# Research Papers — 2026-01 · bundle page 139 of 189

> Full-text markdown of papers #6901–6950 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/139
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/138.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/140.md)

### Hybrid Secure Routing in Mobile Ad-hoc Networks (MANETSs)

Authors: Soundes Oumaima Boufaida, Abdemadjid Benmachiche, Majda Maatallah, Chaouki Chemam
Published: 2026-01-09
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2602.13204v1

Because wireless communication is dynamic and has inherent defects, routing algorithms are crucial in the quickly evolving field of mobile ad hoc networks, or MANETs This study looks at the many security problems that MANETs encounter. These problems, which pose major risks to network performance, include flooding, sinkholes, and black hole assaults to address these challenges. We introduce the Hybrid Secure Routing Protocol (HSRP), which enhances the security and robustness of routing operations by fusing trust-based tactics with cryptographic approaches. HSRP combines the strengths of both proactive and reactive routing strategies, enabling it to adapt dynamically to evolving network conditions while protecting against malicious activities. We use extensive simulations with Network Simulator (NS-2) and a thorough review of the literature to assess HSRP's performance under different attack scenarios. The results show that, in comparison to traditional protocols, HSRP increases throughput and decreases latency, hence improving routing efficiency while simultaneously bolstering data transfer security. With uses in vital domains including military operations and disaster response, this study provides a scalable and workable approach for safe routing in MANETs. The findings highlight how crucial it is to include cutting-edge security features in routing protocol design to guarantee the dependability and integrity of MANETs in practical situations.

---

### Adversarial Network Imagination: Causal LLMs and Digital Twins for Proactive Telecom Mitigation

Authors: Vignesh Sriram, Yuqiao Meng, Luoxi Tang, Zhaohan Xi
Published: 2026-01-09
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2602.13203v2

Telecommunication networks experience complex failures such as fiber cuts, traffic overloads, and cascading outages. Existing monitoring and digital twin systems are largely reactive, detecting failures only after service degradation occurs. We propose Adversarial Network Imagination, a closed-loop framework that integrates a Causal Large Language Model (LLM), a Knowledge Graph, and a Digital Twin to proactively generate, simulate, and evaluate adversarial network failures. The Causal LLM produces structured failure scenarios grounded in network dependencies encoded in the Knowledge Graph. These scenarios are executed within a Digital Twin to measure performance degradation and evaluate mitigation strategies. By iteratively refining scenarios based on simulation feedback, the framework shifts network operations from reactive troubleshooting toward anticipatory resilience analysis.

---

### UniFinEval: Towards Unified Evaluation of Financial Multimodal Models across Text, Images and Videos

Authors: Zhi Yang, Lingfeng Zeng, Fangqi Lou, Qi Qi, Wei Zhang, Zhenyu Wu, Zhenxiong Yu, Jun Han, Zhiheng Jin, Lejie Zhang, Xiaoming Huang, Xiaolong Liang et al.
Published: 2026-01-09
Categories: q-fin.GN, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.22162v1

Multimodal large language models are playing an increasingly significant role in empowering the financial domain, however, the challenges they face, such as multimodal and high-density information and cross-modal multi-hop reasoning, go beyond the evaluation scope of existing multimodal benchmarks. To address this gap, we propose UniFinEval, the first unified multimodal benchmark designed for high-information-density financial environments, covering text, images, and videos. UniFinEval systematically constructs five core financial scenarios grounded in real-world financial systems: Financial Statement Auditing, Company Fundamental Reasoning, Industry Trend Insights, Financial Risk Sensing, and Asset Allocation Analysis. We manually construct a high-quality dataset consisting of 3,767 question-answer pairs in both chinese and english and systematically evaluate 10 mainstream MLLMs under Zero-Shot and CoT settings. Results show that Gemini-3-pro-preview achieves the best overall performance, yet still exhibits a substantial gap compared to financial experts. Further error analysis reveals systematic deficiencies in current models. UniFinEval aims to provide a systematic assessment of MLLMs' capabilities in fine-grained, high-information-density financial environments, thereby enhancing the robustness of MLLMs applications in real-world financial scenarios. Data and code are available at https://github.com/aifinlab/UniFinEval.

---

### The Grammar of Transformers: A Systematic Review of Interpretability Research on Syntactic Knowledge in Language Models

Authors: Nora Graichen, Iria de-Dios-Flores, Gemma Boleda
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19926v3

We present a systematic review of 337 articles evaluating the syntactic abilities of Transformer-based language models (TLMs), reporting on over 3,000 datapoints spanning a wide range of syntactic phenomena, languages, models, and methods. We take the data to collectively show that TLMs encode a non-trivial amount of syntactic knowledge. Behavioral evidence shows strong performance on formal syntactic phenomena, but weaker and more variable performance on phenomena at the syntax-semantics interface. Performance is also consistently lower for languages with less digital support. Probing and mechanistic studies further support the presence of syntactic knowledge in TLMs. Yet, because most work remains observational and methodologically heterogeneous, insight into the detailed computational mechanisms underlying syntactic processing remains limited. At the same time, the literature remains heavily concentrated on English and BERT-like models. We discuss the implications of our results and provide recommendations for future research.

---

### Evaluating Large Language Models for Abstract Evaluation Tasks: An Empirical Study

Authors: Yinuo Liu, Emre Sezgin, Eric A. Youngstrom
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19925v1

Introduction: Large language models (LLMs) can process requests and generate texts, but their feasibility for assessing complex academic content needs further investigation. To explore LLM's potential in assisting scientific review, this study examined ChatGPT-5, Gemini-3-Pro, and Claude-Sonnet-4.5's consistency and reliability in evaluating abstracts compared to one another and to human reviewers. Methods: 160 abstracts from a local conference were graded by human reviewers and three LLMs using one rubric. Composite score distributions across three LLMs and fourteen reviewers were examined. Inter-rater reliability was calculated using intraclass correlation coefficients (ICCs) for within-AI reliability and AI-human concordance. Bland-Altman plots were examined for visual agreement patterns and systematic bias. Results: LLMs achieved good-to-excellent agreement with each other (ICCs: 0.59-0.87). ChatGPT and Claude reached moderate agreement with human reviewers on overall quality and content-specific criteria, with ICCs ~.45-.60 for composite, impression, clarity, objective, and results. They exhibited fair agreement on subjective dimensions, with ICC ranging from 0.23-0.38 for impact, engagement, and applicability. Gemini showed fair agreement on half criteria and no reliability on impact and applicability. Three LLMs showed acceptable or negligible mean difference (ChatGPT=0.24, Gemini=0.42, Claude=-0.02) from the human mean composite scores. Discussion: LLMs could process abstracts in batches with moderate agreement with human experts on overall quality and objective criteria. With appropriate process architecture, they can apply a rubric consistently across volumes of abstracts exceeding feasibility for a human rater. The weaker performance on subjective dimensions indicates that AI should serve a complementary role in evaluation, while human expertise remains essential.

---

### OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling

Authors: Yitian Chen, Cheng Cheng, Yinan Sun, Zi Ling, Dongdong Ge
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.19924v2

We investigate the capabilities and scalability of Large Language Models (LLMs) in optimization modeling, a domain requiring structured reasoning and precise formulation. To this end, we introduce OPT-ENGINE, an extensible benchmark framework with quantifiable and controllable complexity. OPT-ENGINE spans ten canonical Operations Research problems, systematically scaling from Linear Programming to Mixed-Integer Programming, providing a structured environment to probe the limits of automated problem formulation and solving. Utilizing OPT-Engine, we address three pivotal research questions. First, we examine whether Pure-Text Reasoning (PTR) via classical Chain-of-Thought can efficiently tackle optimization tasks, finding that PTR suffers from a critical robustness gap as task complexity increases. Second, we examine whether integrating external computational tools can mitigate PTR's arithmetic weaknesses and improve performance. Our results indicate that while such tools help with local calculations, they still fail to adhere to global optimization constraints. Finally, we pinpoint that for the current SOTA paradigm, Solver-integrated Reasoning (SIR), the automated formulation of constraints represents the primary bottleneck. These findings clarify the limitations of current paradigms and provide a structured roadmap for developing next-generation LLMs for optimization modeling. We release our code and data to facilitate future research (https://github.com/Cardinal-Operations/OPTEngine).

---

### Structure-BiEval: A Self-Supervised, Dual-Track Framework for Decoupling Structure and Content in LLM Evaluation for Web Information Systems

Authors: Boxiang Zhao, Qince Li, Zhonghao Wang, Zelin Cao, Yi Wang, Peng Cheng, Bo Lin
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19923v2

As Large Language Models (LLMs) evolve into the core of Web-based autonomous agents and complex Web Information Systems, their ability to faithfully translate natural language into rigorous structured formats has become paramount, as this capability is critical for Web API invocation and data exchange. However, evaluating this structural fidelity in Web-native payloads remains a challenge: traditional text metrics fail to capture topological consistency in semi-structured Web data, while manual evaluation is prohibitively costly. To address this, we propose Structure-BiEval, a novel self-supervised framework for quantitative, annotation-free assessment tailored for Web data engineering. By leveraging deterministic Intermediate Representations, our framework effectively decouples structure from content, utilizing Content Semantic Accuracy and Normalized Tree Edit Distance as precise metrics. We empirically benchmark 15 state-of-the-art LLMs across dual Web structural topologies, namely Hierarchical Data (Web backend payloads) and Tabular Data (Web frontend presentation). The results reveal substantial variability in structural performance, including cases where mid-sized models unexpectedly outperform larger counterparts in Web data formatting. Furthermore, our findings show that deep recursive nesting poses a consistent challenge for Web agents across varying parameter scales.

---

### HEART: A Unified Benchmark for Assessing Humans and LLMs in Emotional Support Dialogue

Authors: Laya Iyer, Kriti Aggarwal, Sanmi Koyejo, Gail Heyman, Desmond C. Ong, Subhabrata Mukherjee
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19922v2

Supportive conversation depends on skills that go beyond language fluency, including reading emotions, adjusting tone, and navigating moments of resistance, frustration, or distress. Despite rapid progress in language models, we still lack a clear way to understand how their abilities in these interpersonal domains compare to those of humans. We introduce HEART, the first-ever framework that directly compares humans and LLMs on the same multi-turn emotional-support conversations. For each dialogue history, we pair human and model responses and evaluate them through blinded human raters and an ensemble of LLM-as-judge evaluators. All assessments follow a rubric grounded in interpersonal communication science across five dimensions: Human Alignment, Empathic Responsiveness, Attunement, Resonance, and Task-Following. HEART uncovers striking behavioral patterns. Several frontier models approach or surpass the average human responses in perceived empathy and consistency. At the same time, humans maintain advantages in adaptive reframing, tension-naming, and nuanced tone shifts, particularly in adversarial turns. Human and LLM-as-judge preferences align on about 80 percent of pairwise comparisons, matching inter-human agreement, and their written rationales emphasize similar HEART dimensions. This pattern suggests an emerging convergence in the criteria used to assess supportive quality. By placing humans and models on equal footing, HEART reframes supportive dialogue as a distinct capability axis, separable from general reasoning or linguistic fluency. It provides a unified empirical foundation for understanding where model-generated support aligns with human social judgment, where it diverges, and how affective conversational competence scales with model size.

---

### Demystifying Multi-Agent Debate: The Role of Confidence and Diversity

Authors: Xiaochen Zhu, Caiqi Zhang, Yizhou Chi, Tom Stafford, Nigel Collier, Andreas Vlachos
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19921v3

Multi-agent debate (MAD) is widely used to improve large language model (LLM) performance through test-time scaling, yet recent work shows that vanilla MAD often underperforms simple majority vote despite higher computational cost. Studies show that, under homogeneous agents and uniform belief updates, debate preserves expected correctness and therefore cannot reliably improve outcomes. Drawing on findings from human deliberation and collective decision-making, we identify two key mechanisms missing from vanilla MAD: (i) diversity of initial viewpoints and (ii) explicit, calibrated confidence communication. We propose two lightweight interventions. First, a diversity-aware initialisation that selects a more diverse pool of candidate answers, increasing the likelihood that a correct hypothesis is present at the start of debate. Second, a confidence-modulated debate protocol in which agents express calibrated confidence and condition their updates on others' confidence. We show theoretically that diversity-aware initialisation improves the prior probability of MAD success without changing the underlying update dynamics, while confidence-modulated updates enable debate to systematically drift to the correct hypothesis. Empirically, across six reasoning-oriented QA benchmarks, our methods consistently outperform vanilla MAD and majority vote. Our results connect human deliberation with LLM-based debate and demonstrate that simple, principled modifications can substantially enhance debate effectiveness.

---

### Can We Trust LLM Detectors?

Authors: Jivnesh Sandhan, Harshit Jaiswal, Fei Cheng, Yugo Murawaki
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.15301v2

The rapid adoption of LLMs has increased the need for reliable AI text detection, yet existing detectors often fail outside controlled benchmarks. We systematically evaluate 2 dominant paradigms (training-free and supervised) and show that both are brittle under distribution shift, unseen generators, and simple stylistic perturbations. To address these limitations, we propose a supervised contrastive learning (SCL) framework that learns discriminative style embeddings. Experiments show that while supervised detectors excel in-domain, they degrade sharply out-of-domain, and training-free methods remain highly sensitive to proxy choice. Overall, our results expose fundamental challenges in building domain-agnostic detectors. Our code is available at: https://github.com/HARSHITJAIS14/DetectAI

---

### Mixture-of-Experts as Soft Clustering: A Dual Jacobian-PCA Spectral Geometry Perspective

Authors: Feilong Liu
Published: 2026-01-09
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.11616v2

Mixture-of-Experts (MoE) architectures are widely used for efficiency and conditional computation, but their effect on the geometry of learned functions and representations remains poorly understood. We study MoEs through a geometric lens, interpreting routing as soft partitioning into overlapping expert-local charts. We introduce a Dual Jacobian-PCA spectral probe that analyzes local function geometry via Jacobian singular value spectra and representation geometry via weighted PCA of routed hidden states. Using a controlled MLP-MoE setting with exact Jacobian computation, we compare dense, Top-k, and fully soft routing under matched capacity. Across random seeds, MoE routing consistently reduces local sensitivity: expert-local Jacobians show smaller leading singular values and faster spectral decay than dense baselines. Weighted PCA reveals that expert-local representations distribute variance across more principal directions, indicating higher effective rank. We further observe low alignment among expert Jacobians, suggesting decomposition into low-overlap expert-specific transformations. Routing sharpness modulates these effects: Top-k routing yields more concentrated, lower-rank expert structure, while fully soft routing produces broader, higher-rank representations. Experiments on a 3-layer transformer with WikiText confirm curvature reduction on natural language and show lower cross-expert alignment for Top-k routing. These findings support interpreting MoEs as soft partitionings of function space that flatten local curvature while redistributing representation variance, yielding testable predictions for expert scaling, hallucination reduction, and ensemble diversity.

---

### A Review on Machine Learning Approaches for the Prediction of Glucose Levels and Hypogylcemia

Authors: Beyza Cinar, Louisa van den Boom, Maria Maleshkova
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.11615v1

Type 1 Diabetes (T1D) is an autoimmune disease leading to insulin insufficiency. Thus, patients require lifelong insulin therapy, which has a side effect of hypoglycemia. Hypoglycemia is a critical state of decreased blood glucose levels (BGL) below 70 mg/dL and is associated with increased risk of mortality. Machine learning (ML) models can improve diabetes management by predicting hypoglycemia and providing optimal prevention methods. ML models are classified into regression and classification based, that forecast glucose levels and identify events based on defined labels, respectively. This review investigates state-of-the-art models trained on data of continuous glucose monitoring (CGM) devices from patients with T1D. We compare the models' performance across short-term (15 to 120 min) and long term (3 to more than 24 hours) prediction horizons (PHs). Particularly, we explore: 1) How much in advance can glucose values or a hypoglycemic event be accurately predicted? 2) Which models have the best performance? 3) Which factors impact the performance? and 4) Does personalization increase performance? The results show that 1) a PH of up to 1 hour provides the best results. 2) Conventional ML methods yield the best results for classification and DL for regression. A single model cannot adequately classify across multiple PHs. 3) The model performance is influenced by multivariate datasets and the input sequence length (ISL). 4) Personal data enhances performance but due to limited data quality population-based models are preferred.

---

### Multi-modal MRI-Based Alzheimer's Disease Diagnosis with Transformer-based Image Synthesis and Transfer Learning

Authors: Jason Qiu
Published: 2026-01-09
Categories: cs.CV, cs.LG, q-bio.NC
arXiv: https://arxiv.org/abs/2601.11614v1

Alzheimer's disease (AD) is a progressive neurodegenerative disorder in which pathological changes begin many years before the onset of clinical symptoms, making early detection essential for timely intervention. T1-weighted (T1w) Magnetic Resonance Imaging (MRI) is routinely used in clinical practice to identify macroscopic brain alterations, but these changes typically emerge relatively late in the disease course. Diffusion MRI (dMRI), in contrast, is sensitive to earlier microstructural abnormalities by probing water diffusion in brain tissue. dMRI metrics, including fractional anisotropy (FA) and mean diffusivity (MD), provide complementary information about white matter integrity and neurodegeneration. However, dMRI acquisitions are time-consuming and susceptible to motion artifacts, limiting their routine use in clinical populations. To bridge this gap, I propose a 3D TransUNet image synthesis framework that predicts FA and MD maps directly from T1w MRI. My model generates high-fidelity maps, achieving a structural similarity index (SSIM) exceeding 0.93 and a strong Pearson correlation (>0.94) with ground-truth dMRI. When integrated into a multi-modal diagnostic model, these synthetic features boost AD classification accuracy by 5% (78.75%->83.75%) and, most importantly, improve mild cognitive impairment (MCI) detection by 12.5%. This study demonstrates that high-quality diffusion microstructural information can be inferred from routinely acquired T1w MRI, effectively transferring the benefits of multi-modality imaging to settings where diffusion data are unavailable. By reducing scan time while preserving complementary structural and microstructural information, the proposed approach has the potential to improve the accessibility, efficiency, and accuracy of AD diagnosis in clinical practice.

---

### Domain-Specific Self-Supervised Pre-training for Agricultural Disease Classification: A Hierarchical Vision Transformer Study

Authors: Arnav S. Sonavane
Published: 2026-01-09
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.11612v1

We investigate the impact of domain-specific self-supervised pre-training on agricultural disease classification using hierarchical vision transformers. Our key finding is that SimCLR pre-training on just 3,000 unlabeled agricultural images provides a +4.57% accuracy improvement--exceeding the +3.70% gain from hierarchical architecture design. Critically, we show this SSL benefit is architecture-agnostic: applying the same pre-training to Swin-Base yields +4.08%, to ViT-Base +4.20%, confirming practitioners should prioritize domain data collection over architectural choices. Using HierarchicalViT (HVT), a Swin-style hierarchical transformer, we evaluate on three datasets: Cotton Leaf Disease (7 classes, 90.24%), PlantVillage (38 classes, 96.3%), and PlantDoc (27 classes, 87.1%). At matched parameter counts, HVT-Base (78M) achieves 88.91% vs. Swin-Base (88M) at 87.23%, a +1.68% improvement. For deployment reliability, we report calibration analysis showing HVT achieves 3.56% ECE (1.52% after temperature scaling). Code: https://github.com/w2sg-arnav/HierarchicalViT

---

### Integrating Temporal Context into Streaming Data for Human Activity Recognition in Smart Home

Authors: Marina Vicini, Martin Rudorfer, Zhuangzhuang Dai, Luis J. Manso
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.11611v1

With the global population ageing, it is crucial to enable individuals to live independently and safely in their homes. Using ubiquitous sensors such as Passive InfraRed sensors (PIR) and door sensors is drawing increasing interest for monitoring daily activities and facilitating preventative healthcare interventions for the elderly. Human Activity Recognition (HAR) from passive sensors mostly relies on traditional machine learning and includes data segmentation, feature extraction, and classification. While techniques like Sensor Weighting Mutual Information (SWMI) capture spatial context in a feature vector, effectively leveraging temporal information remains a challenge. We tackle this by clustering activities into morning, afternoon, and night, and encoding them into the feature weighting method calculating distinct mutual information matrices. We further propose to extend the feature vector by incorporating time of day and day of week as cyclical temporal features, as well as adding a feature to track the user's location. The experiments show improved accuracy and F1-score over existing state-of-the-art methods in three out of four real-world datasets, with highest gains in a low-data regime. These results highlight the potential of our approach for developing effective smart home solutions to support ageing in place.

---

### Multifaceted Scenario-Aware Hypergraph Learning for Next POI Recommendation

Authors: Yuxi Lin, Yongkang Li, Jie Xing, Zipei Fan
Published: 2026-01-09
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2601.11610v2

Among the diverse services provided by Location-Based Social Networks (LBSNs), Next Point-of-Interest (POI) recommendation plays a crucial role in inferring user preferences from historical check-in trajectories. However, existing sequential and graph-based methods frequently neglect significant mobility variations across distinct contextual scenarios (e.g., tourists versus locals). This oversight results in suboptimal performance due to two fundamental limitations: the inability to capture scenario-specific features and the failure to resolve inherent inter-scenario conflicts. To overcome these limitations, we propose the Multifaceted Scenario-Aware Hypergraph Learning method (MSAHG), a framework that adopts a scenario-splitting paradigm for next POI recommendation. Our main contributions are: (1) Construction of scenario-specific, multi-view disentangled sub-hypergraphs to capture distinct mobility patterns; (2) A parameter-splitting mechanism to adaptively resolve conflicting optimization directions across scenarios while preserving generalization capability. Extensive experiments on three real-world datasets demonstrate that MSAHG consistently outperforms five state-of-the-art methods across diverse scenarios, confirming its effectiveness in multi-scenario POI recommendation.

---

### Auxiliary-predicted Compress Memory Model(ApCM Model): A Neural Memory Storage Model Based on Invertible Compression and Learnable Prediction

Authors: Weinuo Ou
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.11609v2

Current large language models (LLMs) generally lack an effective runtime memory mechanism,making it difficult to adapt to dynamic and personalized interaction requirements. To address this issue, this paper proposes a novel neural memory storage architecture--the Auxiliary Prediction Compression Memory Model (ApCM Model).

---

### Hardware-Aware Reformulation of Convolutions for Efficient Execution on Specialized AI Hardware: A Case Study on NVIDIA Tensor Cores

Authors: Ganesh Bikshandi
Published: 2026-01-09
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2601.11608v1

Convolutional Neural Networks (CNNs) are central to modern AI, but their performance is often limited by hardware constraints. NVIDIA Tensor Cores, for instance, require input channels to be multiples of 8 and sometimes 512 for efficient execution. {\em oneDNN} framework for CPU imposes such a requirement for the blocked format. Traditional approaches address such alignment issue using zero-padding, which can be inefficient. In this work, we present a first-step, hardware-aware reformulation of CNN computations using rewrite rules, restructuring the underlying math to satisfy hardware alignment entirely {\bf post-training} without modifying network weights. While our current implementation focuses on a single transformation for Tensor Cores, this approach is generalizable, laying the foundation to explore additional transformations for CPU and accelerators. This study represents an initial step toward {\em semantic tuning}, a systematic, hardware-aware optimization strategy for efficient deployment of CNN models on specialized AI hardware.

---

### CTHA: Constrained Temporal Hierarchical Architecture for Stable Multi-Agent LLM Systems

Authors: Percy Jardine
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10738v1

Recently, multi-time-scale agent architectures have extended the ubiquitous single-loop paradigm by introducing temporal hierarchies with distinct cognitive layers. While yielding substantial performance gains, this diversification fundamentally compromises the coordination stability intrinsic to unified agent systems, which causes severe inter-layer conflicts, unbounded error propagation, and restricted scalability. To address these challenges, we propose Constrained Temporal Hierarchical Architecture (CTHA), a general framework that projects the inter-layer communication space onto structured manifolds to restore coordination stability, while incorporating principled arbitration mechanisms to ensure coherent decision-making. Specifically, CTHA enforces three key constraints: (1) Message Contract Constraints that formalize information flow between layers via typed summary, plan, and policy packets; (2) Authority Manifold Constraints that bound each layer's decision space according to its temporal scope; and (3) Arbiter Resolution Constraints that guarantee conflict-free composition of multi-layer decisions. Empirical experiments demonstrate that CTHA is effective for complex task execution at scale, offering 47% reduction in failure cascades, 2.3x improvement in sample efficiency, and superior scalability compared to unconstrained hierarchical baselines. We anticipate that CTHA, as a principled extension of temporal hierarchies, will contribute to a deeper understanding of multi-agent coordination and suggest promising directions for the evolution of robust autonomous systems.

---

### Bias Detection and Rotation-Robustness Mitigation in Vision-Language Models and Generative Image Models

Authors: Tarannum Mithila
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.08860v1

Vision-Language Models (VLMs) and generative image models have achieved remarkable performance across multimodal tasks, yet their robustness and fairness under input transformations remain insufficiently explored. This work investigates bias propagation and robustness degradation in state-of-the-art vision-language and generative models, with a particular focus on image rotation and distributional shifts. We analyze how rotation-induced perturbations affect model predictions, confidence calibration, and demographic bias patterns. To address these issues, we propose rotation-robust mitigation strategies that combine data augmentation, representation alignment, and model-level regularization. Experimental results across multiple datasets demonstrate that the proposed methods significantly improve robustness while reducing bias amplification without sacrificing overall performance. This study highlights critical limitations of current multimodal systems and provides practical mitigation techniques for building more reliable and fair AI models.

---

### Affect and Effect: Limitations of regularisation-based continual learning in EEG-based emotion classification

Authors: Nina Peire, Yupei Li, Björn Schuller
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07858v1

Generalisation to unseen subjects in EEG-based emotion classification remains a challenge due to high inter-and intra-subject variability. Continual learning (CL) poses a promising solution by learning from a sequence of tasks while mitigating catastrophic forgetting. Regularisation-based CL approaches, such as Elastic Weight Consolidation (EWC), Synaptic Intelligence (SI), and Memory Aware Synapses (MAS), are commonly used as baselines in EEG-based CL studies, yet their suitability for this problem remains underexplored. This study theoretically and empirically finds that regularisation-based CL methods show limited performance for EEG-based emotion classification on the DREAMER and SEED datasets. We identify a fundamental misalignment in the stability-plasticity trade-off, where regularisation-based methods prioritise mitigating catastrophic forgetting (backward transfer) over adapting to new subjects (forward transfer). We investigate this limitation under subject-incremental sequences and observe that: (1) the heuristics for estimating parameter importance become less reliable under noisy data and covariate shift, (2) gradients on parameters deemed important by these heuristics often interfere with gradient updates required for new subjects, moving optimisation away from the minimum, (3) importance values accumulated across tasks over-constrain the model, and (4) performance is sensitive to subject order. Forward transfer showed no statistically significant improvement over sequential fine-tuning (p > 0.05 across approaches and datasets). The high variability of EEG signals means past subjects provide limited value to future subjects. Regularisation-based continual learning approaches are therefore limited for robust generalisation to unseen subjects in EEG-based emotion classification.

---

### Feature Entanglement-based Quantum Multimodal Fusion Neural Network

Authors: Yu Wu, Qianli Zhou, Jie Geng, Xinyang Deng, Wen Jiang
Published: 2026-01-09
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.07856v1

Multimodal learning aims to enhance perceptual and decision-making capabilities by integrating information from diverse sources. However, classical deep learning approaches face a critical trade-off between the high accuracy of black-box feature-level fusion and the interpretability of less outstanding decision-level fusion, alongside the challenges of parameter explosion and complexity. This paper discusses the accuracy-interpretablity-complexity dilemma under the quantum computation framework and propose a feature entanglement-based quantum multimodal fusion neural network. The model is composed of three core components: a classical feed-forward module for unimodal processing, an interpretable quantum fusion block, and a quantum convolutional neural network (QCNN) for deep feature extraction. By leveraging the strong expressive power of quantum, we have reduced the complexity of multimodal fusion and post-processing to linear, and the fusion process also possesses the interpretability of decision-level fusion. The simulation results demonstrate that our model achieves classification accuracy comparable to classical networks with dozens of times of parameters, exhibiting notable stability and performance across multimodal image datasets.

---

### RoAD Benchmark: How LiDAR Models Fail under Coupled Domain Shifts and Label Evolution

Authors: Subeen Lee, Siyeong Lee, Namil Kim, Jaesik Choi
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.07855v2

For 3D perception systems to operate reliably in real-world environments, they must remain robust to evolving sensor characteristics and changes in object taxonomies. However, existing adaptive learning paradigms struggle in LiDAR settings where domain shifts and label-space evolution occur simultaneously. We introduce \textbf{Robust Autonomous Driving under Dataset shifts (RoAD)}, a benchmark for evaluating model robustness in LiDAR-based object classification under intertwined domain shifts and label evolution, including subclass refinement, unseen-class insertion, and label expansion. RoAD evaluates three learning scenarios with increasing adaptation, from fixed representations (zero-shot transfer and linear probing) to sequential updates (continual learning). Experiments span large-scale autonomous driving datasets, including Waymo, nuScenes, and Argoverse2. Our analysis identifies central failure modes: (i) \textit{limited transferability} under subclass refinement and unseen-class insertion, and on non-vehicle class; and (ii) \textit{accelerated forgetting during continual adaptation}, driven by feature collapse and self-supervised learning objectives.

---

### Immunological Density Shapes Recovery Trajectories in Long COVID

Authors: Jing Wang, Tong Zhang, Xing Niu, Jie Shen, Yiming Luo, Qiaomin Xie, Amar Sra, Zorina Galis, Jeremy Weiss
Published: 2026-01-09
Categories: q-bio.OT, cs.AI
arXiv: https://arxiv.org/abs/2601.07854v1

Post-acute sequelae of SARS-CoV-2 infection (Long COVID) frequently persists for months, yet drivers of clinical remission remain incompletely defined. Here we analyzed 97,564 longitudinal PASC assessments from 13,511 participants with linked vaccination histories to disentangle passive temporal progression from vaccine-associated change. Using a clinically validated threshold (PASC $\geq 12$), trajectories separated into three phenotypes: Protected (persistently sub-threshold), Refractory (persistently symptomatic), and Responders (transitioning from symptomatic to recovered). Across the full cohort, symptom severity increased modestly with elapsed time ($r=0.0521$, $P=1.26\times10^{-59}$), whereas cumulative vaccination showed an inverse association with severity ($r=-0.0434$, $P=5.95\times10^{-42}$). In summary, baseline Long COVID severity appears clinically deterministic. In the absence of intervention, symptoms typically persist without spontaneous resolution. Recovery is primarily associated with repeated immunization.

---

### FinVault: Benchmarking Financial Agent Safety in Execution-Grounded Environments

Authors: Zhi Yang, Runguo Li, Qiqi Qiang, Jiashun Wang, Fangqi Lou, Mengping Li, Dongpo Cheng, Rui Xu, Heng Lian, Shuo Zhang, Xiaolong Liang, Xiaoming Huang et al.
Published: 2026-01-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.07853v2

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce new security risks in high-stakes and highly regulated financial environments. However, existing safety evaluations largely focus on language-model-level content compliance or abstract agent settings, failing to capture execution-grounded risks arising from real operational workflows and state-changing actions. To bridge this gap, we propose FinVault, the first execution-grounded security benchmark for financial agents, comprising 31 regulatory case-driven sandbox scenarios with state-writable databases and explicit compliance constraints, together with 107 real-world vulnerabilities and 963 test cases that systematically cover prompt injection, jailbreaking, financially adapted attacks, as well as benign inputs for false-positive evaluation. Experimental results reveal that existing defense mechanisms remain ineffective in realistic financial agent settings, with average attack success rates (ASR) still reaching up to 50.0\% on state-of-the-art models and remaining non-negligible even for the most robust systems (ASR 6.7\%), highlighting the limited transferability of current safety designs and the need for stronger financial-specific defenses. Our code can be found at https://github.com/aifinlab/FinVault.

---

### Smart Privacy Policy Assistant: An LLM-Powered System for Transparent and Actionable Privacy Notices

Authors: Sriharshini Kalvakuntla, Luoxi Tang, Yuqiao Meng, Zhaohan Xi
Published: 2026-01-09
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06357v1

Most users agree to online privacy policies without reading or understanding them, even though these documents govern how personal data is collected, shared, and monetized. Privacy policies are typically long, legally complex, and difficult for non-experts to interpret. This paper presents the Smart Privacy Policy Assistant, an LLM-powered system that automatically ingests privacy policies, extracts and categorizes key clauses, assigns human-interpretable risk levels, and generates clear, concise explanations. The system is designed for real-time use through browser extensions or mobile interfaces, surfacing contextual warnings before users disclose sensitive information or grant risky permissions. We describe the end-to-end pipeline, including policy ingestion, clause categorization, risk scoring, and explanation generation, and propose an evaluation framework based on clause-level accuracy, policy-level risk agreement, and user comprehension.

---

### Monkey Jump : MoE-Style PEFT for Efficient Multi-Task Learning

Authors: Nusrat Jahan Prottasha, Md Kowsher, Chun-Nam Yu, Chen Chen, Ozlem Garibay
Published: 2026-01-09
Categories: cs.LG, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.06356v1

Mixture-of-experts variants of parameter-efficient fine-tuning enable per-token specialization, but they introduce additional trainable routers and expert parameters, increasing memory usage and training cost. This undermines the core goal of parameter-efficient fine-tuning. We propose Monkey Jump, a method that brings mixture-of-experts-style specialization to parameter-efficient fine-tuning without introducing extra trainable parameters for experts or routers. Instead of adding new adapters as experts, Monkey Jump treats the adapters already present in each Transformer block (such as query, key, value, up, and down projections) as implicit experts and routes tokens among them. Routing is performed using k-means clustering with exponentially moving averaged cluster centers, requiring no gradients and no learned parameters. We theoretically show that token-wise routing increases expressivity and can outperform shared adapters by avoiding cancellation effects. Across multi-task experiments covering 14 text, 14 image, and 19 video benchmarks, Monkey Jump achieves competitive performance with mixture-of-experts-based parameter-efficient fine-tuning methods while using 7 to 29 times fewer trainable parameters, up to 48 percent lower memory consumption, and 1.5 to 2 times faster training. Monkey Jump is architecture-agnostic and can be applied to any adapter-based parameter-efficient fine-tuning method.

---

### CARD: Cluster-level Adaptation with Reward-guided Decoding for Personalized Text Generation

Authors: Yutong Song, Jiang Wu, Weijia Zhang, Chengze Shen, Shaofan Yuan, Weitao Lu, Jian Wang, Yu Wang, Nikil Dutt, Amir M. Rahmani
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06352v3

Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployment. We present CARD, a hierarchical framework that achieves effective personalization through progressive refinement. CARD first clusters users according to shared stylistic patterns and learns group-specific LoRA adapters, enabling robust generalization and strong low-resource performance. To capture individual differences within each cluster, we propose an implicit preference learning mechanism that contrasts user-authored text with cluster-level generations, allowing the model to infer user-specific style preferences without manual annotation. At inference time, CARD injects personalization exclusively at decoding via lightweight user preference vectors and low-rank logit corrections, while keeping the base model frozen. Experiments on the LaMP and LongLaMP benchmarks show that CARD achieves superior generation quality compared to baselines, while significantly improving efficiency and scalability for practical personalized text generation.

---

### A Fast and Effective Method for Euclidean Anticlustering: The Assignment-Based-Anticlustering Algorithm

Authors: Philipp Baumann, Olivier Goldschmidt, Dorit S. Hochbaum, Jason Yang
Published: 2026-01-09
Categories: cs.LG, cs.DM
arXiv: https://arxiv.org/abs/2601.06351v2

Anticlustering is an NP-hard combinatorial optimization problem that consists of partitioning a set of objects into equal-sized groups called anticlusters such that the objects in the same anticluster are as dissimilar as possible and thereby representative of the entire set of objects. Here we study the case where the dissimilarity metric is the squared Euclidean distance between the respective feature vectors. Applications of Euclidean anticlustering include social studies, cross-validation, creating mini-batches for stochastic gradient descent, and finding balanced K-cut partitions. In particular, machine-learning applications such as mini-batch generation involve million-scale datasets and very large values of K, making scalable anticlustering algorithms essential. We propose a new algorithm, the Assignment-Based Anticlustering (ABA) algorithm, that scales to instances with millions of objects and hundreds of thousands of anticlusters within seconds to minutes, which is far beyond what existing anticlustering methods can manage. We demonstrate here, via an extensive computational study, that our algorithm outperforms existing anticlustering methods in both solution quality and running time. This is so also for anticlustering with categories. For the related problem of balanced K-cut partitioning, our algorithm is superior to the well-known METIS method. The code of our algorithm is available on GitHub.

---

### Federated Learning and Class Imbalances

Authors: Siqi Zhu, Joshua D. Kaggie
Published: 2026-01-09
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06348v1

Federated Learning (FL) enables collaborative model training across decentralized devices while preserving data privacy. However, real-world FL deployments face critical challenges such as data imbalances, including label noise and non-IID distributions. RHFL+, a state-of-the-art method, was proposed to address these challenges in settings with heterogeneous client models. This work investigates the robustness of RHFL+ under class imbalances through three key contributions: (1) reproduction of RHFL+ along with all benchmark algorithms under a unified evaluation framework; (2) extension of RHFL+ to real-world medical imaging datasets, including CBIS-DDSM, BreastMNIST and BHI; (3) a novel implementation using NVFlare, NVIDIA's production-level federated learning framework, enabling a modular, scalable and deployment-ready codebase. To validate effectiveness, extensive ablation studies, algorithmic comparisons under various noise conditions and scalability experiments across increasing numbers of clients are conducted.

---

### What Matters When Building Universal Multilingual Named Entity Recognition Models?

Authors: Jonas Golde, Patrick Haller, Alan Akbik
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06347v3

Recent progress in universal multilingual named entity recognition (NER) has been driven by multilingual transformer models, task-specific architectures, custom loss functions, and large-scale training datasets. However, despite substantial prior work, we find that many design decisions for such models are made without systematic justification, with individual components evaluated only in combination rather than in isolation. We argue that this impedes progress in the field by making it difficult to identify which choices improve multilingual generalization. In this work, we conduct an extensive empirical evaluation on transformer backbones, architectures, training objectives, data composition, and threshold selection for zero-shot, multilingual NER models. Building on these findings, we present Otter, a small encoder model that achieves consistent improvements over strong multilingual NER baselines, outperforming similarly sized models by 5.7 percentage points in F1. Further, it remains within 1.4 points of Qwen3-32B and 5.4 points below Gemma3-27B, while being roughly 90x smaller and one to two orders of magnitude faster at inference.

---

### Evaluating Robustness of Large Language Models in Enterprise Applications: Benchmarks for Perturbation Consistency Across Formats and Languages

Authors: Tara Bogavelli, Oluwanifemi Bamgbose, Gabrielle Gauthier Melançon, Fanny Riols, Roshnee Sharma
Published: 2026-01-09
Categories: cs.LG, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.06341v1

Enterprise LLM applications require consistently high quality and reliable performance across diverse scenarios, demanding robustness to minor variations. Existing research shows that even small prompt changes can lead to substantial differences in output, but has mainly focused on a narrow set of perturbations with small academic datasets, limiting their relevance to real-world applications. To address this, we present a comprehensive benchmark suite that evaluates robustness across multiple perturbation types, including general text edits (e.g., punctuation, whitespace), formatting changes (e.g., JSON, YAML), multilingual and cross-lingual inputs, and positional variations in instructions. Evaluating 11 models ranging from 4B to 120B+ parameters, we find that minor perturbations reduce performance by up to 40 percentage points on key enterprise metrics. Critically, we demonstrate that the relationship between model size and robustness is more nuanced than conventional assumptions suggest: an 8B parameter model (Ministral 3 8B) outperforms most larger models, while another 8B model (Llama 3.1 8B) performs worst overall.

---

### Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers

Authors: Binxu Wang, Jingxuan Fan, Xu Pan
Published: 2026-01-09
Categories: cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.06338v2

Diffusion Transformers (DiTs) have greatly advanced text-to-image generation, but models still struggle to generate the correct spatial relations between objects as specified in the text prompt. In this study, we adopt a mechanistic interpretability approach to investigate how a DiT can generate correct spatial relations between objects. We train, from scratch, DiTs of different sizes with different text encoders to learn to generate images containing two objects whose attributes and spatial relations are specified in the text prompt. We find that, although all the models can learn this task to near-perfect accuracy, the underlying mechanisms differ drastically depending on the choice of text encoder. When using random text embeddings, we find that the spatial-relation information is passed to image tokens through a two-stage circuit, involving two cross-attention heads that separately read the spatial relation and single-object attributes in the text prompt. When using a pretrained text encoder (T5), we find that the DiT uses a different circuit that leverages information fusion in the text tokens, reading spatial-relation and single-object information together from a single text token. We further show that, although the in-domain performance is similar for the two settings, their robustness to out-of-domain perturbations differs, potentially suggesting the difficulty of generating correct relations in real-world scenarios.

---

### Future-as-Label: Scalable Supervision from Real-World Outcomes

Authors: Benjamin Turtel, Paul Wilczewski, Danny Franklin, Kris Skothiem
Published: 2026-01-09
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06336v2

Time creates free supervision: forecasts about real-world events resolve to verifiable outcomes. The passage of time provides labels that require no annotation. To exploit this structure, we extend reinforcement learning with verifiable rewards to real-world prediction over time. We train language models to make probabilistic forecasts from causally masked information, using proper scoring rules as the reward function once events resolve. Learning is driven entirely by realized outcomes, enabling scalable outcome-based supervision in open-world prediction. On real-world forecasting benchmarks, Qwen3-32B trained using Foresight Learning improves Brier score by 27% and halves calibration error relative to its pretrained baseline, and outperforms Qwen3-235B on both constructed future-event prediction tasks and the Metaculus benchmark despite a 7x parameter disadvantage.

---

### Foundational Analysis of Safety Engineering Requirements (SAFER)

Authors: Noga Chemo, Yaniv Mordecai, Yoram Reich
Published: 2026-01-09
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.06335v1

We introduce a framework for Foundational Analysis of Safety Engineering Requirements (SAFER), a model-driven methodology supported by Generative AI to improve the generation and analysis of safety requirements for complex safety-critical systems. Safety requirements are often specified by multiple stakeholders with uncoordinated objectives, leading to gaps, duplications, and contradictions that jeopardize system safety and compliance. Existing approaches are largely informal and insufficient for addressing these challenges. SAFER enhances Model-Based Systems Engineering (MBSE) by consuming requirement specification models and generating the following results: (1) mapping requirements to system functions, (2) identifying functions with insufficient requirement specifications, (3) detecting duplicate requirements, and (4) identifying contradictions within requirement sets. SAFER provides structured analysis, reporting, and decision support for safety engineers. We demonstrate SAFER on an autonomous drone system, significantly improving the detection of requirement inconsistencies, enhancing both efficiency and reliability of the safety engineering process. We show that Generative AI must be augmented by formal models and queried systematically, to provide meaningful early-stage safety requirement specifications and robust safety architectures.

---

### Kolmogorov-Arnold Networks-Based Tolerance-Aware Manufacturability Assessment Integrating Design-for-Manufacturing Principles

Authors: Masoud Deylami, Negar Izadipour, Adel Alaeddini
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06334v1

Manufacturability assessment is a critical step in bridging the persistent gap between design and production. While artificial intelligence (AI) has been widely applied to this task, most existing frameworks rely on geometry-driven methods that require extensive preprocessing, suffer from information loss, and offer limited interpretability. This study proposes a methodology that evaluates manufacturability directly from parametric design features, enabling explicit incorporation of dimensional tolerances without requiring computer-aided design (CAD) processing. The approach employs Kolmogorov-Arnold Networks (KANs) to learn functional relationships between design parameters, tolerances, and manufacturability outcomes. A synthetic dataset of 300,000 labeled designs is generated to evaluate performance across three representative scenarios: hole drilling, pocket milling, and combined drilling-milling, while accounting for machining constraints and design-for-manufacturing (DFM) rules. Benchmarking against fourteen machine learning (ML) and deep learning (DL) models shows that KAN achieves the highest performance in all scenarios, with AUC values of 0.9919 for drilling, 0.9841 for milling, and 0.9406 for the combined case. The proposed framework provides high interpretability through spline-based functional visualizations and latent-space projections, enabling identification of the design and tolerance parameters that most strongly influence manufacturability. An industrial case study further demonstrates how the framework enables iterative, parameter-level design modifications that transform a non-manufacturable component into a manufacturable one.

---

### On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation

Authors: Chan-Jan Hsu, Liang-Hsuan Tseng, Yi-Cheng Lin, Yen-Chun Kuo, Ju-Chieh Chou, Kai-Wei Chang, Hung-yi Lee, Carlos Busso
Published: 2026-01-09
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06329v2

Generative spoken language models pretrained on large-scale raw audio can continue a speech prompt with appropriate content while preserving attributes like speaker and emotion, serving as foundation models for spoken dialogue. In prior literature, these models are often evaluated using ``global token perplexity'', which directly applies the text perplexity formulation to speech tokens. However, this practice overlooks fundamental differences between speech and text modalities, possibly leading to an underestimation of the speech characteristics. In this work, we propose a variety of likelihood- and generative-based evaluation methods that serve in place of naive global token perplexity. We demonstrate that the proposed evaluations more faithfully reflect perceived generation quality, as evidenced by stronger correlations with human-rated mean opinion scores (MOS). When assessed under the new metrics, the relative performance landscape of spoken language models is reshaped, revealing a significantly reduced gap between the best-performing model and the human topline. Together, these results suggest that appropriate evaluation is critical for accurately assessing progress in spoken language modeling.

---

### C-World: A Computer Use Agent Environment Creator

Authors: Ziqiao Xi, Shuang Liang, Qi Liu, Jiaqing Zhang, Letian Peng, Fang Nan, Meshal Nayim, Tianhui Zhang, Rishika Mundada, Lianhui Qin, Biwei Huang, Kun Zhou
Published: 2026-01-09
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06328v2

To close the gap between LLM-based agents and humans in planning and reasoning, agents need large-scale, diverse environments for continuous learning -- yet building such environments is itself prohibitively expensive. We present C-World, an environment creation system that enables users to build agent environments on demand. We define a complete agent environment through four components: an Action Space of 5,571 format-unified tools across 204 common applications, a Task Distribution engine that synthesizes long-horizon workflows with wild constraints, a Transition Function implemented as a state controller that injects realistic failures and perturbations, and a Reward Signal combining verifiable metrics with LLM-based judgment. C-World operates in two modes: a realistic mode grounded in live API execution, and a synthesized mode powered by the World Engine, which approximates tool behavior without live service access, enabling scalable environment creation -- including environments for domains and tools that do not yet exist in the real world. Evaluation of nine state-of-the-art LLMs reveals that planning ability is uniformly strong but execution remains the bottleneck, and that constraint following -- not tool invocation -- is the dominant failure mode. The World Engine achieves Spearman $ρ= 0.883$ ranking correlation with real execution, and fine-tuning on just 1,170 C-World trajectories outperforms baselines trained on 119k samples, demonstrating C-World's dual value as a rigorous evaluation environment and a scalable data engine. Our code and data are available at https://ziqiao-git.github.io/C-World/

---

### Sensoformer: Robust Sim-to-Real Inference on Variable-Geometry Sensor Sets via Physics-Structured Randomization

Authors: Zhe Jia, Xiaotian Zhang, Junpeng Li
Published: 2026-01-09
Categories: cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2601.06320v3

Inferring high-dimensional physical states from sparse, ad-hoc sensor arrays is a fundamental challenge across AI for Science and industrial IoT. Standard machine learning architectures struggle in these domains due to irregular, variable-cardinality sensor geometries and the profound sim-to-real distribution shift caused by unmodeled physical heterogeneities. To address these challenges, we propose Sensoformer, a set-attention framework integrated with Physics-Structured Domain Randomization (PSDR). By explicitly randomizing the underlying physical dynamics (e.g., propagation media, extreme noise, and network availability dropout) rather than just visual features, PSDR enforces the learning of domain-invariant physical operators. Using seismic source inversion as a rigorous real-world testbed, Sensoformer is pre-trained on 100,000 synthetics and evaluated on a highly complex real-world catalog. We demonstrate that Sensoformer achieves state-of-the-art precision and outperforms Message Passing Neural Networks (MPNNs) and Neural Operators (e.g., DeepONet) which struggle with extreme spatial sparsity and mixed-modality inputs. Furthermore, interpretability analysis reveals that the attention mechanism autonomously discovers optimal experimental design principles, dynamically prioritizing sparse orthogonal sensors to overcome information bottlenecks.

---

### Random is Faster than Systematic in Multi-Objective Local Search

Authors: Zimin Liang, Miqing Li
Published: 2026-01-09
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.06318v1

Local search is a fundamental method in operations research and combinatorial optimisation. It has been widely applied to a variety of challenging problems, including multi-objective optimisation where multiple, often conflicting, objectives need to be simultaneously considered. In multi-objective local search algorithms, a common practice is to maintain an archive of all non-dominated solutions found so far, from which the algorithm iteratively samples a solution to explore its neighbourhood. A central issue in this process is how to explore the neighbourhood of a selected solution. In general, there are two main approaches: 1) systematic exploration and 2) random sampling. The former systematically explores the solution's neighbours until a stopping condition is met -- for example, when the neighbourhood is exhausted (i.e., the best improvement strategy) or once a better solution is found (i.e., first improvement). In contrast, the latter randomly selects and evaluates only one neighbour of the solution. One may think systematic exploration may be more efficient, as it prevents from revisiting the same neighbours multiple times. In this paper, however, we show that this may not be the case. We first empirically demonstrate that the random sampling method is consistently faster than the systematic exploration method across a range of multi-objective problems. We then give an intuitive explanation for this phenomenon using toy examples, showing that the superior performance of the random sampling method relies on the distribution of ``good neighbours''. Next, we show that the number of such neighbours follows a certain probability distribution during the search. Lastly, building on this distribution, we provide a theoretical insight for why random sampling is more efficient than systematic exploration, regardless of whether the best improvement or first improvement strategy is used.

---

### Annotating Dimensions of Social Perception in Text: A Sentence-Level Dataset of Warmth and Competence

Authors: Mutaz Ayesh, Saif M. Mohammad, Nedjma Ousidhoum
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06316v3

Warmth (W) (often further broken down intoTrust (T) and Sociability (S)) and Competence (C) are central dimensions along which people evaluate individuals and social groups (Fiske, 2018). While these constructs are well established in social psychology, they are only starting to get attention in NLP research through word-level lexicons, which do not fully capture their contextual expression in larger text units and discourse. In this work, we introduce Warmth and Competence Sentences (W&C-Sent), the first sentence-level dataset annotated for warmth and competence. The dataset includes over 1,600 English sentence--target pairs annotated along three dimensions: trust and sociability (components of warmth), and competence. The sentences in W&C-Sent are social media posts that express attitudes and opinions about specific individuals or social groups (the targets of our annotations). We describe the data collection, annotation, and quality-control procedures in detail, and evaluate a range of large language models (LLMs) on their ability to identify trust, sociability, and competence in text. W&C-Sent provides a new resource for analyzing warmth and competence in language and supports future research at the intersection of NLP and computational social science.

---

### VideoWeave: A Data-Centric Approach for Efficient Video Understanding

Authors: Zane Durante, Silky Singh, Arpandeep Khatua, Shobhit Agarwal, Reuben Tan, Yong Jae Lee, Jianfeng Gao, Ehsan Adeli, Li Fei-Fei
Published: 2026-01-09
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06309v1

Training video-language models is often prohibitively expensive due to the high cost of processing long frame sequences and the limited availability of annotated long videos. We present VideoWeave, a simple yet effective approach to improve data efficiency by constructing synthetic long-context training samples that splice together short, captioned videos from existing datasets. Rather than modifying model architectures or optimization objectives, VideoWeave reorganizes available video-text pairs to expand temporal diversity within fixed compute. We systematically study how different data composition strategies like random versus visually clustered splicing and caption enrichment affect downstream performance on downstream video question answering. Under identical compute constraints, models trained with VideoWeave achieve higher accuracy than conventional video finetuning. Our results highlight that reorganizing training data, rather than altering architectures, may offer a simple and scalable path for training video-language models. We link our code for all experiments here.

---

### A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality

Authors: Ishika Agarwal, Zhenlin He, Dhruva Patil, Dilek Hakkani-Tür
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06307v1

Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived from individual words alone. These expressions encode rich, cultural meaning, and have both figurative and literal meanings, making accurate translation difficult. Because models are fairly good at translating compositional text, we investigate GRPO-style fine-tuning using Machine Translation Quality Estimation (MTQE) models as reward functions to train models to better translate idioms. Using Chinese and Hindi idiom datasets, we find that idiom translation abilities improve by ~14 points, general, non-idiomatic translation implicitly improves by ~8 points, and cross-lingual translation abilities (trained on one language, evaluated on another) improves by ~6 points. Overall, our work quantifies the non-compositional translation gap and offers insights for developing LLMs with stronger cross-cultural and figurative language understanding.

---

### SyntaxMind at BLP-2025 Task 1: Leveraging Attention Fusion of CNN and GRU for Hate Speech Detection

Authors: Md. Shihab Uddin Riad
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06306v1

This paper describes our system used in the BLP-2025 Task 1: Hate Speech Detection. We participated in Subtask 1A and Subtask 1B, addressing hate speech classification in Bangla text. Our approach employs a unified architecture that integrates BanglaBERT embeddings with multiple parallel processing branches based on GRUs and CNNs, followed by attention and dense layers for final classification. The model is designed to capture both contextual semantics and local linguistic cues, enabling robust performance across subtasks. The proposed system demonstrated high competitiveness, obtaining 0.7345 micro F1-Score (2nd place) in Subtask 1A and 0.7317 micro F1-Score (5th place) in Subtask 1B.

---

### Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models

Authors: Hoang-Chau Luong, Lingwei Chen
Published: 2026-01-09
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06305v1

Low-Rank Adaptation (LoRA) is widely used for parameter-efficient fine-tuning of large language models, but it is notably ineffective at removing backdoor behaviors from poisoned pretrained models when fine-tuning on clean dataset. Contrary to the common belief that this weakness is caused primarily by low rank, we show that LoRA's vulnerability is fundamentally spectral. Our analysis identifies two key factors: LoRA updates (i) possess insufficient spectral strength, with singular values far below those of pretrained weights, and (ii) exhibit unfavorable spectral alignment, weakly matching clean-task directions while retaining overlap with trigger-sensitive subspaces. We further establish a critical scaling threshold beyond which LoRA can theoretically suppress trigger-induced activations, and we show empirically that standard LoRA rarely reaches this regime. We introduce Regularized Low-Rank Adaptation (RoRA), which improves forgetting by increasing spectral strength and correcting alignment through clean-strengthened regularization, trigger-insensitive constraints, and post-training spectral rescaling. Experiments across multiple NLP benchmarks and attack settings show that RoRA substantially reduces attack success rates while maintaining clean accuracy.

---

### Beyond BeautifulSoup: Benchmarking LLM-Powered Web Scraping for Everyday Users

Authors: Arth Bhardwaj, Nirav Diwan, Gang Wang
Published: 2026-01-09
Categories: cs.CR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.06301v1

Web scraping has historically required technical expertise in HTML parsing, session management, and authentication circumvention, which limited large-scale data extraction to skilled developers. We argue that large language models (LLMs) have democratized web scraping, enabling low-skill users to execute sophisticated operations through simple natural language prompts. While extensive benchmarks evaluate these tools under optimal expert conditions, we show that without extensive manual effort, current LLM-based workflows allow novice users to scrape complex websites that would otherwise be inaccessible. We systematically benchmark what everyday users can do with off-the-shelf LLM tools across 35 sites spanning five security tiers, including authentication, anti-bot, and CAPTCHA controls. We devise and evaluate two distinct workflows: (a) LLM-assisted scripting, where users prompt LLMs to generate traditional scraping code but maintain manual execution control, and (b) end-to-end LLM agents, which autonomously navigate and extract data through integrated tool use. Our results demonstrate that end-to-end agents have made complex scraping accessible - requiring as little as a single prompt with minimal refinement (less than 5 changes) to complete workflows. We also highlight scenarios where LLM-assisted scripting may be simpler and faster for static sites. In light of these findings, we provide simple procedures for novices to use these workflows and gauge what adversaries could achieve using these.

---

### $\texttt{AMEND++}$: Benchmarking Eligibility Criteria Amendments in Clinical Trials

Authors: Trisha Das, Mandis Beigi, Jacob Aptekar, Jimeng Sun
Published: 2026-01-09
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06300v2

Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly amended component. We introduce \textit{eligibility criteria amendment prediction}, a novel NLP task that aims to forecast whether the eligibility criteria of an initial trial protocol will undergo future amendments. To support this task, we release $\texttt{AMEND++}$, a benchmark suite comprising two datasets: $\texttt{AMEND}$, which captures eligibility-criteria version histories and amendment labels from public clinical trials, and $\verb|AMEND_LLM|$, a refined subset curated using an LLM-based denoising pipeline to isolate substantive changes. We further propose $\textit{Change-Aware Masked Language Modeling}$ (CAMLM), a revision-aware pretraining strategy that leverages historical edits to learn amendment-sensitive representations. Experiments across diverse baselines show that CAMLM consistently improves amendment prediction, enabling more robust and cost-effective clinical trial design.

---

### A Targeted Learning Framework for Estimating Restricted Mean Survival Time Difference using Pseudo-observations

Authors: Man Jin, Yixin Fang
Published: 2026-01-09
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2601.06296v2

A targeted learning (TL) framework is developed to estimate the difference in the restricted mean survival time (RMST) for a clinical trial with time-to-event outcomes. The approach starts by defining the target estimand as the RMST difference between investigational and control treatments. Next, an efficient estimation method is introduced: a targeted minimum loss estimator (TMLE) utilizing pseudo-observations. Moreover, a version of the copy reference (CR) approach is developed to perform a sensitivity analysis for right-censoring. The proposed TL framework is demonstrated using a real data application.

---

### How well can off-the-shelf LLMs elucidate molecular structures from mass spectra using chain-of-thought reasoning?

Authors: Yufeng Wang, Lu Wei, Lin Liu, Hao Xu, Haibin Ling
Published: 2026-01-09
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.06289v1

Mass spectrometry (MS) is a powerful analytical technique for identifying small molecules, yet determining complete molecular structures directly from tandem mass spectra (MS/MS) remains a long-standing challenge due to complex fragmentation patterns and the vast diversity of chemical space. Recent progress in large language models (LLMs) has shown promise for reasoning-intensive scientific tasks, but their capability for chemical interpretation is still unclear. In this work, we introduce a Chain-of-Thought (CoT) prompting framework and benchmark that evaluate how LLMs reason about mass spectral data to predict molecular structures. We formalize expert chemists' reasoning steps-such as double bond equivalent (DBE) analysis, neutral loss identification, and fragment assembly-into structured prompts and assess multiple state-of-the-art LLMs (Claude-3.5-Sonnet, GPT-4o-mini, and Llama-3 series) in a zero-shot setting using the MassSpecGym dataset. Our evaluation across metrics of SMILES validity, formula consistency, and structural similarity reveals that while LLMs can produce syntactically valid and partially plausible structures, they fail to achieve chemical accuracy or link reasoning to correct molecular predictions. These findings highlight both the interpretive potential and the current limitations of LLM-based reasoning for molecular elucidation, providing a foundation for future work that combines domain knowledge and reinforcement learning to achieve chemically grounded AI reasoning.

---

### AIConfigurator: Lightning-Fast Configuration Optimization for Multi-Framework LLM Serving

Authors: Tianhao Xu, Yiming Liu, Xianglong Lu, Yijia Zhao, Xuting Zhou, Aichen Feng, Yiyi Chen, Yi Shen, Qin Zhou, Xumeng Chen, Ilya Sherstyuk, Haorui Li et al.
Published: 2026-01-09
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2601.06288v1

Optimizing Large Language Model (LLM) inference in production systems is increasingly difficult due to dynamic workloads, stringent latency/throughput targets, and a rapidly expanding configuration space. This complexity spans not only distributed parallelism strategies (tensor/pipeline/expert) but also intricate framework-specific runtime parameters such as those concerning the enablement of CUDA graphs, available KV-cache memory fractions, and maximum token capacity, which drastically impact performance. The diversity of modern inference frameworks (e.g., TRT-LLM, vLLM, SGLang), each employing distinct kernels and execution policies, makes manual tuning both framework-specific and computationally prohibitive. We present AIConfigurator, a unified performance-modeling system that enables rapid, framework-agnostic inference configuration search without requiring GPU-based profiling. AIConfigurator combines (1) a methodology that decomposes inference into analytically modelable primitives - GEMM, attention, communication, and memory operations while capturing framework-specific scheduling dynamics; (2) a calibrated kernel-level performance database for these primitives across a wide range of hardware platforms and popular open-weights models (GPT-OSS, Qwen, DeepSeek, LLama, Mistral); and (3) an abstraction layer that automatically resolves optimal launch parameters for the target backend, seamlessly integrating into production-grade orchestration systems. Evaluation on production LLM serving workloads demonstrates that AIConfigurator identifies superior serving configurations that improve performance by up to 40% for dense models (e.g., Qwen3-32B) and 50% for MoE architectures (e.g., DeepSeek-V3), while completing searches within 30 seconds on average. Enabling the rapid exploration of vast design spaces - from cluster topology down to engine specific flags.

---