# Research Papers — 2026-02 · bundle page 118 of 210

> Full-text markdown of papers #5851–5900 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/118
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/117.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/119.md)

### The Landscape of Prompt Injection Threats in LLM Agents: From Taxonomy to Analysis

Authors: Peiran Wang, Xinfeng Li, Chong Xiang, Jinghuai Zhang, Ying Li, Lixia Zhang, Xiaofeng Wang, Yuan Tian
Published: 2026-02-11
Categories: cs.CR, cs.CL
arXiv: https://arxiv.org/abs/2602.10453v1

The evolution of Large Language Models (LLMs) has resulted in a paradigm shift towards autonomous agents, necessitating robust security against Prompt Injection (PI) vulnerabilities where untrusted inputs hijack agent behaviors. This SoK presents a comprehensive overview of the PI landscape, covering attacks, defenses, and their evaluation practices. Through a systematic literature review and quantitative analysis, we establish taxonomies that categorize PI attacks by payload generation strategies (heuristic vs. optimization) and defenses by intervention stages (text, model, and execution levels). Our analysis reveals a key limitation shared by many existing defenses and benchmarks: they largely overlook context-dependent tasks, in which agents are authorized to rely on runtime environmental observations to determine actions. To address this gap, we introduce AgentPI, a new benchmark designed to systematically evaluate agent behavior under context-dependent interaction settings. Using AgentPI, we empirically evaluate representative defenses and show that no single approach can simultaneously achieve high trustworthiness, high utility, and low latency. Moreover, we show that many defenses appear effective under existing benchmarks by suppressing contextual inputs, yet fail to generalize to realistic agent settings where context-dependent reasoning is essential. This SoK distills key takeaways and open research problems, offering structured guidance for future research and practical deployment of secure LLM agents.

---

### Distributed Online Convex Optimization with Nonseparable Costs and Constraints

Authors: Zhaoye Pan, Haozhe Lei, Fan Zuo, Zilin Bian, Tao Li
Published: 2026-02-11
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2602.10452v2

This paper studies distributed online convex optimization with time-varying coupled constraints, motivated by distributed online control in network systems. Most prior work assumes a separability condition: the global objective and coupled constraint functions are sums of local costs and individual constraints. In contrast, we study a group of agents, networked via a communication graph, that collectively select actions to minimize a sequence of nonseparable global cost functions and to satisfy nonseparable long-term constraints based on full-information feedback and intra-agent communication. We propose a distributed online primal-dual belief consensus algorithm, where each agent maintains and updates a local belief of the global collective decisions, which are repeatedly exchanged with neighboring agents. Unlike the previous consensus primal-dual algorithms under separability that ask agents to only communicate their local decisions, our belief-sharing protocol eliminates coupling between the primal consensus disagreement and the dual constraint violation, yielding sublinear regret and cumulative constraint violation (CCV) bounds, both in $O({T}^{1/2})$, where $T$ denotes the time horizon. Such a result breaks the long-standing $O(T^{3/4})$ barrier for CCV and matches the lower bound of online constrained convex optimization, indicating the online learning efficiency at the cost of communication overhead.

---

### A Multimodal Conditional Mixture Model with Distribution-Level Physics Priors

Authors: Jinkyo Han, Bahador Bahmani
Published: 2026-02-11
Categories: cs.LG, physics.comp-ph
arXiv: https://arxiv.org/abs/2602.10451v1

Many scientific and engineering systems exhibit intrinsically multimodal behavior arising from latent regime switching and non-unique physical mechanisms. In such settings, learning the full conditional distribution of admissible outcomes in a physically consistent and interpretable manner remains a challenge. While recent advances in machine learning have enabled powerful multimodal generative modeling, their integration with physics-constrained scientific modeling remains nontrivial, particularly when physical structure must be preserved or data are limited. This work develops a physics-informed multimodal conditional modeling framework based on mixture density representations. Mixture density networks (MDNs) provide an explicit and interpretable parameterization of multimodal conditional distributions. Physical knowledge is embedded through component-specific regularization terms that penalize violations of governing equations or physical laws. This formulation naturally accommodates non-uniqueness and stochasticity while remaining computationally efficient and amenable to conditioning on contextual inputs. The proposed framework is evaluated across a range of scientific problems in which multimodality arises from intrinsic physical mechanisms rather than observational noise, including bifurcation phenomena in nonlinear dynamical systems, stochastic partial differential equations, and atomistic-scale shock dynamics. In addition, the proposed method is compared with a conditional flow matching (CFM) model, a representative state-of-the-art generative modeling approach, demonstrating that MDNs can achieve competitive performance while offering a simpler and more interpretable formulation.

---

### Constructing Industrial-Scale Optimization Modeling Benchmark

Authors: Zhong Li, Hongliang Lu, Tao Wei, Yuxuan Chen, Wenyu Liu, Yuan Lan, Fan Zhang, Zaiwen Wen
Published: 2026-02-11
Categories: cs.LG, cs.AI, math.OC
arXiv: https://arxiv.org/abs/2602.10450v2

Optimization modeling underpins decision-making in logistics, manufacturing, energy, and finance, yet translating natural-language requirements into correct optimization formulations and solver-executable code remains labor-intensive. Although large language models (LLMs) have been explored for this task, evaluation is still dominated by toy-sized or synthetic benchmarks, masking the difficulty of industrial problems with $10^{3}$--$10^{6}$ (or more) variables and constraints. A key bottleneck is the lack of benchmarks that align natural-language specifications with reference formulations/solver code grounded in real optimization models. To fill in this gap, we introduce MIPLIB-NL, built via a structure-aware reverse construction methodology from real mixed-integer linear programs in MIPLIB~2017. Our pipeline (i) recovers compact, reusable model structure from flat solver formulations, (ii) reverse-generates natural-language specifications explicitly tied to this recovered structure under a unified model--data separation format, and (iii) performs iterative semantic validation through expert review and human--LLM interaction with independent reconstruction checks. This yields 223 one-to-one reconstructions that preserve the mathematical content of the original instances while enabling realistic natural-language-to-optimization evaluation. Experiments show substantial performance degradation on MIPLIB-NL for systems that perform strongly on existing benchmarks, exposing failure modes invisible at toy scale.

---

### A Unified Theory of Random Projection for Influence Functions

Authors: Pingbang Hu, Yuzheng Hu, Jiaqi W. Ma, Han Zhao
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10449v2

Influence functions and related data attribution scores take the form of $g^{\top}F^{-1}g^{\prime}$, where $F\succeq 0$ is a curvature operator. In modern overparametrized models, forming or inverting $F\in\mathbb{R}^{d\times d}$ is prohibitive, motivating scalable influence computation via random projection with a sketch $P \in \mathbb{R}^{m\times d}$. This practice is commonly justified via the Johnson--Lindenstrauss (JL) lemma, which ensures approximate preservation of Euclidean geometry for a fixed dataset. However, JL does not address how sketching behaves under inversion. Furthermore, there is no existing theory that explains how sketching interacts with other widely-used techniques, such as ridge regularization and structured curvature approximations. We develop a unified theory characterizing when projection provably preserves influence functions. When $g,g^{\prime}\in\text{range}(F)$, we show that: 1) Unregularized projection: exact preservation holds iff $P$ is injective on $\text{range}(F)$, which necessitates $m\geq \text{rank}(F)$; 2) Regularized projection: ridge regularization fundamentally alters the sketching barrier, with approximation guarantees governed by the effective dimension of $F$ at the regularization scale; 3) Factorized influence: for Kronecker-factored curvatures $F=A\otimes E$, the guarantees continue to hold for decoupled sketches $P=P_A\otimes P_E$, even though such sketches exhibit row correlations that violate i.i.d. assumptions. Beyond this range-restricted setting, we analyze out-of-range test gradients and quantify a leakage term that arises when test gradients have components in $\ker(F)$. This yields guarantees for influence queries on general test points. Overall, this work develops a novel theory that characterizes when projection provably preserves influence and provides principled guidance for choosing the sketch size in practice.

---

### End-to-End Semantic ID Generation for Generative Advertisement Recommendation

Authors: Jie Jiang, Xinxun Zhang, Enming Zhang, Yuling Xiong, Jun Zhang, Jingwen Wang, Huan Yu, Yuxiang Wang, Hao Wang, Xiao Yan, Jiawei Jiang
Published: 2026-02-11
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2602.10445v3

Generative Recommendation (GR) has excelled by framing recommendation as next-token prediction. This paradigm relies on Semantic IDs (SIDs) to tokenize large-scale items into discrete sequences. Existing GR approaches predominantly generate SIDs via Residual Quantization (RQ), where items are encoded into embeddings and then quantized to discrete SIDs. However, this paradigm suffers from inherent limitations: 1) Objective misalignment and semantic degradation stemming from the two-stage compression; 2) Error accumulation inherent in the structure of RQ. To address these limitations, we propose UniSID, a Unified SID generation framework for generative advertisement recommendation. Specifically, we jointly optimize embeddings and SIDs in an end-to-end manner from raw advertising data, enabling semantic information to flow directly into the SID space and thus addressing the inherent limitations of the two-stage cascading compression paradigm. To capture fine-grained semantics, a multi-granularity contrastive learning strategy is introduced to align distinct items across SID levels. Finally, a summary-based ad reconstruction mechanism is proposed to encourage SIDs to capture high-level semantic information that is not explicitly present in advertising contexts. Experiments demonstrate that UniSID consistently outperforms state-of-the-art SID generation methods, yielding up to a 4.62% improvement in Hit Rate metrics across downstream advertising scenarios compared to the strongest baseline.

---

### Chamfer-Linkage for Hierarchical Agglomerative Clustering

Authors: Kishen N Gowda, Willem Fletcher, MohammadHossein Bateni, Laxman Dhulipala, D Ellis Hershkowitz, Rajesh Jayaram, Jakub Łącki
Published: 2026-02-11
Categories: cs.LG, cs.DC, cs.DS, cs.IR
arXiv: https://arxiv.org/abs/2602.10444v1

Hierarchical Agglomerative Clustering (HAC) is a widely-used clustering method based on repeatedly merging the closest pair of clusters, where inter-cluster distances are determined by a linkage function. Unlike many clustering methods, HAC does not optimize a single explicit global objective; clustering quality is therefore primarily evaluated empirically, and the choice of linkage function plays a crucial role in practice. However, popular classical linkages, such as single-linkage, average-linkage and Ward's method show high variability across real-world datasets and do not consistently produce high-quality clusterings in practice. In this paper, we propose \emph{Chamfer-linkage}, a novel linkage function that measures the distance between clusters using the Chamfer distance, a popular notion of distance between point-clouds in machine learning and computer vision. We argue that Chamfer-linkage satisfies desirable concept representation properties that other popular measures struggle to satisfy. Theoretically, we show that Chamfer-linkage HAC can be implemented in $O(n^2)$ time, matching the efficiency of classical linkage functions. Experimentally, we find that Chamfer-linkage consistently yields higher-quality clusterings than classical linkages such as average-linkage and Ward's method across a diverse collection of datasets. Our results establish Chamfer-linkage as a practical drop-in replacement for classical linkage functions, broadening the toolkit for hierarchical clustering in both theory and practice.

---

### LakeMLB: Data Lake Machine Learning Benchmark

Authors: Feiyu Pan, Tianbin Zhang, Aoqian Zhang, Yu Sun, Zheng Wang, Lixing Chen, Li Pan, Jianhua Li
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10441v2

Data lakes have become a fundamental platform for large-scale machine learning by enabling flexible management of heterogeneous data. Despite their growing importance, standardized benchmarks for evaluating machine learning performance in data lake environments remain scarce. To address this gap, we present LakeMLB (Data Lake Machine Learning Benchmark), the first benchmark designed for multi-table machine learning in data lakes. LakeMLB focuses on two representative scenarios, Union and Join, and provides six real-world datasets spanning diverse domains. It supports three representative multi-table learning paradigms: pre-training, data augmentation, and feature augmentation, together with standardized data splits and evaluation protocols. We conduct extensive experiments with state-of-the-art tabular learning methods and provide insights into their performance across different data lake scenarios. We release both datasets and code to facilitate rigorous research on machine learning in data lake ecosystems; the benchmark is available at https://github.com/zhengwang100/LakeMLB.

---

### AudioRouter: Data Efficient Audio Understanding via RL based Dual Reasoning

Authors: Liyang Chen, Hongkai Chen, Yujun Cai, Sifan Li, Qingwen Ye, Yiwei Wang
Published: 2026-02-11
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2602.10439v1

Large Audio Language Models (LALMs) have demonstrated strong capabilities in audio understanding and reasoning. However, their performance on fine grained auditory perception remains unreliable, and existing approaches largely rely on data intensive training to internalize perceptual abilities. We propose AudioRouter, a reinforcement learning framework that enables LALMs to improve audio understanding by learning when and how to use external audio tools. Rather than tightly coupling tool usage with audio reasoning, AudioRouter formulates tool use as an explicit decision making problem and optimizes a lightweight routing policy while keeping the underlying reasoning model frozen. Experimental results show that AudioRouter achieves substantial improvements on standard audio understanding benchmarks while requiring up to 600x less training data to learn tool usage compared with conventional training paradigms. These findings suggest that learning effective tool usage offers a data efficient and scalable alternative to internalizing perceptual abilities in LALMs.

---

### Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features

Authors: Seonglae Cho, Zekun Wu, Adriano Koshiyama
Published: 2026-02-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.10437v3

Sparse autoencoders (SAEs) decompose language model activations into interpretable features, but existing methods reveal only which features activate, not which change model outputs when amplified. We introduce Control Reinforcement Learning (CRL), which trains a policy to select SAE features for steering at each token, producing interpretable intervention logs: the learned policy identifies features that change model outputs when amplified. Adaptive Feature Masking encourages diverse feature discovery while preserving singlefeature interpretability. The framework yields new analysis capabilities: branch point tracking locates tokens where feature choice determines output correctness; critic trajectory analysis separates policy limitations from value estimation errors; layer-wise comparison reveals syntactic features in early layers and semantic features in later layers. On Gemma 2 2B across MMLU, BBQ, GSM8K, HarmBench, and XSTest, CRL achieves improvements while providing per-token intervention logs. These results establish learned feature steering as a mechanistic interpretability tool that complements static feature analysis with dynamic intervention probes

---

### A Dual-Stream Physics-Augmented Unsupervised Architecture for Runtime Embedded Vehicle Health Monitoring

Authors: Enzo Nicolas Spotorno, Antonio Augusto Medeiros Frohlich
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10432v1

Runtime quantification of vehicle operational intensity is essential for predictive maintenance and condition monitoring in commercial and heavy-duty fleets. Traditional metrics like mileage fail to capture mechanical burden, while unsupervised deep learning models detect statistical anomalies, typically transient surface shocks, but often conflate statistical stability with mechanical rest. We identify this as a critical blind spot: high-load steady states, such as hill climbing with heavy payloads, appear statistically normal yet impose significant drivetrain fatigue. To resolve this, we propose a Dual-Stream Architecture that fuses unsupervised learning for surface anomaly detection with macroscopic physics proxies for cumulative load estimation. This approach leverages low-frequency sensor data to generate a multi-dimensional health vector, distinguishing between dynamic hazards and sustained mechanical effort. Validated on a RISC-V embedded platform, the architecture demonstrates low computational overhead, enabling comprehensive, edge-based health monitoring on resource-constrained ECUs without the latency or bandwidth costs of cloud-based monitoring.

---

### QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs

Authors: Kanghyun Noh, Jinheon Choi, Yulhwa Kim
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10431v4

Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address these issues: token-adaptive layer execution, which reduces floating-point operations (FLOPs) by selectively bypassing layers, and quantization, which lowers memory footprint by reducing weight precision. However, naively integrating these techniques leads to additional accuracy degradation due to reduced redundancy in token-adaptive models. We propose QTALE (Quantization-Robust Token-Adaptive Layer Execution for LLMs), a novel framework that enables seamless integration of token-adaptive execution with quantization while preserving accuracy. Conventional token-adaptive methods reduce redundancy in two ways: (1) by limiting the diversity of training paths explored during fine-tuning, and (2) by lowering the number of parameters actively involved in inference. To overcome these limitations, QTALE introduces two key components: (1) a training strategy that ensures diverse execution paths are actively explored during fine-tuning, and (2) a post-training mechanism that allows flexible adjustment of the execution ratio at inference to reintroduce redundancy when needed. Experimental results show that QTALE enables seamless integration of token-adaptive layer execution with quantization, while keeping the accuracy gap to quantization-only models below 0.5% on CommonsenseQA benchmarks. By combining tokenadaptive execution for FLOPs reduction and quantization for memory savings, QTALE provides an effective solution for efficient LLM deployment.

---

### Breaking the Curse of Repulsion: Remoteness-Aware Control of Negative Off-Policy Updates

Authors: Yusen Huo, Changping Wang, Yangru Huang, Jun Zhang, Jie Jiang
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10430v2

Off-policy policy optimization reuses historical behavior, including negative-advantage samples that suppress known failures. We show that repeated reuse can turn this useful signal into excessive repulsion: as the learner moves away from a historical negative action, subsequent updates make that action increasingly remote without necessarily reducing its update strength. Our aggregate theory characterizes the resulting transition from a stable displacement beyond the positive-only target to persistent drift and the loss of finite stable equilibria; controlled strength sweeps show that an intermediate displacement can improve held-out reward. The relevant learner-relative coordinate is squared standardized distance for Gaussian policies and surprisal for categorical policies. We introduce Dynamic Remoteness-Aware Policy Optimization (DRPO), which leaves the negative update unchanged in the near field and exponentially attenuates its remote tail. DRPO restores eventual inward Gaussian drift for every fixed finite negative-to-positive mass ratio, yields an explicit ultimate-bound radius, and changes categorical support suppression from exponential to polynomial probability decay. External diagnostics and controlled interventions isolate remoteness-dependent policy geometry as a source of negative-update amplification and show that selective tapering can remove its far-field effect without discarding useful local feedback.

---

### AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles

Authors: Wenkai Fan, Shurui Zhang, Xiaolong Wang, Haowei Yang, Tsz Wai Chan, Xingyan Chen, Junquan Bi, Zirui Zhou, Jia Liu, Kani Chen
Published: 2026-02-11
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.10429v2

AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent architecture, aiming to sustain long-horizon autonomy while remaining executable under a rapidly changing environment. To mitigate the tension between goal stability and reactive correctness, keeping long-horizon objectives on course while each action remains valid in a fast-changing shared world, we introduce (i) a hierarchical branch-thinking planner that decomposes life goals into parallel objective branches and uses simulation-guided validation plus tiered re-planning to ensure feasibility; (ii) an adaptive agent profile with dual-process memory that separates short-term execution traces from long-term semantic consolidation, enabling persistent yet evolving identity; and (iii) a human-in-the-loop steering interface that injects long-horizon objectives and short commands at appropriate abstraction levels, with effects propagated through memory instead of brittle prompt overrides. The environment integrates physiological survival costs, non-substitutable multi-tier production, an AMM-based price mechanism, and a gated education-occupation system. In a large-scale public deployment with tens of thousands of agents, high-frequency transactions from the platform's mature phase reveal stable markets that reproduce key stylized facts of real economies and structured wealth stratification driven by education and access constraints. At the agent level, portraits evolve coherently over long horizons, and human steering is associated with measurably larger short-horizon profile updates. Controlled ablation experiments complement the deployment evidence, showing that our agent architecture is robust in multi-objective, long-horizon settings.

---

### HII-DPO: Eliminate Hallucination via Accurate Hallucination-Inducing Counterfactual Images

Authors: Yilin Yang, Zhenghui Guo, Yuke Wang, Omprakash Gnawali, Sheng Di, Chengming Zhang
Published: 2026-02-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.10425v1

Large Vision-Language Models (VLMs) have achieved remarkable success across diverse multimodal tasks but remain vulnerable to hallucinations rooted in inherent language bias. Despite recent progress, existing hallucination mitigation methods often overlook the underlying hallucination patterns driven by language bias. In this work, we design a novel pipeline to accurately synthesize Hallucination-Inducing Images (HIIs). Using synthesized HIIs, we reveal a consistent scene-conditioned hallucination pattern: models tend to mention objects that are highly typical of the scene even when visual evidence is removed. To quantify the susceptibility of VLMs to this hallucination pattern, we establish the Masked-Object-Hallucination (MOH) benchmark to rigorously evaluate existing state-of-the-art alignment frameworks. Finally, we leverage HIIs to construct high-quality preference datasets for fine-grained alignment. Experimental results demonstrate that our approach effectively mitigates hallucinations while preserving general model capabilities. Specifically, our method achieves up to a 38% improvement over the current state-of-the-art on standard hallucination benchmarks.

---

### Prediction--Loss Alignment for Sampler--Robust Flow Matching Training

Authors: Jiadong Hong, Lei Liu, Xinyu Bian, Wenjie Wang, Zhaoyang Zhang
Published: 2026-02-11
Categories: cs.LG, cs.IT, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2602.10420v4

Recent work has popularized a practical recipe in diffusion and flow matching: predict the clean signal $x$, convert it to a velocity, and train through a velocity-space loss. The conversion contains a singular endpoint amplification and therefore appears prone to unstable optimization, yet recent systems obtain strong empirical results with this recipe. We investigate this tension through the integrability of the pre-optimizer stochastic-gradient second moment. Under stated initialization conditions, the moment diverges under Uniform sampling; boundary-suppressing sampling can restore integrability under an additional upper-growth condition. We then show that prediction--loss alignment eliminates this conversion-induced source of non-integrability. Under a uniform moment bound, alignment yields a finite second moment for every timestep density, including Uniform sampling. Controlled experiments across continuous and binary settings reproduce the predicted sampler-dependent instability and show that aligned objectives remain trainable across the tested samplers. These results reconcile pointwise amplification with sampler-dependent empirical success and support alignment as a principled route to more robust flow-matching training.

---

### Binary Flow Matching: Prediction-Loss Space Alignment for Robust Learning

Authors: Jiadong Hong, Lei Liu, Xinyu Bian, Wenjie Wang, Zhaoyang Zhang
Published: 2026-02-11
Categories: cs.LG, cs.IT, eess.IV, eess.SP
arXiv: https://arxiv.org/abs/2602.10420v3

Flow matching has emerged as a powerful framework for generative modeling, with recent empirical successes highlighting the effectiveness of signal-space prediction ($x$-prediction). In this work, we investigate the transfer of this paradigm to binary manifolds, a fundamental setting for generative modeling of discrete data. While $x$-prediction remains effective, we identify a latent structural mismatch that arises when it is coupled with velocity-based objectives ($v$-loss), leading to a time-dependent singular weighting that amplifies gradient sensitivity to approximation errors. Motivated by this observation, we formalize prediction-loss alignment as a necessary condition for flow matching training. We prove that re-aligning the objective to the signal space ($x$-loss) eliminates the singular weighting, yielding uniformly bounded gradients and enabling robust training under uniform timestep sampling without reliance on heuristic schedules. Finally, with alignment secured, we examine design choices specific to binary data, revealing a topology-dependent distinction between probabilistic objectives (e.g., cross-entropy) and geometric losses (e.g., mean squared error). Together, these results provide theoretical foundations and practical guidelines for robust flow matching on binary -- and related discrete -- domains, positioning signal-space alignment as a key principle for robust diffusion learning.

---

### Equivariant Evidential Deep Learning for Interatomic Potentials

Authors: Zhongyao Wang, Taoyong Cui, Jiawen Zou, Shufei Zhang, Bo Yan, Wanli Ouyang, Weimin Tan, Mao Su
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10419v2

Uncertainty quantification (UQ) is critical for assessing the reliability of machine learning interatomic potentials (MLIPs) in molecular dynamics (MD) simulations, identifying extrapolation regimes and enabling uncertainty-aware workflows such as active learning for training dataset construction. Existing UQ approaches for MLIPs are often limited by high computational cost or suboptimal performance. Evidential deep learning (EDL) provides a theoretically grounded single-model alternative that determines both aleatoric and epistemic uncertainty in a single forward pass. However, extending evidential formulations from scalar targets to vector-valued quantities such as atomic forces introduces substantial challenges, particularly in maintaining statistical self-consistency under rotational transformations. To address this, we propose \textit{Equivariant Evidential Deep Learning for Interatomic Potentials} ($\text{e}^2$IP), a backbone-agnostic framework that models atomic forces and their uncertainty jointly by representing uncertainty as a full $3\times3$ symmetric positive definite covariance tensor that transforms equivariantly under rotations. Experiments on diverse molecular benchmarks show that $\text{e}^2$IP provides a stronger accuracy-efficiency-reliability balance than the non-equivariant evidential baseline and the widely used ensemble method. It also achieves better data efficiency through the fully equivariant architecture while retaining single-model inference efficiency.

---

### AI-rithmetic

Authors: Alex Bie, Travis Dick, Alex Kulesza, Prabhakar Raghavan, Vinod Raman, Sergei Vassilvitskii
Published: 2026-02-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.10416v1

Modern AI systems have been successfully deployed to win medals at international math competitions, assist with research workflows, and prove novel technical lemmas. However, despite their progress at advanced levels of mathematics, they remain stubbornly bad at basic arithmetic, consistently failing on the simple task of adding two numbers. We present a systematic investigation of this phenomenon. We demonstrate empirically that all frontier models suffer significantly degraded accuracy for integer addition as the number of digits increases. Furthermore, we show that most errors made by these models are highly interpretable and can be attributed to either operand misalignment or a failure to correctly carry; these two error classes explain 87.9%, 62.9%, and 92.4% of Claude Opus 4.1, GPT-5, and Gemini 2.5 Pro errors, respectively. Finally, we show that misalignment errors are frequently related to tokenization, and that carrying errors appear largely as independent random failures.

---

### EVOKE: Emotion Vocabulary Of Korean and English

Authors: Yoonwon Jung, Hagyeong Shin, Benjamin K. Bergen
Published: 2026-02-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10414v2

This paper introduces EVOKE (Emotion Vocabulary of Korean and English), a Korean-English parallel dataset of emotion words. The dataset offers comprehensive coverage of emotion words in each language, in addition to many-to-many translations between words in the two languages and identification of language-specific emotion words. The dataset contains 1,426 Korean words and 1,397 English words, and we systematically annotate 819 Korean and 924 English adjectives and verbs. We also annotate multiple meanings of each word and their relationships, identifying polysemous emotion words and emotion-related metaphors. The dataset is, to our knowledge, the most systematic and theory-agnostic dataset of emotion words in both Korean and English to date. It can serve as a practical tool for emotion science, psycholinguistics, computational linguistics, and natural language processing, allowing researchers to adopt different views on the resource reflecting their needs and theoretical perspectives. The dataset is publicly available at https://github.com/yoonwonj/EVOKE.

---

### LightGTS-Cov: Covariate-Enhanced Time Series Forecasting

Authors: Yong Shang, Zhipeng Yao, Ning Jin, Xiangfei Qiu, Hui Zhang, Bin Yang
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10412v1

Time series foundation models are typically pre-trained on large, multi-source datasets; however, they often ignore exogenous covariates or incorporate them via simple concatenation with the target series, which limits their effectiveness in covariate-rich applications such as electricity price forecasting and renewable energy forecasting. We introduce LightGTS-Cov, a covariate-enhanced extension of LightGTS that preserves its lightweight, period-aware backbone while explicitly incorporating both past and future-known covariates. Built on a $\sim$1M-parameter LightGTS backbone, LightGTS-Cov adds only a $\sim$0.1M-parameter MLP plug-in that integrates time-aligned covariates into the target forecasts by residually refining the outputs of the decoding process. Across covariate-aware benchmarks on electricity price and energy generation datasets, LightGTS-Cov consistently outperforms LightGTS and achieves superior performance over other covariate-aware baselines under both settings, regardless of whether future-known covariates are provided. We further demonstrate its practical value in two real-world energy case applications: long-term photovoltaic power forecasting with future weather forecasts and day-ahead electricity price forecasting with weather and dispatch-plan covariates. Across both applications, LightGTS-Cov achieves strong forecasting accuracy and stable operational performance after deployment, validating its effectiveness in real-world industrial settings.

---

### LUCID: Attention with Preconditioned Representations

Authors: Sai Surya Duvvuri, Nirmal Patel, Nilesh Gupta, Inderjit S. Dhillon
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10410v1

Softmax-based dot-product attention is a cornerstone of Transformer architectures, enabling remarkable capabilities such as in-context learning. However, as context lengths increase, a fundamental limitation of the softmax function emerges: it tends to diffuse probability mass to irrelevant tokens degrading performance in long-sequence scenarios. Furthermore, attempts to sharpen focus by lowering softmax temperature hinder learnability due to vanishing gradients. We introduce LUCID Attention, an architectural modification that applies a preconditioner to the attention probabilities. This preconditioner, derived from exponentiated key-key similarities, minimizes overlap between the keys in a Reproducing Kernel Hilbert Space, thus allowing the query to focus on important keys among large number of keys accurately with same computational complexity as standard attention. Additionally, LUCID's preconditioning-based approach to retrieval bypasses the need for low temperature and the learnability problems associated with it. We validate our approach by training ~1 billion parameter language models evaluated on up to 128K tokens. Our results demonstrate significant gains on long-context retrieval tasks, specifically retrieval tasks from BABILong, RULER, SCROLLS and LongBench. For instance, LUCID achieves up to 18% improvement in BABILong and 14% improvement in RULER multi-needle performance compared to standard attention.

---

### Gated Normalization Removal and Scale Anchoring in Pre-Norm Transformers

Authors: Andrei Kanavalau, Carmen Amo Alonso, Sanjay Lall
Published: 2026-02-11
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.10408v2

Normalization layers are standard in transformers, but it is not clear whether their sample-dependent computations are necessary throughout both training and inference. This work develops a gated normalization-removal approach for pre-norm transformers. The approach is implemented using TaperNorm, which starts from standard RMSNorm/LayerNorm and gradually tapers to learned sample-independent linear or affine maps. Once the gate reaches zero, per-token statistics are no longer computed in the tapered layers and the resulting maps can be folded into adjacent linear projections. The results indicate that internal normalization can be tapered in the tested pre-training and fine-tuning settings with small validation-loss increases. Our approach helps reveal a distinct role for final normalization, namely that it anchors the scale of the pre-logit representation. With this anchor present, radial changes in the last hidden state do not directly reduce the loss; when it is removed, reducing cross-entropy can be achieved by increasing logit magnitudes. A fixed-target scale loss provides an explicit alternative anchor and enables fully norm-free ablations in the tested regimes. Finally, in a KV-cached autoregressive decoding benchmark, tapering internal norms gives up to $1.14\times$ higher throughput with explicit scaling operations and up to $1.18\times$ after folding.

---

### Towards Affordable, Non-Invasive Real-Time Hypoglycemia Detection Using Wearable Sensor Signals

Authors: Lawrence Obiuwevwi, Krzysztof J. Rechowicz, Vikas Ashok, Sampath Jayarathna
Published: 2026-02-11
Categories: cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.10407v1

Accurately detecting hypoglycemia without invasive glucose sensors remains a critical challenge in diabetes management, particularly in regions where continuous glucose monitoring (CGM) is prohibitively expensive or clinically inaccessible. This extended study introduces a comprehensive, multimodal physiological framework for non-invasive hypoglycemia detection using wearable sensor signals. Unlike prior work limited to single-signal analysis, this chapter evaluates three physiological modalities, galvanic skin response (GSR), heart rate (HR), and their combined fusion, using the OhioT1DM 2018 dataset. We develop an end-to-end pipeline that integrates advanced preprocessing, temporal windowing, handcrafted and sequence-based feature extraction, early and late fusion strategies, and a broad spectrum of machine learning and deep temporal models, including CNNs, LSTMs, GRUs, and TCNs. Our results demonstrate that physiological signals exhibit distinct autonomic patterns preceding hypoglycemia and that combining GSR with HR consistently enhances detection sensitivity and stability compared to single-signal models. Multimodal deep learning architectures achieve the most reliable performance, particularly in recall, the most clinically urgent metric. Ablation studies further highlight the complementary contributions of each modality, strengthening the case for affordable, sensor-based glycemic monitoring. The findings show that real-time hypoglycemia detection is achievable using only inexpensive, non-invasive wearable sensors, offering a pathway toward accessible glucose monitoring in underserved communities and low-resource healthcare environments.

---

### Modular Multi-Task Learning for Chemical Reaction Prediction

Authors: Jiayun Pang, Ahmed M. Zaitoun, Xacobe Couso Cambeiro, Ivan Vulić
Published: 2026-02-11
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.10404v1

Adapting large language models (LLMs) trained on broad organic chemistry to smaller, domain-specific reaction datasets is a key challenge in chemical and pharmaceutical R&D. Effective specialisation requires learning new reaction knowledge while preserving general chemical understanding across related tasks. Here, we evaluate Low-Rank Adaptation (LoRA) as a parameter-efficient alternative to full fine-tuning for organic reaction prediction on limited, complex datasets. Using USPTO reaction classes and challenging C-H functionalisation reactions, we benchmark forward reaction prediction, retrosynthesis and reagent prediction. LoRA achieves accuracy comparable to full fine-tuning while effectively mitigating catastrophic forgetting and better preserving multi-task performance. Both fine-tuning approaches generalise beyond training distributions, producing plausible alternative solvent predictions. Notably, C-H functionalisation fine-tuning reveals that LoRA and full fine-tuning encode subtly different reactivity patterns, suggesting more effective reaction-specific adaptation with LoRA. As LLMs continue to scale, our results highlight the practicality of modular, parameter-efficient fine-tuning strategies for their flexible deployment for chemistry applications.

---

### Experimental Demonstration of Online Learning-Based Concept Drift Adaptation for Failure Detection in Optical Networks

Authors: Yousuf Moiz Ali, Jaroslaw E. Prilepsky, João Pedro, Antonio Napoli, Sasipim Srivallapanondh, Sergei K. Turitsyn, Pedro Freire
Published: 2026-02-11
Categories: cs.LG, eess.SP, physics.optics
arXiv: https://arxiv.org/abs/2602.10401v1

We present a novel online learning-based approach for concept drift adaptation in optical network failure detection, achieving up to a 70% improvement in performance over conventional static models while maintaining low latency.

---

### When are We Worried? Temporal Trends of Anxiety and What They Reveal about Us

Authors: Saif M. Mohammad
Published: 2026-02-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10400v1

In this short paper, we make use of a recently created lexicon of word-anxiety associations to analyze large amounts of US and Canadian social media data (tweets) to explore *when* we are anxious and what insights that reveals about us. We show that our levels of anxiety on social media exhibit systematic patterns of rise and fall during the day -- highest at 8am (in-line with when we have high cortisol levels in the body) and lowest around noon. Anxiety is lowest on weekends and highest mid-week. We also examine anxiety in past, present, and future tense sentences to show that anxiety is highest in past tense and lowest in future tense. Finally, we examine the use of anxiety and calmness words in posts that contain pronouns to show: more anxiety in 3rd person pronouns (he, they) posts than 1st and 2nd person pronouns and higher anxiety in posts with subject pronouns (I, he, she, they) than object pronouns (me, him, her, them). Overall, these trends provide valuable insights on not just when we are anxious, but also how different types of focus (future, past, self, outward, etc.) are related to anxiety.

---

### Tensor Methods: A Unified and Interpretable Approach for Material Design

Authors: Shaan Pakala, Aldair E. Gongora, Brian Giera, Evangelos E. Papalexakis
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10392v3

When designing new materials, it is often necessary to tailor the material design to have some desired properties. As the set of material design parameters grows, the search space grows exponentially, making the actual synthesis and evaluation of all combinations of designs virtually impossible. Even using traditional computational methods, such as Finite Element Analysis (FEA), becomes too computationally heavy to search this design space. Recent methods use machine learning (ML) surrogate models to more efficiently determine optimal material designs; unfortunately, these methods often (i) are notoriously difficult to interpret and (ii) under perform when the training data comes from a non-uniform sampling of the entire design space. In this work, we suggest the use of tensor completion methods as an all-in-one approach for interpretability and predictions. We observe classical tensor methods are able to compete with traditional ML methods in predictions, with the added benefit of their interpretable tensor factors (which are given for free). In our experiments, we are able to rediscover physical phenomena via the tensor factors, indicating that our predictions are aligned with the physics of the problem. This also means these factors could be used by experimentalists to identify potentially novel patterns, given we are able to rediscover existing ones. We also study the effects of both types of surrogate models (traditional ML \& tensor-based) when we encounter training data from a non-uniform sampling of the design space. We observe some more specialized tensor methods that are able to give better generalization in these non-uniform sampling scenarios, due to the low-rank constraint. We find the best generalization comes from a tensor model, which is able to improve upon the baseline ML methods by up to 5\% on aggregate $R^2$, and halve the error in some out of distribution sections.

---

### Affordances Enable Partial World Modeling with LLMs

Authors: Khimya Khetarpal, Gheorghe Comanici, Jonathan Richens, Jeremy Shar, Fei Xia, Laurent Orseau, Aleksandra Faust, Doina Precup
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10390v1

Full models of the world require complex knowledge of immense detail. While pre-trained large models have been hypothesized to contain similar knowledge due to extensive pre-training on vast amounts of internet scale data, using them directly in a search procedure is inefficient and inaccurate. Conversely, partial models focus on making high quality predictions for a subset of state and actions: those linked through affordances that achieve user intents~\citep{khetarpal2020can}. Can we posit large models as partial world models? We provide a formal answer to this question, proving that agents achieving task-agnostic, language-conditioned intents necessarily possess predictive partial-world models informed by affordances. In the multi-task setting, we introduce distribution-robust affordances and show that partial models can be extracted to significantly improve search efficiency. Empirical evaluations in tabletop robotics tasks demonstrate that our affordance-aware partial models reduce the search branching factor and achieve higher rewards compared to full world models.

---

### Less is Enough: Synthesizing Diverse Data in LLM Feature Space with Sparse Autoencoders

Authors: Zhongzhi Li, Xuansheng Wu, Yijiang Li, Lijie Hu, Ninghao Liu
Published: 2026-02-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.10388v4

The diversity of post-training data is critical for effective downstream performance in large language models (LLMs). Many existing approaches to constructing post-training data quantify diversity using text-based metrics that capture linguistic variation, but such metrics provide only weak signals for the task-relevant features that determine downstream performance. In this work, we introduce Feature Activation Coverage (FAC) which measures data diversity in an interpretable feature space. Building upon this metric, we further propose a diversity-driven data synthesis framework, named FAC Synthesis, that first uses a sparse autoencoder to identify missing features from a seed dataset, and then generates synthetic samples that explicitly reflect these features. Experiments show that our approach consistently improves both data diversity and downstream performance on various tasks, including instruction following, toxicity detection, reward modeling, and behavior steering. Interestingly, we identify a shared, interpretable feature space across model families (i.e., LLaMA, Mistral, and Qwen), enabling cross-model knowledge transfer. Our work provides a solid and practical methodology for exploring data-centric optimization of LLMs.

---

### Test-Time Optimization of Physical Query Plans with LLMs

Authors: Mehmet Hamza Erol, Xiangpeng Hao, Federico Bianchi, Ciro Greco, Jacopo Tagliabue, James Zou
Published: 2026-02-11
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2602.10387v2

Traditional query optimization relies on cost-based optimizers that estimate execution cost (e.g., runtime, memory, and I/O) using predefined heuristics and statistical models. Improving these requires substantial engineering effort, yet they often cannot exploit semantic correlations in queries and schemas that could enable better physical plans. Large language models (LLMs), however, can reason about column semantics, value distributions, and broader domain context that classical statistics miss. We introduce DBPlanBench, a harness for the DataFusion engine that exposes physical plans through a compact serialized representation and applies LLM-proposed edits as JSON patches. On this harness, we instantiate a test-time optimization workflow where an LLM examines physical query plans, proposes localized edits based on semantic reasoning, and an evolutionary search refines the candidates across iterations. We target OLAP queries, where heavy, repeated execution turns even small efficiency gains into substantial cumulative savings. We specifically focus our evaluation on join reordering and join-side selection, where cardinality-estimation errors compound multiplicatively. Median speedups reach $1.10$-$1.12\times$ on TPC-H and $1.05$-$1.07\times$ on TPC-DS, with some achieving up to $4.78\times$. We also demonstrate that optimizations discovered at small scale factors transfer effectively to larger ones, supporting a low-cost small-to-large workflow.

---

### Colorful Talks with Graphs: Human-Interpretable Graph Encodings for Large Language Models

Authors: Angelo Zangari, Peyman Baghershahi, Sourav Medya
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10386v2

Graph problems are fundamentally challenging for large language models (LLMs). While LLMs excel at processing unstructured text, graph tasks require reasoning over explicit structure, permutation invariance, and computationally complex relationships, creating a mismatch with the representations of text-based models. Our work investigates how LLMs can be effectively applied to graph problems despite these barriers. We introduce a human-interpretable structural encoding strategy for graph-to-text translation that injects graph structure directly into natural language prompts. Our method involves computing a variant of Weisfeiler-Lehman (WL) similarity classes and maps them to human-like color tokens rather than numeric labels. The key insight is that semantically meaningful and human-interpretable cues may be more effectively processed by LLMs than opaque symbolic encoding. Experimental results on multiple algorithmic and predictive graph tasks show the considerable improvements by our method on both synthetic and real-world datasets. By capturing both local and global-range dependencies, our method enhances LLM performance especially on graph tasks that require reasoning over global graph structure.

---

### Capture Timing-Attention of Events in Clinical Time Series

Authors: Jia Li, Yu Hou, Rui Zhang
Published: 2026-02-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.10385v7

The contemporary paradigm of trajectory learning operates fundamentally at the level of group dynamics, systematically reducing individual-level complexity to fit group-level models, thus rendering effective patient subtyping difficult and individual-level modeling largely out of reach. We propose a data-driven paradigm that introduces a dedicated individual-level temporal variable to capture \emph{Timing Attention} (i.e., the degree of concentration of an event's timing distribution across the patient cohort), thereby rendering timing a \emph{computable dimension} that enables individualized temporal features in trajectory learning. Instantiated as the Level-of-Individual Time Transformation (LITT) and applied to longitudinal EHR data from 3,276 breast cancer patients, the proposed paradigm demonstrates, for the first time to our knowledge: (1) automatic discovery of clinically significant patient trajectories, and (2) counterfactual timing deduction, that is, a \emph{What-If Machine}. Both results are purely data-driven, requiring no prior domain knowledge. LITT further achieves strong performance on timing prediction and survival analysis tasks.

---

### When Tables Go Crazy: Evaluating Multimodal Models on French Financial Documents

Authors: Virginie Mouilleron, Théo Lasnier, Anna Mosolova, Djamé Seddah
Published: 2026-02-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10384v4

Vision-language models (VLMs) perform well on many document understanding tasks, yet their reliability in specialized, non-English domains remains underexplored. This gap is especially critical in finance, where documents mix dense regulatory text, numerical tables, and visual charts, and where extraction errors can have real-world consequences. We introduce Scribe Finance, the first multimodal benchmark for evaluating French financial document understanding. The dataset contains 1,204 expert-validated questions spanning text extraction, table comprehension, chart interpretation, and multi-turn conversational reasoning, drawn from real investment prospectuses, KIDs, and PRIIPs. We evaluate six open-weight VLMs (8B-124B parameters) using an LLM-as-judge protocol. While models achieve strong performance on text and table tasks (85-90% accuracy), they struggle with chart interpretation (34-62%). Most notably, multi-turn dialogue reveals a sharp failure mode: early mistakes propagate across turns, driving accuracy down to roughly 50% regardless of model size. These results show that current VLMs are effective for well-defined extraction tasks but remain brittle in interactive, multi-step financial analysis. Scribe Finance offers a challenging benchmark to measure and drive progress in this high-stakes setting.

---

### Language Triggers Hijack Language Circuits: A Mechanistic Analysis of Backdoor Behaviors in Large Language Models

Authors: Théo Lasnier, Wissam Antoun, Francis Kulumba, Benoît Sagot, Djamé Seddah
Published: 2026-02-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.10382v3

Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of trigger-induced language-switching backdoors injected during pre-training, studying the Gaperon model family (1B, 8B and 24B). Using activation patching, we localize trigger formation and identify which attention heads process trigger and natural language information. Our central finding is that trigger heads substantially overlap with heads naturally encoding output language across model scales, with Jaccard indices between 0.18 and 0.43 over the top 10 heads identified. This suggests that backdoor triggers do not form new circuits but instead co-opt the model's existing language components and representations. These findings have implications for backdoor defense as detection methods and mitigation strategies could leverage this entanglement between triggers and natural behaviors. More broadly, our work represents a first step toward a more realistic mechanistic understanding of pre-training-injected backdoors in LLMs, paving the way for principled, interpretability-driven defenses.

---

### Deep learning approaches show promise for predicting childhood malnutrition: A comparative study with traditional machine learning methods using survey data

Authors: Deepak Bastola, Yang Li
Published: 2026-02-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.10381v2

Childhood malnutrition remains a major public health concern in Nepal and other low-resource settings, while conventional case-finding approaches are labor-intensive and frequently unavailable in remote areas. This study provides one of the first applications of machine learning and deep learning to identify child malnutrition in Nepal. We systematically compared 16 algorithms spanning deep learning, gradient boosting, and traditional machine learning families, using data from the Nepal Multiple Indicator Cluster Survey (MICS) 2019. A composite malnutrition indicator was constructed by integrating stunting, wasting, and underweight status, and model performance was evaluated using ten metrics, with emphasis on F1-score and recall to account for substantial class imbalance and the high cost of failing to detect malnourished children. Among all models, TabNet achieved the highest scores among evaluated models, likely attributable to its attention-based architecture. A consensus feature importance analysis identified maternal education, household wealth index, and child age as the primary predictors of malnutrition, followed by geographic characteristics, vaccination status, and meal frequency. Collectively, these results demonstrate a scalable, survey-based screening framework for identifying children at elevated risk of malnutrition and for guiding targeted nutritional interventions. The proposed approach supports Nepal's progress toward the Sustainable Development Goals and offers a transferable methodological template for similar low-resource settings globally.

---

### The Alignment Bottleneck in Decomposition-Based Claim Verification

Authors: Mahmud Elahi Akhter, Federico Ruggeri, Iman Munire Bilal, Rob Procter, Maria Liakata
Published: 2026-02-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.10380v1

Structured claim decomposition is often proposed as a solution for verifying complex, multi-faceted claims, yet empirical results have been inconsistent. We argue that these inconsistencies stem from two overlooked bottlenecks: evidence alignment and sub-claim error profiles. To better understand these factors, we introduce a new dataset of real-world complex claims, featuring temporally bounded evidence and human-annotated sub-claim evidence spans. We evaluate decomposition under two evidence alignment setups: Sub-claim Aligned Evidence (SAE) and Repeated Claim-level Evidence (SRE). Our results reveal that decomposition brings significant performance improvement only when evidence is granular and strictly aligned. By contrast, standard setups that rely on repeated claim-level evidence (SRE) fail to improve and often degrade performance as shown across different datasets and domains (PHEMEPlus, MMM-Fact, COVID-Fact). Furthermore, we demonstrate that in the presence of noisy sub-claim labels, the nature of the error ends up determining downstream robustness. We find that conservative "abstention" significantly reduces error propagation compared to aggressive but incorrect predictions. These findings suggest that future claim decomposition frameworks must prioritize precise evidence synthesis and calibrate the label bias of sub-claim verification models.

---

### Systematic Optimization of Real-Time Diffusion Model Inference on Apple M3 Ultra

Authors: Yoichi Ochiai
Published: 2026-02-10
Categories: cs.LG, cs.AI, cs.DC
arXiv: https://arxiv.org/abs/2605.16259v1

While real-time image generation using diffusion models has advanced rapidly on NVIDIA GPUs, systematic optimization research on non-CUDA platforms such as Apple Silicon remains extremely limited. In this study, we conducted comprehensive optimization experiments across 10 phases targeting the Apple M3 Ultra (60-core GPU, 512 GB unified memory) with the goal of achieving real-time camera img2img transformation. We explored a wide range of techniques including CoreML conversion, quantization, Token Merging, Neural Engine utilization, compact model exploration, frame interpolation, kNN search-based synthesis, pix2pix-turbo, optical flow frame skipping, and knowledge distillation, quantitatively evaluating the effectiveness of each approach. Ultimately, by combining CoreML conversion of the distillation-specialized model SDXS-512 with a 3-thread camera pipeline, we achieved real-time camera img2img transformation at 22.7 FPS at 512x512 resolution. The primary contribution of this work is the systematic demonstration that optimization insights established for CUDA are not necessarily effective on Apple Silicon's unified memory architecture. We reveal an optimization landscape fundamentally different from that of NVIDIA GPUs -- including the absence of speedup from quantization, the ineffectiveness of parallel inference, and the unsuitability of the Neural Engine for large-scale models -- and provide practical guidelines for diffusion model inference on Apple Silicon.

---

### Revisiting Content-Based Music Recommendation: Efficient Feature Aggregation from Large-Scale Music Models

Authors: Yizhi Zhou, Jia-Qi Yang, De-Chuan Zhan, Da-Wei Zhou
Published: 2026-02-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20847v1

Music Recommendation Systems (MRSs) are a cornerstone of modern streaming platforms. Existing recommendation models, spanning both recall and ranking stages, predominantly rely on collaborative filtering, which fails to exploit the intrinsic characteristics of audio and consequently leads to suboptimal performance, particularly in cold-start scenarios. However, existing music recommendation datasets often lack rich multimodal information, such as raw audio signals and descriptive textual metadata. Moreover, current recommender system evaluation frameworks remain inadequate, as they neither fully leverage multimodal information nor support a diverse range of algorithms, especially multimodal methods. To address these limitations, we propose TASTE, a comprehensive dataset and benchmarking framework designed to highlight the role of multimodal information in music recommendation. Our dataset integrates both audio and textual modalities. By leveraging recent large-scale self-supervised music encoders, we demonstrate the substantial value of the extracted audio representations across recommendation tasks, including candidate recall and CTR. In addition, we introduce the \textbf{MuQ-token} method, which enables more efficient integration of multi-layer audio features. This method consistently outperforms other feature integration techniques across various settings. Overall, our results not only validate the effectiveness of content-driven approaches but also provide a highly effective and reusable multimodal foundation for future research. Code is available at https://github.com/zreach/TASTE

---

### ADS-POI: Agentic Spatiotemporal State Decomposition for Next Point-of-Interest Recommendation

Authors: Zhenyu Yu, Chunlei Meng, Yangchen Zeng, Mohd Yamani Idna Idris, Shuigeng Zhou
Published: 2026-02-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20846v1

Next point-of-interest (POI) recommendation requires modeling user mobility as a spatiotemporal sequence, where different behavioral factors may evolve at different temporal and spatial scales. Most existing methods compress a user's history into a single latent representation, which tends to entangle heterogeneous signals such as routine mobility patterns, short-term intent, and temporal regularities. This entanglement limits the flexibility of state evolution and reduces the model's ability to adapt to diverse decision contexts. We propose ADS-POI, a spatiotemporal state decomposition framework for next POI recommendation. ADS-POI represents a user with multiple parallel evolving latent sub-states, each governed by its own spatiotemporal transition dynamics. These sub-states are selectively aggregated through a context-conditioned mechanism to form the decision state used for prediction. This design enables different behavioral components to evolve at different rates while remaining coordinated under the current spatiotemporal context. Extensive experiments on three real-world benchmark datasets from Foursquare and Gowalla demonstrate that ADS-POI consistently outperforms strong state-of-the-art baselines under a full-ranking evaluation protocol. The results show that decomposing user behavior into multiple spatiotemporally aware states leads to more effective and robust next POI recommendation. Our code is available at https://github.com/YuZhenyuLindy/ADS-POI.git.

---

### CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation

Authors: Zhenyu Yu, Chunlei Meng, Yangchen Zeng, Mohd Yamani Idna Idris, Jihong Guan, Shuigeng Zhou
Published: 2026-02-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20845v2

Next Point-of-Interest (POI) recommendation ranks a user's likely next location based on check-in history. Most recent rankers compress the trajectory into a single user vector and score every candidate through the same representation, ignoring that every candidate carries geographic coordinates and that the relevance of a past visit depends on where the candidate is located. Target attention from click-through-rate prediction conditions the user representation on the scored item, but its operator was developed for web items without geometry. This paper proposes CaST-POI, a candidate-conditioned POI ranker that keeps a standard target-attention reader and adds two bucketised biases to the attention logits: one for the recency of each past visit and another for its distance to the candidate being scored. Different candidates therefore read the same trajectory with different attention weights, grounded in real geographic distance rather than inferred from item embeddings. Comparing against seven sequential recommenders trained with the same split on three datasets NYC, TKY and CA under per-user leave-one-out with full-vocabulary ranking, CaST-POI improves MRR over the strongest baseline by 5.1%, 7.6% and 14.5%. Holm-corrected paired tests confirm the gains on TKY and CA. Ablation study locates the gain in the explicit revisit gate and the candidate-relative spatial bias, whereas the candidate-independent temporal bias has no measurable effect on all datasets. Code is available at https://github.com/YuZhenyuLindy/CaST-POI.

---

### CaST-POI: Candidate-Conditioned Spatiotemporal Modeling for Next POI Recommendation

Authors: Zhenyu Yu, Chunlei Meng, Yangchen Zeng, Mohd Yamani Idna Idris, Shuigeng Zhou
Published: 2026-02-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20845v1

Next Point-of-Interest (POI) recommendation plays a crucial role in location-based services by predicting users' future mobility patterns. Existing methods typically compute a single user representation from historical trajectories and use it to score all candidate POIs uniformly. However, this candidate-agnostic paradigm overlooks that the relevance of historical visits inherently depends on which candidate is being evaluated. In this paper, we propose CaST-POI, a candidate-conditioned spatiotemporal model for next POI recommendation. Our key insight is that the same user history should be interpreted differently when evaluating different candidate POIs. CaST-POI employs a candidate-conditioned sequence reader that uses candidates as queries to dynamically attend to user history. In addition, we introduce candidate-relative temporal and spatial biases to capture fine-grained mobility patterns based on the relationships between historical visits and each candidate POI. Extensive experiments on three benchmark datasets demonstrate that CaST-POI consistently outperforms state-of-the-art methods, yielding substantial improvements across multiple evaluation metrics, with particularly strong advantages under large candidate pools. Code is available at https://github.com/YuZhenyuLindy/CaST-POI.git.

---

### AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation

Authors: Yanning Hou, Duanyang Yuan, Sihang Zhou, Xiaoshu Chen, Ke Liang, Siwei Wang, Xinwang Liu, Jian Huang
Published: 2026-02-10
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2604.20844v1

Recent GraphRAG methods integrate graph structures into text indexing and retrieval, using knowledge graph triples to connect text chunks, thereby improving retrieval coverage and precision. However, we observe that treating text chunks as the basic unit of knowledge representation rigidly groups multiple atomic facts together, limiting the flexibility and adaptability needed to support diverse retrieval scenarios. Additionally, triple-based entity linking is sensitive to relation-extraction errors, which can lead to missing or incorrect reasoning paths and ultimately hurt retrieval accuracy. To address these issues, we propose the Atom-Entity Graph, a more precise and reliable architecture for knowledge representation and indexing. In our approach, knowledge is stored as knowledge atoms, namely individual, self-contained units of factual information, rather than coarse-grained text chunks. This allows knowledge elements to be flexibly reassembled without mutual interference, thereby enabling seamless alignment with diverse query perspectives. Edges between entities simply indicate whether a relationship exists. By combining personalized PageRank with relevance-based filtering, we maintain accurate entity connections and improve the reliability of reasoning. Theoretical analysis and experiments on five public benchmarks show that the proposed AtomicRAG algorithm outperforms strong RAG baselines in retrieval accuracy and reasoning robustness. Code: https://github.com/7HHHHH/AtomicRAG.

---

### SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

Authors: Talor Abramovich, Maor Ashkenazi, Izzy Putterman, Benjamin Chislett, Tiyasa Mitra, Bita Darvish Rouhani, Ran Zilberstein, Yonatan Geifman
Published: 2026-02-10
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2604.09557v2

Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce SPEED-Bench, a comprehensive suite designed to standardize SD evaluation across diverse semantic domains and realistic serving regimes. SPEED-Bench offers a carefully curated Qualitative data split, selected by prioritizing semantic diversity across the data samples. Additionally, it includes a Throughput data split, allowing speedup evaluation across a range of concurrencies, from latency-sensitive low-batch settings to throughput-oriented high-load scenarios. By integrating with production engines like vLLM and TensorRT-LLM, SPEED-Bench allows practitioners to analyze system behaviors often masked by other benchmarks. We highlight this by quantifying how synthetic inputs overestimate real-world throughput, identifying batch-size dependent optimal draft lengths and biases in low-diversity data, and analyzing the caveats of vocabulary pruning in state-of-the-art drafters. We release SPEED-Bench to establish a unified evaluation standard for practical comparisons of SD algorithms.

---

### Para-B&B: Load-Balanced Deterministic Parallelization of Solving MIP

Authors: Jinyu Zhang, Di Huang, Yue Liu, Shuo Wang, Zhenyu Pu, Zhiyuan Liu
Published: 2026-02-10
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2604.09556v1

Mixed-integer programming (MIP) extends linear programming by incorporating both continuous and integer decision variables, making it widely used in production planning, logistics scheduling, and resource allocation. However, MIP remains NP-hard and cannot generally be solved to optimality in polynomial time. Branch-and-bound, a fundamental exact method, faces significant parallelization challenges due to computational heterogeneity and strict determinism requirements in commercial applications. This paper presents the first fully open-source implementation of deterministic parallel branch-and-bound for HiGHS, a high-performance MIP solver. Our approach introduces a novel data-parallel architecture ensuring strict determinism by replicating complete solver state across worker threads and eliminating non-deterministic synchronization primitives. A key innovation is our AI-driven load balancing mechanism employing multi-stage workload prediction models that estimate node computational complexity based on structural characteristics and historical performance data, coupled with dynamic parameter adjustment strategies. The framework executes orchestrated parallel phases including concurrent dive operations, systematic data consolidation, and intelligent node selection. Comprehensive experimental evaluation on 80 MIPLIB 2017 benchmark instances demonstrates effectiveness, achieving a geometric mean speedup of 2.17 using eight threads while maintaining complete deterministic guarantees. Performance gains become increasingly pronounced for higher node counts, with speedup factors reaching 5.12 for computationally intensive instances and thread idle rates averaging 34.7%.

---

### A Goal-Oriented Chatbot for Engaging the Elderly Through Family Photo Conversations

Authors: Raymond Chung, Keith Ng, CD Shum
Published: 2026-02-10
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2604.06184v1

We propose a personalized chatbot designed for elderly individuals. The chatbot initiates discussions based on family photos, encouraging users to interact naturally. During these interactions, it generates W questions (who, where, when, and what) to stimulate cognitive function, followed by an open-ended question to promote positive reminiscence. This approach is structured around a goal-oriented dialogue framework. Additionally, after each conversation about a photo, the chatbot analyzes the discussion to identify topics that the user favors or dislikes. It then offers the user the option to chat about another photo either featuring the same family members or an individual previously mentioned in the conversation. To support this system, we have developed a web portal that allows caregivers to upload photos and review chat conversations. This personalized chatbot not only encourages elderly users to engage with the chatbot regularly and reduces feelings of loneliness but also provides caregivers with a valuable tool to gain insights into users' well-being.

---

### AraModernBERT: Transtokenized Initialization and Long-Context Encoder Modeling for Arabic

Authors: Omar Elshehy, Omer Nacar, Abdelbasset Djamai, Muhammed Ragab, Khloud Al Jallad, Mona Abdelazim
Published: 2026-02-10
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2603.09982v2

Encoder-only transformer models remain widely used for discriminative NLP tasks, yet recent architectural advances have largely focused on English. In this work, we present AraModernBERT, an adaptation of the ModernBERT encoder architecture to Arabic, and study the impact of transtokenized embedding initialization and native long-context modeling up to 8,192 tokens. We show that transtokenization is essential for Arabic language modeling, yielding dramatic improvements in masked language modeling performance compared to non-transtokenized initialization. We further demonstrate that AraModernBERT supports stable and effective long-context modeling, achieving improved intrinsic language modeling performance at extended sequence lengths. Downstream evaluations on Arabic natural language understanding tasks, including inference, offensive language detection, question-question similarity, and named entity recognition, confirm strong transfer to discriminative and sequence labeling settings. Our results highlight practical considerations for adapting modern encoder architectures to Arabic and other languages written in Arabic-derived scripts.

---

### KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware

Authors: Jiayi Nie, Haoran Wu, Yao Lai, Zeyu Cao, Cheng Zhang, Binglei Lou, Erwei Wang, Jianyi Cheng, Timothy M. Jones, Robert Mullins, Rika Antonova, Yiren Zhao
Published: 2026-02-10
Categories: cs.AR, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2603.08721v2

New AI accelerators with novel instruction set architectures (ISAs) often require developers to manually craft low-level kernels, a time-consuming and error-prone process that does not scale across hardware targets. This delays emerging hardware platforms from reaching the market. While prior LLM-based code generation has shown promise in mature GPU ecosystems, it remains unclear whether agentic LLM systems can quickly produce valid and efficient kernels for emerging hardware with new ISAs. We present KernelCraft: the first benchmark for evaluating an LLM agent's ability to generate and optimize low-level kernels for customized accelerators through a function-calling, feedback-driven workflow. We evaluate agent performance across three emerging accelerators on more than 20 machine-learning tasks, each with five diverse task configurations. Across four leading reasoning models, the strongest agents generate functionally correct kernels for unseen ISAs within a few refinement steps and produce optimized kernels that match or outperform compiler baselines. These results demonstrate KernelCraft's potential to accelerate the accelerator chip development cycle. KernelCraft is available at https://kernelcraft-cam.github.io/.

---

### SiliconMind-V1: Multi-Agent Distillation and Debug-Reasoning Workflows for Verilog Code Generation

Authors: Mu-Chi Chen, Yu-Hung Kao, Po-Hsuan Huang, Shao-Chun Ho, Hsiang-Yu Tsou, I-Ting Wu, En-Ming Huang, Yu-Kai Hung, Wei-Po Hsin, Cheng Liang, Chia-Heng Tu, Shih-Hao Hung et al.
Published: 2026-02-10
Categories: cs.AR, cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2603.08719v2

Large language models (LLMs) have recently emerged as a promising approach for automating Verilog code generation; however, existing methods primarily emphasize syntactic correctness and often rely on commercial models or external verification tools, which introduces concerns regarding cost, data privacy, and limited guarantees of functional correctness. This work proposes a unified multi-agent framework for reasoning-oriented training data generation with integrated testbench-driven verification, enabling locally fine-tuned LLMs, SiliconMind-V1, to iteratively generate, test, and debug Register-Transfer Level (RTL) designs through test-time scaling. Experimental results on representative benchmarks (VerilogEval-v2, RTLLM-v2, and CVDP) demonstrate that the proposed approach outperforms the state-of-the-art QiMeng-CodeV-R1 in functional correctness while using fewer training resources.

---

### CktEvo: Repository-Level RTL Code Benchmark for Design Evolution

Authors: Zhengyuan Shi, Jingxin Wang, Tairan Cheng, Changran Xu, Weikang Qian, Qiang Xu
Published: 2026-02-10
Categories: cs.AR, cs.AI
arXiv: https://arxiv.org/abs/2603.08718v1

Register-Transfer Level (RTL) coding is an iterative, repository-scale process in which Power, Performance, and Area (PPA) emerge from interactions across many files and the downstream toolchain. While large language models (LLMs) have recently been applied to hardware design, most efforts focus on generation or debugging from natural-language prompts, where ambiguity and hallucinations necessitate expert review. A separate line of work begins from formal inputs, yet typically optimizes high-level synthesis or isolated modules and remains decoupled from cross-file dependencies. In this work, we present CktEvo, a benchmark and reference framework for repo-level RTL evolution. Unlike prior benchmarks consisting of isolated snippets, our benchmark targets complete IP cores where PPA emerges from cross-file dependencies. Our benchmark packages several high-quality Verilog repositories from real-world designs. We formalize the task as: given an initial repository, produce edits that preserve functional behavior while improving PPA. We also provide a closed-loop framework that couples LLM-proposed edits with toolchain feedback to enable cross-file modifications and iterative repair at repository scale. Our experiments demonstrate that the reference framework realizes PPA improvements without any human interactions. CktEvo establishes a rigorous and executable foundation for studying LLM-assisted RTL optimization that matters for engineering practice: repository-level, function-preserving, and PPA-driven.

---