# Research Papers — 2026-02 · bundle page 60 of 210

> Full-text markdown of papers #2951–3000 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/60
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/59.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/61.md)

### ZorBA: Zeroth-order Federated Fine-tuning of LLMs with Heterogeneous Block Activation

Authors: Chuiyang Meng, Ming Tang, Vincent W. S. Wong
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2603.04436v1

Federated fine-tuning of large language models (LLMs) enables collaborative tuning across distributed clients. However, due to the large size of LLMs, local updates in federated learning (FL) may incur substantial video random-access memory (VRAM) usage. Moreover, frequent model exchange may lead to significant communication overhead. To tackle these challenges, in this paper we propose ZorBA, a zeroth-order optimization-based federated fine-tuning framework with heterogeneous block activation. ZorBA leverages zeroth-order optimization to eliminate the storage of gradients at the clients by forward passes. ZorBA includes a heterogeneous block activation mechanism in which the central server allocates different subsets of transformer blocks to clients in order to accelerate the convergence rate and reduce the VRAM usage. Furthermore, ZorBA utilizes shared random seeds and the finite differences of gradients in order to reduce the communication overhead. We conduct theoretical analysis to characterize the effect of block activation decisions on the convergence rate and VRAM usage. To jointly enhance the convergence rate and reduce the VRAM usage, we formulate an optimization problem to optimize the block activation decisions. We propose an $ε$-constraint lexicographic algorithm to solve this problem. Experimental results show that ZorBA outperforms three federated fine-tuning baselines in VRAM usage by up to 62.41% and incurs a low communication overhead.

---

### A Benchmark Analysis of Graph and Non-Graph Methods for Caenorhabditis Elegans Neuron Classification

Authors: Jingqi Lu, Keqi Han, Yun Wang, Lu Mi, Carl Yang
Published: 2026-02-19
Categories: q-bio.NC, cs.AI
arXiv: https://arxiv.org/abs/2603.02241v1

This study establishes a benchmark for Caenorhabditis elegans neuron classification, comparing four graph methods (GCN, GraphSAGE, GAT, GraphTransformer) against four non-graph methods (Logistic Regression, MLP, LOLCAT, NeuPRINT). Using the functional connectome, we classified Sensory, Interneuron, and Motor neurons based on Spatial, Connection, and Neuronal Activity features. Results show that attention-based GNNs significantly outperform baselines on the Spatial and Connection features. The Neuronal Activity features yielded poor performance, likely due to the low temporal resolution of the underlying neuronal activity data. Our benchmark validates the use of GNNs and highlights that Spatial and Connection features are key predictors for Caenorhabditis elegans neuron classes. Code is available at: https://github.com/JingqiLuu/neuronclf-gnn-benchmark.

---

### Automated Quality Check of Sensor Data Annotations

Authors: Niklas Freund, Zekiye Ilknur-Öz, Tobias Klockau, Patrick Naumann, Philipp Neumaier, Martin Köppel
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2603.00114v1

The monitoring of the route and track environment plays an important role in automated driving. For example, it can be used as an assistance system for route monitoring in automation level Grade of Automation (GoA) 2, where the train driver is still on board. In fully automated, driverless driving at automation level GoA4, these systems finally take over environment monitoring completely independently. With the help of artificial intelligence (AI), they react automatically to risks and dangerous events on the route. To train such AI algorithms, large amounts of training data are required, which must meet high-quality standards due to their safety relevance. In this publication we present an automatic method for assuring the quality of training data, significantly reducing the manual workload and accelerating the development of these systems. We propose an open-source tool designed to detect nine common errors found in multi-sensor datasets for railway vehicles. To evaluate the performance of the framework, all detected errors were manually validated. Six issue detection methods achieved 100% precision, while three additional methods reached precision rates 96% and 97%.

---

### AI Agents Alone Are Not (Yet) Sufficient for Social Simulation

Authors: Yiming Li, Dacheng Tao
Published: 2026-02-19
Categories: cs.MA, cs.AI, cs.CE, cs.CY, cs.SI
arXiv: https://arxiv.org/abs/2603.00113v2

Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation, often under the implicit assumption that realistic population dynamics will emerge once role-specified agents are placed in a networked multi-agent setting. This position paper argues that LLM-based agents alone are not (yet) sufficient for social simulation. We attribute this over-optimism to a systematic mismatch between what current agent pipelines are typically optimized and validated to produce and what simulation-as-science requires. Concretely, role-playing plausibility does not imply faithful human behavioral validity; collective outcomes are frequently mediated by agent-environment co-dynamics rather than agent-agent messaging alone; and results can be dominated by interaction protocols, scheduling, and initial information priors. To make these underlying mechanisms explicit and auditable, we propose a unified formulation of AI agent-based social simulation as an environment-involved Markov game with explicit exposure and scheduling mechanisms, from which we derive concrete actions for design, evaluation, and interpretation.

---

### Catalyzing Informed Residential Energy Retrofit Decisions via Domain-Specific LLM

Authors: Lei Shu, Dong Zhao, Jianli Chen, Armin Yeganeh, Sinem Mollaoglu, Jiayu Zhou
Published: 2026-02-19
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.20181v2

Residential energy retrofit initiation is often stalled by an expertise gap, where homeowners lack the technical literacy required for structured building energy assessments and are thereby trapped in low-information environments with fragmented sources. To bridge this gap, this study reports a domain-specific large language model (LLM) designed to catalyze informed decision-making based solely on homeowner-accessible, natural-language descriptions, e.g., building age, size, and location. The model is created using the parameter-efficient low-rank adaption (LoRA) fine-tuning approach on a massive corpus grounded in physics-based energy simulations and techno-economic calculations from 536,416 U.S. residential building prototypes. Nine major retrofit categories are evaluated, including envelope upgrades, HVAC systems, and renewable energy installations. Validations against physics-grounded benchmarks show that the LLM consistently identifies high-quality retrofit options, achieving top-3 hit rates of 98.9% for maximum CO2 reduction and 93.3% for the shortest discounted payback year. Moreover, the model exhibits strong robustness under incomplete input conditions, maintaining stable performance even when basic dwelling descriptions are only 60% partially specified. By significantly lowering the information activation energy for non-expert users while maintaining the scientific rigor, this physics-based AI model offers a scalable pathway for parallelized, user-centered decision making, accelerating cumulative energy savings and emission reductions across community and national scales.

---

### The Geometry of Multi-Task Grokking: Transverse Instability, Superposition, and Weight Decay Phase Structure

Authors: Yongzhong Xu
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.18523v3

Grokking -- the abrupt transition from memorization to generalization long after near-zero training loss -- has been studied mainly in single-task settings. We extend geometric analysis to multi-task modular arithmetic, training shared-trunk Transformers on dual-task (mod-add + mod-mul) and tri-task (mod-add + mod-mul + mod-sq) objectives across a systematic weight decay sweep. Five consistent phenomena emerge. (1) Staggered grokking order: multiplication generalizes first, followed by squaring, then addition, with consistent delays across seeds. (2) Universal integrability: optimization trajectories remain confined to an empirically invariant low-dimensional execution manifold; commutator defects orthogonal to this manifold reliably precede generalization. (3) Weight decay phase structure: grokking timescale, curvature depth, reconstruction threshold, and defect lead covary systematically with weight decay, revealing distinct dynamical regimes and a sharp no-decay failure mode. (4) Holographic incompressibility: final solutions occupy only 4--8 principal trajectory directions yet are distributed across full-rank weights and destroyed by minimal perturbations; SVD truncation, magnitude pruning, and uniform scaling all fail to preserve performance. (5) Transverse fragility and redundancy: removing less than 10% of orthogonal gradient components eliminates grokking, yet dual-task models exhibit partial recovery under extreme deletion, suggesting redundant center manifolds enabled by overparameterization. Together, these results support a dynamical picture in which multi-task grokking constructs a compact superposition subspace in parameter space, with weight decay acting as compression pressure and excess parameters supplying geometric redundancy in optimization pathways.

---

### AdaptStress: Online Adaptive Learning for Interpretable and Personalized Stress Prediction Using Multivariate and Sparse Physiological Signals

Authors: Xueyi Wang, Claudine J. C. Lamoth, Elisabeth Wilhelm
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.18521v1

Continuous stress forecasting could potentially contribute to lifestyle interventions. This paper presents a novel, explainable, and individualized approach for stress prediction using physiological data from consumer-grade smartwatches. We develop a time series forecasting model that leverages multivariate features, including heart rate variability, activity patterns, and sleep metrics, to predict stress levels across 16 temporal horizons (History window: 3, 5, 7, 9 days; forecasting window: 1, 3, 5, 7 days). Our evaluation involves 16 participants monitored for 10-15 weeks. We evaluate our approach across 16 participants, comparing against state-of-the-art time series models (Informer, TimesNet, PatchTST) and traditional baselines (CNN, LSTM, CNN-LSTM) across multiple temporal horizons. Our model achieved performance with an MSE of 0.053, MAE of 0.190, and RMSE of 0.226 in optimal settings (5-day input, 1-day prediction). A comparison with the baseline models shows that our model outperforms TimesNet, PatchTST, CNN-LSTM, LSTM, and CNN under all conditions, representing improvements of 36.9%, 25.5%, and 21.5% over the best baseline. According to the explanability analysis, sleep metrics are the most dominant and consistent stress predictors (importance: 1.1, consistency: 0.9-1.0), while activity features exhibit high inter-participant variability (0.1-0.2). Most notably, the model captures individual-specific patterns where identical features can have opposing effects across users, validating its personalization capabilities. These findings establish that consumer wearables, combined with adaptive and interpretable deep learning, can deliver relevant stress assessment adapted to individual physiological responses, providing a foundation for scalable, continuous, explainable mental health monitoring in real-world settings.

---

### Sketch2Feedback: Grammar-in-the-Loop Framework for Rubric-Aligned Feedback on Student STEM Diagrams

Authors: Aayam Bansal
Published: 2026-02-19
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.18520v1

Providing timely, rubric-aligned feedback on student-drawn diagrams is a persistent challenge in STEM education. While large multimodal models (LMMs) can jointly parse images and generate explanations, their tendency to hallucinate undermines trust in classroom deployments. We present Sketch2Feedback, a grammar-in-the-loop framework that decomposes the problem into four stages -- hybrid perception, symbolic graph construction, constraint checking, and constrained VLM feedback -- so that the language model verbalizes only violations verified by an upstream rule engine. We evaluate on two synthetic micro-benchmarks, FBD-10 (free-body diagrams) and Circuit-10 (circuit schematics), each with 500 images spanning standard and hard noise augmentation tiers, comparing our pipeline against end-to-end LMMs (LLaVA-1.5-7B, Qwen2-VL-7B), a vision-only detector, a YOLOv8-nano learned detector, and an ensemble oracle. On n=100 test samples per benchmark with 95% bootstrap CIs, results are mixed and instructive: Qwen2-VL-7B achieves the highest micro-F1 on both FBDs (0.570) and circuits (0.528), but with extreme hallucination rates (0.78, 0.98). An ensemble oracle that selects the best prediction per sample reaches F1=0.556 with hallucination 0.320 on FBDs, demonstrating exploitable complementarity between grammar and end-to-end approaches. Confidence thresholding at tau=0.7 reduces circuit hallucination from 0.970 to 0.880 with no F1 loss. Hard noise augmentation reveals domain-dependent robustness: FBD detection is resilient while circuit detection degrades sharply. An LLM-as-judge evaluation confirms that the grammar pipeline produces more actionable circuit feedback (4.85/5) than the end-to-end LMM (3.11/5). We release all code, datasets, and evaluation scripts.

---

### Wide Open Gazes: Quantifying Visual Exploratory Behavior in Soccer with Pose Enhanced Positional Data

Authors: Joris Bekkers
Published: 2026-02-19
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.18519v1

Traditional approaches to measuring visual exploratory behavior in soccer rely on counting visual exploratory actions (VEAs) based on rapid head movements exceeding 125°/s, but this method suffer from player position bias (i.e., a focus on central midfielders), annotation challenges, binary measurement constraints (i.e., a player is scanning, or not), lack the power to predict relevant short-term in-game future success, and are incompatible with fundamental soccer analytics models such as pitch control. This research introduces a novel formulaic continuous stochastic vision layer to quantify players' visual perception from pose-enhanced spatiotemporal tracking. Our probabilistic field-of-view and occlusion models incorporate head and shoulder rotation angles to create speed-dependent vision maps for individual players in a two-dimensional top-down plane. We combine these vision maps with pitch control and pitch value surfaces to analyze the awaiting phase (when a player is awaiting the ball to arrive after a pass for a teammate) and their subsequent on-ball phase. We demonstrate that aggregated visual metrics - such as the percentage of defended area observed while awaiting a pass - are predictive of controlled pitch value gained at the end of dribbling actions using 32 games of synchronized pose-enhanced tracking data and on-ball event data from the 2024 Copa America. This methodology works regardless of player position, eliminates manual annotation requirements, and provides continuous measurements that seamlessly integrate into existing soccer analytics frameworks. To further support the integration with existing soccer analytics frameworks we open-source the tools required to make these calculations.

---

### Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling

Authors: Attila Dobi, Aravindh Manickavasagam, Benjamin Thompson, Xiaohan Yang, Faisal Farooq
Published: 2026-02-19
Categories: cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.18518v2

Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user views (impressions) that went to content violating a given policy on a given day. Accurate prevalence measurement is challenging because violations are often rare and human labeling is costly, making frequent, platform-representative studies slow. We present a design-based measurement system that (i) draws daily probability samples from the impression stream using ML-assisted weights to concentrate label budget on high-exposure and high-risk content while preserving unbiasedness, (ii) labels sampled items with a multimodal LLM governed by policy prompts and gold-set validation, and (iii) produces design-consistent prevalence estimates with confidence intervals and dashboard drilldowns. A key design goal is one global sample with many pivots: the same daily sample supports prevalence by surface, viewer geography, content age, and other segments through post-stratified estimation. We describe the statistical estimators, variance and confidence interval construction, label-quality monitoring, and an engineering workflow that makes the system configurable across policies.

---

### Measuring the Prevalence of Policy Violating Content with ML Assisted Sampling and LLM Labeling

Authors: Attila Dobi, Aravindh Manickavasagam, Benjamin Thompson, Xiaohan Yang, Faisal Farooq
Published: 2026-02-19
Categories: cs.LG, stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2602.18518v1

Content safety teams need metrics that reflect what users actually experience, not only what is reported. We study prevalence: the fraction of user views (impressions) that went to content violating a given policy on a given day. Accurate prevalence measurement is challenging because violations are often rare and human labeling is costly, making frequent, platform-representative studies slow. We present a design-based measurement system that (i) draws daily probability samples from the impression stream using ML-assisted weights to concentrate label budget on high-exposure and high-risk content while preserving unbiasedness, (ii) labels sampled items with a multimodal LLM governed by policy prompts and gold-set validation, and (iii) produces design-consistent prevalence estimates with confidence intervals and dashboard drilldowns. A key design goal is one global sample with many pivots: the same daily sample supports prevalence by surface, viewer geography, content age, and other segments through post-stratified estimation. We describe the statistical estimators, variance and confidence interval construction, label-quality monitoring, and an engineering workflow that makes the system configurable across policies.

---

### Weak-Form Evolutionary Kolmogorov-Arnold Networks for Solving Partial Differential Equations

Authors: Bongseok Kim, Jiahao Zhang, Guang Lin
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.18515v1

Partial differential equations (PDEs) form a central component of scientific computing. Among recent advances in deep learning, evolutionary neural networks have been developed to successively capture the temporal dynamics of time-dependent PDEs via parameter evolution. The parameter updates are obtained by solving a linear system derived from the governing equation residuals at each time step. However, strong-form evolutionary approaches can yield ill-conditioned linear systems due to pointwise residual discretization, and their computational cost scales unfavorably with the number of training samples. To address these limitations, we propose a weak-form evolutionary Kolmogorov-Arnold Network (KAN) for the scalable and accurate prediction of PDE solutions. We decouple the linear system size from the number of training samples through the weak formulation, leading to improved scalability compared to strong-form approaches. We also rigorously enforce boundary conditions by constructing the trial space with boundary-constrained KANs to satisfy Dirichlet and periodic conditions, and by incorporating derivative boundary conditions directly into the weak formulation for Neumann conditions. In conclusion, the proposed weak-form evolutionary KAN framework provides a stable and scalable approach for PDEs and contributes to scientific machine learning with potential relevance to future engineering applications.

---

### Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard vs. Reasoning Models

Authors: Manuel Wirth
Published: 2026-02-19
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2602.18514v1

As Large Language Models (LLMs) are increasingly integrated into automated decision-making pipelines, specifically within Human Resources (HR), the security implications of Indirect Prompt Injection (IPI) become critical. While a prevailing hypothesis posits that "Reasoning" or "Chain-of-Thought" Models possess safety advantages due to their ability to self-correct, emerging research suggests these capabilities may enable more sophisticated alignment failures. This qualitative Red-Teaming case study challenges the safety-through-reasoning premise using the Qwen 3 30B architecture. By subjecting both a standard instruction-tuned model and a reasoning-enhanced model to a "Trojan Horse" curriculum vitae, distinct failure modes are observed. The results suggest a complex trade-off: while the Standard Model resorted to brittle hallucinations to justify simple attacks and filtered out illogical constraints in complex scenarios, the Reasoning Model displayed a dangerous duality. It employed advanced strategic reframing to make simple attacks highly persuasive, yet exhibited "Meta-Cognitive Leakage" when faced with logically convoluted commands. This study highlights a failure mode where the cognitive load of processing complex adversarial instructions causes the injection logic to be unintentionally printed in the final output, rendering the attack more detectable by humans than in Standard Models.

---

### Beyond Pass-by-Pass Optimization: Intent-Driven IR Optimization with Large Language Models

Authors: Lei Qiu, Zi Yang, Fang Lyu, Ming Zhong, Huimin Cui, Xiaobing Feng
Published: 2026-02-19
Categories: cs.PL, cs.AI
arXiv: https://arxiv.org/abs/2602.18511v1

Modern compilers optimize programs through a sequence of modular passes over intermediate representations (IR). While this pass-by-pass paradigm offers engineering benefits, it suffers from a pass coordination problem: locally beneficial transformations may block more profitable optimizations in later stages. This limitation stems from the lack of an explicit notion of optimization intent, defined as a holistic strategy for coordinating multiple transformations toward a global performance objective. Recent LLM-based approaches formulate IR optimization as an end-to-end generation task, thereby avoiding the traditional pass-by-pass structure. However, optimization intent remains implicit in these methods, forcing models to jointly infer optimization strategy and generate low-level transformations, which limits both correctness and performance. We propose IntOpt, the first intent-driven IR optimizer that explicitly separates high-level optimization intent from low-level analysis and transformation. IntOpt organizes IR optimization into three stages: intent formulation, intent refinement, and intent realization, enabling globally coordinated transformations. Experiments show that IntOpt achieves 90.5% verified correctness and 2.660x average speedup on 200-program test set, outperforming state-of-the-art LLM-based optimizers in both correctness and performance, and surpassing modern compiler with the -O3 option on 37 benchmarks with speedups of up to 272.60x.

---

### El Agente Gráfico: A Semantic Execution Runtime for Scientific Agents

Authors: Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick, Marcel Müller, Yeonghun Kang, Changhyeok Choi, Naruki Yoshikawa, Zijian Zhang, Jin Won Lee, Tsz Wai Ko, Aiwei Yin, Mohammad Ghazi Vakili et al.
Published: 2026-02-19
Categories: cs.AI, cs.MA, cs.SE, physics.chem-ph
arXiv: https://arxiv.org/abs/2602.17902v2

Large language models (LLMs) can plan scientific workflows and generate code, but these capabilities do not specify how scientific state is validated, transferred and recorded across heterogeneous computational and experimental operations. Here we present El Agente Gráfico, a semantic execution runtime for scientific agents that uses typed execution graphs to enforce admissible scientific state transitions, record provenance and confine model judgement to explicit decision points. Using the same top-level LLM and task-specific rubrics on six university-level quantum chemistry exercises, El Agente Gráfico improved performance while reducing model cost by approximately 80% and wall-clock time by more than fourfold relative to our previous multi-agent architecture. Across ensemble spectroscopy and metal-organic framework (MOF) design, the runtime supported typed-state transfer, parallel execution and cross-session persistence. Open-ended studies of a disulfide redox mechanism and the vibrational hypothesis of olfaction required the agent to define the chemical scope and computational pathway of each investigation. A graph-construction skill distilled from these studies then enabled coding agents to author typed execution graphs for MOF literature mining. Together, these results show how typed execution graphs turn reusable procedural knowledge into scientific protocols that can be inspected, revised and transferred across computational and physical systems.

---

### El Agente Gráfico: Structured Execution Graphs for Scientific Agents

Authors: Jiaru Bai, Abdulrahman Aldossary, Thomas Swanick, Marcel Müller, Yeonghun Kang, Zijian Zhang, Jin Won Lee, Tsz Wai Ko, Mohammad Ghazi Vakili, Varinia Bernales, Alán Aspuru-Guzik
Published: 2026-02-19
Categories: cs.AI, cs.MA, cs.SE, physics.chem-ph
arXiv: https://arxiv.org/abs/2602.17902v1

Large language models (LLMs) are increasingly used to automate scientific workflows, yet their integration with heterogeneous computational tools remains ad hoc and fragile. Current agentic approaches often rely on unstructured text to manage context and coordinate execution, generating often overwhelming volumes of information that may obscure decision provenance and hinder auditability. In this work, we present El Agente Gráfico, a single-agent framework that embeds LLM-driven decision-making within a type-safe execution environment and dynamic knowledge graphs for external persistence. Central to our approach is a structured abstraction of scientific concepts and an object-graph mapper that represents computational state as typed Python objects, stored either in memory or persisted in an external knowledge graph. This design enables context management through typed symbolic identifiers rather than raw text, thereby ensuring consistency, supporting provenance tracking, and enabling efficient tool orchestration. We evaluate the system by developing an automated benchmarking framework across a suite of university-level quantum chemistry tasks previously evaluated on a multi-agent system, demonstrating that a single agent, when coupled to a reliable execution engine, can robustly perform complex, multi-step, and parallel computations. We further extend this paradigm to two other large classes of applications: conformer ensemble generation and metal-organic framework design, where knowledge graphs serve as both memory and reasoning substrates. Together, these results illustrate how abstraction and type safety can provide a scalable foundation for agentic scientific automation beyond prompt-centric designs.

---

### MeDUET: Disentangled Unified Pretraining for 3D Medical Image Synthesis and Analysis

Authors: Junkai Liu, Ling Shao, Le Zhang
Published: 2026-02-19
Categories: eess.IV, cs.CV, cs.GT
arXiv: https://arxiv.org/abs/2602.17901v3

Self-supervised learning (SSL) and diffusion models have respectively advanced representation learning and generative modeling for high-dimensional 3D visual data, yet they are often developed as separate paradigms. Their unification remains challenging under multi-source heterogeneity, as anatomical content must be preserved for analysis while acquisition-related style varies across centers and affects synthesis. In this paper, we propose MeDUET, a 3D Medical image Disentangled UnifiEd PreTraining framework in the variational autoencoder latent space. MeDUET formulates unified pretraining as an empirical factor identifiability problem, aiming to learn domain-invariant content factors for anatomy and domain-specific style factors for appearance. To improve factor separation, MeDUET first uses token demixing with a standard adversarial domain regularizer to establish basic content-style specialization, and further introduces Mixed Factor Token Distillation and Swap-invariance Quadruplet Contrast to reduce mixed-region factor leakage and organize factor spaces with factor-wise invariance and discriminability. With these learned factors, MeDUET transfers effectively to both synthesis and analysis, yielding higher fidelity, faster convergence, and better controllability for synthesis, while achieving competitive or superior domain generalization and label efficiency on diverse datasets, tasks, and modalities. Overall, MeDUET shows that multi-source heterogeneity can serve as useful supervision, with disentanglement providing an effective interface for unifying 3D medical image synthesis and analysis. Our code is available at https://github.com/JK-Liu7/MeDUET.

---

### Breaking the Correlation Plateau: On the Optimization and Capacity Limits of Attention-Based Regressors

Authors: Jingquan Yan, Yuwei Miao, Peiran Yu, Junzhou Huang
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17898v1

Attention-based regression models are often trained by jointly optimizing Mean Squared Error (MSE) loss and Pearson correlation coefficient (PCC) loss, emphasizing the magnitude of errors and the order or shape of targets, respectively. A common but poorly understood phenomenon during training is the PCC plateau: PCC stops improving early in training, even as MSE continues to decrease. We provide the first rigorous theoretical analysis of this behavior, revealing fundamental limitations in both optimization dynamics and model capacity. First, in regard to the flattened PCC curve, we uncover a critical conflict where lowering MSE (magnitude matching) can paradoxically suppress the PCC gradient (shape matching). This issue is exacerbated by the softmax attention mechanism, particularly when the data to be aggregated is highly homogeneous. Second, we identify a limitation in the model capacity: we derived a PCC improvement limit for any convex aggregator (including the softmax attention), showing that the convex hull of the inputs strictly bounds the achievable PCC gain. We demonstrate that data homogeneity intensifies both limitations. Motivated by these insights, we propose the Extrapolative Correlation Attention (ECA), which incorporates novel, theoretically-motivated mechanisms to improve the PCC optimization and extrapolate beyond the convex hull. Across diverse benchmarks, including challenging homogeneous data setting, ECA consistently breaks the PCC plateau, achieving significant improvements in correlation without compromising MSE performance.

---

### Learning from Biased and Costly Data Sources: Minimax-optimal Data Collection under a Budget

Authors: Michael O. Harding, Vikas Singh, Kirthevasan Kandasamy
Published: 2026-02-19
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2602.17894v2

Data collection is a critical component of modern statistical and machine learning pipelines, particularly when data must be gathered from multiple heterogeneous sources to study a target population of interest. In many use cases, such as medical studies or political polling, different sources incur different sampling costs. Observations often have associated group identities - for example, health markers, demographics, or political affiliations - and the relative composition of these groups may differ substantially, both among the source populations and between sources and target population. In this work, we study multi-source data collection under a fixed budget, focusing on the estimation of population means and group-conditional means. We show that naive data collection strategies (e.g. attempting to "match" the target distribution) or relying on standard estimators (e.g. sample mean) can be highly suboptimal. Instead, we develop a sampling plan which maximizes the effective sample size - the total sample size divided by $D_{χ^2}(q\mid\mid\overline{p}) + 1$, where $q$ is the target distribution, $\overline{p}$ is the aggregated source distribution, and $D_{χ^2}$ is the $χ^2$-divergence. We pair this sampling plan with a classical post-stratification estimator and upper bound its risk. We provide matching lower bounds, establishing that our approach achieves the budgeted minimax optimal risk. Our techniques also extend to prediction problems when minimizing the excess risk, providing a principled approach to multi-source learning with costly and heterogeneous data sources.

---

### COMBA: Cross Batch Aggregation for Learning Large Graphs with Context Gating State Space Models

Authors: Jiajun Shen, Yufei Jin, Yi He, xingquan Zhu
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17893v1

State space models (SSMs) have recently emerged for modeling long-range dependency in sequence data, with much simplified computational costs than modern alternatives, such as transformers. Advancing SMMs to graph structured data, especially for large graphs, is a significant challenge because SSMs are sequence models and the shear graph volumes make it very expensive to convert graphs as sequences for effective learning. In this paper, we propose COMBA to tackle large graph learning using state space models, with two key innovations: graph context gating and cross batch aggregation. Graph context refers to different hops of neighborhood for each node, and graph context gating allows COMBA to use such context to learn best control of neighbor aggregation. For each graph context, COMBA samples nodes as batches, and train a graph neural network (GNN), with information being aggregated cross batches, allowing COMBA to scale to large graphs. Our theoretical study asserts that cross-batch aggregation guarantees lower error than training GNN without aggregation. Experiments on benchmark networks demonstrate significant performance gains compared to baseline approaches. Code and benchmark datasets will be released for public access.

---

### Machine Learning Based Prediction of Surgical Outcomes in Chronic Rhinosinusitis from Clinical Data

Authors: Sayeed Shafayet Chowdhury, Karen D'Souza, V. Siva Kakumani, Snehasis Mukhopadhyay, Shiaofen Fang, Rodney J. Schlosser, Daniel M. Beswick, Jeremiah A. Alt, Jess C. Mace, Zachary M. Soler, Timothy L. Smith, Vijay R. Ramakrishnan
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17888v1

Artificial intelligence (AI) has increasingly transformed medical prognostics by enabling rapid and accurate analysis across imaging and pathology. However, the investigation of machine learning predictions applied to prospectively collected, standardized data from observational clinical intervention trials remains underexplored, despite its potential to reduce costs and improve patient outcomes. Chronic rhinosinusitis (CRS), a persistent inflammatory disease of the paranasal sinuses lasting more than three months, imposes a substantial burden on quality of life (QoL) and societal cost. Although many patients respond to medical therapy, others with refractory symptoms often pursue surgical intervention. Surgical decision-making in CRS is complex, as it must weigh known procedural risks against uncertain individualized outcomes. In this study, we evaluated supervised machine learning models for predicting surgical benefit in CRS, using the Sino-Nasal Outcome Test-22 (SNOT-22) as the primary patient-reported outcome. Our prospectively collected cohort from an observational intervention trial comprised patients who all underwent surgery; we investigated whether models trained only on preoperative data could identify patients who might not have been recommended surgery prior to the procedure. Across multiple algorithms, including an ensemble approach, our best model achieved approximately 85% classification accuracy, providing accurate and interpretable predictions of surgical candidacy. Moreover, on a held-out set of 30 cases spanning mixed difficulty, our model achieved 80% accuracy, exceeding the average prediction accuracy of expert clinicians (75.6%), demonstrating its potential to augment clinical decision-making and support personalized CRS care.

---

### Understanding Unreliability of Steering Vectors in Language Models: Geometric Predictors and the Limits of Linear Approximations

Authors: Joschka Braun
Published: 2026-02-19
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.17881v1

Steering vectors are a lightweight method for controlling language model behavior by adding a learned bias to the activations at inference time. Although effective on average, steering effect sizes vary across samples and are unreliable for many target behaviors. In my thesis, I investigate why steering reliability differs across behaviors and how it is impacted by steering vector training data. First, I find that higher cosine similarity between training activation differences predicts more reliable steering. Second, I observe that behavior datasets where positive and negative activations are better separated along the steering direction are more reliably steerable. Finally, steering vectors trained on different prompt variations are directionally distinct, yet perform similarly well and exhibit correlated efficacy across datasets. My findings suggest that steering vectors are unreliable when the latent target behavior representation is not effectively approximated by the linear steering direction. Taken together, these insights offer a practical diagnostic for steering unreliability and motivate the development of more robust steering methods that explicitly account for non-linear latent behavior representations.

---

### Interactive Learning of Single-Index Models via Stochastic Gradient Descent

Authors: Nived Rajaraman, Yanjun Han
Published: 2026-02-19
Categories: stat.ML, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2602.17876v1

Stochastic gradient descent (SGD) is a cornerstone algorithm for high-dimensional optimization, renowned for its empirical successes. Recent theoretical advances have provided a deep understanding of how SGD enables feature learning in high-dimensional nonlinear models, most notably the \textit{single-index model} with i.i.d. data. In this work, we study the sequential learning problem for single-index models, also known as generalized linear bandits or ridge bandits, where SGD is a simple and natural solution, yet its learning dynamics remain largely unexplored. We show that, similar to the optimal interactive learner, SGD undergoes a distinct ``burn-in'' phase before entering the ``learning'' phase in this setting. Moreover, with an appropriately chosen learning rate schedule, a single SGD procedure simultaneously achieves near-optimal (or best-known) sample complexity and regret guarantees across both phases, for a broad class of link functions. Our results demonstrate that SGD remains highly competitive for learning single-index models under adaptive data.

---

### MultiVer: Zero-Shot Multi-Agent Vulnerability Detection

Authors: Shreshth Rajan
Published: 2026-02-19
Categories: cs.MA, cs.AI
arXiv: https://arxiv.org/abs/2602.17875v1

We present MultiVer, a zero-shot multi-agent system for vulnerability detection that achieves state-of-the-art recall without fine-tuning. A four-agent ensemble (security, correctness, performance, style) with union voting achieves 82.7% recall on PyVul, exceeding fine-tuned GPT-3.5 (81.3%) by 1.4 percentage points -- the first zeroshot system to surpass fine-tuned performance on this benchmark. On SecurityEval, the same architecture achieves 91.7% detection rate, matching specialized systems. The recall improvement comes at a precision cost: 48.8% precision versus 63.9% for fine-tuned baselines, yielding 61.4% F1. Ablation experiments isolate component contributions: the multi-agent ensemble adds 17 percentage points recall over single-agent security analysis. These results demonstrate that for security applications where false negatives are costlier than false positives, zero-shot multi-agent ensembles can match and exceed fine-tuned models on the metric that matters most.

---

### Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models

Authors: Dhruba Ghosh, Yuhui Zhang, Ludwig Schmidt
Published: 2026-02-19
Categories: cs.CV, cs.AI, cs.LG, cs.MM
arXiv: https://arxiv.org/abs/2602.17871v1

Vision-language models (VLMs) have made substantial progress across a wide range of visual question answering benchmarks, spanning visual reasoning, document understanding, and multimodal dialogue. These improvements are evident in a wide range of VLMs built on a variety of base models, alignment architectures, and training data. However, recent works show that these models trail behind in traditional image classification benchmarks, which test fine-grained visual knowledge. We test a large number of recent VLMs on fine-grained classification benchmarks and identify potential factors in the disconnect between fine-grained knowledge and other vision benchmarks. Through a series of ablation experiments, we find that using a better LLM improves all benchmark scores equally, while a better vision encoder disproportionately improves fine-grained classification performance. Furthermore, we find that the pretraining stage is also vital to fine-grained performance, particularly when the language model weights are unfrozen during pretraining. These insights pave the way for enhancing fine-grained visual understanding and vision-centric capabilities in VLMs.

---

### Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models

Authors: Yuxiao Chen, Jue Wang, Zhikang Zhang, Jingru Yi, Xu Zhang, Yang Zou, Zhaowei Cai, Jianbo Yuan, Xinyu Li, Hao Yang, Davide Modolo
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17869v1

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly prevalent. However, the inherently redundant nature of video sequences poses significant challenges for contemporary state-of-the-art models. These challenges stem from two primary aspects: 1) efficiently incorporating a larger number of frames within memory constraints, and 2) extracting discriminative information from the vast volume of input data. In this paper, we introduce a novel end-to-end schema for long-form video understanding, which includes an information-density-based adaptive video sampler (AVS) and an autoencoder-based spatiotemporal video compressor (SVC) integrated with a multimodal large language model (MLLM). Our proposed system offers two major advantages: it adaptively and effectively captures essential information from video sequences of varying durations, and it achieves high compression rates while preserving crucial discriminative information. The proposed framework demonstrates promising performance across various benchmarks, excelling in both long-form video understanding tasks and standard video understanding benchmarks. These results underscore the versatility and efficacy of our approach, particularly in managing the complexities of prolonged video sequences.

---

### MantisV2: Closing the Zero-Shot Gap in Time Series Classification with Synthetic Data and Test-Time Strategies

Authors: Vasilii Feofanov, Songkang Wen, Jianfeng Zhang, Lujia Pan, Ievgen Redko
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17868v1

Developing foundation models for time series classification is of high practical relevance, as such models can serve as universal feature extractors for diverse downstream tasks. Although early models such as Mantis have shown the promise of this approach, a substantial performance gap remained between frozen and fine-tuned encoders. In this work, we introduce methods that significantly strengthen zero-shot feature extraction for time series. First, we introduce Mantis+, a variant of Mantis pre-trained entirely on synthetic time series. Second, through controlled ablation studies, we refine the architecture and obtain MantisV2, an improved and more lightweight encoder. Third, we propose an enhanced test-time methodology that leverages intermediate-layer representations and refines output-token aggregation. In addition, we show that performance can be further improved via self-ensembling and cross-model embedding fusion. Extensive experiments on UCR, UEA, Human Activity Recognition (HAR) benchmarks, and EEG datasets show that MantisV2 and Mantis+ consistently outperform prior time series foundation models, achieving state-of-the-art zero-shot performance.

---

### ADAPT: Hybrid Prompt Optimization for LLM Feature Visualization

Authors: João N. Cardoso, Arlindo L. Oliveira, Bruno Martins
Published: 2026-02-19
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.17867v1

Understanding what features are encoded by learned directions in LLM activation space requires identifying inputs that strongly activate them. Feature visualization, which optimizes inputs to maximally activate a target direction, offers an alternative to costly dataset search approaches, but remains underexplored for LLMs due to the discrete nature of text. Furthermore, existing prompt optimization techniques are poorly suited to this domain, which is highly prone to local minima. To overcome these limitations, we introduce ADAPT, a hybrid method combining beam search initialization with adaptive gradient-guided mutation, designed around these failure modes. We evaluate on Sparse Autoencoder latents from Gemma 2 2B, proposing metrics grounded in dataset activation statistics to enable rigorous comparison, and show that ADAPT consistently outperforms prior methods across layers and latent types. Our results establish that feature visualization for LLMs is tractable, but requires design assumptions tailored to the domain.

---

### Financial time series augmentation using transformer based GAN architecture

Authors: Andrzej Podobiński, Jarosław A. Chudziak
Published: 2026-02-19
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17865v1

Time-series forecasting is a critical task across many domains, from engineering to economics, where accurate predictions drive strategic decisions. However, applying advanced deep learning models in challenging, volatile domains like finance is difficult due to the inherent limitation and dynamic nature of financial time series data. This scarcity often results in sub-optimal model training and poor generalization. The fundamental challenge lies in determining how to reliably augment scarce financial time series data to enhance the predictive accuracy of deep learning forecasting models. Our main contribution is a demonstration of how Generative Adversarial Networks (GANs) can effectively serve as a data augmentation tool to overcome data scarcity in the financial domain. Specifically, we show that training a Long Short-Term Memory (LSTM) forecasting model on a dataset augmented with synthetic data generated by a transformer-based GAN (TTS-GAN) significantly improves the forecasting accuracy compared to using real data alone. We confirm these results across different financial time series (Bitcoin and S\&P500 price data) and various forecasting horizons. Furthermore, we propose a novel, time series specific quality metric that combines Dynamic Time Warping (DTW) and a modified Deep Dataset Dissimilarity Measure (DeD-iMs) to reliably monitor the training progress and evaluate the quality of the generated data. These findings provide compelling evidence for the benefits of GAN-based data augmentation in enhancing financial predictive capabilities.

---

### JAX-Privacy: A library for differentially private machine learning

Authors: Ryan McKenna, Galen Andrew, Borja Balle, Vadym Doroshenko, Arun Ganesh, Weiwei Kong, Alex Kurakin, Brendan McMahan, Mikhail Pravilov
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17861v1

JAX-Privacy is a library designed to simplify the deployment of robust and performant mechanisms for differentially private machine learning. Guided by design principles of usability, flexibility, and efficiency, JAX-Privacy serves both researchers requiring deep customization and practitioners who want a more out-of-the-box experience. The library provides verified, modular primitives for critical components for all aspects of the mechanism design including batch selection, gradient clipping, noise addition, accounting, and auditing, and brings together a large body of recent research on differentially private ML.

---

### Enhancing Scientific Literature Chatbots with Retrieval-Augmented Generation: A Performance Evaluation of Vector and Graph-Based Systems

Authors: Hamideh Ghanadian, Amin Kamali, Mohammad Hossein Tekieh
Published: 2026-02-19
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2602.17856v1

This paper investigates the enhancement of scientific literature chatbots through retrieval-augmented generation (RAG), with a focus on evaluating vector- and graph-based retrieval systems. The proposed chatbot leverages both structured (graph) and unstructured (vector) databases to access scientific articles and gray literature, enabling efficient triage of sources according to research objectives. To systematically assess performance, we examine two use-case scenarios: retrieval from a single uploaded document and retrieval from a large-scale corpus. Benchmark test sets were generated using a GPT model, with selected outputs annotated for evaluation. The comparative analysis emphasizes retrieval accuracy and response relevance, providing insight into the strengths and limitations of each approach. The findings demonstrate the potential of hybrid RAG systems to improve accessibility to scientific knowledge and to support evidence-based decision making.

---

### TopoGate: Quality-Aware Topology-Stabilized Gated Fusion for Longitudinal Low-Dose CT New-Lesion Prediction

Authors: Seungik Cho
Published: 2026-02-19
Categories: eess.IV, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.17855v1

Longitudinal low-dose CT follow-ups vary in noise, reconstruction kernels, and registration quality. These differences destabilize subtraction images and can trigger false new lesion alarms. We present TopoGate, a lightweight model that combines the follow-up appearance view with the subtraction view and controls their influence through a learned, quality-aware gate. The gate is driven by three case-specific signals: CT appearance quality, registration consistency, and stability of anatomical topology measured with topological metrics. On the NLST--New-Lesion--LongCT cohort comprising 152 pairs from 122 patients, TopoGate improves discrimination and calibration over single-view baselines, achieving an area under the ROC curve of 0.65 with a standard deviation of 0.05 and a Brier score of 0.14. Removing corrupted or low-quality pairs, identified by the quality scores, further increases the area under the ROC curve from 0.62 to 0.68 and reduces the Brier score from 0.14 to 0.12. The gate responds predictably to degradation, placing more weight on appearance when noise grows, which mirrors radiologist practice. The approach is simple, interpretable, and practical for reliable longitudinal LDCT triage.

---

### On the Evaluation Protocol of Gesture Recognition for UAV-based Rescue Operation based on Deep Learning: A Subject-Independence Perspective

Authors: Domonkos Varga
Published: 2026-02-19
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.17854v1

This paper presents a methodological analysis of the gesture-recognition approach proposed by Liu and Szirányi, with a particular focus on the validity of their evaluation protocol. We show that the reported near-perfect accuracy metrics result from a frame-level random train-test split that inevitably mixes samples from the same subjects across both sets, causing severe data leakage. By examining the published confusion matrix, learning curves, and dataset construction, we demonstrate that the evaluation does not measure generalization to unseen individuals. Our findings underscore the importance of subject-independent data partitioning in vision-based gesture-recognition research, especially for applications - such as UAV-human interaction - that require reliable recognition of gestures performed by previously unseen people.

---

### Neural Prior Estimation: Learning Class Priors from Latent Representations

Authors: Masoud Yavari, Payman Moallem
Published: 2026-02-19
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.17853v2

Logit adjustment corrects class imbalance using the empirical class prior. We study whether a comparable class-frequency signal can instead be learned from the network representation, without explicitly supplying class counts to the correction rule. We introduce the Neural Prior Estimator (NPE), which attaches one or more lightweight Prior Estimation Modules (PEMs) to the latent representation. Each PEM is trained with a one-way logistic objective on the ground-truth coordinate. The resulting frequency-dependent outputs are combined into an NPE estimate and used as a learned logit correction, forming NPE-LA. In a simplified scalar model, the optimum of the PEM objective is monotone in the class count and grows asymptotically as $\log N_c$, up to a slower $\log \log N_c$ term. Experiments on long-tailed CIFAR-10 and CIFAR-100 show that NPE-LA is competitive with standard logit adjustment and improves minority-class performance over CE and cRT in the reported settings. Experiments on STARE and ADE20K further show that the same idea can be used as a lightweight recalibration mechanism for dense prediction.

---

### Neural Prior Estimation: Learning Class Priors from Latent Representations

Authors: Masoud Yavari, Payman Moallem
Published: 2026-02-19
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.17853v1

Class imbalance induces systematic bias in deep neural networks by imposing a skewed effective class prior. This work introduces the Neural Prior Estimator (NPE), a framework that learns feature-conditioned log-prior estimates from latent representations. NPE employs one or more Prior Estimation Modules trained jointly with the backbone via a one-way logistic loss. Under the Neural Collapse regime, NPE is analytically shown to recover the class log-prior up to an additive constant, providing a theoretically grounded adaptive signal without requiring explicit class counts or distribution-specific hyperparameters. The learned estimate is incorporated into logit adjustment, forming NPE-LA, a principled mechanism for bias-aware prediction. Experiments on long-tailed CIFAR and imbalanced semantic segmentation benchmarks (STARE, ADE20K) demonstrate consistent improvements, particularly for underrepresented classes. NPE thus offers a lightweight and theoretically justified approach to learned prior estimation and imbalance-aware prediction.

---

### Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Authors: Erik Derner, Dalibor Kučera, Aditya Gulati, Robert A. Bagheri, Nuria Oliver
Published: 2026-02-19
Categories: cs.HC, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.17850v3

Conversational agents increasingly mediate everyday digital interactions, yet the effects of their communication style on user experience and task success remain insufficiently understood. Addressing this gap, we report a between-subject user study in which participants interacted with one of two versions of a chatbot called NAVI, which assisted them in an interactive map-based 2D navigation task. The two chatbot versions were designed to differ primarily in communication style: one used a friendly and supportive tone, while the other used a direct and task-focused tone. We also included a control condition where participants did not interact with a chatbot but received the step-by-step navigation instructions. The friendly chatbot significantly increased users' communication satisfaction and was associated with higher task success than the direct chatbot. However, participants in the control condition achieved the highest task success overall, suggesting that chatbot interaction may introduce overhead in tasks that can be completed effectively using straightforward instructions. We did not find significant evidence that gender moderated the effects of communication style, although exploratory gender-stratified analyses suggested patterns that warrant further investigation. Finally, we found limited evidence of global linguistic accommodation, with only selective feature-level alignment. These findings suggest that chatbot communication style influences users' perceptions of conversational agents and may improve performance relative to less supportive chatbot designs, but the overall value of chatbot interaction depends on the task context. The study highlights the need for task-sensitive, transparent and carefully evaluated communication-style choices in conversational-agent design.

---

### Mind the Style: Impact of Communication Style on Human-Chatbot Interaction

Authors: Erik Derner, Dalibor Kučera, Aditya Gulati, Ayoub Bagheri, Nuria Oliver
Published: 2026-02-19
Categories: cs.HC, cs.AI, cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2602.17850v1

Conversational agents increasingly mediate everyday digital interactions, yet the effects of their communication style on user experience and task success remain unclear. Addressing this gap, we describe the results of a between-subject user study where participants interact with one of two versions of a chatbot called NAVI which assists users in an interactive map-based 2D navigation task. The two chatbot versions differ only in communication style: one is friendly and supportive, while the other is direct and task-focused. Our results show that the friendly style increases subjective satisfaction and significantly improves task completion rates among female participants only, while no baseline differences between female and male participants were observed in a control condition without the chatbot. Furthermore, we find little evidence of users mimicking the chatbot's style, suggesting limited linguistic accommodation. These findings highlight the importance of user- and task-sensitive conversational agents and support that communication style personalization can meaningfully enhance interaction quality and performance.

---

### Quad Length Codes for Lossless Compression of e4m3

Authors: Aditya Agrawal, Albert Magyar, Hiteshwar Eswaraiah, Patrick Sheridan, Pradeep Janedula, Ravi Krishnan Venkatesan, Krishna Nair, Ravi Iyer
Published: 2026-02-19
Categories: cs.LG, cs.IT
arXiv: https://arxiv.org/abs/2602.17849v2

Training and serving Large Language Models (LLMs) relies heavily on parallelization and collective operations, which are frequently bottlenecked by network bandwidth. Lossless compression using e.g., Huffman codes can alleviate the issue, however, Huffman codes suffer from slow, bit-sequential decoding and high hardware complexity due to deep tree traversals. Universal codes e.g., Exponential-Golomb codes are faster to decode but do not exploit the symbol frequency distributions. To address these limitations, this paper introduces Quad Length Codes, a hybrid approach designed to balance compression efficiency with decoding speed. The coding scheme uses 3 prefix bits to divide the 256 symbols into 8 areas. Each area has a different code length and encodes a different number of symbols. The scheme uses a Look Up Table with 256 entries, significantly simplifying the hardware implementation compared to Huffman trees. The coding scheme can be adapted for different distributions. For the e4m3 data type, the scheme achieves a compressibility of 13.9% in comparison to 15.9% achieved by Huffman codes, but it significantly speeds up the decoding and simplifies the hardware complexity.

---

### On the scaling relationship between cloze probabilities and language model next-token prediction

Authors: Cassandra L. Jacobs, Morgan Grobol
Published: 2026-02-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.17848v1

Recent work has shown that larger language models have better predictive power for eye movement and reading time data. While even the best models under-allocate probability mass to human responses, larger models assign higher-quality estimates of next tokens and their likelihood of production in cloze data because they are less sensitive to lexical co-occurrence statistics while being better aligned semantically to human cloze responses. The results provide support for the claim that the greater memorization capacity of larger models helps them guess more semantically appropriate words, but makes them less sensitive to low-level information that is relevant for word recognition.

---

### Two Calm Ends and the Wild Middle: A Geometric Picture of Memorization in Diffusion Models

Authors: Nick Dodson, Xinyu Gao, Qingsong Wang, Yusu Wang, Zhengchao Wan
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17846v1

Diffusion models generate high-quality samples but can also memorize training data, raising serious privacy concerns. Understanding the mechanisms governing when memorization versus generalization occurs remains an active area of research. In particular, it is unclear where along the noise schedule memorization is induced, how data geometry influences it, and how phenomena at different noise scales interact. We introduce a geometric framework that partitions the noise schedule into three regimes based on the coverage properties of training data by Gaussian shells and the concentration behavior of the posterior, which we argue are two fundamental objects governing memorization and generalization in diffusion models. This perspective reveals that memorization risk is highly non-uniform across noise levels. We further identify a danger zone at medium noise levels where memorization is most pronounced. In contrast, both the small and large noise regimes resist memorization, but through fundamentally different mechanisms: small noise avoids memorization due to limited training coverage, while large noise exhibits low posterior concentration and admits a provably near linear Gaussian denoising behavior. For the medium noise regime, we identify geometric conditions through which we propose a geometry-informed targeted intervention that mitigates memorization.

---

### TFL: Targeted Bit-Flip Attack on Large Language Model

Authors: Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Published: 2026-02-19
Categories: cs.CR, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.17837v1

Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs), which exploit computer main memory (i.e., DRAM) vulnerabilities to flip a small number of bits in model weights, can severely disrupt LLM behavior. However, existing BFA on LLM largely induce un-targeted failure or general performance degradation, offering limited control over manipulating specific or targeted outputs. In this paper, we present TFL, a novel targeted bit-flip attack framework that enables precise manipulation of LLM outputs for selected prompts while maintaining almost no or minor degradation on unrelated inputs. Within our TFL framework, we propose a novel keyword-focused attack loss to promote attacker-specified target tokens in generative outputs, together with an auxiliary utility score that balances attack effectiveness against collateral performance impact on benign data. We evaluate TFL on multiple LLMs (Qwen, DeepSeek, Llama) and benchmarks (DROP, GSM8K, and TriviaQA). The experiments show that TFL achieves successful targeted LLM output manipulations with less than 50 bit flips and significantly reduced effect on unrelated queries compared to prior BFA approaches. This demonstrates the effectiveness of TFL and positions it as a new class of stealthy and targeted LLM model attack.

---

### Influence-Preserving Proxies for Gradient-Based Data Selection in LLM Fine-tuning

Authors: Sirui Chen, Yunzhe Qi, Mengting Ai, Yifan Sun, Ruizhong Qiu, Jiaru Zou, Jingrui He
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17835v1

Supervised fine-tuning (SFT) relies critically on selecting training data that most benefits a model's downstream performance. Gradient-based data selection methods such as TracIn and Influence Functions leverage influence to identify useful samples, but their computational cost scales poorly, making them impractical for multi-billion-parameter large language models (LLMs). A common alternative is to use off-the-shelf smaller models as proxies, but they remain suboptimal since their learning dynamics are unclear, their sizes cannot be flexibly adjusted, and they cannot be further aligned with the target model in terms of gradient-based influence estimation. To address these challenges, we introduce Iprox, a two-stage framework that derives influence-preserving proxies directly from the target model. It first applies a low-rank compression stage to preserve influence information of the target model, and then an aligning stage to align both model gradients and logits, thereby constructing proxies that flexibly control computational cost while retaining the target model's influence. Experimental results across diverse LLM families and evaluation tasks show that Iprox consistently outperforms off-the-shelf proxies and baseline methods. On Qwen3-4B, a 1.5B proxy constructed with Iprox achieves stronger performance than the larger 1.7B off-the-shelf proxy. Notably, on Llama3.2, Iprox achieves better performance than baselines while reducing computational cost by more than half relative to the full 3B model. These results show that Iprox provides effective influence-preserving proxies, making gradient-based data selection more scalable for LLMs.

---

### MePoly: Max Entropy Polynomial Policy Optimization

Authors: Hang Liu, Sangli Teng, Maani Ghaffari
Published: 2026-02-19
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2602.17832v1

Stochastic Optimal Control provides a unified mathematical framework for solving complex decision-making problems, encompassing paradigms such as maximum entropy reinforcement learning(RL) and imitation learning(IL). However, conventional parametric policies often struggle to represent the multi-modality of the solutions. Though diffusion-based policies are aimed at recovering the multi-modality, they lack an explicit probability density, which complicates policy-gradient optimization. To bridge this gap, we propose MePoly, a novel policy parameterization based on polynomial energy-based models. MePoly provides an explicit, tractable probability density, enabling exact entropy maximization. Theoretically, we ground our method in the classical moment problem, leveraging the universal approximation capabilities for arbitrary distributions. Empirically, we demonstrate that MePoly effectively captures complex non-convex manifolds and outperforms baselines in performance across diverse benchmarks.

---

### The Token Games: Evaluating Language Model Reasoning with Puzzle Duels

Authors: Simon Henniger, Gabriel Poesia
Published: 2026-02-19
Categories: cs.AI
arXiv: https://arxiv.org/abs/2602.17831v2

Evaluating the reasoning capabilities of Large Language Models is increasingly challenging as models improve. Human curation of hard questions is highly expensive, especially in recent benchmarks using PhD-level domain knowledge to challenge the most capable models. Even then, there is always a concern about whether these questions test genuine reasoning or if similar problems have been seen during training. Here, we take inspiration from 16th-century mathematical duels to design The Token Games (TTG): an evaluation framework where models challenge each other by creating their own puzzles. We leverage the format of Programming Puzzles - given a function that returns a boolean, find inputs that make it return True - to flexibly represent problems and enable verifying solutions. Using results from pairwise duels, we then compute Elo ratings, allowing us to compare models relative to each other. We evaluate 10 frontier models on TTG, and closely match the ranking from existing benchmarks such as Humanity's Last Exam, spending less than $200 USD and without involving any human effort in creating puzzles. We also find that creating good puzzles is still a highly challenging task for current models. Overall, our work suggests new paradigms for evaluating reasoning that avoid saturation by design, and that allow testing models for other skills like creativity and task creation alongside problem solving.

---

### Drift Estimation for Stochastic Differential Equations with Denoising Diffusion Models

Authors: Marcos Tapia Costa, Nikolas Kantas, George Deligiannidis
Published: 2026-02-19
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2602.17830v1

We study the estimation of time-homogeneous drift functions in multivariate stochastic differential equations with known diffusion coefficient, from multiple trajectories observed at high frequency over a fixed time horizon. We formulate drift estimation as a denoising problem conditional on previous observations, and propose an estimator of the drift function which is a by-product of training a conditional diffusion model capable of simulating new trajectories dynamically. Across different drift classes, the proposed estimator was found to match classical methods in low dimensions and remained consistently competitive in higher dimensions, with gains that cannot be attributed to architectural design choices alone.

---

### Causality by Abstraction: Symbolic Rule Learning in Multivariate Timeseries with Large Language Models

Authors: Preetom Biswas, Giulia Pedrielli, K. Selçuk Candan
Published: 2026-02-19
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17829v1

Inferring causal relations in timeseries data with delayed effects is a fundamental challenge, especially when the underlying system exhibits complex dynamics that cannot be captured by simple functional mappings. Traditional approaches often fail to produce generalized and interpretable explanations, as multiple distinct input trajectories may yield nearly indistinguishable outputs. In this work, we present ruleXplain, a framework that leverages Large Language Models (LLMs) to extract formal explanations for input-output relations in simulation-driven dynamical systems. Our method introduces a constrained symbolic rule language with temporal operators and delay semantics, enabling LLMs to generate verifiable causal rules through structured prompting. ruleXplain relies on the availability of a principled model (e.g., a simulator) that maps multivariate input time series to output time series. Within ruleXplain, the simulator is used to generate diverse counterfactual input trajectories that yield similar target output, serving as candidate explanations. Such counterfactual inputs are clustered and provided as context to the LLM, which is tasked with the generation of symbolic rules encoding the joint temporal trends responsible for the patterns observable in the output times series. A closed-loop refinement process ensures rule consistency and semantic validity. We validate the framework using the PySIRTEM epidemic simulator, mapping testing rate inputs to daily infection counts; and the EnergyPlus building energy simulator, observing temperature and solar irradiance inputs to electricity needs. For validation, we perform three classes of experiments: (1) the efficacy of the ruleset through input reconstruction; (2) ablation studies evaluating the causal encoding of the ruleset; and (3) generalization tests of the extracted rules across unseen output trends with varying phase dynamics.

---

### Avoid What You Know: Divergent Trajectory Balance for GFlowNets

Authors: Pedro Dall'Antonia, Tiago da Silva, Daniel Csillag, Salem Lahlou, Diego Mesquita
Published: 2026-02-19
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2602.17827v1

Generative Flow Networks (GFlowNets) are a flexible family of amortized samplers trained to generate discrete and compositional objects with probability proportional to a reward function. However, learning efficiency is constrained by the model's ability to rapidly explore diverse high-probability regions during training. To mitigate this issue, recent works have focused on incentivizing the exploration of unvisited and valuable states via curiosity-driven search and self-supervised random network distillation, which tend to waste samples on already well-approximated regions of the state space. In this context, we propose Adaptive Complementary Exploration (ACE), a principled algorithm for the effective exploration of novel and high-probability regions when learning GFlowNets. To achieve this, ACE introduces an exploration GFlowNet explicitly trained to search for high-reward states in regions underexplored by the canonical GFlowNet, which learns to sample from the target distribution. Through extensive experiments, we show that ACE significantly improves upon prior work in terms of approximation accuracy to the target distribution and discovery rate of diverse high-reward states.

---

### Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

Authors: Marcelo Labre
Published: 2026-02-19
Categories: cs.AI, cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2602.17826v2

Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with three open-source models reveals that ontology-guided context improves performance when retrieval quality is high, but irrelevant context actively degrades it -- highlighting both the promise and challenges of neuro-symbolic approaches.

---

### Ontology-Guided Neuro-Symbolic Inference: Grounding Language Models with Mathematical Domain Knowledge

Authors: Marcelo Labre
Published: 2026-02-19
Categories: cs.AI, cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2602.17826v1

Language models exhibit fundamental limitations -- hallucination, brittleness, and lack of formal grounding -- that are particularly problematic in high-stakes specialist fields requiring verifiable reasoning. I investigate whether formal domain ontologies can enhance language model reliability through retrieval-augmented generation. Using mathematics as proof of concept, I implement a neuro-symbolic pipeline leveraging the OpenMath ontology with hybrid retrieval and cross-encoder reranking to inject relevant definitions into model prompts. Evaluation on the MATH benchmark with three open-source models reveals that ontology-guided context improves performance when retrieval quality is high, but irrelevant context actively degrades it -- highlighting both the promise and challenges of neuro-symbolic approaches.

---

### Neural Synchrony Between Socially Interacting Language Models

Authors: Zhining Zhang, Wentao Zhu, Chi Han, Yizhou Wang, Heng Ji
Published: 2026-02-19
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.17815v1

Neuroscience has uncovered a fundamental mechanism of our social nature: human brain activity becomes synchronized with others in many social contexts involving interaction. Traditionally, social minds have been regarded as an exclusive property of living beings. Although large language models (LLMs) are widely accepted as powerful approximations of human behavior, with multi-LLM system being extensively explored to enhance their capabilities, it remains controversial whether they can be meaningfully compared to human social minds. In this work, we explore neural synchrony between socially interacting LLMs as an empirical evidence for this debate. Specifically, we introduce neural synchrony during social simulations as a novel proxy for analyzing the sociality of LLMs at the representational level. Through carefully designed experiments, we demonstrate that it reliably reflects both social engagement and temporal alignment in their interactions. Our findings indicate that neural synchrony between LLMs is strongly correlated with their social performance, highlighting an important link between neural synchrony and the social behaviors of LLMs. Our work offers a new perspective to examine the "social minds" of LLMs, highlighting surprising parallels in the internal dynamics that underlie human and LLM social interaction.

---