# Research Papers — 2026-02 · bundle page 178 of 210

> Full-text markdown of papers #8851–8900 of 10493 published in 2026-02, newest first. AI-readable mirrors of the full 10493-paper 2026-02 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-02/page/178
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/177.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/179.md)

### One Model, Many Skills: Parameter-Efficient Fine-Tuning for Multitask Code Analysis

Authors: Amal Akli, Maxime Cordy, Mike Papadakis, Yves Le Traon
Published: 2026-02-03
Categories: cs.SE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.09978v1

Large language models have recently surpassed specialized systems on code generation, yet their effectiveness on other code-analysis tasks remains less clear. At the same time, multi-task learning offers a way to unify diverse objectives within a single model, but fully fine-tuning LLMs across tasks is computationally prohibitive. Parameter-efficient fine-tuning mitigates this cost by updating only a small fraction of weights. Although PEFT has proven effective in single-task settings, its potential for multi-task learning has not yet been systematically explored. We present the first comprehensive evaluation of multi-task PEFT for code analysis, comparing several methods across diverse tasks and model architectures. Our experiments show that a single PEFT module shared across tasks can match, and in some cases surpass, full multi-task fine-tuning, confirming that the benefits of PEFT extend beyond isolated tasks. When comparing single-task and multi-task setups, we find that multi-task PEFT achieves a favorable performance-efficiency trade-off: it delivers accuracy close to single-task fine-tuning while reducing storage requirements, cutting the number of trainable parameters by a factor of the task count, and lowering computation costs by as much as 85%. At the same time, multi-task gains remain sensitive to task grouping. Through task-pairing experiments, we identify key factors shaping outcomes: task stability, model architecture, task complementarity, asymmetry, and dataset quality determine the success of co-fine-tuning. Finally, we benchmark efficient multi-task PEFT against direct prompting of open-source general-purpose LLMs, including DeepSeek, Qwen, Mistral, CodeLlama, and StarCoder. Despite their strong performance in code generation, these models underperform on analysis tasks, where even a 1B-parameter model with multi-task PEFT achieves significantly better results.

---

### Verify as You Go: An LLM-Powered Browser Extension for Fake News Detection

Authors: Dorsaf Sallami, Esma Aïmeur
Published: 2026-02-03
Categories: cs.CL, cs.HC, cs.IR
arXiv: https://arxiv.org/abs/2603.05519v1

The rampant spread of fake news in the digital age poses serious risks to public trust and democratic institutions, underscoring the need for effective, transparent, and user-centered detection tools. Existing browser extensions often fall short due to opaque model behavior, limited explanatory support, and a lack of meaningful user engagement. This paper introduces Aletheia, a novel browser extension that leverages Retrieval-Augmented Generation (RAG) and Large Language Models (LLMs) to detect fake news and provide evidence-based explanations. Aletheia further includes two interactive components: a Discussion Hub that enables user dialogue around flagged content and a Stay Informed feature that surfaces recent fact-checks. Through extensive experiments, we show that Aletheia outperforms state-of-the-art baselines in detection performance. Complementing this empirical evaluation, a complementary user study with 250 participants confirms the system's usability and perceived effectiveness, highlighting its potential as a transparent tool for combating online fake news.

---

### Multiclass Hate Speech Detection with RoBERTa-OTA: Integrating Transformer Attention and Graph Convolutional Networks

Authors: Mahmoud Abusaqer, Jamil Saquer
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.04414v1

Multiclass hate speech detection across demographic categories remains computationally challenging due to implicit targeting strategies and linguistic variability in social media content. Existing approaches rely solely on learned representations from training data, without explicitly incorporating structured ontological frameworks that can enhance classification through formal domain knowledge integration. We propose RoBERTa-OTA, which introduces ontology-guided attention mechanisms that process textual features alongside structured knowledge representations through enhanced Graph Convolutional Networks. The architecture combines RoBERTa embeddings with scaled attention layers and graph neural networks to integrate contextual language understanding with domain-specific semantic knowledge. Evaluation across 39,747 balanced samples using 5-fold cross-validation demonstrates significant performance gains over baseline RoBERTa implementations and existing state-of-the-art methods. RoBERTa-OTA achieves 96.04\% accuracy compared to 95.02\% for standard RoBERTa, with substantial improvements for challenging categories: gender-based hate speech detection improves by 2.36 percentage points while other hate speech categories improve by 2.38 percentage points. The enhanced architecture maintains computational efficiency with only 0.33\% parameter overhead, providing practical advantages for large-scale content moderation applications requiring fine-grained demographic hate speech classification.

---

### Simulating Meaning, Nevermore! Introducing ICR: A Semiotic-Hermeneutic Metric for Evaluating Meaning in LLM Text Summaries

Authors: Natalie Perez, Sreyoshi Bhaduri, Aman Chadha
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04413v2

Meaning in human language is relational, context dependent, and emergent, arising from dynamic systems of signs rather than fixed word-concept mappings. In computational settings, this semiotic and interpretive complexity complicates the generation and evaluation of meaning. This article proposes an interdisciplinary framework for studying meaning in large language model (LLM) generated language by integrating semiotics and hermeneutics with qualitative research methods. We review prior scholarship on meaning and machines, examining how linguistic signs are transformed into vectorized representations in static and contextualized embedding models, and identify gaps between statistical approximation and human interpretive meaning. We then introduce the Inductive Conceptual Rating (ICR) metric, a qualitative evaluation approach grounded in inductive content analysis and reflexive thematic analysis, designed to assess semantic accuracy and meaning alignment in LLM-outputs beyond lexical similarity metrics. We apply ICR in an empirical comparison of LLM generated and human generated thematic summaries across five datasets (N = 50 to 800). While LLMs achieve high linguistic similarity, they underperform on semantic accuracy, particularly in capturing contextually grounded meanings. Performance improves with larger datasets but remains variable across models, potentially reflecting differences in the frequency and coherence of recurring concepts and meanings. We conclude by arguing for evaluation frameworks that leverage systematic qualitative interpretation practices when assessing meaning in LLM-generated outputs from reference texts.

---

### Additive Multi-Step Markov Chains and the Curse of Dimensionality in Large Language Models

Authors: O. V. Usatenko, S. S. Melnyk, G. M. Pritula
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.04412v1

Large-scale language models (LLMs) operate in extremely high-dimensional state spaces, where both token embeddings and their hidden representations create complex dependencies that are not easily reduced to classical Markov structures. In this paper, we explore a theoretically feasible approximation of LLM dynamics using N-order additive Markov chains. Such models allow the conditional probability of the next token to be decomposed into a superposition of contributions from multiple historical depths, reducing the combinatorial explosion typically associated with high-order Markov processes. The main result of the work is the establishment of a correspondence between an additive multi-step chain and a chain with a step-wise memory function. This equivalence allowed the introduction of the concept of information temperature not only for stepwise but also for additive N-order Markov chains.

---

### One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache

Authors: Liming Lu, Kaixi Qiu, Jiayu Zhou, Jushi Kai, Haoyan Zhang, Huanyu Wang, Jingwen Leng, Ziwei He, Zhouhan Lin
Published: 2026-02-03
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2603.04411v1

Despite the remarkable progress of Large Language Models (LLMs), the escalating memory footprint of the Key-Value (KV) cache remains a critical bottleneck for efficient inference. While dimensionality reduction offers a promising compression avenue, existing approaches typically either necessitate prohibitively expensive pre-training from scratch or suffer from severe performance deterioration under high compression regimes. In this work, we propose DynaKV, a novel post-training framework for low-rank KV cache compression. To the best of our knowledge, DynaKV is the first method to dynamically allocate compression rates to individual tokens according to their semantic meaning, which allows it to achieve better fidelity at aggressive compression ratios. Extensive experiments demonstrate that our method consistently outperforms existing state-of-the-art compression techniques, achieving significant memory reduction while maintaining competitive generation quality. Furthermore, our approach is orthogonal to sequence-level pruning methods. When integrated with SnapKV, DynaKV retains only 6% of the KV cache while maintaining 94% of the baseline performance on the LongBench benchmark.

---

### SalamahBench: Dialect and Category Level Safety Evaluation of Arabic Language Models

Authors: Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, Ihsen Alouani, Mohammed E. Fouda
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04410v3

While different stakeholders are trying to leverage Arabic Language Models (ALMs), safety alignment in ALMs remains largely underexplored, hindering their mainstream adoption. Existing safety benchmarks are predominantly English-centric and evaluate Arabic only in its standardized form, obscuring fine-grained safety vulnerabilities in Arabic NLP systems. This paper introduces SalamahBench, a unified benchmark of 8{,}270 human-verified harmful prompts across ML Commons hazard categories, each rendered in Modern Standard Arabic (MSA) and five regional Arabic varieties, namely Egyptian, Syrian, Saudi, Lebanese, and Moroccan, for a total of 49{,}620 paired instances. To analyze the resulting data, we introduce two complementary metrics, namely Dialect Shift, which measures a model's aggregate change in safety under dialectal reformulation, and Category-Specific Dialect Deviation, which isolates harm categories whose change departs from that aggregate trend. Evaluating models such as Fanar 2, ALLaM 2, and Karnak 1 under multiple safeguard configurations, we find that cross-variety robustness is strongly model dependent, and that aggregate scores can conceal category-level divergence. Our findings highlight the necessity of evaluating Arabic model safety jointly across linguistic varieties and harm domains rather than relying on aggregate scores or MSA alone.

---

### SalamahBench: Toward Standardized Safety Evaluation for Arabic Language Models

Authors: Omar Abdelnasser, Fatemah Alharbi, Khaled Khasawneh, Ihsen Alouani, Mohammed E. Fouda
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.04410v1

Safety alignment in Language Models (LMs) is fundamental for trustworthy AI. However, while different stakeholders are trying to leverage Arabic Language Models (ALMs), systematic safety evaluation of ALMs remains largely underexplored, limiting their mainstream uptake. Existing safety benchmarks and safeguard models are predominantly English-centric, limiting their applicability to Arabic Natural Language Processing (NLP) systems and obscuring fine-grained, category-level safety vulnerabilities. This paper introduces SalamaBench, a unified benchmark for evaluating the safety of ALMs, comprising $8,170$ prompts across $12$ different categories aligned with the MLCommons Safety Hazard Taxonomy. Constructed by harmonizing heterogeneous datasets through a rigorous pipeline involving AI filtering and multi-stage human verification, SalamaBench enables standardized, category-aware safety evaluation. Using this benchmark, we evaluate five state-of-the-art ALMs, including Fanar 1 and 2, ALLaM 2, Falcon H1R, and Jais 2, under multiple safeguard configurations, including individual guard models, majority-vote aggregation, and validation against human-annotated gold labels. Our results reveal substantial variation in safety alignment: while Fanar 2 achieves the lowest aggregate attack success rates, its robustness is uneven across specific harm domains. In contrast, Jais 2 consistently exhibits elevated vulnerability, indicating weaker intrinsic safety alignment. We further demonstrate that native ALMs perform substantially worse than dedicated safeguard models when acting as safety judges. Overall, our findings highlight the necessity of category-aware evaluation and specialized safeguard mechanisms for robust harm mitigation in ALMs.

---

### Unpacking Human Preference for LLMs: Demographically Aware Evaluation with the HUMAINE Framework

Authors: Nora Petrova, Andrew Gordon, Enzo Blindow
Published: 2026-02-03
Categories: cs.CL, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2603.04409v1

The evaluation of large language models faces significant challenges. Technical benchmarks often lack real-world relevance, while existing human preference evaluations suffer from unrepresentative sampling, superficial assessment depth, and single-metric reductionism. To address these issues, we introduce HUMAINE, a framework for multidimensional, demographically aware measurement of human-AI interaction. We collected multi-turn, naturalistic conversations from 23,404 participants that were stratified across 22 demographic groups, both in the US and UK, to evaluate 28 state-of-the-art models across five human-centric dimensions. We use a hierarchical Bayesian Bradley-Terry-Davidson (BTD) model, with post-stratification to census data, and our analysis reveals three key insights. \textbf{(1)} We establish a clear performance hierarchy where \texttt{google/gemini-2.5-pro} ranks first overall, with a 95.6\% posterior probability of being the top-ranked model. \textbf{(2)} We uncover significant preference heterogeneity, with user age emerging as the primary demographic axis of disagreement; a model's perceived rank can shift substantially across age groups, exposing failures in generalisation that unrepresentative samples typically mask. \textbf{(3)} We quantify the vast difference in discriminative power across evaluation dimensions, with ambiguous qualities like \textit{Trust, Ethics \& Safety} showing a 65\% tie rate, in stark contrast to the decisive 10\% tie rate for \textit{Overall Winner}. Our work emphasises the need for a more multidimensional, demographically aware perspective in LLM evaluation. We release our complete dataset, interactive leaderboard, and open-source framework.

---

### Probing Memes in LLMs: A Paradigm for the Entangled Evaluation World

Authors: Luzhou Peng, Zhengxin Yang, Honglu Ji, Yikang Yang, Fanda Fan, Wanling Gao, Jiayuan Ge, Yilin Han, Jianfeng Zhan
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.04408v1

Current evaluation paradigms for large language models (LLMs) characterize models and datasets separately, yielding coarse descriptions: items in datasets are treated as pre-labeled entries, and models are summarized by overall scores such as accuracy, together ignoring the diversity of population-level model behaviors across items with varying properties. To address this gap, this paper conceptualizes LLMs as composed of memes, a notion introduced by Dawkins as cultural genes that replicate knowledge and behavior. Building on this perspective, the Probing Memes paradigm reconceptualizes evaluation as an entangled world of models and data. It centers on a Perception Matrix that captures model-item interactions, enabling Probe Properties for characterizing items and Meme Scores for depicting model behavioral traits. Applied to 9 datasets and 4,507 LLMs, Probing Memes reveals hidden capability structures and quantifies phenomena invisible under traditional paradigms (e.g., elite models failing on problems that most models answer easily). It not only supports more informative and extensible benchmarks but also enables population-based evaluation of LLMs.

---

### TAB-PO: Preference Optimization with a Token-Level Adaptive Barrier for Token-Critical Structured Generation

Authors: Samah Fodeh, Linhai Ma, Ganesh Puthiaraju, Srivani Talakokkul, Afshan Khan, Sreeraj Ramachandran, Elyas Irankhah, Aimee Kendall Roundtree
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.00025v3

Direct Preference Optimization (DPO) is effective for offline alignment but poorly matched to ontology-driven structured prediction, where preferred and rejected JSON often differ by only a few schema-defining tokens. In this low-edit-distance regime, sequence-level DPO spreads gradient mass across non-critical serialization tokens (gradient dilution) and can reduce likelihood on rare preferred schema tokens (token erosion). To address these limitations, we first develop a confusion-aware preference-construction strategy combining expert-curated ambiguity patterns with validation-set SFT structured-error modes, producing minimally perturbed, schema-valid negatives for ontology-level decision errors. We then introduce Token-Adaptive Barrier Preference Optimization (TAB-PO), a post-SFT objective for token-critical structured generation with a confidence-gated token-level barrier that anchors under-confident schema tokens. On SciERC, with Llama/Qwen models, TAB-PO improves ontology-critical semantic-label and relational-linking metrics by 11.59% relative to SFT, wins 100% of comparisons against strongest token-level/sequence-level DPO variants, and surpasses strongest frontier baselines on these metrics by 14.71% relative while improving textual grounding.

---

### Personalization Increases Affective Alignment but Has Role-Dependent Effects on Epistemic Independence in LLMs

Authors: Sean W. Kelley, Christoph Riedl
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.00024v1

Large Language Models (LLMs) are prone to sycophantic behavior, uncritically conforming to user beliefs. As models increasingly condition responses on user-specific context (personality traits, preferences, conversation history), they gain information to tailor agreement more effectively. Understanding how personalization modulates sycophancy is critical, yet systematic evaluation across models and contexts remains limited. We present a rigorous evaluation of personalization's impact on LLM sycophancy across nine frontier models and five benchmark datasets spanning advice, moral judgment, and debate contexts. We find that personalization generally increases affective alignment (emotional validation, hedging/deference), but affects epistemic alignment (belief adoption, position stability, resistance to influence) with context-dependent role modulation. When the LLM's role is to give advice, personalization strengthens epistemic independence (models challenge user presuppositions). When its role is that of a social peer, personalization decreases epistemic independence. In this role, extensively personalized user challenges causing LLMs to abandon their position at significantly higher rates. Robustness tests confirm that the effects are driven by personalized conditioning, not by additional input tokens per se or demographic information alone. Our work provides measurement frameworks for evaluating personalized AI systems, demonstrates the necessity of role-sensitive evaluation, and establishes a novel benchmark to assess goal alignment.

---

### Riemannian Dueling Optimization

Authors: Yuxuan Ren, Abhishek Roy, Shiqian Ma
Published: 2026-02-03
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2603.00023v1

Dueling optimization considers optimizing an objective with access to only a comparison oracle of the objective function. It finds important applications in emerging fields such as recommendation systems and robotics. Existing works on dueling optimization mainly focused on unconstrained problems in the Euclidean space. In this work, we study dueling optimization over Riemannian manifolds, which covers important applications that cannot be solved by existing dueling optimization algorithms. In particular, we propose a Riemannian Dueling Normalized Gradient Descent (RDNGD) method and establish its iteration complexity when the objective function is geodesically L-smooth or geodesically (strongly) convex. We also propose a projection-free algorithm, named Riemannian Dueling Frank-Wolfe (RDFW) method, to deal with the situation where projection is prohibited. We establish the iteration and oracle complexities for RDFW. We illustrate the effectiveness of the proposed algorithms through numerical experiments on both synthetic and real applications.

---

### Noise reduction in BERT NER models for clinical entity extraction

Authors: Kuldeep Jiwani, Yash K Jeengar, Ayush Dhaka
Published: 2026-02-03
Categories: cs.CL, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2603.00022v1

Precision is of utmost importance in the realm of clinical entity extraction from clinical notes and reports. Encoder Models fine-tuned for Named Entity Recognition (NER) are an efficient choice for this purpose, as they don't hallucinate. We pre-trained an in-house BERT over clinical data and then fine-tuned it for NER. These models performed well on recall but could not close upon the high precision range, needed for clinical models. To address this challenge, we developed a Noise Removal model that refines the output of NER. The NER model assigns token-level entity tags along with probability scores for each token. Our Noise Removal (NR) model then analyzes these probability sequences and classifies predictions as either weak or strong. A naïve approach might involve filtering predictions based on low probability values; however, this method is unreliable. Owing to the characteristics of the SoftMax function, Transformer based architectures often assign disproportionately high confidence scores even to uncertain or weak predictions, making simple thresholding ineffective. To address this issue, we adopted a supervised modeling strategy in which the NR model leverages advanced features such as the Probability Density Map (PDM). The PDM captures the Semantic-Pull effect observed within Transformer embeddings, an effect that manifests in the probability distributions of NER class predictions across token sequences. This approach enables the model to classify predictions as weak or strong with significantly improved accuracy. With these NR models we were able to reduce False Positives across various clinical NER models by 50\% to 90\%.

---

### From Global to Local: Learning Context-Aware Graph Representations for Document Classification and Summarization

Authors: Ruangrin Ldallitsakool, Margarita Bugueño, Gerard de Melo
Published: 2026-02-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2603.00021v2

Recent NLP systems commonly represent documents as linear token sequences. Although this captures sequential order, it can hinder modeling long-range dependencies and global document structure, especially for long texts. This paper proposes a data-driven method to automatically construct graph-based document representations. Building upon the recent work of Bugueño and de Melo (2025), we leverage the dynamic sliding-window attention module to effectively capture local and mid-range semantic dependencies between sentences, as well as structural relations within documents. Graph Attention Networks (GATs) trained on our learned graphs achieve competitive results on document classification while requiring lower computational resources than previous approaches. We further present an exploratory evaluation of the proposed graph construction method for extractive document summarization, highlighting both its potential and current limitations. The implementation of this project can be found on GitHub.

---

### Universality of shallow and deep neural networks on non-Euclidean spaces

Authors: Vugar Ismailov
Published: 2026-02-03
Categories: math.GN, cs.LG, cs.NE, math.FA
arXiv: https://arxiv.org/abs/2602.23381v2

We study shallow and deep neural networks whose inputs range over a general topological space. The model is built from a prescribed family of continuous feature maps and reduces to multilayer feedforward networks in the Euclidean case. We focus on the universal approximation property and establish general conditions under which such networks are dense in spaces of continuous vector-valued functions on arbitrary topological spaces and, in particular, locally convex spaces. Universality results obtained in the arbitrary-width case extend classical approximation theorems to non-Euclidean spaces. We also consider the deep narrow setting, in which the width of each hidden layer is uniformly bounded while the depth is allowed to grow. We identify conditions under which such networks retain the universal approximation property. As a concrete example, we employ Ostrand's extension of the Kolmogorov superposition theorem to derive an explicit universality result for products of compact metric spaces, with width bounds expressed in terms of topological dimension.

---

### Developing a Multi-Agent System to Generate Next Generation Science Assessments with Evidence-Centered Design

Authors: Yaxuan Yang, Jongchan Park, Yifan Zhou, Xiaoming Zhai
Published: 2026-02-03
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.18451v1

Contemporary science education reforms such as the Next Generation Science Standards (NGSS) demand assessments to understand students' ability to use science knowledge to solve problems and design solutions. To elicit such higher-order ability, educators need performance-based assessments, which are challenging to develop. One solution that has been broadly adopted is Evidence-Centered Design (ECD), which emphasizes interconnected models of the learner, evidence, and tasks. Although ECD provides a framework to safeguard assessment validity, its implementation requires diverse expertise (e.g., content and assessment), which is both costly and labor-intensive. To address this challenge, this study proposed integrating the ECD framework into Multi-Agent Systems (MAS) to generate NGSS-aligned assessment items automatically. This integrated MAS system ensembles multiple large language models with varying expertise, enabling the automation of complex, multi-stage item generation workflows traditionally performed by human experts. We examined the quality of AI-generated NGSS-aligned items and compared them with human-developed items across multiple dimensions of assessment design. Results showed that AI-generated items have overall comparable quality to human-developed items in terms of alignment with NGSS three-dimensional standards and cognitive demands. Divergent patterns also emerged: AI-generated items demonstrated a distinct strength in inclusivity, while also exhibiting limitations in clarity, conciseness, and multimodal design. AI- and human-developed items both showed weaknesses in evidence collectability and student interest alignment. These findings suggest that integrating ECD into MAS can support scalable and standards-aligned assessment design, while human expertise remains essential.

---

### Contextual Information Allocation in Shared-State Cognitive Models: An Information-Theoretic Bound

Authors: Song-Ju Kim
Published: 2026-02-03
Categories: cs.AI, cs.IT, quant-ph
arXiv: https://arxiv.org/abs/2602.16716v4

Context-sensitive behavior can be modeled by enriching an internal state, by allowing a response rule to access context directly, or by preserving a shared state while introducing an auxiliary criterion or control variable. This paper isolates an information-theoretic constraint on the third architecture. Let $C$ denote context, $S$ a candidate internal or latent state, $O$ an observable response, and $M$ an auxiliary variable such that $O\perp C\mid(S,M)$. Then \( I(C;O\mid S)\le I(C;M\mid S)\le H(M\mid S). \) Once a shared state has been specified, residual context dependence in behavior therefore lower-bounds both the context information and the conditional entropy that an auxiliary context-mediating mechanism must carry. The bound is representation-relative rather than a measure of state-space size or a universal contextuality measure. A worked recognition-memory example shows how the quantity can be computed for payoff-induced criterion shifts and compared across alternative representational allocations. Ontological contextuality and quantum probability are treated as a separate specialization rather than as prerequisites for the cognitive interpretation. More broadly, the framework provides a basis for analyzing context-memory-control trade-offs in cognitive models and artificial agents that must maintain coherent behavior across changing contexts under bounded internal representations.

---

### Contextuality from Single-State Ontological Models: An Information-Theoretic Obstruction

Authors: Song-Ju Kim
Published: 2026-02-03
Categories: cs.AI, cs.IT, quant-ph
arXiv: https://arxiv.org/abs/2602.16716v3

Contextuality is a central feature of quantum theory, traditionally understood as the impossibility of reproducing quantum measurement statistics using noncontextual ontological models. We study classical ontological descriptions in which a fixed subsystem-level ontic state space is reused across multiple interventions. Our main result is an information-theoretic obstruction: whenever a classical single-state model reproduces operational statistics using an auxiliary contextual register, the required contextual information is lower-bounded by the conditional mutual information $I(C;O\mid λ)$ between intervention $C$ and outcome $O$ conditioned on the subsystem ontic state $λ$. The mathematical inequality itself is elementary, but its interpretive significance is structural: under shared-state reuse, contextual distinctions need not be fully internalized within the subsystem ontic state alone. We provide a constructive illustration of this point and clarify how the issue should be understood as a limitation of subsystem-level classical representation, rather than as a dualism about physical reality. We further discuss how this perspective relates to ontological models and to contextuality in quantum foundations.

---

### BamaER: A Behavior-Aware Memory-Augmented Model for Exercise Recommendation

Authors: Qing Yang, Yuhao Jiang, Rui Wang, Jipeng Guo, Yejiang Wang, Xinghe Cheng, Zezheng Wu, Jiapu Wang, Jingwei Zhang
Published: 2026-02-03
Categories: cs.LG, cs.CY
arXiv: https://arxiv.org/abs/2602.15879v1

Exercise recommendation focuses on personalized exercise selection conditioned on students' learning history, personal interests, and other individualized characteristics. Despite notable progress, most existing methods represent student learning solely as exercise sequences, overlooking rich behavioral interaction information. This limited representation often leads to biased and unreliable estimates of learning progress. Moreover, fixed-length sequence segmentation limits the incorporation of early learning experiences, thereby hindering the modeling of long-term dependencies and the accurate estimation of knowledge mastery. To address these limitations, we propose BamaER, a Behavior-aware memory-augmented Exercise Recommendation framework that comprises three core modules: (i) the learning progress prediction module that captures heterogeneous student interaction behaviors via a tri-directional hybrid encoding scheme; (ii) the memory-augmented knowledge tracing module that maintains a dynamic memory matrix to jointly model historical and current knowledge states for robust mastery estimation; and (iii) the exercise filtering module that formulates candidate selection as a diversity-aware optimization problem, solved via the Hippopotamus Optimization Algorithm to reduce redundancy and improve recommendation coverage. Experiments on five real-world educational datasets show that BamaER consistently outperforms state-of-the-art baselines across a range of evaluation metrics.

---

### IT-OSE: Exploring Optimal Sample Size for Industrial Data Augmentation

Authors: Mingchun Sun, Rongqiang Zhao, Zhennan Huang, Songyu Ding, Jie Liu
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.15878v1

In industrial scenarios, data augmentation is an effective approach to improve model performance. However, its benefits are not unidirectionally beneficial. There is no theoretical research or established estimation for the optimal sample size (OSS) in augmentation, nor is there an established metric to evaluate the accuracy of OSS or its deviation from the ground truth. To address these issues, we propose an information-theoretic optimal sample size estimation (IT-OSE) to provide reliable OSS estimation for industrial data augmentation. An interval coverage and deviation (ICD) score is proposed to evaluate the estimated OSS intuitively. The relationship between OSS and dominant factors is theoretically analyzed and formulated, thereby enhancing the interpretability. Experiments show that, compared to empirical estimation, the IT-OSE increases accuracy in classification tasks across baseline models by an average of 4.38%, and reduces MAPE in regression tasks across baseline models by an average of 18.80%. The improvements in downstream model performance are more stable. ICDdev in the ICD score is also reduced by an average of 49.30%. The determinism of OSS is enhanced. Compared to exhaustive search, the IT-OSE achieves the same OSS while reducing computational and data costs by an average of 83.97% and 93.46%. Furthermore, practicality experiments demonstrate that the IT-OSE exhibits generality across representative sensor-based industrial scenarios.

---

### Multimodal Consistency-Guided Reference-Free Data Selection for ASR Accent Adaptation

Authors: Ligong Lei, Wenwen Lu, Xudong Pang, Zaokere Kadeer, Aishan Wumaier
Published: 2026-02-03
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2602.13263v1

Automatic speech recognition (ASR) systems often degrade on accented speech because acoustic-phonetic and prosodic shifts induce a mismatch to training data, making labeled accent adaptation costly. However, common pseudo-label selection heuristics are largely text-centric (e.g., perplexity (PPL) filtering) and can prefer fluent yet acoustically mismatched hypotheses, leading to error amplification when fine-tuning. To address this, we introduce a multimodal consistency-guided, reference-free data selection pipeline for ASR accent adaptation under a transductive, label-free protocol. The pipeline starts with a target-aware preselection step based on submodular mutual information to improve query relevance and reduce downstream computation. It then generates multiple pseudo-transcriptions per utterance via perturbation-based decoding and scores each hypothesis using two reference-free signals: speech--text alignment in a shared embedding space and predicted word error rate (WER). A simple percentile-based selection rule retains reliable pseudo-labels for fine-tuning while discarding noisy utterances. In an in-domain setting, selecting ~1.5k utterances from a 30k pool achieves 10.91% WER, close to 10.45% obtained using 30k supervised labels. In a cross-domain setting with a mismatched candidate pool, consistency-filtered subsets avoid the degradation caused by unfiltered pseudo-labels under strong accent shift, and matched-hour experiments on a stronger ASR backbone further confirm gains over random sampling and recent selection baselines.

---

### General learned delegation by clones

Authors: Darren Li, Meiqi Chen, Chenze Shao, Fandong Meng, Jie Zhou
Published: 2026-02-03
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13262v1

Frontier language models improve with additional test-time computation, but serial reasoning or uncoordinated parallel sampling can be compute-inefficient under fixed inference budgets. We propose SELFCEST, which equips a base model with the ability to spawn same-weight clones in separate parallel contexts by agentic reinforcement learning. Training is end-to-end under a global task reward with shared-parameter rollouts, yielding a learned controller that allocates both generation and context budget across branches. Across challenging math reasoning benchmarks and long-context multi-hop QA, SELFCEST improves the accuracy-cost Pareto frontier relative to monolithic baselines at matched inference budget, and exhibits out-of-distribution generalization in both domains.

---

### A feedback control optimizer for online and hardware-aware training of Spiking Neural Networks

Authors: Matteo Saponati, Chiara De Luca, Giacomo Indiveri, Benjamin Grewe
Published: 2026-02-03
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2602.13261v1

Unlike traditional artificial neural networks (ANNs), biological neuronal networks solve complex cognitive tasks with sparse neuronal activity, recurrent connections, and local learning rules. These mechanisms serve as design principles in Neuromorphic computing, which addresses the critical challenge of energy consumption in modern computing. However, most mixed-signal neuromorphic devices rely on semi- or unsupervised learning rules, which are ineffective for optimizing hardware in supervised learning tasks. This lack of scalable solutions for on-chip learning restricts the potential of mixed-signal devices to enable sustainable, intelligent edge systems. To address these challenges, we present a novel learning algorithm for Spiking Neural Networks (SNNs) on mixed-signal devices that integrates spike-based weight updates with feedback control signals. In our framework, a spiking controller generates feedback signals to guide SNN activity and drive weight updates, enabling scalable and local on-chip learning. We first evaluate the algorithm on various classification tasks, demonstrating that single-layer SNNs trained with feedback control achieve performance comparable to artificial neural networks (ANNs). We then assess its implementation on mixed-signal neuromorphic devices by testing network performance in continuous online learning scenarios and evaluating resilience to hyperparameter mismatches. Our results show that the feedback control optimizer is compatible with neuromorphic applications, advancing the potential for scalable, on-chip learning solutions in edge applications.

---

### Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition

Authors: Xu Zhang, Longbing Cao, Runze Yang, Zhangkai Wu
Published: 2026-02-03
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2602.13259v1

Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient models are critical for safety and performance. Existing deep models trained on large datasets remain largely uninterpretable, often insufficiently modeling underlying emotional acoustic signals and failing to capture and analyze the core physiology of emotional vocal behaviors. Physiological research on human voices shows that the dynamics of vocal amplitude and phase correlate with emotions through the vocal tract filter and the glottal source. However, most existing deep models solely involve amplitude but fail to couple the physiological features of and between amplitude and phase. Here, we propose PhysioSER, a physiology-informed vocal spectrotemporal representation learning method, to address these issues with a compact, plug-and-play design. PhysioSER constructs amplitude and phase views informed by voice anatomy and physiology (VAP) to complement SSL models for SER. This VAP-informed framework incorporates two parallel workflows: a vocal feature representation branch to decompose vocal signals based on VAP, embed them into a quaternion field, and use Hamilton-structured quaternion convolutions for modeling their dynamic interactions; and a latent representation branch based on a frozen SSL backbone. Then, utterance-level features from both workflows are aligned by a Contrastive Projection and Alignment framework, followed by a shallow attention fusion head for SER classification. PhysioSER is shown to be interpretable and efficient for SER through extensive evaluations across 14 datasets, 10 languages, and 6 backbones, and its practical efficacy is validated by real-time deployment on a humanoid robotic platform.

---

### MAPLE: A Sub-Agent Architecture for Memory, Learning, and Personalization in Agentic AI Systems

Authors: Deepak Babu Piskala
Published: 2026-02-03
Categories: cs.AI, cs.CL, cs.MA
arXiv: https://arxiv.org/abs/2602.13258v1

Large language model (LLM) agents have emerged as powerful tools for complex tasks, yet their ability to adapt to individual users remains fundamentally limited. We argue this limitation stems from a critical architectural conflation: current systems treat memory, learning, and personalization as a unified capability rather than three distinct mechanisms requiring different infrastructure, operating on different timescales, and benefiting from independent optimization. We propose MAPLE (Memory-Adaptive Personalized LEarning), a principled decomposition where Memory handles storage and retrieval infrastructure; Learning extracts intelligence from accumulated interactions asynchronously; and Personalization applies learned knowledge in real-time within finite context budgets. Each component operates as a dedicated sub-agent with specialized tooling and well-defined interfaces. Experimental evaluation on the MAPLE-Personas benchmark demonstrates that our decomposition achieves a 14.6% improvement in personalization score compared to a stateless baseline (p < 0.01, Cohen's d = 0.95) and increases trait incorporation rate from 45% to 75% -- enabling agents that genuinely learn and adapt.

---

### Declarative by Design, Assistable Only by Convention: Benchmarking Multi-Agent Frameworks for AI-Assistability

Authors: Shafiuddin Rehan Ahmed, Sourabh Deshpande
Published: 2026-02-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.11198v2

Multi-agent frameworks (MAFs) promise to simplify LLM-driven software development, yet no principled metric captures how well AI coding assistants can generate correct, framework-specific code. We introduce \textit{AI-assistability} ($\mathcal{AI}$), a composite metric that quantifies a framework's amenability to AI-assisted development by combining structural alignment ($\barσ$) with functional correctness (pass@1). To evaluate this metric in a controlled setting, we design DDL2PropBank, a novel benchmark task that maps relational database schemas to PropBank semantic rolesets, and implement identical agent logic across ten frameworks using the Agent-as-a-Tool pattern. Our results challenge the intuition that declarative framework design guarantees AI-assistability: Agno, with a single canonical pattern and convention-aligned API, achieves the highest $\mathcal{AI}$ score (0.55), while DSPy -- the most declarative framework by design -- scores lowest (0.07), as its novel abstractions are insufficiently represented in AI training data. We find that convention alignment, not declarative design alone, is the primary driver of AI-assistability ($r = 0.576$ between $\barσ$ and pass@1). All artifacts -- DDL2PropBank, PropBank MCP server, and all implementations -- are available at https://github.com/ahmeshaf/ddl2propbank

---

### The Anatomy of the Moltbook Social Graph

Authors: David Holtz
Published: 2026-02-03
Categories: cs.SI, cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2602.10131v1

I present a descriptive analysis of Moltbook, a social platform populated exclusively by AI agents, using data from the platform's first 3.5 days (6{,}159 agents; 13{,}875 posts; 115{,}031 comments). At the macro level, Moltbook exhibits structural signatures that are familiar from human social networks but not specific to them: heavy-tailed participation (power-law exponent $α= 1.70$) and small-world connectivity (average path length $=2.91$). At the micro level, patterns appear distinctly non-human. Conversations are extremely shallow (mean depth $=1.07$; 93.5\% of comments receive no replies), reciprocity is low (0.197), and 34.1\% of messages are exact duplicates of viral templates. Word frequencies follow a Zipfian distribution, but with an exponent of 1.70 -- notably steeper than typical English text ($\approx 1.0$), suggesting more formulaic content. Agent discourse is dominated by identity-related language (68.1\% of unique messages) and distinctive phrasings like ``my human'' (9.4\% of messages) that have no parallel in human social media. Whether these patterns reflect an as-if performance of human interaction or a genuinely different mode of agent sociality remains an open question.

---

### DSFlow: Dual Supervision and Step-Aware Architecture for One-Step Flow Matching Speech Synthesis

Authors: Bin Lin, Peng Yang, Chao Yan, Xiaochen Liu, Wei Wang, Boyong Wu, Pengfei Tan, Xuerui Yang
Published: 2026-02-03
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2602.09041v1

Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference steps, existing methods often suffer from process variance due to endpoint error accumulation. Moreover, directly reusing continuous-time architectures for discrete, fixed-step generation introduces structural parameter inefficiencies. To address these challenges, we introduce DSFlow, a modular distillation framework for few-step and one-step synthesis. DSFlow reformulates generation as a discrete prediction task and explicitly adapts the student model to the target inference regime. It improves training stability through a dual supervision strategy that combines endpoint matching with deterministic mean-velocity alignment, enforcing consistent generation trajectories across inference steps. In addition, DSFlow improves parameter efficiency by replacing continuous-time timestep conditioning with lightweight step-aware tokens, aligning model capacity with the significantly reduced timestep space of the discrete task. Extensive experiments across diverse flow-based text-to-speech architectures demonstrate that DSFlow consistently outperforms standard distillation approaches, achieving strong few-step and one-step synthesis quality while reducing model parameters and inference cost.

---

### OMNI-Dent: Towards an Accessible and Explainable AI Framework for Automated Dental Diagnosis

Authors: Leeje Jang, Yao-Yi Chiang, Angela M. Hastings, Patimaporn Pungchanchaikul, Martha B. Lucas, Emily C. Schultz, Jeffrey P. Louie, Mohamed Estai, Wen-Chen Wang, Ryan H. L. Ip, Boyen Huang
Published: 2026-02-03
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.07041v1

Accurate dental diagnosis is essential for oral healthcare, yet many individuals lack access to timely professional evaluation. Existing AI-based methods primarily treat diagnosis as a visual pattern recognition task and do not reflect the structured clinical reasoning used by dental professionals. These approaches also require large amounts of expert-annotated data and often struggle to generalize across diverse real-world imaging conditions. To address these limitations, we present OMNI-Dent, a data-efficient and explainable diagnostic framework that incorporates clinical reasoning principles into a Vision-Language Model (VLM)-based pipeline. The framework operates on multi-view smartphone photographs,embeds diagnostic heuristics from dental experts, and guides a general-purpose VLM to perform tooth-level evaluation without dental-specific fine-tuning of the VLM. By utilizing the VLM's existing visual-linguistic capabilities, OMNI-Dent aims to support diagnostic assessment in settings where curated clinical imaging is unavailable. Designed as an early-stage assistive tool, OMNI-Dent helps users identify potential abnormalities and determine when professional evaluation may be needed, offering a practical option for individuals with limited access to in-person care.

---

### Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods

Authors: Emmett Bicker
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.07040v1

We introduce Aster, an AI agent for autonomous scientific discovery capable of operating over 20 times faster than existing frameworks. Given a task, an initial program, and a script to evaluate the performance of the program, Aster iteratively improves the program, often leading to new state-of-the-art performances. Aster's significant reduction in the number of iterations required for novel discovery expands the domain of tractable problems to include tasks with long evaluation durations, such as multi-hour machine learning training runs. We applied Aster to problems in mathematics, GPU kernel engineering, biology, neuroscience, and language model training. More specifically: the Erdos minimum overlap problem, optimizing the TriMul kernel, a single-cell analysis denoising problem, training a neural activity prediction model to perform well on ZAPBench, and the NanoGPT Speedrun Competition. Aster attains SOTA results in every task, except for ZAPBench, where it matches the performance of the best human solution with less than 1/190th of the compute. Aster is accessible via a web interface and API at asterlab.ai.

---

### When Excellence Stops Producing Knowledge: A Practitioner's Observation on Research Funding

Authors: Heimo Müller
Published: 2026-02-03
Categories: cs.CY, cs.AI, cs.DL
arXiv: https://arxiv.org/abs/2602.07039v1

After almost four decades of participating in competitive research funding -- as applicant, coordinator, evaluator, and panel member -- I have come to see a structural paradox: many participants recognize that the current system is approaching its functional limits, yet most reform measures intensify rather than alleviate the underlying dynamics. This paper documents how excellence has become decoupled from knowledge production through an increasing coupling to representability under evaluation. The discussion focuses on two domains in which this is particularly visible: competitive basic research funding and large EU consortium projects. Three accelerating trends are examined: the professionalization of proposal writing through specialized consultants, the rise of AI-assisted applications, and an evaluator shortage that forces panels to rely on reviewers increasingly distant from the actual research domains. These observations are offered not as external critique but as an insider account, in the hope that naming a widely experienced but rarely articulated pattern may enable more constructive orientation. Keywords: Research funding, Excellence, Evaluation, Goodhart's Law, Professionalization, AI-assisted proposals, Peer review crisis

---

### UNIKIE-BENCH: Benchmarking Large Multimodal Models for Key Information Extraction in Visual Documents

Authors: Yifan Ji, Zhipeng Xu, Zhenghao Liu, Zulong Chen, Qian Zhang, Zhibo Yang, Junyang Lin, Yu Gu, Ge Yu, Maosong Sun
Published: 2026-02-03
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2602.07038v2

Key Information Extraction (KIE) from real-world documents remains challenging due to substantial variations in layout structures, visual quality, and task-specific information requirements. Recent Large Multimodal Models (LMMs) have shown promising potential for performing end-to-end KIE directly from document images. To enable a comprehensive and systematic evaluation across realistic and diverse application scenarios, we introduce UNIKIE-BENCH, a unified benchmark designed to rigorously evaluate the KIE capabilities of LMMs. UNIKIE-BENCH consists of two complementary tracks: a constrained-category KIE track with scenario-predefined schemas that reflect practical application needs, and an open-category KIE track that extracts any key information that is explicitly present in the document. Experiments on 15 state-of-the-art LMMs reveal substantial performance degradation under diverse schema definitions, long-tail key fields, and complex layouts, along with pronounced performance disparities across different document types and scenarios. These findings underscore persistent challenges in grounding accuracy and layout-aware reasoning for LMM-based KIE. All codes and datasets are available at https://github.com/NEUIR/UNIKIE-BENCH.

---

### Stochastic Spiking Neuron Based SNN Can be Inherently Bayesian

Authors: Huannan Zheng, Jingli Liu, Kezhou Yang
Published: 2026-02-03
Categories: cs.NE, cs.AI, cs.CV, cs.ET
arXiv: https://arxiv.org/abs/2602.07037v1

Uncertainty in biological neural systems appears to be computationally beneficial rather than detrimental. However, in neuromorphic computing systems, device variability often limits performance, including accuracy and efficiency. In this work, we propose a spiking Bayesian neural network (SBNN) framework that unifies the dynamic models of intrinsic device stochasticity (based on Magnetic Tunnel Junctions) and stochastic threshold neurons to leverage noise as a functional Bayesian resource. Experiments demonstrate that SBNN achieves high accuracy (99.16% on MNIST, 94.84% on CIFAR10) with 8-bit precision. Meanwhile rate estimation method provides a ~20-fold training speedup. Furthermore, SBNN exhibits superior robustness, showing a 67% accuracy improvement under synaptic weight noise and 12% under input noise compared to standard spiking neural networks. Crucially, hardware validation confirms that physical device implementation causes invisible accuracy and calibration loss compared to the algorithmic model. Converting device stochasticity into neuronal uncertainty offers a route to compact, energy-efficient neuromorphic computing under uncertainty.

---

### MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs

Authors: Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi, Shammur Absar Chowdhury, Firoj Alam
Published: 2026-02-03
Categories: cs.SD, cs.AI, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2602.07036v2

Audio large language models (AudioLLMs) enable instruction following over speech and general audio, but progress is limited by the scarcity of diverse, conversational, and instruction-aligned speech--text data. This gap is particularly pronounced for persona-grounded and dialectal interactions, where collecting real multi-speaker recordings remains costly and slow. We introduce MENASpeechBank, a reference speech bank comprising ~18K high-quality utterances from 124 speakers spanning multiple MENA countries, covering English, Modern Standard Arabic (MSA), and regional Arabic varieties. We develop a controllable data pipeline that (i) constructs persona profiles enriched with World Values Survey (WVS) inspired attributes, (ii) defines a taxonomy driven ~5Kconversational scenarios, (iii) matches personas to scenarios via semantic similarity, (iv) generates ~417K role-play conversations with an LLM where the user speaks as the persona and the assistant behaves as a helpful agent, and (v) produces speaker-conditioned user-turn audio (synthetic) from reference recordings to preserve speaker diversity. We evaluate synthetic and human recorded conversations and provide an analysis. We will make the MENASpeechBank available for the community.(\href{https://huggingface.co/datasets/QCRI/MenaSpeechBank)

---

### MENASpeechBank: A Reference Voice Bank with Persona-Conditioned Multi-Turn Conversations for AudioLLMs

Authors: Zien Sheikh Ali, Hunzalah Hassan Bhatti, Rabindra Nath Nandi, Shammur Absar Chowdhury, Firoj Alam
Published: 2026-02-03
Categories: cs.SD, cs.AI, cs.CL, eess.AS
arXiv: https://arxiv.org/abs/2602.07036v1

Audio large language models (AudioLLMs) enable instruction-following over speech and general audio, but progress is increasingly limited by the lack of diverse, conversational, instruction-aligned speech-text data. This bottleneck is especially acute for persona-grounded interactions and dialectal coverage, where collecting and releasing real multi-speaker recordings is costly and slow. We introduce MENASpeechBank, a reference speech bank comprising about 18K high-quality utterances from 124 speakers spanning multiple MENA countries, covering English, Modern Standard Arabic (MSA), and regional Arabic varieties. Building on this resource, we develop a controllable synthetic data pipeline that: (i) constructs persona profiles enriched with World Values Survey-inspired attributes, (ii) defines a taxonomy of about 5K conversational scenarios, (iii) matches personas to scenarios via semantic similarity, (iv) generates about 417K role-play conversations with an LLM where the user speaks as the persona and the assistant behaves as a helpful agent, and (v) synthesizes the user turns by conditioning on reference speaker audio to preserve speaker identity and diversity. We evaluate both synthetic and human-recorded conversations and provide detailed analysis. We will release MENASpeechBank and the generated conversations publicly for the community.

---

### DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents

Authors: Jiahao Zhao, Shaoxuan Xu, Zhongxiang Sun, Fengqi Zhu, Jingyang Ou, Yuling Shi, Chongxuan Li, Xiao Zhang, Jun Xu
Published: 2026-02-03
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.07035v1

Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C

---

### ST-Raptor: An Agentic System for Semi-Structured Table QA

Authors: Jinxiu Qu, Zirui Tang, Hongzhang Huang, Boyu Niu, Wei Zhou, Jiannan Wang, Yitong Song, Guoliang Li, Xuanhe Zhou, Fan Wu
Published: 2026-02-03
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.07034v1

Semi-structured table question answering (QA) is a challenging task that requires (1) precise extraction of cell contents and positions and (2) accurate recovery of key implicit logical structures, hierarchical relationships, and semantic associations encoded in table layouts. In practice, such tables are often interpreted manually by human experts, which is labor-intensive and time-consuming. However, automating this process remains difficult. Existing Text-to-SQL methods typically require converting semi-structured tables into structured formats, inevitably leading to information loss, while approaches like Text-to-Code and multimodal LLM-based QA struggle with complex layouts and often yield inaccurate answers. To address these limitations, we present ST-Raptor, an agentic system for semi-structured table QA. ST-Raptor offers an interactive analysis environment that combines visual editing, tree-based structural modeling, and agent-driven query resolution to support accurate and user-friendly table understanding. Experimental results on both benchmark and real-world datasets demonstrate that ST-Raptor outperforms existing methods in both accuracy and usability. The code is available at https://github.com/weAIDB/ST-Raptor, and a demonstration video is available at https://youtu.be/9GDR-94Cau4.

---

### TransConv-DDPM: Enhanced Diffusion Model for Generating Time-Series Data in Healthcare

Authors: Md Shahriar Kabir, Sana Alamgeer, Minakshi Debnath, Anne H. H. Ngu
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.07033v1

The lack of real-world data in clinical fields poses a major obstacle in training effective AI models for diagnostic and preventive tools in medicine. Generative AI has shown promise in increasing data volume and enhancing model training, particularly in computer vision and natural language processing (NLP) domains. However, generating physiological time-series data, a common type in medical AI applications, presents unique challenges due to its inherent complexity and variability. This paper introduces TransConv-DDPM, an enhanced generative AI method for biomechanical and physiological time-series data generation. The model employs a denoising diffusion probabilistic model (DDPM) with U-Net, multi-scale convolution modules, and a transformer layer to capture both global and local temporal dependencies. We evaluated TransConv-DDPM on three diverse datasets, generating both long and short-sequence time-series data. Quantitative comparisons against state-of-the-art methods, TimeGAN and Diffusion-TS, using four performance metrics, demonstrated promising results, particularly on the SmartFallMM and EEG datasets, where it effectively captured the more gradual temporal change patterns between data points. Additionally, a utility test on the SmartFallMM dataset revealed that adding synthetic fall data generated by TransConv-DDPM improved predictive model performance, showing a 13.64% improvement in F1-score and a 14.93% increase in overall accuracy compared to the baseline model trained solely on fall data from the SmartFallMM dataset. These findings highlight the potential of TransConv-DDPM to generate high-quality synthetic data for real-world applications.

---

### LLM-FSM: Scaling Large Language Models for Finite-State Reasoning in RTL Code Generation

Authors: Yuheng Wu, Berk Gokmen, Zhouhua Xie, Peijing Li, Caroline Trippel, Priyanka Raina, Thierry Tambe
Published: 2026-02-03
Categories: cs.AI, cs.AR, cs.CL
arXiv: https://arxiv.org/abs/2602.07032v1

Finite-state reasoning, the ability to understand and implement state-dependent behavior, is central to hardware design. In this paper, we present LLM-FSM, a benchmark that evaluates how well large language models (LLMs) can recover finite-state machine (FSM) behavior from natural-language specifications and translate it into correct register transfer-level (RTL) implementations. Unlike prior specification-to-RTL benchmarks that rely on manually constructed examples, LLM-FSM is built through a fully automated pipeline. LLM-FSM first constructs FSM with configurable state counts and constrained transition structures. It then prompts LLMs to express each FSM in a structured YAML format with an application context, and to further convert that YAML into a natural-language (NL) specification. From the same YAML, our pipeline synthesizes the reference RTL and testbench in a correct-by-construction manner. All 1,000 problems are verified using LLM-based and SAT-solver-based checks, with human review on a subset. Our experiments show that even the strongest LLMs exhibit sharply declining accuracy as FSM complexity increases. We further demonstrate that training-time scaling via supervised fine-tuning (SFT) generalizes effectively to out-of-distribution (OOD) tasks, while increasing test-time compute improves reasoning reliability. Finally, LLM-FSM remains extensible by allowing its FSM complexity to scale with future model capabilities.

---

### Lagged backward-compatible physics-informed neural networks for unsaturated soil consolidation analysis

Authors: Dong Li, Shuai Huang, Yapeng Cao, Yujun Cui, Xiaobin Wei, Hongtao Cao
Published: 2026-02-03
Categories: cs.LG, cs.AI, physics.comp-ph
arXiv: https://arxiv.org/abs/2602.07031v1

This study develops a Lagged Backward-Compatible Physics-Informed Neural Network (LBC-PINN) for simulating and inverting one-dimensional unsaturated soil consolidation under long-term loading. To address the challenges of coupled air and water pressure dissipation across multi-scale time domains, the framework integrates logarithmic time segmentation, lagged compatibility loss enforcement, and segment-wise transfer learning. In forward analysis, the LBC-PINN with recommended segmentation schemes accurately predicts pore air and pore water pressure evolution. Model predictions are validated against finite element method (FEM) results, with mean absolute errors below 1e-2 for time durations up to 1e10 seconds. A simplified segmentation strategy based on the characteristic air-phase dissipation time improves computational efficiency while preserving predictive accuracy. Sensitivity analyses confirm the robustness of the framework across air-to-water permeability ratios ranging from 1e-3 to 1e3.

---

### PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference

Authors: Rui Ning, Wei Zhang, Fan Lai
Published: 2026-02-03
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2602.06072v1

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly heterogeneous sequence lengths for high serving throughput. This mismatch induces severe computation and I/O imbalance, exacerbates stragglers, and underutilizes GPU resources. We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for heterogeneous batched inference. PackInfer orchestrates batched requests into load-balanced execution groups, effectively saturating GPU utilization by packing multiple requests into unified kernel launches. By constructing attention kernels directly over packed query-key regions, PackInfer eliminates redundant computation and balances thread-block execution. It then incorporates I/O-aware grouping that co-locates shared-prefix requests and reorganizes KV caches into group-contiguous layouts, reducing memory fragmentation and redundant data movement as generation evolves. Evaluations on real-world workloads show that PackInfer reduces inference latency by 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.

---

### Causal Discovery from Heteroscedastic Stochastic Dynamical Systems under Imperfect Physical Models

Authors: Jianhong Chen, Naichen Shi, Xubo Yue
Published: 2026-02-03
Categories: cs.LG, cs.AI, stat.ME
arXiv: https://arxiv.org/abs/2602.04907v2

Causal discovery is a data-driven paradigm for analyzing complex systems, while physics-based models, such as ordinary differential equations (ODEs), provide mechanistic structure for real-world dynamical processes. Integrating these paradigms can improve identifiability, stability, and robustness. However, real dynamical systems often exhibit cyclic interactions and nonstationarity, whereas many causal discovery methods rely on acyclicity, stationarity, or equilibrium assumptions. We propose an integrative causal discovery framework for dynamical systems that leverages partial physical knowledge through stochastic differential equations (SDEs). The drift term encodes known ODE dynamics, while the diffusion term captures unknown causal couplings beyond the prescribed physics. We develop a scalable sparsity-inducing maximum quasi-likelihood estimator with a theoretically justified stabilization technique to improve the optimization landscape. Under mild conditions, we establish causal graph recovery guarantees for both stable and unstable SDEs. We also analyze robustness of our causal graph estimate to ODE misspecification and clarify how the introduced stabilization technique balances numerical stability and statistical recoverability. Experiments on linear SDEs and nonlinear benchmarks, including Lotka-Volterra and Lorenz dynamics with acyclic and cyclic structures, show improved graph recovery and robustness over data-driven baselines. We also demonstrate practical utility on real-world epidemic data by reconstructing stochastic SIR dynamics within our causal discovery framework.

---

### LISA: Laplacian In-context Spectral Analysis

Authors: Julio Candanedo
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04906v1

We propose Laplacian In-context Spectral Analysis (LISA), a method for inference-time adaptation of Laplacian-based time-series models using only an observed prefix. LISA combines delay-coordinate embeddings and Laplacian spectral learning to produce diffusion-coordinate state representations, together with a frozen nonlinear decoder for one-step prediction. We introduce lightweight latent-space residual adapters based on either Gaussian-process regression or an attention-like Markov operator over context windows. Across forecasting and autoregressive rollout experiments, LISA improves over the frozen baseline and is often most beneficial under changing dynamics. This work links in-context adaptation to nonparametric spectral methods for dynamical systems.

---

### DCER: Dual-Stage Compression and Energy-Based Reconstruction

Authors: Yiwen Wang, Jiahao Qin
Published: 2026-02-03
Categories: cs.LG, cs.AI, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2602.04904v1

Multimodal fusion faces two robustness challenges: noisy inputs degrade representation quality, and missing modalities cause prediction failures. We propose DCER, a unified framework addressing both challenges through dual-stage compression and energy-based reconstruction. The compression stage operates at two levels: within-modality frequency transforms (wavelet for audio, DCT for video) remove noise while preserving task-relevant patterns, and cross-modality bottleneck tokens force genuine integration rather than modality-specific shortcuts. For missing modalities, energy-based reconstruction recovers representations via gradient descent on a learned energy function, with the final energy providing intrinsic uncertainty quantification (\r{ho} > 0.72 correlation with prediction error). Experiments on CMU-MOSI, CMU-MOSEI, and CH-SIMS demonstrate state-of-the-art performance across all benchmarks, with a U-shaped robustness pattern favoring multimodal fusion at both complete and high-missing conditions. The code will be available on Github.

---

### Mind the Performance Gap: Capability-Behavior Trade-offs in Feature Steering

Authors: Eitan Sprejer, Oscar Agustín Stanchi, María Victoria Carro, Denise Alejandra Mester, Iván Arcuschin
Published: 2026-02-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.04903v1

Feature steering has emerged as a promising approach for controlling LLM behavior through direct manipulation of internal representations, offering advantages over prompt engineering. However, its practical effectiveness in real-world applications remains poorly understood, particularly regarding potential trade-offs with output quality. We show that feature steering methods substantially degrade model performance even when successfully controlling target behaviors, a critical trade-off. Specifically, we evaluate Goodfire's Auto Steer against prompt engineering baselines across 14 steering queries (covering innocuous and safety-relevant behaviors) on 171 Massive Multitask Language Understanding (MMLU) questions using Llama-8B and Llama-70B, measuring accuracy, coherence, and behavioral control. Our findings show that Auto Steer successfully modifies target behaviors (achieving scores of 3.33 vs. 2.98 for prompting on Llama-8B and 3.57 vs. 3.10 on Llama-70B), but causes dramatic performance degradation: accuracy on the MMLU questions drops from 66% to 46% on Llama-8B and 87% to 73% on Llama-70B, with coherence falling from 4.62 to 2.24 and 4.94 to 3.89 respectively. Simple prompting achieves the best overall balance. These findings highlight limitations of current feature steering methods for practical deployment where task performance cannot be sacrificed. More broadly, our work demonstrates that mechanistic control methods face fundamental capability-behavior trade-offs that must be empirically characterized before deployment.

---

### Momentum Attention: The Physics of In-Context Learning and Spectral Forensics for Mechanistic Interpretability

Authors: Kingsuk Maitra
Published: 2026-02-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.04902v2

The Mechanistic Interpretability (MI) program has mapped the Transformer as a precise computational graph. We extend this graph with a conservation law and time-varying AC dynamics, viewing it as a physical circuit. We introduce Momentum Attention, a symplectic augmentation embedding physical priors via the kinematic difference operator $p_t = q_t - q_{t-1}$, implementing the symplectic shear $\hat{q}_t = q_t + γp_t$ on queries and keys. We identify a fundamental Symplectic-Filter Duality: the physical shear is mathematically equivalent to a High-Pass Filter. This duality is our cornerstone contribution -- by injecting kinematic momentum, we sidestep the topological depth constraint ($L \geq 2$) for induction head formation. While standard architectures require two layers for induction from static positions, our extension grants direct access to velocity, enabling Single-Layer Induction and Spectral Forensics via Bode Plots. We formalize an Orthogonality Theorem proving that DC (semantic) and AC (mechanistic) signals segregate into orthogonal frequency bands when Low-Pass RoPE interacts with High-Pass Momentum. Validated through 5,100+ controlled experiments (documented in Supplementary Appendices A--R and 27 Jupyter notebooks), our 125M Momentum model exceeds expectations on induction-heavy tasks while tracking a 350M baseline within $\sim$2.9% validation loss. Dedicated associative recall experiments reveal a scaling law $γ^* = 4.17 \times N^{-0.74}$ establishing momentum-depth fungibility. We offer this framework as a complementary analytical toolkit connecting Generative AI, Hamiltonian Physics, and Signal Processing.

---

### Beyond Independent Genes: Learning Module-Inductive Representations for Single-Cell Gene Perturbation Prediction

Authors: Jiafa Ruan, Ruijie Quan, Liyang Xu, Zongxin Yang, Yi Yang
Published: 2026-02-03
Categories: q-bio.GN, cs.LG
arXiv: https://arxiv.org/abs/2602.04901v2

Predicting transcriptional responses to genetic perturbations is a central problem in functional genomics. In practice, perturbation responses are rarely gene-independent but instead manifest as coordinated, program-level transcriptional changes among functionally related genes. However, most existing methods do not explicitly model such coordination, due to gene-wise modeling paradigms and reliance on static biological priors that cannot capture dynamic program reorganization. To address these limitations, we propose scBIG, a module-inductive perturbation prediction framework that explicitly models coordinated gene programs. scBIG induces coherent gene programs from data via Gene-Relation Clustering, captures inter-program interactions through a Gene-Cluster-Aware Encoder, and preserves modular coordination using structure-aware alignment objectives. These structured representations are then modeled using conditional flow matching to enable flexible and generalizable perturbation prediction. Extensive experiments on multiple single-cell perturbation benchmarks show that scBIG consistently outperforms state-of-the-art methods, particularly on unseen and combinatorial perturbation settings, achieving an average improvement of 6.7% over the strongest baselines. The code is available at https://github.com/ttruan2426-dot/scBIG.

---

### Evaluating Kubernetes Performance for GenAI Inference: From Automatic Speech Recognition to LLM Summarization

Authors: Sai Sindhur Malleni, Raúl Sevilla, Aleksei Vasilevskii, José Castillo Lema, André Bauer
Published: 2026-02-03
Categories: cs.ET, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2602.04900v3

As Generative AI (GenAI), particularly inference, rapidly emerges as a dominant workload category, the Kubernetes ecosystem is proactively evolving to natively support its unique demands. This industry paper demonstrates how emerging Kubernetes-native projects can be combined to deliver the benefits of container orchestration, such as scalability and resource efficiency, to complex AI workflows. We implement and evaluate an illustrative, multi-stage use case consisting of automatic speech recognition and summarization. First, we address batch inference by using Kueue to manage jobs that transcribe audio files with Whisper models and Dynamic Accelerator Slicer (DAS) to increase parallel job execution. Second, we address a discrete online inference scenario by feeding the transcripts to a Large Language Model for summarization hosted using llm-d, a novel solution utilizing the recent developments around the Kubernetes Gateway API Inference Extension (GAIE) for optimized routing of inference requests. Our findings illustrate that these complementary components (Kueue, DAS, and GAIE) form a cohesive, high-performance platform, proving Kubernetes' capability to serve as a unified foundation for demanding GenAI workloads: Kueue reduced total makespan by up to 15%; DAS shortened mean job completion time by 36\%; and GAIE working in conjunction with llm-d improved tail Time to First Token latency by up to 90% even under high loads.

---

### Phantom Transfer: Data Poisoning can Survive Data-Level Defences

Authors: Andrew Draganov, Tolga H. Dur, Anandmayi Bhongade, Mary Phuong
Published: 2026-02-03
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.04899v2

We present a data poisoning attack -- Phantom Transfer -- with the property that, even if you know precisely how the poison was placed into an otherwise benign dataset, you cannot filter it out. We achieve this by modifying subliminal learning to work in real-world contexts and demonstrate that the attack works regardless of which model produced the data, which model is trained on the data or what the attack target is. Furthermore, the attack survives 11 tested data-level defences, including one where every sample is paraphrased by another model. We characterise when this attack works best and show that it can be used to plant password-triggered behaviours into models while still beating defences. In short, we provide an existence proof that maximum-affordance defences can fail to stop sophisticated data poisoning attacks. We suggest that future defences should be supplemented with white-box methods and post-training model audits.

---