on reasoning-oriented evaluations. Within a fixed architecture, larger models typically improve performance, but architectural choices dominate scale when comparing across model families. Moreover, strong multilingual performance in the base model does not reliably predict post-CPT outcomes; robust architectures coupled with task-aligned data provide a more dependable recipe. Finally, our best models improve long-context performance, including document-level translation. Models and code have been released on (Huggingface)(https://huggingface.co/collections/McGill-NLP/afriquellm) and (Github)(https://github.com/McGill-NLP/AfriqueLLM). --- ### Context Matters: Peer-Aware Student Behavioral Engagement Measurement via VLM Action Parsing and LLM Sequence Classification Authors: Ahmed Abdelkawy, Ahmed Elsayed, Asem Ali, Aly Farag, Thomas Tretter, Michael McIntyre Published: 2026-01-10 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.06394v4 Understanding student behavior in the classroom is essential to improve both pedagogical quality and student engagement. Existing methods for predicting student engagement typically require substantial annotated data to model the diversity of student behaviors, yet privacy concerns often restrict researchers to their own proprietary datasets. Moreover, the classroom context, represented in peers' actions, is ignored. To address the aforementioned limitation, we propose a novel three-stage framework for video-based student engagement measurement. First, we explore the few-shot adaptation of the vision-language model for student action recognition, which is fine-tuned to distinguish among action categories with a few training samples. Second, to handle continuous and unpredictable student actions, we utilize the sliding temporal window technique to divide each student's 2-minute-long video into non-overlapping segments. Each segment is assigned an action category via the fine-tuned VLM model, generating a sequence of action predictions. Finally, we leverage the large language model to classify this entire sequence of actions, together with the classroom context, as belonging to an engaged or disengaged student. The experimental results demonstrate the effectiveness of the proposed approach in identifying student engagement. The source code will be available at https://github.com/ahmed-nady/context_aware_student_engagement. --- ### Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing Authors: Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen, Javier Tejedor, Ling Li, Min-Hsiu Hsieh Published: 2026-01-10 Categories: quant-ph, cs.LG, eess.SP arXiv: https://arxiv.org/abs/2601.06392v1 We introduce CL-QAS, a continual quantum architecture search framework that mitigates the challenges of costly amplitude encoding and catastrophic forgetting in variational quantum circuits. The method uses Tensor-Train encoding to efficiently compress high-dimensional stochastic signals into low-rank quantum feature representations. A bi-loop learning strategy separates circuit parameter optimization from architecture exploration, while an Elastic Weight Consolidation regularization ensures stability across sequential tasks. We derive theoretical upper bounds on approximation, generalization, and robustness under quantum noise, demonstrating that CL-QAS achieves controllable expressivity, sample-efficient generalization, and smooth convergence without barren plateaus. Empirical evaluations on electrocardiogram (ECG)-based signal classification and financial time-series forecasting confirm substantial improvements in accuracy, balanced accuracy, F1 score, and reward. CL-QAS maintains strong forward and backward transfer and exhibits bounded degradation under depolarizing and readout noise, highlighting its potential for adaptive, noise-resilient quantum learning on near-term devices. --- ### Object-WIPER : Training-Free Object and Associated Effect Removal in Videos Authors: Saksham Singh Kushwaha, Sayan Nag, Yapeng Tian, Kuldeep Kulkarni Published: 2026-01-10 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.06391v2 In this paper, we introduce Object-WIPER, a training-free framework for removing dynamic objects and their associated visual effects from videos, and inpainting them with semantically consistent and temporally coherent content. Our approach leverages a pre-trained text-to-video diffusion transformer (DiT). Given an input video, a user-provided object mask, and query tokens describing the target object and its effects, we localize relevant visual tokens via visual-text cross-attention and visual self-attention. This produces an intermediate effect mask that we fuse with the user mask to obtain a final foreground token mask to replace. We first invert the video through the DiT to obtain structured noise, then reinitialize the masked tokens with Gaussian noise while preserving background tokens. During denoising, we copy values for the background tokens saved during inversion to maintain scene fidelity. To address the lack of suitable evaluation, we introduce a new object removal metric that rewards temporal consistency among foreground tokens across consecutive frames, coherence between foreground and background tokens within each frame, and dissimilarity between the input and output foreground tokens. Experiments on DAVIS and a newly curated real-world associated effect benchmark (WIPER-Bench) show that Object-WIPER surpasses both training-based and training-free baselines in terms of the metric, achieving clean removal and temporally stable reconstruction without any retraining. Our new benchmark, source code, and pre-trained models will be publicly available. --- ### Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs Authors: Zakaria Baba, Alexandre M. Bayen, Alexi Canesse, Maria Laura Delle Monache, Martin Drieux, Zhe Fu, Nathan Lichtlé, Zihe Liu, Hossein Nick Zinat Matin, Benedetto Piccoli Published: 2026-01-10 Categories: math.NA, cs.LG arXiv: https://arxiv.org/abs/2601.06388v1 We present a neural network-based method for learning scalar hyperbolic conservation laws. Our method replaces the traditional numerical flux in finite volume schemes with a trainable neural network while preserving the conservative structure of the scheme. The model can be trained both in a supervised setting with efficiently generated synthetic data or in an unsupervised manner, leveraging the weak formulation of the partial differential equation. We provide theoretical results that our model can perform arbitrarily well, and provide associated upper bounds on neural network size. Extensive experiments demonstrate that our method often outperforms efficient schemes such as Godunov's scheme, WENO, and Discontinuous Galerkin for comparable computational budgets. Finally, we demonstrate the effectiveness of our method on a traffic prediction task, leveraging field experimental highway data from the Berkeley DeepDrive drone dataset. --- ### An Efficient Evolutionary Algorithm for Few-for-Many Optimization Authors: Ke Shang, Hisao Ishibuchi, Zexuan Zhu, Qingfu Zhang Published: 2026-01-10 Categories: cs.NE arXiv: https://arxiv.org/abs/2601.06387v1 Few-for-many (F4M) optimization, recently introduced as a novel paradigm in multi-objective optimization, aims to find a small set of solutions that effectively handle a large number of conflicting objectives. Unlike traditional many-objective optimization methods, which typically attempt comprehensive coverage of the Pareto front, F4M optimization emphasizes finding a small representative solution set to efficiently address high-dimensional objective spaces. Motivated by the computational complexity and practical relevance of F4M optimization, this paper proposes a new evolutionary algorithm explicitly tailored for efficiently solving F4M optimization problems. Inspired by SMS-EMOA, our proposed approach employs a $(μ+1)$-evolution strategy guided by the objective of F4M optimization. Furthermore, to facilitate rigorous performance assessment, we propose a novel benchmark test suite specifically designed for F4M optimization by leveraging the similarity between the R2 indicator and F4M formulations. Our test suite is highly flexible, allowing any existing multi-objective optimization problem to be transformed into a corresponding F4M instance via scalarization using the weighted Tchebycheff function. Comprehensive experimental evaluations on benchmarks demonstrate the superior performance of our algorithm compared to existing state-of-the-art algorithms, especially on instances involving a large number of objectives. The source code of the proposed algorithm will be released publicly. Source code is available at https://github.com/MOL-SZU/SoM-EMOA. --- ### Hierarchical Pooling and Explainability in Graph Neural Networks for Tumor and Tissue-of-Origin Classification Using RNA-seq Data Authors: Thomas Vaitses Fontanari, Mariana Recamonde-Mendoza Published: 2026-01-10 Categories: cs.LG, q-bio.GN arXiv: https://arxiv.org/abs/2601.06381v1 This study explores the use of graph neural networks (GNNs) with hierarchical pooling and multiple convolution layers for cancer classification based on RNA-seq data. We combine gene expression data from The Cancer Genome Atlas (TCGA) with a precomputed STRING protein-protein interaction network to classify tissue origin and distinguish between normal and tumor samples. The model employs Chebyshev graph convolutions (K=2) and weighted pooling layers, aggregating gene clusters into 'supernodes' across multiple coarsening levels. This approach enables dimensionality reduction while preserving meaningful interactions. Saliency methods were applied to interpret the model by identifying key genes and biological processes relevant to cancer. Our findings reveal that increasing the number of convolution and pooling layers did not enhance classification performance. The highest F1-macro score (0.978) was achieved with a single pooling layer. However, adding more layers resulted in over-smoothing and performance degradation. However, the model proved highly interpretable through gradient methods, identifying known cancer-related genes and highlighting enriched biological processes, and its hierarchical structure can be used to develop new explainable architectures. Overall, while deeper GNN architectures did not improve performance, the hierarchical pooling structure provided valuable insights into tumor biology, making GNNs a promising tool for cancer biomarker discovery and interpretation --- ### HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agents Authors: Ningning Zhang, Xingxing Yang, Zhizhong Tan, Weiping Deng, Wenyong Wang Published: 2026-01-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06377v1 Although long-term memory systems have made substantial progress in recent years, they still exhibit clear limitations in adaptability, scalability, and self-evolution under continuous interaction settings. Inspired by cognitive theories, we propose HiMem, a hierarchical long-term memory framework for long-horizon dialogues, designed to support memory construction, retrieval, and dynamic updating during sustained interactions. HiMem constructs cognitively consistent Episode Memory via a Topic-Aware Event--Surprise Dual-Channel Segmentation strategy, and builds Note Memory that captures stable knowledge through a multi-stage information extraction pipeline. These two memory types are semantically linked to form a hierarchical structure that bridges concrete interaction events and abstract knowledge, enabling efficient retrieval without sacrificing information fidelity. HiMem supports both hybrid and best-effort retrieval strategies to balance accuracy and efficiency, and incorporates conflict-aware Memory Reconsolidation to revise and supplement stored knowledge based on retrieval feedback. This design enables continual memory self-evolution over long-term use. Experimental results on long-horizon dialogue benchmarks demonstrate that HiMem consistently outperforms representative baselines in accuracy, consistency, and long-term reasoning, while maintaining favorable efficiency. Overall, HiMem provides a principled and scalable design paradigm for building adaptive and self-evolving LLM-based conversational agents. The code is available at https://github.com/jojopdq/HiMem. --- ### Talking to Extraordinary Objects: Folktales Offer Analogies for Interacting with Technology Authors: Martha Larson Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06372v1 Speech and language are valuable for interacting with technology. It would be ideal to be able to decouple their use from anthropomorphization, which has recently met an important moment of reckoning. In the world of folktales, language is everywhere and talking to extraordinary objects is not unusual. This overview presents examples of the analogies that folktales offer. Extraordinary objects in folktales are diverse and also memorable. Language capacity and intelligence are not always connected to humanness. Consideration of folktales can offer inspiration and insight for using speech and language for interacting with technology. --- ### From Easy to Hard++: Promoting Differentially Private Image Synthesis Through Spatial-Frequency Curriculum Authors: Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang Published: 2026-01-10 Categories: cs.CR, cs.CV arXiv: https://arxiv.org/abs/2601.06368v1 To improve the quality of Differentially private (DP) synthetic images, most studies have focused on improving the core optimization techniques (e.g., DP-SGD). Recently, we have witnessed a paradigm shift that takes these techniques off the shelf and studies how to use them together to achieve the best results. One notable work is DP-FETA, which proposes using `central images' for `warming up' the DP training and then using traditional DP-SGD. Inspired by DP-FETA, we are curious whether there are other such tools we can use together with DP-SGD. We first observe that using `central images' mainly works for datasets where there are many samples that look similar. To handle scenarios where images could vary significantly, we propose FETA-Pro, which introduces frequency features as `training shortcuts.' The complexity of frequency features lies between that of spatial features (captured by `central images') and full images, allowing for a finer-grained curriculum for DP training. To incorporate these two types of shortcuts together, one challenge is to handle the training discrepancy between spatial and frequency features. To address it, we leverage the pipeline generation property of generative models (instead of having one model trained with multiple features/objectives, we can have multiple models working on different features, then feed the generated results from one model into another) and use a more flexible design. Specifically, FETA-Pro introduces an auxiliary generator to produce images aligned with noisy frequency features. Then, another model is trained with these images, together with spatial features and DP-SGD. Evaluated across five sensitive image datasets, FETA-Pro shows an average of 25.7% higher fidelity and 4.1% greater utility than the best-performing baseline, under a privacy budget $ε= 1$. --- ### SafeGPT: Preventing Data Leakage and Unethical Outputs in Enterprise LLM Use Authors: Pratyush Desai, Luoxi Tang, Yuqiao Meng, Zhaohan Xi Published: 2026-01-10 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.06366v3 Large Language Models (LLMs) are transforming enterprise workflows but introduce security and ethics challenges when employees inadvertently share confidential data or generate policy-violating content. This paper proposes SafeGPT, a two-sided guardrail system preventing sensitive data leakage and unethical outputs. SafeGPT integrates input-side detection/redaction, output-side moderation/reframing, and human-in-the-loop feedback. Experiments demonstrate SafeGPT effectively reduces data leakage risk and biased outputs while maintaining satisfaction. --- ### Human-in-the-Loop Interactive Report Generation for Chronic Disease Adherence Authors: Xiaotian Zhang, Jinhong Yu, Pengwei Yan, Le Jiang, Xingyi Shen, Mumo Cheng, Xiaozhong Liu Published: 2026-01-10 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.06364v1 Chronic disease management requires regular adherence feedback to prevent avoidable hospitalizations, yet clinicians lack time to produce personalized patient communications. Manual authoring preserves clinical accuracy but does not scale; AI generation scales but can undermine trust in patient-facing contexts. We present a clinician-in-the-loop interface that constrains AI to data organization and preserves physician oversight through recognition-based review. A single-page editor pairs AI-generated section drafts with time-aligned visualizations, enabling inline editing with visual evidence for each claim. This division of labor (AI organizes, clinician decides) targets both efficiency and accountability. In a pilot with three physicians reviewing 24 cases, AI successfully generated clinically personalized drafts matching physicians' manual authoring practice (overall mean 4.86/10 vs. 5.0/10 baseline), requiring minimal physician editing (mean 8.3\% content modification) with zero safety-critical issues, demonstrating effective automation of content generation. However, review time remained comparable to manual practice, revealing an accountability paradox: in high-stakes clinical contexts, professional responsibility requires complete verification regardless of AI accuracy. We contribute three interaction patterns for clinical AI collaboration: bounded generation with recognition-based review via chart-text pairing, automated urgency flagging that analyzes vital trends and adherence patterns with fail-safe escalation for missed critical monitoring tasks, and progressive disclosure controls that reduce cognitive load while maintaining oversight. These patterns indicate that clinical AI efficiency requires not only accurate models, but also mechanisms for selective verification that preserve accountability. --- ### Do Implicit Personalization and Explicit Styles Conflict? PsPLUG: A Lightweight Plug-in for Balancing Personalization and Style in Customized LLMs Authors: Yutong Song, Jiang Wu, Shaofan Yuan, Chengze Shen, Jian Wang, Yu Wang, Nikil Dutt, Amir M. Rahmani Published: 2026-01-10 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.06362v3 Personalized large language models are often expected to follow explicit style instructions, yet we find that such instructions can undermine the user-specific characteristics that personalization methods aim to preserve. We call this failure mode personalization collapse: explicit style control can conflict with implicit user preferences. To address this challenge, we propose PsPLUG, a lightweight plug-in that learns a user-specific residual after accounting for the requested style. PsPLUG also allows us to tune personalization strength at inference time. Our experiments show that explicit style instructions can diminish personalization in existing methods, whereas PsPLUG better preserves user preferences while providing precise control over the balance between personalization and style adherence. --- ### Average shortest-path length in word-adjacency networks: Chinese versus English Authors: Jakub Dec, Michał Dolina, Stanisław Drożdż, Jarosław Kwapień, Jin Liu, Tomasz Stanisz Published: 2026-01-10 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.06361v1 Complex networks provide powerful tools for analyzing and understanding the intricate structures present in various systems, including natural language. Here, we analyze topology of growing word-adjacency networks constructed from Chinese and English literary works written in different periods. Unconventionally, instead of considering dictionary words only, we also include punctuation marks as if they were ordinary words. Our approach is based on two arguments: (1) punctuation carries genuine information related to emotional state, allows for logical grouping of content, provides a pause in reading, and facilitates understanding by avoiding ambiguity, and (2) our previous works have shown that punctuation marks behave like words in a Zipfian analysis and, if considered together with regular words, can improve authorship attribution in stylometric studies. We focus on a functional dependence of the average shortest path length $L(N)$ on a network size $N$ for different epochs and individual novels in their original language as well as for translations of selected novels into the other language. We approximate the empirical results with a growing network model and obtain satisfactory agreement between the two. We also observe that $L(N)$ behaves asymptotically similar for both languages if punctuation marks are included but becomes sizably larger for Chinese if punctuation marks are neglected. --- ### Computational Mapping of Reactive Stroma in Prostate Cancer Yields Interpretable, Prognostic Biomarkers Authors: Mara Pleasure, Ekaterina Redekop, Dhakshina Ilango, Zichen Wang, Vedrana Ivezic, Kimberly Flores, Israa Laklouk, Jitin Makker, Gregory Fishbein, Anthony Sisk, William Speier, Corey W. Arnold Published: 2026-01-10 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2601.06360v1 Current histopathological grading of prostate cancer relies primarily on glandular architecture, largely overlooking the tumor microenvironment. Here, we present PROTAS, a deep learning framework that quantifies reactive stroma (RS) in routine hematoxylin and eosin (H&E) slides and links stromal morphology to underlying biology. PROTAS-defined RS is characterized by nuclear enlargement, collagen disorganization, and transcriptomic enrichment of contractile pathways. PROTAS detects RS robustly in the external Prostate, Lung, Colorectal, and Ovarian (PLCO) dataset and, using domain-adversarial training, generalizes to diagnostic biopsies. In head-to-head comparisons, PROTAS outperforms pathologists for RS detection, and spatial RS features predict biochemical recurrence independently of established prognostic variables (c-index 0.80). By capturing subtle stromal phenotypes associated with tumor progression, PROTAS provides an interpretable, scalable biomarker to refine risk stratification. --- ### OVT-MLCS: An Online Visual Tool for MLCS Mining from Long or Big Sequences Authors: Zhi Wang, Yanni Li, Tihua Duan, Bing Liu, Liyong Zhang, Hui Li Published: 2026-01-09 Categories: cs.DB, cs.AI arXiv: https://arxiv.org/abs/2604.13037v1 Mining multiple longest common subsequences (\textit{MLCS}) from a set of sequences of three or more over a finite alphabet $Σ$ (a classical NP-hard problem) is an important task in a wide variety of application fields. Unfortunately, there is still no exact \textit{MLCS} algorithm/tool that can handle long (length $\ge$ 1,000) or big (length $\ge$ 10,000) sequences, which seriously hinders the development and utilization of massive long or big sequences from various application fields today. To address the challenge, we first propose a novel key point-based \textit{MLCS} algorithm for mining big sequences, called \textit{KP-MLCS}, and then present a new method, which can compactly represent all mined \textit{MLCSs} and quickly reveal common patterns among them. Furthermore, by introducing some new techniques, e.g., real-time graphic visualization and serialization, we have developed a new online visual \textit{MLCS} mining tool, called OVT-MLCS. OVT-MLCS demonstrates that it not only enables effective online mining, storing, and downloading of \textit{MLCSs} in the form of graphs and text from long or big sequences with a scale of 3 to 5000 but also provides user-friendly interactive functions to facilitate inspection and analysis of the mined \textit{MLCS}s. We believe that the functions provided by OVT-MLCS will promote stronger and wider applications of \textit{MLCS}. --- ### EviSnap: Faithful Evidence-Cited Explanations for Cold-Start Cross-Domain Recommendation Authors: Yingjun Dai, Ahmed El-Roby Published: 2026-01-09 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2604.06172v1 Cold-start cross-domain recommender (CDR) systems predict a user's preferences in a target domain using only their source-domain behavior, yet existing CDR models either map opaque embeddings or rely on post-hoc or LLM-generated rationales that are hard to audit. We introduce EviSnap a lightweight CDR framework whose predictions are explained by construction with evidence-cited, faithful rationales. EviSnap distills noisy reviews into compact facet cards using an LLM offline, pairing each facet with verbatim supporting sentences. It then induces a shared, domain-agnostic concept bank by clustering facet embeddings and computes user-positive, user-negative, and item-presence concept activations via evidence-weighted pooling. A single linear concept-to-concept map transfers users across domains, and a linear scoring head yields per-concept additive contributions, enabling exact score decompositions and counterfactual 'what-if' edits grounded in the cited sentences. Experiments on the Amazon Reviews dataset across six transfers among Books, Movies, and Music show that EviSnap consistently outperforms strong mapping and review-text baselines while passing deletion- and sufficiency-based tests for explanation faithfulness. --- ### LLM-Augmented Knowledge Base Construction For Root Cause Analysis Authors: Nguyen Phuc Tran, Brigitte Jaumard, Oscar Delgado, Tristan Glatard, Karthikeyan Premkumar, Kun Ni Published: 2026-01-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2604.06171v1 Communications networks now form the backbone of our digital world, with fast and reliable connectivity. However, even with appropriate redundancy and failover mechanisms, it is difficult to guarantee "five 9s" (99.999 %) reliability, requiring rapid and accurate root cause analysis (RCA) during outages. In the event of an outage, rapid and accurate RCA becomes essential to restore service and prevent future disruptions. This study evaluates three Large Language Model (LLM) methodologies - Fine-Tuning, RAG, and a Hybrid approach - for constructing a Root Cause Analysis (RCA) Knowledge Base from support tickets. We compare their performance using a comprehensive suite of lexical and semantic similarity metrics. Our experiments on a real industrial dataset demonstrate that the generated knowledge base provides an excellent starting point for accelerating RCA tasks and improving network resilience. --- ### A Framework for Low-Latency, LLM-driven Multimodal Interaction on the Pepper Robot Authors: Erich Studerus, Vivienne Jia Zhong, Stephan Vonschallen Published: 2026-01-09 Categories: cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2603.21013v1 Despite recent advances in integrating Large Language Models (LLMs) into social robotics, two weaknesses persist. First, existing implementations on platforms like Pepper often rely on cascaded Speech-to-Text (STT)->LLM->Text-to-Speech (TTS) pipelines, resulting in high latency and the loss of paralinguistic information. Second, most implementations fail to fully leverage the LLM's capabilities for multimodal perception and agentic control. We present an open-source Android framework for the Pepper robot that addresses these limitations through two key innovations. First, we integrate end-to-end Speech-to-Speech (S2S) models to achieve low-latency interaction while preserving paralinguistic cues and enabling adaptive intonation. Second, we implement extensive Function Calling capabilities that elevate the LLM to an agentic planner, orchestrating robot actions (navigation, gaze control, tablet interaction) and integrating diverse multimodal feedback (vision, touch, system state). The framework runs on the robot's tablet but can also be built to run on regular Android smartphones or tablets, decoupling development from robot hardware. This work provides the HRI community with a practical, extensible platform for exploring advanced LLM-driven embodied interaction. --- ### Bug Severity Prediction in Software Projects Using Supervised Machine Learning Models Authors: Nafisha Tamanna Nice Published: 2026-01-09 Categories: cs.SE, cs.LG arXiv: https://arxiv.org/abs/2603.00004v1 Bug severity prediction is important in software maintenance, because it helps the development teams to prioritize bugs that have a significant impact on the operation, stability and security of the system. In large software projects bug repositories will grow at very rapid rate making classification of severity manual work labourious and unreliable and prone to human biasness. Many efforts have thus been dedicated on automated ways of severity prediction in the literature of software engineering research.This study compares different classifiers that are based on supervised machine learning algorithms for predicting bug severity levels using historical repository data from Eclipse Bugzilla. Evaluated methods range from linear classifiers, gradient boosting trees, distance method and transformer-based models, and text features, which are obtained from tokenization, TF-IDF, and n-grams and imbalance correction methods. Models were evaluated in terms of accuracy, precision, recall, F1 score, (AUC-ROC) and confusion matrix. Ensemble tree methods and DistilBERT achieved the top overall accuracy, while linear models performed best in recall of critical bugs which indicates some precision-recall tradeoff in imbalanced severity prediction. These findings provide useful actionable insight in choosing algorithms for automated bug triage, which can improve the quality of software through effective scalable prioritization. Keywords: Bug severity prediction, Supervised machine learning, Classification models, Software quality assurance, Historical bug data, Predictive analytics. ---