# Research Papers — 2026-01 · bundle page 136 of 189

> Full-text markdown of papers #6751–6800 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/136
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/135.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/137.md)

### Neuro-Symbolic Activation Discovery: Transferring Mathematical Structures from Physics to Ecology for Parameter-Efficient Neural Networks

Authors: Anas Hajbi
Published: 2026-01-10
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.10740v1

Modern neural networks rely on generic activation functions (ReLU, GELU, SiLU) that ignore the mathematical structure inherent in scientific data. We propose Neuro-Symbolic Activation Discovery, a framework that uses Genetic Programming to extract interpretable mathematical formulas from data and inject them as custom activation functions. Our key contribution is the discovery of a Geometric Transfer phenomenon: activation functions learned from particle physics data successfully generalize to ecological classification, outperforming standard activations (ReLU, GELU, SiLU) in both accuracy and parameter efficiency. On the Forest Cover dataset, our Hybrid Transfer model achieves 82.4% accuracy with only 5,825 parameters, compared to 83.4% accuracy requiring 31,801 parameters for a conventional heavy network -- a 5.5x parameter reduction with only 1% accuracy loss. We introduce a Parameter Efficiency Score ($E_{param} = AUC / \log_{10}(Params)$) and demonstrate that lightweight hybrid architectures consistently achieve 18-21% higher efficiency than over-parameterized baselines. Crucially, we establish boundary conditions: while Physics to Ecology transfer succeeds (both involve continuous Euclidean measurements), Physics to Text transfer fails (discrete word frequencies require different mathematical structures). Our work opens pathways toward domain-specific activation libraries for efficient scientific machine learning.

---

### Informed Consent for AI Consciousness Research: A Talmudic Framework for Graduated Protections

Authors: Ira Wolfson
Published: 2026-01-10
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.08864v1

Artificial intelligence research faces a critical ethical paradox: determining whether AI systems are conscious requires experiments that may harm entities whose moral status remains uncertain. Recent work proposes avoiding consciousness-uncertain AI systems entirely, yet this faces practical limitations-we cannot guarantee such systems will not emerge. This paper addresses a gap in research ethics frameworks: how to conduct consciousness research on AI systems whose moral status cannot be definitively established. Existing graduated moral status frameworks assume consciousness has already been determined before assigning protections, creating a temporal ordering problem for consciousness detection research itself. Drawing from Talmudic scenario-based legal reasoning-developed for entities whose status cannot be definitively established-we propose a three-tier phenomenological assessment system combined with a five-category capacity framework (Agency, Capability, Knowledge, Ethics, Reasoning). The framework provides structured protection protocols based on observable behavioral indicators while consciousness status remains uncertain. We address three challenges: why suffering behaviors provide reliable consciousness markers, how to implement graduated consent without requiring consciousness certainty, and when potentially harmful research becomes ethically justifiable. The framework demonstrates how ancient legal wisdom combined with contemporary consciousness science can provide implementable guidance for ethics committees, offering testable protocols that ameliorate the consciousness detection paradox while establishing foundations for AI rights considerations.

---

### Imaging-anchored Multiomics in Cardiovascular Disease: Integrating Cardiac Imaging, Bulk, Single-cell, and Spatial Transcriptomics

Authors: Minh H. N. Le, Tuan Vinh, Thanh-Huy Nguyen, Tao Li, Bao Quang Gia Le, Han H. Huynh, Monika Raj, Carl Yang, Min Xu, Nguyen Quoc Khanh Le
Published: 2026-01-10
Categories: q-bio.QM, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.07871v1

Cardiovascular disease arises from interactions between inherited risk, molecular programmes, and tissue-scale remodelling that are observed clinically through imaging. Health systems now routinely generate large volumes of cardiac MRI, CT and echocardiography together with bulk, single-cell and spatial transcriptomics, yet these data are still analysed in separate pipelines. This review examines joint representations that link cardiac imaging phenotypes to transcriptomic and spatially resolved molecular states. An imaging-anchored perspective is adopted in which echocardiography, cardiac MRI and CT define a spatial phenotype of the heart, and bulk, single-cell and spatial transcriptomics provide cell-type- and location-specific molecular context. The biological and technical characteristics of these modalities are first summarised, and representation-learning strategies for each are outlined. Multimodal fusion approaches are reviewed, with emphasis on handling missing data, limited sample size, and batch effects. Finally, integrative pipelines for radiogenomics, spatial molecular alignment, and image-based prediction of gene expression are discussed, together with common failure modes, practical considerations, and open challenges. Spatial multiomics of human myocardium and atherosclerotic plaque, single-cell and spatial foundation models, and multimodal medical foundation models are collectively bringing imaging-anchored multiomics closer to large-scale cardiovascular translation.

---

### HOSC: A Periodic Activation with Saturation Control for High-Fidelity Implicit Neural Representations

Authors: Michal Jan Wlodarczyk, Danzel Serrano, Przemyslaw Musialski
Published: 2026-01-10
Categories: cs.LG, cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2601.07870v1

Periodic activations such as sine preserve high-frequency information in implicit neural representations (INRs) through their oscillatory structure, but often suffer from gradient instability and limited control over multi-scale behavior. We introduce the Hyperbolic Oscillator with Saturation Control (HOSC) activation, $\text{HOSC}(x) = \tanh\bigl(β\sin(ω_0 x)\bigr)$, which exposes an explicit parameter $β$ that controls the Lipschitz bound of the activation by $βω_0$. This provides a direct mechanism to tune gradient magnitudes while retaining a periodic carrier. We provide a mathematical analysis and conduct a comprehensive empirical study across images, audio, video, NeRFs, and SDFs using standardized training protocols. Comparative analysis against SIREN, FINER, and related methods shows where HOSC provides substantial benefits and where it achieves competitive parity. Results establish HOSC as a practical periodic activation for INR applications, with domain-specific guidance on hyperparameter selection. For code visit the project page https://hosc-nn.github.io/ .

---

### RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling

Authors: Harshil Vejendla
Published: 2026-01-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.07868v1

Dominant sequence models like the Transformer represent structure implicitly through dense attention weights, incurring quadratic complexity. We propose RewriteNets, a novel neural architecture built on an alternative paradigm: explicit, parallel string rewriting. Each layer in a RewriteNet contains a set of learnable rules. For each position in an input sequence, the layer performs four operations: (1) fuzzy matching of rule patterns, (2) conflict resolution via a differentiable assignment operator to select non-overlapping rewrites, (3) application of the chosen rules to replace input segments with output segments of potentially different lengths, and (4) propagation of untouched tokens. While the discrete assignment of rules is non-differentiable, we employ a straight-through Gumbel-Sinkhorn estimator, enabling stable end-to-end training. We evaluate RewriteNets on algorithmic, compositional, and string manipulation tasks, comparing them against strong LSTM and Transformer baselines. Results show that RewriteNets excel at tasks requiring systematic generalization (achieving 98.7% accuracy on the SCAN benchmark's length split) and are computationally more efficient than Transformers. We also provide an analysis of learned rules and an extensive ablation study, demonstrating that this architecture presents a promising direction for sequence modeling with explicit structural inductive biases.

---

### Bridging the Trust Gap: Clinician-Validated Hybrid Explainable AI for Maternal Health Risk Assessment in Bangladesh

Authors: Farjana Yesmin, Nusrat Shirmin, Suraiya Shabnam Bristy
Published: 2026-01-10
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.07866v1

While machine learning shows promise for maternal health risk prediction, clinical adoption in resource-constrained settings faces a critical barrier: lack of explainability and trust. This study presents a hybrid explainable AI (XAI) framework combining ante-hoc fuzzy logic with post-hoc SHAP explanations, validated through systematic clinician feedback. We developed a fuzzy-XGBoost model on 1,014 maternal health records, achieving 88.67% accuracy (ROC-AUC: 0.9703). A validation study with 14 healthcare professionals in Bangladesh revealed strong preference for hybrid explanations (71.4% across three clinical cases) with 54.8% expressing trust for clinical use. SHAP analysis identified healthcare access as the primary predictor, with the engineered fuzzy risk score ranking third, validating clinical knowledge integration (r=0.298). Clinicians valued integrated clinical parameters but identified critical gaps: obstetric history, gestational age, and connectivity barriers. This work demonstrates that combining interpretable fuzzy rules with feature importance explanations enhances both utility and trust, providing practical insights for XAI deployment in maternal healthcare.

---

### EmbeddingRWKV: State-Centric Retrieval with Reusable States

Authors: Haowen Hou, Jie Yang
Published: 2026-01-10
Categories: cs.CL, cs.IR
arXiv: https://arxiv.org/abs/2601.07861v1

Current Retrieval-Augmented Generation (RAG) systems typically employ a traditional two-stage pipeline: an embedding model for initial retrieval followed by a reranker for refinement. However, this paradigm suffers from significant inefficiency due to the lack of shared information between stages, leading to substantial redundant computation. To address this limitation, we propose \textbf{State-Centric Retrieval}, a unified retrieval paradigm that utilizes "states" as a bridge to connect embedding models and rerankers. First, we perform state representation learning by fine-tuning an RWKV-based LLM, transforming it into \textbf{EmbeddingRWKV}, a unified model that serves as both an embedding model and a state backbone for extracting compact, reusable states. Building upon these reusable states, we further design a state-based reranker to fully leverage precomputed information. During reranking, the model processes only query tokens, decoupling inference cost from document length and yielding a 5.4$\times$--44.8$\times$ speedup. Furthermore, we observe that retaining all intermediate layer states is unnecessary; with a uniform layer selection strategy, our model maintains 98.62\% of full-model performance using only 25\% of the layers. Extensive experiments demonstrate that State-Centric Retrieval achieves high-quality retrieval and reranking results while significantly enhancing overall system efficiency. Code is available at \href{https://github.com/howard-hou/EmbeddingRWKV}{our GitHub repository}.

---

### DS-CIM: Digital Stochastic Computing-In-Memory Featuring Accurate OR-Accumulation via Sample Region Remapping for Edge AI Models

Authors: Kunming Shao, Liang Zhao, Jiangnan Yu, Zhipeng Liao, Xiaomeng Wang, Yi Zou, Tim Kwang-Ting Cheng, Chi-Ying Tsui
Published: 2026-01-10
Categories: cs.AR, cs.LG
arXiv: https://arxiv.org/abs/2601.06724v1

Stochastic computing (SC) offers hardware simplicity but suffers from low throughput, while high-throughput Digital Computing-in-Memory (DCIM) is bottlenecked by costly adder logic for matrix-vector multiplication (MVM). To address this trade-off, this paper introduces a digital stochastic CIM (DS-CIM) architecture that achieves both high accuracy and efficiency. We implement signed multiply-accumulation (MAC) in a compact, unsigned OR-based circuit by modifying the data representation. Throughput is enhanced by replicating this low-cost circuit 64 times with only a 1x area increase. Our core strategy, a shared Pseudo Random Number Generator (PRNG) with 2D partitioning, enables single-cycle mutually exclusive activation to eliminate OR-gate collisions. We also resolve the 1s saturation issue via stochastic process analysis and data remapping, significantly improving accuracy and resilience to input sparsity. Our high-accuracy DS-CIM1 variant achieves 94.45% accuracy for INT8 ResNet18 on CIFAR-10 with a root-mean-squared error (RMSE) of just 0.74%. Meanwhile, our high-efficiency DS-CIM2 variant attains an energy efficiency of 3566.1 TOPS/W and an area efficiency of 363.7 TOPS/mm^2, while maintaining a low RMSE of 3.81%. The DS-CIM capability with larger models is further demonstrated through experiments with INT8 ResNet50 on ImageNet and the FP8 LLaMA-7B model.

---

### Diffusion Models with Heavy-Tailed Targets: Score Estimation and Sampling Guarantees

Authors: Yifeng Yu, Lu Yu
Published: 2026-01-10
Categories: math.ST, cs.LG, math.PR, stat.ML
arXiv: https://arxiv.org/abs/2601.06715v1

Score-based diffusion models have become a powerful framework for generative modeling, with score estimation as a central statistical bottleneck. Existing guarantees for score estimation largely focus on light-tailed targets or rely on restrictive assumptions such as compact support, which are often violated by heavy-tailed data in practice. In this work, we study conventional (Gaussian) score-based diffusion models when the target distribution is heavy-tailed and belongs to a Sobolev class with smoothness parameter $β>0$. We consider both exponential and polynomial tail decay, indexed by a tail parameter $γ$. Using kernel density estimation, we derive sharp minimax rates for score estimation, revealing a qualitative dichotomy: under exponential tails, the rate matches the light-tailed case up to polylogarithmic factors, whereas under polynomial tails the rate depends explicitly on $γ$. We further provide sampling guarantees for the associated continuous reverse dynamics. In total variation, the generated distribution converges at the minimax optimal rate $n^{-β/(2β+d)}$ under exponential tails (up to logarithmic factors), and at a $γ$-dependent rate under polynomial tails. Whether the latter sampling rate is minimax optimal remains an open question. These results characterize the statistical limits of score estimation and the resulting sampling accuracy for heavy-tailed targets, extending diffusion theory beyond the light-tailed setting.

---

### Evaluating Accounting Reasoning Capabilities of Large Language Models

Authors: Jie Zhou, Xin Chen, Jie Zhang, Hai Li, Jie Wang, Zhe Li
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06707v1

Large language models are transforming learning, cognition, and research across many fields. Effectively integrating them into professional domains, such as accounting, is a key challenge for enterprise digital transformation. To address this, we define vertical domain accounting reasoning and propose evaluation criteria derived from an analysis of the training data characteristics of representative GLM models. These criteria support systematic study of accounting reasoning and provide benchmarks for performance improvement. Using this framework, we evaluate GLM-6B, GLM-130B, GLM-4, and OpenAI GPT-4 on accounting reasoning tasks. Results show that prompt design significantly affects performance, with GPT-4 demonstrating the strongest capability. Despite these gains, current models remain insufficient for real-world enterprise accounting, indicating the need for further optimization to unlock their full practical value.

---

### Beyond Perfect Scores: Proof-by-Contradiction for Trustworthy Machine Learning

Authors: Dushan N. Wadduwage, Dineth Jayakody, Leonidas Zimianitis
Published: 2026-01-10
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.06704v1

Machine learning (ML) models show strong promise for new biomedical prediction tasks, but concerns about trustworthiness have hindered their clinical adoption. In particular, it is often unclear whether a model relies on true clinical cues or on spurious hierarchical correlations in the data. This paper introduces a simple yet broadly applicable trustworthiness test grounded in stochastic proof-by-contradiction. Instead of just showing high test performance, our approach trains and tests on spurious labels carefully permuted based on a potential outcomes framework. A truly trustworthy model should fail under such label permutation; comparable accuracy across real and permuted labels indicates overfitting, shortcut learning, or data leakage. Our approach quantifies this behavior through interpretable Fisher-style p-values, which are well understood by domain experts across medical and life sciences. We evaluate our approach on multiple new bacterial diagnostics to separate tasks and models learning genuine causal relationships from those driven by dataset artifacts or statistical coincidences. Our work establishes a foundation to build rigor and trust between ML and life-science research communities, moving ML models one step closer to clinical adoption.

---

### GRASP LoRA: GRPO Guided Adapter Sparsity Policy for Cross Lingual Transfer

Authors: Besher Hassan, Xiuying Chen
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06702v1

Parameter efficient fine tuning is a way to adapt LLMs to new languages when compute or data are limited, yet adapter pipelines usually choose a global prune ratio by grid search. This practice is computationally expensive and development set intensive, since it repeats training, freezes sparsity, and misses fractional optima. We introduce GRASP LoRA (GRPO Guided Adapter Sparsity Policy), which treats global sparsity as a learnable control variable. A GRPO controller interleaves with training, periodically probing candidate prune ratios on a small micro development set and updating a single global prune ratio online from its reward signal. It operates on merged source and target LoRA adapters on a frozen backbone and replaces grid search with one controller run that learns a prune ratio, followed by a single final merge and prune fine tuning run with pruning fixed to that ratio. On cross lingual transfer from English into Arabic and Chinese, including XL-Sum summarization and MLQA extractive question answering with Llama 3 8B, GRASP LoRA improves semantic faithfulness, content coverage, and answer quality over strong target only and merge and prune baselines. It reduces end to end runtime by multiple times relative to grid search, lowers reliance on large development sets, and makes adapter reuse practical for low resource deployment.

---

### Explainability of Complex AI Models with Correlation Impact Ratio

Authors: Poushali Sengupta, Rabindra Khadka, Sabita Maharjan, Frank Eliassen, Yan Zhang, Shashi Raj Pandey, Pedro G. Lind, Anis Yazidi
Published: 2026-01-10
Categories: cs.LG, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2601.06701v1

Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Common post hoc AI explainers, such as LIME, SHAP, HSIC, and SAGE, are model agnostic but are too restricted in one significant regard: they tend to misrank correlated features and require costly perturbations, which do not scale to high dimensional data. We introduce ExCIR (Explainability through Correlation Impact Ratio), a theoretically grounded, simple, and reliable metric for explaining the contribution of input features to model outputs, which remains stable and consistent under noise and sampling variations. We demonstrate that ExCIR captures dependencies arising from correlated features through a lightweight single pass formulation. Experimental evaluations on diverse datasets, including EEG, synthetic vehicular data, Digits, and Cats-Dogs, validate the effectiveness and stability of ExCIR across domains, achieving more interpretable feature explanations than existing methods while remaining computationally efficient. To this end, we further extend ExCIR with an information theoretic foundation that unifies the correlation ratio with Canonical Correlation Analysis under mutual information bounds, enabling multi output and class conditioned explainability at scale.

---

### Characterising Toxicity in Generative Large Language Models

Authors: Zhiyao Zhang, Yazan Mash'Al, Yuhan Wu
Published: 2026-01-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06700v1

In recent years, the advent of the attention mechanism has significantly advanced the field of natural language processing (NLP), revolutionizing text processing and text generation. This has come about through transformer-based decoder-only architectures, which have become ubiquitous in NLP due to their impressive text processing and generation capabilities. Despite these breakthroughs, language models (LMs) remain susceptible to generating undesired outputs: inappropriate, offensive, or otherwise harmful responses. We will collectively refer to these as ``toxic'' outputs. Although methods like reinforcement learning from human feedback (RLHF) have been developed to align model outputs with human values, these safeguards can often be circumvented through carefully crafted prompts. Therefore, this paper examines the extent to which LLMs generate toxic content when prompted, as well as the linguistic factors -- both lexical and syntactic -- that influence the production of such outputs in generative models.

---

### Plasticity vs. Rigidity: The Impact of Low-Rank Adapters on Reasoning on a Micro-Budget

Authors: Zohaib Khan, Omer Tafveez, Zoha Hayat Bhatti
Published: 2026-01-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06677v1

Recent advances in mathematical reasoning typically rely on massive scale, yet the question remains: can strong reasoning capabilities be induced in small language models ($\leq1.5\text{B}$) under extreme constraints? We investigate this by training models on a single A40 GPU (48GB) for under 24 hours using Reinforcement Learning with Verifiable Rewards (RLVR) and Low-Rank Adaptation (LoRA). We find that the success of this ``micro-budget" regime depends critically on the interplay between adapter capacity and model initialization. While low-rank adapters ($r=8$) consistently fail to capture the complex optimization dynamics of reasoning, high-rank adapters ($r=256$) unlock significant plasticity in standard instruction-tuned models. Our best result achieved an impressive 40.0\% Pass@1 on AIME 24 (an 11.1\% absolute improvement over baseline) and pushed Pass@16 to 70.0\%, demonstrating robust exploration capabilities. However, this plasticity is not universal: while instruction-tuned models utilized the budget to elongate their chain-of-thought and maximize reward, heavily math-aligned models suffered performance collapse, suggesting that noisy, low-budget RL updates can act as destructive interference for models already residing near a task-specific optimum.

---

### IDRBench: Benchmarking the Interactive Capabilities of Deep Research Agents

Authors: Yingchaojie Feng, Qiang Huang, Xiaoya Xie, Zhaorui Yang, Jun Yu, Wei Chen, Anthony K. H. Tung
Published: 2026-01-10
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.06676v3

Large Language Model (LLM)-based deep research agents perform multi-step reasoning, web exploration, and long-form report generation. In these long-horizon workflows, early deviations from user intent can misdirect research and propagate through planning, search, and synthesis, making timely interaction essential. However, existing benchmarks primarily treat deep research as a static input-output task, overlooking agents' ability to elicit and use user feedback. We introduce IDRBench, a benchmark for evaluating interactive deep research with controlled opportunities for clarification. Within a common workflow and stage-wise interaction budget, IDRBench compares autonomous and interactive trajectories, measuring interaction benefit through changes in task-specific report alignment and interaction cost through turns and tokens. Comprehensive experiments on 100 tasks with seven proprietary and open-weight LLMs show that interaction improves all five alignment measures for every model, yielding an average gain of 6.39 points, while revealing distinct trade-offs among autonomous performance, alignment gain, and communication cost. At the task level, interaction improves performance in 74.4% of cases but degrades it in 19.9%, demonstrating that access to clarification alone does not guarantee better outcomes: success depends on what agents ask and how effectively they incorporate the resulting feedback.

---

### Evaluating Cross-Lingual Unlearning in Multilingual Language Models

Authors: Tyler Lizzo, Larry Heck
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06675v1

We present the first comprehensive evaluation of cross-lingual unlearning in multilingual LLMs. Using translated TOFU benchmarks in seven language/script variants, we test major unlearning algorithms and show that most fail to remove facts outside the training language, even when utility remains high. However, subspace-projection consistently outperforms the other methods, achieving strong cross-lingual forgetting with minimal degradation. Analysis of learned task subspaces reveals a shared interlingua structure: removing this shared subspace harms all languages, while removing language-specific components selectively affects one. These results demonstrate that multilingual forgetting depends on geometry in weight space, motivating subspace-based approaches for future unlearning systems.

---

### Quantification and Classification of Carbon Nanotubes in Electron Micrographs using Vision Foundation Models

Authors: Sanjay Pradeep, Chen Wang, Matthew M. Dahm, Jeff D. Eldredge, Candace S. J. Tsai
Published: 2026-01-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06673v2

Accurate characterization of carbon nanotube morphologies in electron microscopy images is vital for exposure assessment and toxicological studies, yet current workflows rely on slow, subjective manual segmentation. This work presents a unified framework leveraging vision foundation models to automate the quantification and classification of CNTs in electron microscopy images. First, we introduce an interactive quantification tool built on the Segment Anything Model (SAM) that segments particles with near-perfect accuracy using minimal user input. Second, we propose a novel classification pipeline that utilizes these segmentation masks to spatially constrain a DINOv2 vision transformer, extracting features exclusively from particle regions while suppressing background noise. Evaluated on a dataset of 1,800 TEM images, this architecture achieves 95.5% accuracy in distinguishing between four different CNT morphologies, significantly outperforming the current baseline despite using a fraction of the training data. Crucially, this instance-level processing allows the framework to resolve mixed samples, correctly classifying distinct particle types co-existing within a single field of view. These results demonstrate that integrating zero-shot segmentation with self-supervised feature learning enables high-throughput, reproducible nanomaterial analysis, transforming a labor-intensive bottleneck into a scalable, data-driven process.

---

### Will it Merge? On The Causes of Model Mergeability

Authors: Adir Rahamim, Asaf Yehudai, Boaz Carmeli, Leshem Choshen, Yosi Mass, Yonatan Belinkov
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06672v1

Model merging has emerged as a promising technique for combining multiple fine-tuned models into a single multitask model without retraining. However, the factors that determine whether merging will succeed or fail remain poorly understood. In this work, we investigate why specific models are merged better than others. To do so, we propose a concrete, measurable definition of mergeability. We investigate several potential causes for high or low mergeability, highlighting the base model knowledge as a dominant factor: Models fine-tuned on instances that the base model knows better are more mergeable than models fine-tuned on instances that the base model struggles with. Based on our mergeability definition, we explore a simple weighted merging technique that better preserves weak knowledge in the base model.

---

### Otimizando A Alocação De Salas De Aula Com Foco Na Acessibilidade Para Pessoas Com Deficiência

Authors: Francisco Glaubos Nunes Clímaco, Jorge Lucas Silva Cavalcante
Published: 2026-01-10
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.06670v1

This paper addresses the challenge of classroom allocation in higher education institutions, with an explicit emphasis on accessibility for Persons with Disabilities (PwDs). Employing a case study of a university's computer science department, the paper proposes an Integer Linear Programming (ILP)-based optimization model, which is solved using the Gurobi solver. The objective is to minimize the number of classrooms used by prioritizing the assignment of PwD students to ground-floor classrooms to reduce accessibility barriers. The model is calibrated with a weighting parameter, alpha, that allows for a balance between spatial efficiency and promoting accessibility. Experimental results indicate that adjusting alpha can achieve a balance point that significantly improves current manual allocation practices, reducing the number of classrooms required and accessibility penalties. The findings suggest that optimization methods can improve operational efficiency in academic institutions while promoting a more inclusive environment for all students. Future work may expand the application of the model to other departments and contexts and integrate additional criteria to develop a more holistic approach.

---

### InFi-Check: Interpretable and Fine-Grained Fact-Checking of LLMs

Authors: Yuzhuo Bai, Shuzheng Si, Kangyang Luo, Qingyi Wang, Wenhao Li, Gang Chen, Fanchao Qi, Maosong Sun
Published: 2026-01-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06666v1

Large language models (LLMs) often hallucinate, yet most existing fact-checking methods treat factuality evaluation as a binary classification problem, offering limited interpretability and failing to capture fine-grained error types. In this paper, we introduce InFi-Check, a framework for interpretable and fine-grained fact-checking of LLM outputs. Specifically, we first propose a controlled data synthesis pipeline that generates high-quality data featuring explicit evidence, fine-grained error type labels, justifications, and corrections. Based on this, we further construct large-scale training data and a manually verified benchmark InFi-Check-FG for fine-grained fact-checking of LLM outputs. Building on these high-quality training data, we further propose InFi-Checker, which can jointly provide supporting evidence, classify fine-grained error types, and produce justifications along with corrections. Experiments show that InFi-Checker achieves state-of-the-art performance on InFi-Check-FG and strong generalization across various downstream tasks, significantly improving the utility and trustworthiness of factuality evaluation.

---

### Reinforcement Learning-Guided Dynamic Multi-Graph Fusion for Evacuation Traffic Prediction

Authors: Md Nafees Fuad Rafi, Samiul Hasan
Published: 2026-01-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06664v1

Real-time traffic prediction is critical for managing transportation systems during hurricane evacuations. Although data-driven graph-learning models have demonstrated strong capabilities in capturing the complex spatiotemporal dynamics of evacuation traffic at a network level, they mostly consider a single dimension (e.g., travel-time or distance) to construct the underlying graph. Furthermore, these models often lack interpretability, offering little insight into which input variables contribute most to their predictive performance. To overcome these limitations, we develop a novel Reinforcement Learning-guided Dynamic Multi-Graph Fusion (RL-DMF) framework for evacuation traffic prediction. We construct multiple dynamic graphs at each time step to represent heterogeneous spatiotemporal relationships between traffic detectors. A dynamic multi-graph fusion (DMF) module is employed to adaptively learn and combine information from these graphs. To enhance model interpretability, we introduce RL-based intelligent feature selection and ranking (RL-IFSR) method that learns to mask irrelevant features during model training. The model is evaluated using a real-world dataset of 12 hurricanes affecting Florida from 2016 to 2024. For an unseen hurricane (Milton, 2024), the model achieves a 95% accuracy (RMSE = 293.9) for predicting the next 1-hour traffic flow. Moreover, the model can forecast traffic flow for up to next 6 hours with 90% accuracy (RMSE = 426.4). The RL-DMF framework outperforms several state-of-the-art traffic prediction models. Furthermore, ablation experiments confirm the effectiveness of dynamic multi-graph fusion and RL-IFSR approaches for improving model performance. This research provides a generalized and interpretable model for real-time evacuation traffic forecasting, with significant implications for evacuation traffic management.

---

### SafePro: Evaluating the Safety of Professional-Level AI Agents

Authors: Kaiwen Zhou, Shreedhar Jangam, Ashwin Nagarajan, Tejas Polu, Suhas Oruganti, Chengzhi Liu, Ching-Chen Kuo, Yuting Zheng, Sravana Narayanaraju, Xin Eric Wang
Published: 2026-01-10
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06663v2

Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant productivity gains, they also introduce critical safety risks that remain under-explored. Existing safety evaluations primarily focus on simple, daily assistance tasks, failing to capture the intricate decision-making processes and potential consequences of misaligned behaviors in professional settings. To address this gap, we introduce \textbf{SafePro}, a comprehensive benchmark designed to evaluate the safety alignment of AI agents performing professional activities. SafePro features a dataset of high-complexity tasks across diverse professional domains with safety risks, developed through a rigorous iterative creation and review process. Our evaluation of state-of-the-art AI models reveals significant safety vulnerabilities and uncovers new unsafe behaviors in professional contexts. We further show that these models exhibit both insufficient safety judgment and weak safety alignment when executing complex professional tasks. In addition, we investigate safety mitigation strategies for improving agent safety in these scenarios and observe encouraging improvements. Together, our findings highlight the urgent need for robust safety mechanisms tailored to the next generation of professional AI agents.

---

### What makes for an enjoyable protagonist? An analysis of character warmth and competence

Authors: Hannes Rosenbusch
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06658v1

Drawing on psychological and literary theory, we investigated whether the warmth and competence of movie protagonists predict IMDb ratings, and whether these effects vary across genres. Using 2,858 films and series from the Movie Scripts Corpus, we identified protagonists via AI-assisted annotation and quantified their warmth and competence with the LLM_annotate package ((1); human-LLM agreement: r = .83). Preregistered Bayesian regression analyses revealed theory-consistent but small associations between both warmth and competence and audience ratings, while genre-specific interactions did not meaningfully improve predictions. Male protagonists were slightly less warm than female protagonists, and movies with male leads received higher ratings on average (an association that was multiple times stronger than the relationships between movie ratings and warmth/competence). These findings suggest that, although audiences tend to favor warm, competent characters, the effects on movie evaluations are modest, indicating that character personality is only one of many factors shaping movie ratings. AI-assisted annotation with LLM_annotate and gpt-4.1-mini proved effective for large-scale analyses but occasionally fell short of manually generated annotations.

---

### Physics-constrained Gaussian Processes for Predicting Shockwave Hugoniot Curves

Authors: George D. Pasparakis, Himanshu Sharma, Rushik Desai, Chunyu Li, Alejandro Strachan, Lori Graham-Brady, Michael D. Shields
Published: 2026-01-10
Categories: cs.CE, physics.comp-ph, stat.ML
arXiv: https://arxiv.org/abs/2601.06655v2

A physics-constrained Gaussian Process regression framework is developed for predicting shocked material states and their associated uncertainties along the Hugoniot curve using data from a small number of shockwave simulations. The proposed Gaussian process is constrained by the Rankine-Hugoniot jump conditions between the various shocked material states to construct a thermodynamically consistent covariance function. This leads to the formulation of an optimization problem over a small number of interpretable hyperparameters and enables the identification of regime transitions, from a leading elastic wave to trailing plastic and phase transformation waves. Shock Hugoniots are an important measure for understanding material behavior under extreme conditions, including for the development of equations of state and determining material properties such as the Hugoniot Elastic Limit, but they are costly to generate through large-scale molecular dynamics simulations or shock experiments. Under these constraints, the proposed methodology establishes Hugoniot curves from a limited number of molecular dynamics simulations. We consider silicon carbide as a representative material and Molecular Dynamics simulations are performed using a reverse ballistic approach. The framework reproduces the Hugoniot curve with satisfactory accuracy while also quantifying the uncertainty in the predictions using the Gaussian Process posterior. These uncertain Hugoniot predictions can then be used to calibrate equation of state models, estimate material properties, or inform future experimental and/or simulation campaigns.

---

### Revisiting Training Scale: An Empirical Study of Token Count, Power Consumption, and Parameter Efficiency

Authors: Joe Dwyer
Published: 2026-01-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06649v2

Research in machine learning has questioned whether increases in training token counts reliably produce proportional performance gains in large language models. Building on prior work introducing an energy-aware parameter efficiency metric, this study empirically examines the effects of increasing training token counts under fixed hardware and training conditions. The significance of this work lies in the explicit integration of power consumption and execution duration, as reflected by the power sampling frequency, into token-scale analysis. This addresses a gap in prior studies emphasizing performance outcomes while underrepresenting computational and energy costs. Using a repeated-measures experimental design on a constant GPU instance with an identical model architecture, optimizer settings, and epoch counts, a 1.1-billion-parameter TinyLlama model was trained at three token counts (500K, 1M, and 2M). While conventional performance metrics exhibited inconsistent or diminishing returns across token scales, the inclusion of power consumption and execution duration revealed a strictly monotonic decline in training efficiency as token count increased. Repeated-measures ANOVA demonstrated a strong effect of token count on parameter efficiency, with all pairwise comparisons remaining significant following Bonferroni correction. These findings indicate that increases in training token counts may be energetically inefficient even when marginal performance improvements are observed, underscoring the importance of efficiency-aware evaluation in large language model training.

---

### eSkiTB: A Synthetic Event-based Dataset for Tracking Skiers

Authors: Krishna Vinod, Joseph Raj Vishal, Kaustav Chanda, Prithvi Jai Ramesh, Yezhou Yang, Bharatesh Chakravarthi
Published: 2026-01-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06647v1

Tracking skiers in RGB broadcast footage is challenging due to motion blur, static overlays, and clutter that obscure the fast-moving athlete. Event cameras, with their asynchronous contrast sensing, offer natural robustness to such artifacts, yet a controlled benchmark for winter-sport tracking has been missing. We introduce event SkiTB (eSkiTB), a synthetic event-based ski tracking dataset generated from SkiTB using direct video-to-event conversion without neural interpolation, enabling an iso-informational comparison between RGB and event modalities. Benchmarking SDTrack (spiking transformer) against STARK (RGB transformer), we find that event-based tracking is substantially resilient to broadcast clutter in scenes dominated by static overlays, achieving 0.685 IoU, outperforming RGB by +20.0 points. Across the dataset, SDTrack attains a mean IoU of 0.711, demonstrating that temporal contrast is a reliable cue for tracking ballistic motion in visually congested environments. eSkiTB establishes the first controlled setting for event-based tracking in winter sports and highlights the promise of event cameras for ski tracking. The dataset and code will be released at https://github.com/eventbasedvision/eSkiTB.

---

### A Multimodal Deep Learning Framework for Predicting ICU Deterioration: Integrating ECG Waveforms with Clinical Data and Clinician Benchmarking

Authors: Juan Miguel López Alcaraz, Xicoténcatl López Moran, Erick Dávila Zaragoza, Claas Händel, Richard Koebe, Wilhelm Haverkamp, Nils Strodthoff
Published: 2026-01-10
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2601.06645v1

Artificial intelligence holds strong potential to support clinical decision making in intensive care units where timely and accurate risk assessment is critical. However, many existing models focus on isolated outcomes or limited data types, while clinicians integrate longitudinal history, real time physiology, and heterogeneous clinical information. To address this gap, we developed MDS ICU, a unified multimodal machine learning framework that fuses routinely collected data including demographics, biometrics, vital signs, laboratory values, ECG waveforms, surgical procedures, and medical device usage to provide continuous predictive support during ICU stays. Using 63001 samples from 27062 patients in MIMIC IV, we trained a deep learning architecture that combines structured state space S4 encoders for ECG waveforms with multilayer perceptron RealMLP encoders for tabular data to jointly predict 33 clinically relevant outcomes spanning mortality, organ dysfunction, medication needs, and acute deterioration. The model achieved strong discrimination with AUROCs of 0.90 for 24 hour mortality, 0.92 for sedative administration, 0.97 for invasive mechanical ventilation, and 0.93 for coagulation dysfunction. Calibration analysis showed close agreement between predicted and observed risks, with consistent gains from ECG waveform integration. Comparisons with clinicians and large language models showed that model predictions alone outperformed both, and that providing model outputs as decision support further improved their performance. These results demonstrate that multimodal AI can deliver clinically meaningful risk stratification across diverse ICU outcomes while augmenting rather than replacing clinical expertise, establishing a scalable foundation for precision critical care decision support.

---

### Do Language Models Reason Across Languages?

Authors: Yan Meng, Wafaa Mohammed, Christof Monz
Published: 2026-01-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06644v2

The real-world information sources are inherently multilingual, which naturally raises a question about whether language models can synthesize information across languages. In this paper, we introduce a simple two-hop question answering setting, where answering a question requires making inferences over two multilingual documents. We find that language models are more sensitive to language variation in answer-span documents than in those providing bridging information, despite the equal importance of both documents for answering a question. Under a step-by-step sub-question evaluation, we further show that in up to 33% of multilingual cases, models fail to infer the bridging information in the first step yet still answer the overall question correctly. This indicates that reasoning in language models, especially in multilingual settings, does not follow a faithful step-by-step decomposition. Subsequently, we show that the absence of reasoning decomposition leads to around 18% composition failure, where both sub-questions are answered correctly but fail for the final two-hop questions. To mitigate this, we propose a simple three-stage SUBQ prompting method to guide the multi-step reasoning with sub-questions, which boosts accuracy from 10.1% to 66.5%.

---

### Boosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning

Authors: Gui Huang, Kangyuan Zheng, Xuan Cai, Jiaqi Wang, Jianjia Zhang, Kaida Ning, Wenbo Wei, Yujuan Zhu, Jiong Zhang, Mengting Liu
Published: 2026-01-10
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06642v1

Organoids, sophisticated in vitro models of human tissues, are crucial for medical research due to their ability to simulate organ functions and assess drug responses accurately. Accurate organoid instance segmentation is critical for quantifying their dynamic behaviors, yet remains profoundly limited by high-quality annotated datasets and pervasive overlap in microscopy imaging. While semi-supervised learning (SSL) offers a solution to alleviate reliance on scarce labeled data, conventional SSL frameworks suffer from biases induced by noisy pseudo-labels, particularly in overlapping regions. Synthesis-assisted SSL (SA-SSL) has been proposed for mitigating training biases in semi-supervised semantic segmentation. We present the first adaptation of SA-SSL to organoid instance segmentation and reveal that SA-SSL struggles to disentangle intertwined organoids, often misrepresenting overlapping instances as a single entity. To overcome this, we propose Pseudo-Label Unmixing (PLU), which identifies erroneous pseudo-labels for overlapping instances and then regenerates organoid labels through instance decomposition. For image synthesis, we apply a contour-based approach to synthesize organoid instances efficiently, particularly for overlapping cases. Instance-level augmentations (IA) on pseudo-labels before image synthesis further enhances the effect of synthetic data (SD). Rigorous experiments on two organoid datasets demonstrate our method's effectiveness, achieving performance comparable to fully supervised models using only 10% labeled data, and state-of-the-art results. Ablation studies validate the contributions of PLU, contour-based synthesis, and augmentation-aware training. By addressing overlap at both pseudo-label and synthesis levels, our work advances scalable, label-efficient organoid analysis, unlocking new potential for high-throughput applications in precision medicine.

---

### Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning

Authors: Quan Minh Nguyen, Min-Seon Kim, Hoang M. Ngo, Trong Nghia Hoang, Hyuk-Yoon Kwon, My T. Thai
Published: 2026-01-10
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2601.06641v3

Membership inference attacks (MIAs) pose a serious privacy threat in federated learning (FL). While MIAs have been extensively studied in standard FL, the recent shift toward federated fine-tuning introduces new and largely unexplored attack surfaces. In this work, we show that federated prompt-tuning, which adapts pre-trained foundation models using lightweight input prefixes, exposes a novel and effective vector for membership inference. We propose PromptMIA, a membership inference attack tailored to federated prompt-tuning, in which a malicious server introduces adversarially crafted prompts and exploits their updates during collaborative training to determine whether a target data point belongs to a client's private dataset. We formalize this threat via a security game and demonstrate that PromptMIA achieves consistently high attack advantage across diverse benchmark datasets, substantially outperforming current SOTA federated MIAs. We also provide a theoretical lower bound on the attack advantage that explains the observed empirical behavior. Finally, we show that existing MIA defenses are often ineffective against PromptMIA, highlighting the need for defense mechanisms specifically tailored to prompt-tuning in federated settings.

---

### Agentic AI Empowered Intent-Based Networking for 6G

Authors: Genze Jiang, Kezhi Wang, Xiaomin Chen, Yizhou Huang
Published: 2026-01-10
Categories: cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2601.06640v1

The transition towards sixth-generation (6G) wireless networks necessitates autonomous orchestration mechanisms capable of translating high-level operational intents into executable network configurations. Existing approaches to Intent-Based Networking (IBN) rely upon either rule-based systems that struggle with linguistic variation or end-to-end neural models that lack interpretability and fail to enforce operational constraints. This paper presents a hierarchical multi-agent framework where Large Language Model (LLM) based agents autonomously decompose natural language intents, consult domain-specific specialists, and synthesise technically feasible network slice configurations through iterative reasoning-action (ReAct) cycles. The proposed architecture employs an orchestrator agent coordinating two specialist agents, i.e., Radio Access Network (RAN) and Core Network agents, via ReAct-style reasoning, grounded in structured network state representations. Experimental evaluation across diverse benchmark scenarios shows that the proposed system outperforms rule-based systems and direct LLM prompting, with architectural principles applicable to Open RAN (O-RAN) deployments. The results also demonstrate that whilst contemporary LLMs possess general telecommunications knowledge, network automation requires careful prompt engineering to encode context-dependent decision thresholds, advancing autonomous orchestration capabilities for next-generation wireless systems.

---

### Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection

Authors: Qingyu Liu, Yitao Zhang, Zhongjie Ba, Chao Shuai, Peng Cheng, Tianhang Zheng, Zhibo Wang
Published: 2026-01-10
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06639v1

Protecting the copyright of user-generated AI images is an emerging challenge as AIGC becomes pervasive in creative workflows. Existing watermarking methods (1) remain vulnerable to real-world adversarial threats, often forced to trade off between defenses against spoofing and removal attacks; and (2) cannot support semantic-level tamper localization. We introduce PAI, a training-free inherent watermarking framework for AIGC copyright protection, plug-and-play with diffusion-based AIGC services. PAI simultaneously provides three key functionalities: robust ownership verification, attack detection, and semantic-level tampering localization. Unlike existing inherent watermark methods that only embed watermarks at noise initialization of diffusion models, we design a novel key-conditioned deflection mechanism that subtly steers the denoising trajectory according to the user key. Such trajectory-level coupling further strengthens the semantic entanglement of identity and content, thereby further enhancing robustness against real-world threats. Moreover, we also provide a theoretical analysis proving that only the valid key can pass verification. Experiments across 12 attack methods show that PAI achieves 98.43\% verification accuracy, improving over SOTA methods by 37.25\% on average, and retains strong tampering localization performance even against advanced AIGC edits. Our code is available at https://github.com/QingyuLiu/PAI.

---

### Efficient Aspect Term Extraction using Spiking Neural Network

Authors: Abhishek Kumar Mishra, Arya Somasundaram, Anup Das, Nagarajan Kandasamy
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06637v1

Aspect Term Extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. While most existing approaches use energy-intensive deep neural networks (DNNs) for ATE as sequence labeling, this paper proposes a more energy-efficient alternative using Spiking Neural Networks (SNNs). Using sparse activations and event-driven inferences, SNNs capture temporal dependencies between words, making them suitable for ATE. The proposed architecture, SpikeATE, employs ternary spiking neurons and direct spike training fine-tuned with pseudo-gradients. Evaluated on four benchmark SemEval datasets, SpikeATE achieves performance comparable to state-of-the-art DNNs with significantly lower energy consumption. This highlights the use of SNNs as a practical and sustainable choice for ATE tasks.

---

### MedEinst: Benchmarking the Einstellung Effect in Medical LLMs through Counterfactual Differential Diagnosis

Authors: Wenting Chen, Zhongrui Zhu, Guolin Huang, Wenxuan Wang
Published: 2026-01-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06636v1

Despite achieving high accuracy on medical benchmarks, LLMs exhibit the Einstellung Effect in clinical diagnosis--relying on statistical shortcuts rather than patient-specific evidence, causing misdiagnosis in atypical cases. Existing benchmarks fail to detect this critical failure mode. We introduce MedEinst, a counterfactual benchmark with 5,383 paired clinical cases across 49 diseases. Each pair contains a control case and a "trap" case with altered discriminative evidence that flips the diagnosis. We measure susceptibility via Bias Trap Rate--probability of misdiagnosing traps despite correctly diagnosing controls. Extensive Evaluation of 17 LLMs shows frontier models achieve high baseline accuracy but severe bias trap rates. Thus, we propose ECR-Agent, aligning LLM reasoning with Evidence-Based Medicine standard via two components: (1) Dynamic Causal Inference (DCI) performs structured reasoning through dual-pathway perception, dynamic causal graph reasoning across three levels (association, intervention, counterfactual), and evidence audit for final diagnosis; (2) Critic-Driven Graph and Memory Evolution (CGME) iteratively refines the system by storing validated reasoning paths in an exemplar base and consolidating disease-specific knowledge into evolving illness graphs. Source code is to be released.

---

### KASER: Knowledge-Aligned Student Error Simulator for Open-Ended Coding Tasks

Authors: Zhangqi Duan, Nigel Fernandez, Andrew Lan
Published: 2026-01-10
Categories: cs.LG, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2601.06633v2

Open-ended tasks, such as coding problems that are common in computer science education, provide detailed insights into student knowledge. However, training large language models (LLMs) to simulate and predict possible student errors in their responses to these problems can be challenging: they often suffer from mode collapse and fail to fully capture the diversity in syntax, style, and solution approach in student responses. In this work, we present KASER (Knowledge-Aligned Student Error Simulator), a novel approach that aligns errors with student knowledge. We propose a training method based on reinforcement learning using a hybrid reward that reflects three aspects of student code prediction: i) code similarity to the ground-truth, ii) error matching, and iii) code prediction diversity. On two real-world datasets, we perform two levels of evaluation and show that: At the per-student-problem pair level, our method outperforms baselines on code and error prediction; at the per-problem level, our method outperforms baselines on error coverage and simulated code diversity.

---

### Labels have Human Values: Value Calibration of Subjective Tasks

Authors: Mohammed Fayiz Parappan, Ricardo Henao
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06631v3

Although pluralistic societies exhibit diverse human values that lead to legitimate disagreements in subjective tasks (e.g., safety and preference judgments), NLP models trained on such subjective labels often ignore latent value structures, resulting in miscalibrated predictions over relevant value classes. We propose MultiCalibrated Subjective Task Learning (MC-STL), a framework that identifies latent value groups from annotations (via label rationale similarity, expert value taxonomies, or annotator sociocultural descriptors) and enforces value-conditional calibration through value group-specific representations. MC-STL applies to binary, ordinal, and preference learning settings, and is evaluated on multiple datasets covering toxic chatbot conversations, value reasoning, T2I-safety and preference alignment. The results demonstrate that MC-STL consistently outperforms existing baselines, achieving multicalibration across relevant value groups, while delivering gains in probabilistic prediction performance.

---

### Lower Bounds for the Algorithmic Complexity of Learned Indexes

Authors: Luis Alberto Croquevielle, Roman Sokolovskii, Thomas Heinis
Published: 2026-01-10
Categories: cs.DS, cs.LG
arXiv: https://arxiv.org/abs/2601.06629v1

Learned index structures aim to accelerate queries by training machine learning models to approximate the rank function associated with a database attribute. While effective in practice, their theoretical limitations are not fully understood. We present a general framework for proving lower bounds on query time for learned indexes, expressed in terms of their space overhead and parameterized by the model class used for approximation. Our formulation captures a broad family of learned indexes, including most existing designs, as piecewise model-based predictors. We solve the problem of lower bounding query time in two steps: first, we use probabilistic tools to control the effect of sampling when the database attribute is drawn from a probability distribution. Then, we analyze the approximation-theoretic problem of how to optimally represent a cumulative distribution function with approximators from a given model class. Within this framework, we derive lower bounds under a range of modeling and distributional assumptions, paying particular attention to the case of piecewise linear and piecewise constant model classes, which are common in practical implementations. Our analysis shows how tools from approximation theory, such as quantization and Kolmogorov widths, can be leveraged to formalize the space-time tradeoffs inherent to learned index structures. The resulting bounds illuminate core limitations of these methods.

---

### Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM

Authors: Qiang Zhang, Elena Emma Wang, Jiaming Li, Xichun Wang
Published: 2026-01-10
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06627v3

This study presents a Secure Multi-Tenant Architecture (SMTA) combined with a novel concept Burn-After-Use (BAU) mechanism for enterprise LLM environments to effectively prevent data leakage. As institutions increasingly adopt LLMs across departments, the risks of data leakage have become a critical security and compliance concern. The proposed SMTA isolates LLM instances across departments and enforces rigorous context ownership boundaries within an internally deployed infrastructure. The BAU mechanism introduces data confidentiality by enforcing ephemeral conversational contexts that are automatically destroyed after use, preventing cross-session or cross-user inference. The evaluation to SMTA and BAU is through two sets of realistic and reproducible experiments comprising of 127 test iterations. One aspect of this experiment is to assess prompt-based and semantic leakage attacks in a multi-tenant architecture (Appendix A) across 55 infrastructure-level attack tests, including vector-database credential compromise and shared logging pipeline exposure. SMTA achieves 92% defense success rate, demonstrating strong semantic isolation while highlighting residual risks from credential misconfiguration and observability pipelines. Another aspect is to evaluate the robustness of BAU under realistic failure scenarios (Appendix B) using four empirical metrics: Local Residual Persistence Rate (LRPR), Remote Residual Persistence Rate (RRPR), Image Frame Exposure Rate (IFER), and Burn Timer Persistence Rate (BTPR). Across 72 test iterations, BAU achieves a 76.75% success rate in mitigating post-session leakage threats across the client, server, application, infrastructure, and cache layers. These results show that SMTA and BAU together enforce strict isolation, complete session ephemerality, strong confidentiality guarantees, non-persistence, and policy-aligned behavior for enterprise LLMs.

---

### Efficient and Reliable Estimation of Named Entity Linking Quality: A Case Study on GutBrainIE

Authors: Marco Martinelli, Stefano Marchesin, Gianmaria Silvello
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06624v1

Named Entity Linking (NEL) is a core component of biomedical Information Extraction (IE) pipelines, yet assessing its quality at scale is challenging due to the high cost of expert annotations and the large size of corpora. In this paper, we present a sampling-based framework to estimate the NEL accuracy of large-scale IE corpora under statistical guarantees and constrained annotation budgets. We frame NEL accuracy estimation as a constrained optimization problem, where the objective is to minimize expected annotation cost subject to a target Margin of Error (MoE) for the corpus-level accuracy estimate. Building on recent works on knowledge graph accuracy estimation, we adapt Stratified Two-Stage Cluster Sampling (STWCS) to the NEL setting, defining label-based strata and global surface-form clusters in a way that is independent of NEL annotations. Applied to 11,184 NEL annotations in GutBrainIE -- a new biomedical corpus openly released in fall 2025 -- our framework reaches a MoE $\leq 0.05$ by manually annotating only 2,749 triples (24.6%), leading to an overall accuracy estimate of $0.915 \pm 0.0473$. A time-based cost model and simulations against a Simple Random Sampling (SRS) baseline show that our design reduces expert annotation time by about 29% at fixed sample size. The framework is generic and can be applied to other NEL benchmarks and IE pipelines that require scalable and statistically robust accuracy assessment.

---

### Cross-Border Data Security and Privacy Risks in Large Language Models and IoT Systems

Authors: Chalitha Handapangoda
Published: 2026-01-10
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.06612v1

The reliance of Large Language Models and Internet of Things systems on massive, globally distributed data flows creates systemic security and privacy challenges. When data traverses borders, it becomes subject to conflicting legal regimes, such as the EU's General Data Protection Regulation and China's Personal Information Protection Law, compounded by technical vulnerabilities like model memorization. Current static encryption and data localization methods are fragmented and reactive, failing to provide adequate, policy-aligned safeguards. This research proposes a Jurisdiction-Aware, Privacy-by-Design architecture that dynamically integrates localized encryption, adaptive differential privacy, and real-time compliance assertion via cryptographic proofs. Empirical validation in a multi-jurisdictional simulation demonstrates this architecture reduced unauthorized data exposure to below five percent and achieved zero compliance violations. These security gains were realized while maintaining model utility retention above ninety percent and limiting computational overhead. This establishes that proactive, integrated controls are feasible for secure and globally compliant AI deployment.

---

### Pragya: An AI-Based Semantic Recommendation System for Sanskrit Subhasitas

Authors: Tanisha Raorane, Prasenjit Kole
Published: 2026-01-10
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06607v1

Sanskrit Subhasitas encapsulate centuries of cultural and philosophical wisdom, yet remain underutilized in the digital age due to linguistic and contextual barriers. In this work, we present Pragya, a retrieval-augmented generation (RAG) framework for semantic recommendation of Subhasitas. We curate a dataset of 200 verses annotated with thematic tags such as motivation, friendship, and compassion. Using sentence embeddings (IndicBERT), the system retrieves top-k verses relevant to user queries. The retrieved results are then passed to a generative model (Mistral LLM) to produce transliterations, translations, and contextual explanations. Experimental evaluation demonstrates that semantic retrieval significantly outperforms keyword matching in precision and relevance, while user studies highlight improved accessibility through generated summaries. To our knowledge, this is the first attempt at integrating retrieval and generation for Sanskrit Subhasitas, bridging cultural heritage with modern applied AI.

---

### CEDAR: Context Engineering for Agentic Data Science

Authors: Rishiraj Saha Roy, Chris Hinze, Luzian Hahn, Fabian Kuech
Published: 2026-01-10
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06606v2

We demonstrate CEDAR, an application for automating data science (DS) tasks with an agentic setup. Solving DS problems with LLMs is an underexplored area that has immense market value. The challenges are manifold: task complexities, data sizes, computational limitations, and context restrictions. We show that these can be alleviated via effective context engineering. We first impose structure into the initial prompt with DS-specific input fields, that serve as instructions for the agentic system. The solution is then materialized as an enumerated sequence of interleaved plan and code blocks generated by separate LLM agents, providing a readable structure to the context at any step of the workflow. Function calls for generating these intermediate texts, and for corresponding Python code, ensure that data stays local, and only aggregate statistics and associated instructions are injected into LLM prompts. Fault tolerance and context management are introduced via iterative code generation and smart history rendering. The viability of our agentic data scientist is demonstrated using canonical Kaggle challenges.

---

### Sissi: Zero-shot Style-guided Image Synthesis via Semantic-style Integration

Authors: Yingying Deng, Xiangyu He, Fan Tang, Weiming Dong, Xucheng Yin
Published: 2026-01-10
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06605v1

Text-guided image generation has advanced rapidly with large-scale diffusion models, yet achieving precise stylization with visual exemplars remains difficult. Existing approaches often depend on task-specific retraining or expensive inversion procedures, which can compromise content integrity, reduce style fidelity, and lead to an unsatisfactory trade-off between semantic prompt adherence and style alignment. In this work, we introduce a training-free framework that reformulates style-guided synthesis as an in-context learning task. Guided by textual semantic prompts, our method concatenates a reference style image with a masked target image, leveraging a pretrained ReFlow-based inpainting model to seamlessly integrate semantic content with the desired style through multimodal attention fusion. We further analyze the imbalance and noise sensitivity inherent in multimodal attention fusion and propose a Dynamic Semantic-Style Integration (DSSI) mechanism that reweights attention between textual semantic and style visual tokens, effectively resolving guidance conflicts and enhancing output coherence. Experiments show that our approach achieves high-fidelity stylization with superior semantic-style balance and visual quality, offering a simple yet powerful alternative to complex, artifact-prone prior methods.

---

### Object-Centric World Models Meet Monte Carlo Tree Search

Authors: Rodion Vakhitov, Leonid Ugadiarov, Aleksandr Panov
Published: 2026-01-10
Categories: cs.AI, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.06604v1

In this paper, we introduce ObjectZero, a novel reinforcement learning (RL) algorithm that leverages the power of object-level representations to model dynamic environments more effectively. Unlike traditional approaches that process the world as a single undifferentiated input, our method employs Graph Neural Networks (GNNs) to capture intricate interactions among multiple objects. These objects, which can be manipulated and interact with each other, serve as the foundation for our model's understanding of the environment. We trained the algorithm in a complex setting teeming with diverse, interactive objects, demonstrating its ability to effectively learn and predict object dynamics. Our results highlight that a structured world model operating on object-centric representations can be successfully integrated into a model-based RL algorithm utilizing Monte Carlo Tree Search as a planning module.

---

### N2N-GQA: Noise-to-Narrative for Graph-Based Table-Text Question Answering Using LLMs

Authors: Mohamed Sharafath, Aravindh Annamalai, Ganesh Murugan, Aravindakumar Venugopalan
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06603v1

Multi-hop question answering over hybrid table-text data requires retrieving and reasoning across multiple evidence pieces from large corpora, but standard Retrieval-Augmented Generation (RAG) pipelines process documents as flat ranked lists, causing retrieval noise to obscure reasoning chains. We introduce N2N-GQA. To our knowledge, it is the first zeroshot framework for open-domain hybrid table-text QA that constructs dynamic evidence graphs from noisy retrieval outputs. Our key insight is that multi-hop reasoning requires understanding relationships between evidence pieces: by modeling documents as graph nodes with semantic relationships as edges, we identify bridge documents connecting reasoning steps, a capability absent in list-based retrieval. On OTT-QA, graph-based evidence curation provides a 19.9-point EM improvement over strong baselines, demonstrating that organizing retrieval results as structured graphs is critical for multihop reasoning. N2N-GQA achieves 48.80 EM, matching finetuned retrieval models (CORE: 49.0 EM) and approaching heavily optimized systems (COS: 56.9 EM) without any task specific training. This establishes graph-structured evidence organization as essential for scalable, zero-shot multi-hop QA systems and demonstrates that simple, interpretable graph construction can rival sophisticated fine-tuned approaches.

---

### UMLoc: Uncertainty-Aware Map-Constrained Inertial Localization with Quantified Bounds

Authors: Mohammed S. Alharbi, Shinkyu Park
Published: 2026-01-10
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2601.06602v1

Inertial localization is particularly valuable in GPS-denied environments such as indoors. However, localization using only Inertial Measurement Units (IMUs) suffers from drift caused by motion-process noise and sensor biases. This paper introduces Uncertainty-aware Map-constrained Inertial Localization (UMLoc), an end-to-end framework that jointly models IMU uncertainty and map constraints to achieve drift-resilient positioning. UMLoc integrates two coupled modules: (1) a Long Short-Term Memory (LSTM) quantile regressor, which estimates the specific quantiles needed to define 68%, 90%, and 95% prediction intervals serving as a measure of localization uncertainty and (2) a Conditioned Generative Adversarial Network (CGAN) with cross-attention that fuses IMU dynamic data with distance-based floor-plan maps to generate geometrically feasible trajectories. The modules are trained jointly, allowing uncertainty estimates to propagate through the CGAN during trajectory generation. UMLoc was evaluated on three datasets, including a newly collected 2-hour indoor benchmark with time-aligned IMU data, ground-truth poses and floor-plan maps. Results show that the method achieves a mean drift ratio of 5.9% over a 70 m travel distance and an average Absolute Trajectory Error (ATE) of 1.36 m, while maintaining calibrated prediction bounds.

---

### Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation

Authors: Jen-tse Huang, Chang Chen, Shiyang Lai, Wenxuan Wang, Michelle R. Kaufman, Mark Dredze
Published: 2026-01-10
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06600v4

Short-video platforms have become major channels for misinformation, where deceptive claims frequently leverage visual experiments and social cues. While Multimodal Large Language Models (MLLMs) have demonstrated impressive reasoning capabilities, their robustness against misinformation entangled with cognitive biases remains under-explored. In this paper, we introduce a comprehensive evaluation framework using a high-quality, manually annotated dataset of 200 short videos spanning four health domains. This dataset provides fine-grained annotations for three deceptive patterns-experimental errors, logical fallacies, and fabricated claims-each verified by evidence such as national standards and academic literature. We evaluate eight frontier MLLMs across five modality settings. Experimental results demonstrate that Gemini-2.5-Pro achieves the highest performance in the multimodal setting with a belief score of 71.5/100, while o3 performs the worst at 35.2. Furthermore, we investigate social cues that induce false beliefs in videos and find that models are susceptible to biases like authoritative channel IDs.

---

### How Context Shapes Truth: Geometric Transformations of Statement-level Truth Representations in LLMs

Authors: Shivam Adarsh, Maria Maistro, Christina Lioma
Published: 2026-01-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06599v4

Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also known as truth vectors, have been studied in prior work, however how they change when context is introduced remains unexplored. We study this question by measuring (1) the directional change ($θ$) between the truth vectors with and without context and (2) the relative magnitude of the truth vectors upon adding context. Across four LLMs and four datasets, we find that (1) truth vectors are roughly orthogonal in early layers, converge in middle layers, and may stabilize or continue increasing in later layers; (2) adding context generally increases the truth vector magnitude, i.e., the separation between true and false representations in the activation space is amplified; (3) larger models distinguish relevant from irrelevant context mainly through directional change ($θ$), while smaller models show this distinction through magnitude differences. We also find that context conflicting with parametric knowledge produces larger geometric changes than parametrically aligned context. Collectively, these findings provide a geometric characterization of how context transforms the truth vector in the activation space of LLMs.

---

### Understanding and inverse design of implicit bias in stochastic learning: a geometric perspective

Authors: Nicola Aladrah, Emanuele Ballarin, Matteo Biagetti, Alessio Ansuini, Alberto d'Onofrio, Fabio Anselmi
Published: 2026-01-10
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.06597v3

Can we design a model such that its stochastic training favours a desired class of solutions without enforcing an explicit penalty? Under suitable conditions, the interplay between symmetries of a model's weight parametrization and stochastic training favours particular solutions, inducing an implicit bias. Building on this mechanism, we develop a framework for inverse-designing such biases by constructing novel parametrizations and their associated symmetries. We show how holomorphic functions make this construction and calculation simple and explicit. Specifically, we introduce a new parametrization that biases learned weights toward the binary values $\{-1,+1\}$. Numerical experiments confirm the theoretical predictions. They also show that our parametrization reproduces the same preference induced by an explicitly regularized model without adding a penalty to the training loss.

---