# Research Papers — 2026-02 · bundle page 168 of 210

> Full-text markdown of papers #8351–8400 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/168
[← Previous bundle](https://aipod.dev/papers/archive/2026-02/page/167.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-02/page/169.md)

### Forecasting Future Language: Context Design for Mention Markets

Authors: Sumin Kim, Jihoon Kwon, Yoon Kim, Nicole Kagan, Raffi Khatchadourian, Wonbin Ahn, Alejandro Lopez-Lira, Jaewon Lee, Yoontae Hwang, Oscar Levy, Yongjae Lee, Chanyeol Choi
Published: 2026-02-04
Categories: q-fin.GN, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.21229v2

Mention markets, a type of prediction market in which contracts resolve based on whether a specified keyword is mentioned during a future public event, require accurate probabilistic forecasts of keyword-mention outcomes. While recent work shows that large language models (LLMs) can generate forecasts competitive with human forecasters, it remains unclear how input context should be designed to support accurate prediction. In this paper, we study this question through experiments on earnings-call mention markets, which require forecasting whether a company will mention a specified keyword during its upcoming call. We run controlled comparisons varying (i) which contextual information is provided (news and/or prior earnings-call transcripts) and (ii) how \textit{market probability}, (i.e., prediction market contract price) is used. We introduce Market-Conditioned Prompting (MCP), which explicitly treats the market-implied probability as a prior and instructs the LLM to update this prior using textual evidence, rather than re-predicting the base rate from scratch. In our experiments, we find three insights: (1) richer context consistently improves forecasting performance; (2) market-conditioned prompting (MCP), which treats the market probability as a prior and updates it using textual evidence, yields better-calibrated forecasts; and (3) a mixture of the market probability and MCP (MixMCP) outperforms the market baseline. By dampening the LLM's posterior update with the market prior, MixMCP yields more robust predictions than either the market or the LLM alone.

---

### ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following

Authors: Yuancheng Yang, Lin Yang, Xu Wang, Chao Tong, Haihua Yang
Published: 2026-02-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.21228v2

As applications of large language models (LLMs) become increasingly complex, the demand for robust complex instruction following capabilities is growing accordingly. We argue that a thorough understanding of the instruction itself, especially the latent reasoning structure embedded between the lines, is crucial for improving instruction following. Therefore we target complex instructions that involve implicit reasoning, intricate logical relations, and multi-constraint dependencies. We propose ImpRIF, a method to enhance LLMs' understanding of implicit reasoning instructions, thereby improving its ability to follow complex instructions. We formalize such instructions as verifiable reasoning graphs, enabling programmatic verification and graph-driven chain-of-thought reasoning. Based on this formulation, we synthesize large-scale single- and multi-turn data, propose fine-tuning with graph reasoning, and apply reinforcement learning to explicitly train models to reason along the graph. On five complex instruction following benchmarks, our models substantially outperform their base models. These results demonstrate that enhancing implicit reasoning capabilities can significantly improve complex instruction following.

---

### Budget-Aware Agentic Routing via Boundary-Guided Training

Authors: Caiqi Zhang, Menglin Xia, Xuchao Zhang, Daniel Madrigal, Ankur Mallick, Samuel Kessler, Victor Ruehle, Saravan Rajmohan
Published: 2026-02-04
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2602.21227v1

As large language models (LLMs) evolve into autonomous agents that execute long-horizon workflows, invoking a high-capability model at every step becomes economically unsustainable. While model routing is effective for single-turn queries, agentic routing is a sequential, path-dependent problem: early mistakes compound, feedback is often at the end of the episode, and deployments often demand strict per-task spending limits. We propose Budget-Aware Agentic Routing, which selects between a cheap and an expensive model at each step to optimize the cost--success frontier and to operate under strict per-task budgets. We propose Boundary-Guided Training, which leverages two boundary policies (always-small vs.\ always-large) to build a difficulty taxonomy and to anchor learning under sparse rewards. Our approach warms start with boundary-guided SFT data synthesis via stratified sampling of cost-efficient trajectories, then applies Boundary-Guided Policy Optimization (BoPO), combining boundary-relative rewards with a reference-guided advantage to avoid degenerate cheap-failure solutions. Experiment results show that our method improves the efficiency frontier, matching strong routing baselines at substantially lower cost while demonstrating generalization to strict inference-time budget constraints. Overall, our work establishes a foundational framework for agentic routing, shifting the paradigm from static model selection to dynamic, budget-aware sequential decision-making.

---

### VISION-ICE: Video-based Interpretation and Spatial Identification of Arrhythmia Origins via Neural Networks in Intracardiac Echocardiography

Authors: Dorsa EPMoghaddam, Feng Gao, Drew Bernard, Kavya Sinha, Mehdi Razavi, Behnaam Aazhang
Published: 2026-02-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.20165v1

Contemporary high-density mapping techniques and preoperative CT/MRI remain time and resource intensive in localizing arrhythmias. AI has been validated as a clinical decision aid in providing accurate, rapid real-time analysis of echocardiographic images. Building on this, we propose an AI-enabled framework that leverages intracardiac echocardiography (ICE), a routine part of electrophysiology procedures, to guide clinicians toward areas of arrhythmogenesis and potentially reduce procedural time. Arrhythmia source localization is formulated as a three-class classification task, distinguishing normal sinus rhythm, left-sided, and right-sided arrhythmias, based on ICE video data. We developed a 3D Convolutional Neural Network trained to discriminate among the three aforementioned classes. In ten-fold cross-validation, the model achieved a mean accuracy of 66.2% when evaluated on four previously unseen patients (substantially outperforming the 33.3% random baseline). These results demonstrate the feasibility and clinical promise of using ICE videos combined with deep learning for automated arrhythmia localization. Leveraging ICE imaging could enable faster, more targeted electrophysiological interventions and reduce the procedural burden of cardiac ablation. Future work will focus on expanding the dataset to improve model robustness and generalizability across diverse patient populations.

---

### Exploring the Ethical Concerns in User Reviews of Mental Health Apps using Topic Modeling and Sentiment Analysis

Authors: Mohammad Masudur Rahman, Beenish Moalla Chaudhry
Published: 2026-02-04
Categories: cs.CY, cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2602.18454v1

The rapid growth of AI-driven mental health mobile apps has raised concerns about their ethical considerations and user trust. This study proposed a natural language processing (NLP)-based framework to evaluate ethical aspects from user-generated reviews from the Google Play Store and Apple App Store. After gathering and cleaning the data, topic modeling was applied to identify latent themes in the context of ethics using topic words and then map them to well-recognized existing ethical principles described in different ethical frameworks; in addition to that, a bottom-up approach is applied to find any new and emergent ethics from the reviews using a transformer-based zero-shot classification model. Sentiment analysis was then used to capture how users feel about each ethical aspect. The obtained results reveal that well-known ethical considerations are not enough for the modern AI-based technologies and are missing emerging ethical challenges, showing how these apps either uphold or overlook key moral values. This work contributes to developing an ongoing evaluation system that can enhance the fairness, transparency, and trustworthiness of AI-powered mental health chatbots.

---

### LLM-Assisted Replication for Quantitative Social Science

Authors: So Kubota, Hiromu Yakura, Samuel Coavoux, Sho Yamada, Yuki Nakamura
Published: 2026-02-04
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2602.18453v1

The replication crisis, the failure of scientific claims to be validated by further research, is one of the most pressing issues for empirical research. This is partly an incentive problem: replication is costly and less well rewarded than original research. Large language models (LLMs) have accelerated scientific production by streamlining writing, coding, and reviewing, yet this acceleration risks outpacing verification. To address this, we present an LLM-based system that replicates statistical analyses from social science papers and flags potential problems. Quantitative social science is particularly well-suited to automation because it relies on standard statistical models, shared public datasets, and uniform reporting formats such as regression tables and summary statistics. We present a prototype that iterates LLM-based text interpretation, code generation, execution, and discrepancy analysis, demonstrating its capabilities by reproducing key results from a seminal sociology paper. We also outline application scenarios including pre-submission checks, peer-review support, and meta-scientific audits, positioning AI verification as assistive infrastructure that strengthens research integrity.

---

### RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity

Authors: Gaia A. Bertolino, Yuwei Zhang, Tong Xia, Domenico Talia, Cecilia Mascolo
Published: 2026-02-04
Categories: cs.SD, cs.LG, eess.AS
arXiv: https://arxiv.org/abs/2602.18452v3

As conversational multimodal AI tools are increasingly adopted to process patient data for health assessment, robust benchmarks are needed to measure progress and expose failure modes under realistic conditions. Despite the importance of respiratory audio for mobile health screening, respiratory audio question answering remains underexplored, with existing studies evaluated narrowly and lacking real-world heterogeneity across modalities, devices, and question types. We hence introduce the \textbf{Respiratory-Audio Question-Answering (RA-QA) benchmark}, including a standardized data generation pipeline, a comprehensive multimodal QA collection, and a unified evaluation protocol. RA-QA harmonizes public RA datasets into a collection of 9 million format-diverse QA pairs covering diagnostic and contextual attributes. We benchmark general audio-language models as well as domain-specific architectures, establishing reproducible reference points and showing how current approaches fail under heterogeneity.

---

### Optimal Multi-Debris Mission Planning in LEO: A Deep Reinforcement Learning Approach with Co-Elliptic Transfers and Refueling

Authors: Agni Bandyopadhyay, Gunther Waxenegger-Wilfing
Published: 2026-02-04
Categories: cs.LG, cs.RO, physics.space-ph
arXiv: https://arxiv.org/abs/2602.17685v1

This paper addresses the challenge of multi target active debris removal (ADR) in Low Earth Orbit (LEO) by introducing a unified coelliptic maneuver framework that combines Hohmann transfers, safety ellipse proximity operations, and explicit refueling logic. We benchmark three distinct planning algorithms Greedy heuristic, Monte Carlo Tree Search (MCTS), and deep reinforcement learning (RL) using Masked Proximal Policy Optimization (PPO) within a realistic orbital simulation environment featuring randomized debris fields, keep out zones, and delta V constraints. Experimental results over 100 test scenarios demonstrate that Masked PPO achieves superior mission efficiency and computational performance, visiting up to twice as many debris as Greedy and significantly outperforming MCTS in runtime. These findings underscore the promise of modern RL methods for scalable, safe, and resource efficient space mission planning, paving the way for future advancements in ADR autonomy.

---

### CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

Authors: Xiao Zhu, Xinyu Zhou, Boyu Zhu, Hanxu Hu, Mingzhe Du, Haotian Zhang, Huiming Wang, Zhijiang Guo
Published: 2026-02-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17684v3

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality test cases. We propose CodeScaler, a reward model designed to scale both reinforcement learning training and test-time inference for code generation. CodeScaler is trained on carefully curated preference data derived from verified code problems and incorporates syntax-aware code extraction and validity-preserving reward shaping to ensure stable and robust optimization. Across four coding benchmarks, CodeScaler consistently outperforms execution-based RL by +1.55 points on Qwen3-8B-Base and +4.23 points on Qwen3-14B-Base. By further scaling to 44K problems with additional synthetic data, CodeScaler yields +14.64 points improvement over the base model without requiring any test cases. At inference time, CodeScaler serves as an effective test-time scaling method, achieving performance comparable to unit test approaches while providing a 10-fold reduction in latency. Moreover, CodeScaler surpasses existing reward models on RM-Bench not only in the code domain (+3.3 points), but also in general and reasoning domains (+2.7 points on average).

---

### CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models

Authors: Xiao Zhu, Xinyu Zhou, Boyu Zhu, Hanxu Hu, Mingzhe Du, Haotian Zhang, Huiming Wang, Zhijiang Guo
Published: 2026-02-04
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2602.17684v2

Reinforcement Learning from Verifiable Rewards (RLVR) has driven recent progress in code large language models by leveraging execution-based feedback from unit tests, but its scalability is fundamentally constrained by the availability and reliability of high-quality test cases. We propose CodeScaler, a reward model designed to scale both reinforcement learning training and test-time inference for code generation. CodeScaler is trained on carefully curated preference data derived from verified code problems and incorporates syntax-aware code extraction and validity-preserving reward shaping to ensure stable and robust optimization. Across four coding benchmarks, CodeScaler consistently outperforms execution-based RL by +1.55 points on Qwen3-8B-Base and +4.23 points on Qwen3-14B-Base. By further scaling to 44K problems with additional synthetic data, CodeScaler yields +14.64 points improvement over the base model without requiring any test cases. At inference time, CodeScaler serves as an effective test-time scaling method, achieving performance comparable to unit test approaches while providing a 10-fold reduction in latency. Moreover, CodeScaler surpasses existing reward models on RM-Bench not only in the code domain (+3.3 points), but also in general and reasoning domains (+2.7 points on average).

---

### Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates

Authors: Irene Iele, Giulia Romoli, Daniele Molino, Elena Mulero Ayllón, Filippo Ruffini, Paolo Soda, Matteo Tortora
Published: 2026-02-04
Categories: cs.LG, cs.CV, stat.ML
arXiv: https://arxiv.org/abs/2602.17683v3

Short-term forecasting of vegetation dynamics is a key enabler for data-driven decision support in precision agriculture. Normalized Difference Vegetation Index (NDVI) forecasting from satellite observations, however, remains challenging due to sparse and irregular sampling caused by cloud masking, as well as the heterogeneous climatic conditions under which crops evolve. In this work, we propose a probabilistic forecasting framework for field-level NDVI prediction under sparse, irregular clear-sky acquisitions. The architecture separates the encoding of historical NDVI and meteorological observations from future exogenous covariates, fusing both representations for multi-step quantile prediction. To address irregular revisit patterns and horizon-dependent uncertainty, we introduce a temporal-distance weighted quantile loss that aligns the training objective with the effective forecasting horizon. In addition, we incorporate cumulative and extreme-weather feature engineering to capture delayed meteorological effects relevant to vegetation response. Experiments on European satellite data show that the proposed approach outperforms statistical, deep learning, and time-series baselines on both pointwise and probabilistic evaluation metrics. Ablation studies confirm that target history is the primary driver of performance, with meteorological covariates providing additional gains in the full multimodal setting. The code is available at https://github.com/arco-group/ndvi-forecasting.

---

### Duality Models: An Embarrassingly Simple One-step Generation Paradigm

Authors: Peng Sun, Xinyi Shang, Tao Lin, Zhiqiang Shen
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17682v1

Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current time $t$ to modulate outputs between a local multi-step derivative ($r = t$) and a global few-step integral ($r = 0$). However, the conventional "one input, one output" paradigm enforces a partition of the training budget, often allocating a significant portion (e.g., 75% in MeanFlow) solely to the multi-step objective for stability. This separation forces a trade-off: allocating sufficient samples to the multi-step objective leaves the few-step generation undertrained, which harms convergence and limits scalability. To this end, we propose Duality Models (DuMo) via a "one input, dual output" paradigm. Using a shared backbone with dual heads, DuMo simultaneously predicts velocity $v_t$ and flow-map $u_t$ from a single input $x_t$. This applies geometric constraints from the multi-step objective to every sample, bounding the few-step estimation without separating training objectives, thereby significantly improving stability and efficiency. On ImageNet 256 $\times$ 256, a 679M Diffusion Transformer with SD-VAE achieves a state-of-the-art (SOTA) FID of 1.79 in just 2 steps. Code is available at: https://github.com/LINs-lab/DuMo

---

### LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs

Authors: Ofir Gordon, Lior Dikstein, Arnon Netzer, Idan Achituve, Hai Victor Habi
Published: 2026-02-04
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2602.17681v2

Post-training quantization (PTQ) is a widely used approach for reducing the memory and compute costs of large language models (LLMs). Recent studies have shown that applying invertible transformations to activations can significantly improve quantization robustness by reducing activation outliers; however, existing approaches are largely restricted to rotation or Hadamard-based transformations. Moreover, most studies focused primarily on traditional quantization schemes, whereas modern hardware increasingly supports the microscaling (MX) data format. Attempts to combine both showed severe performance degradation, leading prior work to introduce assumptions on the transformations. In this work, we take a complementary perspective. First, we provide a theoretical analysis of transformations under MX quantization by deriving a bound on the quantization error. Our analysis emphasizes the importance of accounting for both the activation distribution and the underlying quantization structure. Building on this analysis, we propose LATMiX, a method that generalizes outlier reduction to learnable invertible affine transformations optimized using standard deep learning tools. Experiments show consistent improvements in average accuracy for MX low-bit quantization over strong baselines on a wide range of zero-shot benchmarks, across multiple model sizes.

---

### BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMs

Authors: Yujia Wang, Jihong Guan, Wengen Li, Shuigeng Zhou, Xuhong Wang
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.17680v1

Existing Protein Language Models (PLMs) often suffer from limited adaptability to multiple tasks and exhibit poor generalization across diverse biological contexts. In contrast, general-purpose Large Language Models (LLMs) lack the capability to interpret protein sequences and fall short in domain-specific knowledge, limiting their capacity for effective biosemantic reasoning. To combine the advantages of both, we propose BioBridge, a domain-adaptive continual pretraining framework for protein understanding. This framework employs Domain-Incremental Continual Pre-training (DICP) to infuse protein domain knowledge and general reasoning corpus into a LLM simultaneously, effectively mitigating catastrophic forgetting. Cross-modal alignment is achieved via a PLM-Projector-LLM pipeline, which maps protein sequence embeddings into the semantic space of the language model. Ultimately, an end-to-end optimization is adopted to uniformly support various tasks, including protein property prediction and knowledge question-answering. Our proposed BioBridge demonstrates performance comparable to that of mainstream PLMs on multiple protein benchmarks, such as EC and BindingDB. It also achieves results on par with LLMs on general understanding tasks like MMLU and RACE. This showcases its innovative advantage of combining domain-specific adaptability with general-purpose language competency.

---

### Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization

Authors: Saksham Kiroriwal, Julius Pfrommer, Jürgen Beyerer
Published: 2026-02-04
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2602.17679v2

Bayesian optimization (BO) is a powerful method for optimizing black-box manufacturing processes, but its performance is often limited when dealing with high-dimensional multi-stage systems, where we can observe intermediate outputs. Standard BO models the process as a black box and ignores the intermediate observations and the underlying process structure. Partially Observable Gaussian Process Networks (POGPN) model the process as a Directed Acyclic Graph (DAG). However, using intermediate observations is challenging when the observations are high-dimensional state-space time series. Process-expert knowledge can be used to extract low-dimensional latent features from the high-dimensional state-space data. We propose POGPN-JPSS, a framework that combines POGPN with Joint Parameter and State-Space (JPSS) modeling to use intermediate extracted information. We demonstrate the effectiveness of POGPN-JPSS on a challenging, high-dimensional simulation of a multi-stage bioethanol production process. Our results show that POGPN-JPSS significantly outperforms state-of-the-art methods by achieving the desired performance threshold twice as fast and with greater reliability. The fast optimization directly translates to substantial savings in time and resources. This highlights the importance of combining expert knowledge with structured probabilistic models for rapid process maturation.

---

### A Quantum-inspired Hybrid Swarm Intelligence and Decision-Making for Multi-Criteria ADAS Calibration

Authors: Sanjai Pathak, Ashish Mani, Amlan Chatterjee
Published: 2026-02-04
Categories: cs.NE
arXiv: https://arxiv.org/abs/2602.15043v1

The tuning of Advanced Driver Assistance Systems (ADAS) involves resolving trade-offs among several competing objectives, including operational safety, system responsiveness, energy usage, and passenger comfort. This work introduces a novel optimization framework based on Quantum-Inspired Hybrid Swarm Intelligence (QiHSI), in which quantum-inspired mechanisms are embedded within a multi-objective salp swarm optimization process to strengthen global search capability and preserve population diversity in complex, high-dimensional decision spaces. In addition, a decision-maker-in-the-loop strategy is incorporated to incorporate adaptive expert guidance, enabling the optimization process to respond dynamically to changing design priorities and system constraints. The effectiveness of QiHSI is assessed using established multi-objective benchmark problems as well as a practical ADAS calibration scenario. Experimental comparisons with several state-of-the-art evolutionary and swarm-based algorithms, including MSSA, MOPSO, MOEA/D, SPEA2, NSGA-III, and RVEA, show that the proposed method consistently produces well-distributed Pareto-optimal solutions with faster convergence and improved adaptability. These findings demonstrate that QiHSI offers a reliable and scalable approach for intelligent ADAS calibration, supporting the development of more responsive, efficient, and safety-oriented autonomous driving technologies.

---

### Combining scEEG and PPG for reliable sleep staging using lightweight wearables

Authors: Jiawei Wang, Liang Xu, Shuntian Zheng, Yu Guan, Kaichen Wang, Ziqing Zhang, Chen Chen, Laurence T. Yang, Sai Gu
Published: 2026-02-04
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2602.15042v1

Reliable sleep staging remains challenging for lightweight wearable devices such as single-channel electroencephalography (scEEG) or photoplethysmography (PPG). scEEG offers direct measurement of cortical activity and serves as the foundation for sleep staging, yet exhibits limited performance on light sleep stages. PPG provides a low-cost complement that captures autonomic signatures effective for detecting light sleep. However, prior PPG-based methods rely on full night recordings (8 - 10 hours) as input context, which is less practical to provide timely feedback for sleep intervention. In this work, we investigate scEEG-PPG fusion for 4-class sleep staging under short-window (30 s - 30 min) constraints. First, we evaluate the temporal context required for each modality, to better understand the relationship of sleep staging performance with respect to monitoring window. Second, we investigate three fusion strategies: score-level fusion, cross-attention fusion enabling feature-level interactions, and Mamba-enhanced fusion incorporating temporal context modeling. Third, we train and evaluate on the Multi-Ethnic Study of Atherosclerosis (MESA) dataset and perform cross-dataset validation on the Cleveland Family Study (CFS) and the Apnea, Bariatric surgery, and CPAP (ABC) datasets. The Mamba-enhanced fusion achieves the best performance on MESA (Cohen's Kappa $κ$ = 0.798, Acc = 86.9%), with particularly notable improvement in light sleep classification (F1-score: 85.63% vs. 77.76%, recall: 82.85% vs. 69.95% for scEEG alone), and generalizes well to CFS and ABC datasets with different populations. These findings suggest that scEEG-PPG fusion is a promising approach for lightweight wearable based sleep monitoring, offering a pathway toward more accessible sleep health assessment. Source code of this project can be found at: https://github.com/DavyWJW/scEEG-PPGFusion

---

### Symmetric Composition of Anisotropic Operators for Global Subseasonal-to-Seasonal Climate Forecasting

Authors: Ziyu Zhou, Yuchen Fang, Weilin Ruan, Tian Zhou, Shiyu Wang, James Kwok, Yuxuan Liang
Published: 2026-02-04
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.15040v2

Accurate global Subseasonal-to-Seasonal (S2S) climate forecasting is critical for disaster preparedness and resource management, yet it remains challenging due to chaotic atmospheric dynamics. Despite advances in geometry-aware representations, existing methods do not specify how the zonal and meridional interactions that govern real atmospheric dynamics should be explicitly coordinated and composed, leaving an important architectural gap for S2S forecasting. In this paper, we propose AnisoCast, which explicitly models anisotropic global atmospheric dynamics for accurate S2S climate forecasting. It couples: (1) an Anisotropic Embedding strategy that tokenizes the global grid into latitudinal rings, preserving the integrity of zonal periodic structures; and (2) stacked Aniso Blocks that arrange latent Zonal and Meridional Operators in a weight-shared palindromic composition inspired by symmetric operator splitting. Extensive experiments on the ERA5 reanalysis dataset demonstrate that AnisoCast establishes a new state-of-the-art, significantly outperforming existing methods in both forecasting accuracy and computational efficiency.

---

### SOON: Symmetric Orthogonal Operator Network for Global Subseasonal-to-Seasonal Climate Forecasting

Authors: Ziyu Zhou, Tian Zhou, Shiyu Wang, James Kwok, Yuxuan Liang
Published: 2026-02-04
Categories: physics.ao-ph, cs.LG
arXiv: https://arxiv.org/abs/2602.15040v1

Accurate global Subseasonal-to-Seasonal (S2S) climate forecasting is critical for disaster preparedness and resource management, yet it remains challenging due to chaotic atmospheric dynamics. Existing models predominantly treat atmospheric fields as isotropic images, conflating the distinct physical processes of zonal wave propagation and meridional transport, and leading to suboptimal modeling of anisotropic dynamics. In this paper, we propose the Symmetric Orthogonal Operator Network (SOON) for global S2S climate forecasting. It couples: (1) an Anisotropic Embedding strategy that tokenizes the global grid into latitudinal rings, preserving the integrity of zonal periodic structures; and (2) a stack of SOON Blocks that models the alternating interaction of Zonal and Meridional Operators via a symmetric decomposition, structurally mitigating discretization errors inherent in long-term integration. Extensive experiments on the Earth Reanalysis 5 dataset demonstrate that SOON establishes a new state-of-the-art, significantly outperforming existing methods in both forecasting accuracy and computational efficiency.

---

### Human-Centered Explainable AI for Security Enhancement: A Deep Intrusion Detection Framework

Authors: Md Muntasir Jahid Ayan, Md. Shahriar Rashid, Tazzina Afroze Hassan, Hossain Md. Mubashshir Jamil, Mahbubul Islam, Lisan Al Amin, Rupak Kumar Das, Farzana Akter, Faisal Quader
Published: 2026-02-04
Categories: cs.AI, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2602.13271v1

The increasing complexity and frequency of cyber-threats demand intrusion detection systems (IDS) that are not only accurate but also interpretable. This paper presented a novel IDS framework that integrated Explainable Artificial Intelligence (XAI) to enhance transparency in deep learning models. The framework was evaluated experimentally using the benchmark dataset NSL-KDD, demonstrating superior performance compared to traditional IDS and black-box deep learning models. The proposed approach combined Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) networks for capturing temporal dependencies in traffic sequences. Our deep learning results showed that both CNN and LSTM reached 0.99 for accuracy, whereas LSTM outperformed CNN at macro average precision, recall, and F-1 score. For weighted average precision, recall, and F-1 score, both models scored almost similarly. To ensure interpretability, the XAI model SHapley Additive exPlanations (SHAP) was incorporated, enabling security analysts to understand and validate model decisions. Some notable influential features were srv_serror_rate, dst_host_srv_serror_rate, and serror_rate for both models, as pointed out by SHAP. We also conducted a trust-focused expert survey based on IPIP6 and Big Five personality traits via an interactive UI to evaluate the system's reliability and usability. This work highlighted the potential of combining performance and transparency in cybersecurity solutions and recommends future enhancements through adaptive learning for real-time threat detection.

---

### Deep Learning CNN for Pneumonia Detection: Advancing Digital Health in Society 5.0

Authors: Hadi Almohab
Published: 2026-02-04
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2602.13270v1

Pneumonia is a serious global health problem, contributing to high morbidity and mortality, especially in areas with limited diagnostic tools and healthcare resources. This study develops a Convolutional Neural Network (CNN) based on deep learning to automatically detect pneumonia from chest X-ray images. The method involves training the model on labeled datasets with preprocessing techniques such as normalization, data augmentation, and image quality enhancement to improve robustness and generalization. Testing results show that the optimized model achieves 91.67% accuracy, ROC-AUC of 0.96, and PR-AUC of 0.95, demonstrating strong performance in distinguishing pneumonia from normal images. In conclusion, this CNN model has significant potential as a fast, consistent, and reliable diagnostic aid, supporting Society 5.0 by integrating artificial intelligence to improve healthcare services and public well-being.

---

### Expected Moral Shortfall for Ethical Competence in Decision-making Models

Authors: Aisha Aijaz, Raghava Mutharaju, Manohar Kumar
Published: 2026-02-04
Categories: cs.CY, cs.LG
arXiv: https://arxiv.org/abs/2602.13268v1

Moral cognition is a crucial yet underexplored aspect of decision-making in AI models. Regardless of the application domain, it should be a consideration that allows for ethically aligned decision-making. This paper presents a multifaceted contribution to this research space. Firstly, a comparative analysis of techniques to instill ethical competence into AI models has been presented to gauge them on multiple performance metrics. Second, a novel mathematical discretization of morality and a demonstration of its real-life application have been conveyed and tested against other techniques on two datasets. This value is modeled as the risk of loss incurred by the least moral cases, or an Expected Moral Shortfall (EMS), which we direct the AI model to minimize in order to maximize its performance while retaining ethical competence. Lastly, the paper discusses the tradeoff between preliminary AI decision-making metrics such as model performance, complexity, and scale of ethical competence to recognize the true extent of practical social impact.

---

### SOAR: Regression-based LiDAR Relocalization for UAVs

Authors: Hengyu Mu, Jianshi Wu, Yuxin Guo, XianLian Lin, Qingyong Hu, Sheng Ao, Chenglu Wen, Cheng Wang
Published: 2026-02-04
Categories: cs.CV, cs.RO, eess.IV
arXiv: https://arxiv.org/abs/2602.13267v3

Regression-based LiDAR relocalization has recently emerged as a promising solution for high-precision positioning in GNSS-denied environments. However, these methods are primarily tailored to autonomous driving, exhibiting significantly degraded accuracy in unmanned aerial vehicle (UAV) scenarios due to arbitrary pose variations and irregular flight paths. In this paper, we propose SOAR, a regression-based LiDAR relocalization framework for UAVs. Specifically, we introduce a locality-preserving sliding window attention module with locally invariant positional encoding to capture discriminative geometric structures robust to viewpoint changes. A coordinate-independent feature initialization module is further designed to eliminate sensitivity to global transformations. Furthermore, most existing UAV datasets are limited to evaluate LiDAR relocalization in real-world, due to the lack of synchronized LiDAR scans, accurate 6-DoF poses, or multiple traversals. Thus, we construct a large-scale UAV LiDAR localization dataset with 4 scenes and 13 irregular paths exhibiting rotation and altitude variations, providing a more realistic benchmark for UAVs. Extensive experiments demonstrate that our method achieves state-of-the-art performance, improving the localization success rate by 40% and reducing mean error over 10m on UAVLoc. Our code and dataset will be released soon.

---

### Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models

Authors: Souradeep Chattopadhyay, Brendan Kennedy, Sai Munikoti, Soumik Sarkar, Karl Pazdernik
Published: 2026-02-04
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.13264v1

In the critical task of making generative models trustworthy and robust, methods for Uncertainty Quantification (UQ) have begun to show encouraging potential. However, many of these methods rely on rigid heuristics that fail to generalize across tasks and modalities. Here, we propose a novel framework for UQ that is highly flexible and approaches or surpasses the performance of prior heuristic methods. We introduce Directional Concentration Uncertainty (DCU), a novel statistical procedure for quantifying the concentration of embeddings based on the von Mises-Fisher (vMF) distribution. Our method captures uncertainty by measuring the geometric dispersion of multiple generated outputs from a language model using continuous embeddings of the generated outputs without any task specific heuristics. In our experiments, we show that DCU matches or exceeds calibration levels of prior works like semantic entropy (Kuhn et al., 2023) and also generalizes well to more complex tasks in multi-modal domains. We present a framework for the wider potential of DCU and its implications for integration into UQ for multi-modal and agentic frameworks.

---

### Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought Reasoning

Authors: Donald Ye, Max Loffgren, Om Kotadia, Linus Wong, Jonas Rohweder
Published: 2026-02-04
Categories: cs.CL
arXiv: https://arxiv.org/abs/2602.11201v2

Chain-of-Thought (CoT) explanations are widely used to interpret how language models solve complex problems, yet it remains unclear whether these step-by-step explanations reflect how the model actually reaches its answer, or merely post-hoc justifications. We propose Normalized Logit Difference Decay (NLDD), a metric that measures whether individual reasoning steps are faithful to the model's decision-making process. Our approach corrupts individual reasoning steps from the explanation and measures how much the model's confidence in its answer drops, to determine if a step is truly important. By standardizing these measurements, NLDD enables rigorous cross-model comparison across different architectures. Testing three model families across syntactic, logical, and arithmetic tasks, we discover a consistent Reasoning Horizon (k*) at 70--85% of chain length, beyond which reasoning tokens have little or negative effect on the final answer. We also find that models can encode correct internal representations while completely failing the task. These results show that accuracy alone does not reveal whether a model actually reasons through its chain. NLDD offers a way to measure when CoT matters.

---

### AM-FM: A Foundation Model for Ambient Intelligence Through WiFi

Authors: Guozhen Zhu, Yuqian Hu, Sakila Jayaweera, Weihang Gao, Wei-Hsiang Wang, Jiaxuan Zhang, Beibei Wang, Chenshu Wu, K. J. Ray Liu
Published: 2026-02-04
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2602.11200v1

Ambient intelligence, continuously understanding human presence, activity, and physiology in physical spaces, is fundamental to smart environments, health monitoring, and human-computer interaction. WiFi infrastructure provides a ubiquitous, always-on, privacy-preserving substrate for this capability across billions of IoT devices. Yet this potential remains largely untapped, as wireless sensing has typically relied on task-specific models that require substantial labeled data and limit practical deployment. We present AM-FM, the first foundation model for ambient intelligence and sensing through WiFi. AM-FM is pre-trained on 9.2 million unlabeled Channel State Information (CSI) samples collected over 439 days from 20 commercial device types deployed worldwide, learning general-purpose representations via contrastive learning, masked reconstruction, and physics-informed objectives tailored to wireless signals. Evaluated on public benchmarks spanning nine downstream tasks, AM-FM shows strong cross-task performance with improved data efficiency, demonstrating that foundation models can enable scalable ambient intelligence using existing wireless infrastructure.

---

### When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification

Authors: Jiale Zhao, Ke Fang, Lu Cheng
Published: 2026-02-04
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.11199v2

Large language models (LLMs) often respond even when prompts omit critical details or include misleading information, leading to hallucinations or reinforced misconceptions. We study how to evaluate and improve LLMs' ability to decide when and what to ask for clarification without sacrificing task performance. We introduce AskBench, an interactive benchmark that converts standard QA pairs into multi-turn interactions with explicit checkpoints. A unified judge loop evaluates final answers and simulates user responses as needed. AskBench covers two settings: AskMind, with intent-deficient queries requiring clarification, and AskOverconfidence, with queries containing false premises that must be identified and corrected. We further propose rubric-guided reinforcement learning with verifier-based rewards (RLVR), which uses structured rubrics to encourage targeted clarification. Experiments show consistent improvements in accuracy, rubric adherence, and interaction efficiency, with strong generalization to unseen domains.

---

### Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition

Authors: Aditya Srinivas Menon, Kumud Tripathi, Raj Gohil, Pankaj Wasnik
Published: 2026-02-04
Categories: eess.AS, cs.LG, cs.SD
arXiv: https://arxiv.org/abs/2602.09043v1

Self-supervised learning (SSL) has advanced speech processing but suffers from quadratic complexity due to self-attention. To address this, SummaryMixing (SM) has been proposed as a linear-time alternative that summarizes entire utterances using mean pooling but lacks sufficient local context. In this work, we introduce Windowed SummaryMixing (WSM), which enhances SM by integrating local neighborhood summaries alongside the global summary, maintaining efficiency while improving temporal dependencies. Additionally, we introduce a selective fine-tuning approach, replacing self-attention layers in SSL models with WSM blocks and fine-tuning only these blocks in low-resource settings. Our approach improves ASR performance while reducing peak VRAM usage by 40\% in the SSL models. WSM blocks have linear-time complexity with enhanced context awareness. Selectively replacing some attention layers reduces compute, memory, and latency, making it ideal for low-resource speech recognition.

---

### Reliable and Responsible Foundation Models: A Comprehensive Survey

Authors: Xinyu Yang, Junlin Han, Rishi Bommasani, Jinqi Luo, Wenjie Qu, Wangchunshu Zhou, Adel Bibi, Xiyao Wang, Jaehong Yoon, Elias Stengel-Eskin, Shengbang Tong, Lingfeng Shen et al.
Published: 2026-02-04
Categories: cs.LG, cs.AI, cs.CL, cs.CV, cs.CY
arXiv: https://arxiv.org/abs/2602.08145v1

Foundation models, including Large Language Models (LLMs), Multimodal Large Language Models (MLLMs), Image Generative Models (i.e, Text-to-Image Models and Image-Editing Models), and Video Generative Models, have become essential tools with broad applications across various domains such as law, medicine, education, finance, science, and beyond. As these models see increasing real-world deployment, ensuring their reliability and responsibility has become critical for academia, industry, and government. This survey addresses the reliable and responsible development of foundation models. We explore critical issues, including bias and fairness, security and privacy, uncertainty, explainability, and distribution shift. Our research also covers model limitations, such as hallucinations, as well as methods like alignment and Artificial Intelligence-Generated Content (AIGC) detection. For each area, we review the current state of the field and outline concrete future research directions. Additionally, we discuss the intersections between these areas, highlighting their connections and shared challenges. We hope our survey fosters the development of foundation models that are not only powerful but also ethical, trustworthy, reliable, and socially responsible.

---

### SPARE: Self-distillation for PARameter-Efficient Removal

Authors: Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch, Luis H. Arribas, Juan C. S. M. Avedillo
Published: 2026-02-04
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.07058v2

Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite recent progress, unlearning in text-to-image diffusion models remains challenging due to high computational costs and the difficulty of balancing effective forgetting with retention of unrelated concepts. We introduce Self-distillation for PARameter Efficient Removal (SPARE), a two-stage unlearning method for image generation that combines parameter localization with self-distillation. SPARE first identifies parameters most responsible for generation of the unwanted concepts using gradient-based saliency and constrains updates through sparse low rank adapters, ensuring lightweight, localized modifications. In a second stage, SPARE applies a self-distillation objective that overwrites the unwanted concept with a user-defined surrogate while preserving behavior for other concepts. In addition we proposed a timestep sampling scheme for diffusion models to target only the crucial timesteps for a given concept leading to efficient unlearning. SPARE surpasses the current state-of-the-art on the UnlearnCanvas benchmark, and ablation studies on several datasets indicate fine-grained control over the forgetting-retention trade-off. Our results demonstrate that SPARE achieves strong concept erasure and high retainability across various domains, making it a suitable solution for selective unlearning in diffusion-based image generation models.

---

### RECITYGEN -- Interactive and Generative Participatory Urban Design Tool with Latent Diffusion and Segment Anything

Authors: Di Mo, Mingyang Sun, Chengxiu Yin, Runjia Tian, Yanhong Wu, Liyan Xu
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.07057v1

Urban design profoundly impacts public spaces and community engagement. Traditional top-down methods often overlook public input, creating a gap in design aspirations and reality. Recent advancements in digital tools, like City Information Modelling and augmented reality, have enabled a more participatory process involving more stakeholders in urban design. Further, deep learning and latent diffusion models have lowered barriers for design generation, providing even more opportunities for participatory urban design. Combining state-of-the-art latent diffusion models with interactive semantic segmentation, we propose RECITYGEN, a novel tool that allows users to interactively create variational street view images of urban environments using text prompts. In a pilot project in Beijing, users employed RECITYGEN to suggest improvements for an ongoing Urban Regeneration project. Despite some limitations, RECITYGEN has shown significant potential in aligning with public preferences, indicating a shift towards more dynamic and inclusive urban planning methods. The source code for the project can be found at RECITYGEN GitHub.

---

### MTS-CSNet: Multiscale Tensor Factorization for Deep Compressive Sensing on RGB Images

Authors: Mehmet Yamac, Lei Xu, Serkan Kiranyaz, Moncef Gabbouj
Published: 2026-02-04
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2602.07056v1

Deep learning based compressive sensing (CS) methods typically learn sampling operators using convolutional or block wise fully connected layers, which limit receptive fields and scale poorly for high dimensional data. We propose MTSCSNet, a CS framework based on Multiscale Tensor Summation (MTS) factorization, a structured operator for efficient multidimensional signal processing. MTS performs mode-wise linear transformations with multiscale summation, enabling large receptive fields and effective modeling of cross-dimensional correlations. In MTSCSNet, MTS is first used as a learnable CS operator that performs linear dimensionality reduction in tensor space, with its adjoint defining the initial back-projection, and is then applied in the reconstruction stage to directly refine this estimate. This results in a simple feed-forward architecture without iterative or proximal optimization, while remaining parameter and computation efficient. Experiments on standard CS benchmarks show that MTSCSNet achieves state-of-the-art reconstruction performance on RGB images, with notable PSNR gains and faster inference, even compared to recent diffusion-based CS methods, while using a significantly more compact feed-forward architecture.

---

### Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?

Authors: Pingyue Zhang, Zihan Huang, Yue Wang, Jieyu Zhang, Letian Xue, Zihan Wang, Qineng Wang, Keshigeyan Chandrasegaran, Ruohan Zhang, Yejin Choi, Ranjay Krishna, Jiajun Wu et al.
Published: 2026-02-04
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.07055v1

Spatial embodied intelligence requires agents to act to acquire information under partial observability. While multimodal foundation models excel at passive perception, their capacity for active, self-directed exploration remains understudied. We propose Theory of Space, defined as an agent's ability to actively acquire information through self-directed, active exploration and to construct, revise, and exploit a spatial belief from sequential, partial observations. We evaluate this through a benchmark where the goal is curiosity-driven exploration to build an accurate cognitive map. A key innovation is spatial belief probing, which prompts models to reveal their internal spatial representations at each step. Our evaluation of state-of-the-art models reveals several critical bottlenecks. First, we identify an Active-Passive Gap, where performance drops significantly when agents must autonomously gather information. Second, we find high inefficiency, as models explore unsystematically compared to program-based proxies. Through belief probing, we diagnose that while perception is an initial bottleneck, global beliefs suffer from instability that causes spatial knowledge to degrade over time. Finally, using a false belief paradigm, we uncover Belief Inertia, where agents fail to update obsolete priors with new evidence. This issue is present in text-based agents but is particularly severe in vision-based models. Our findings suggest that current foundation models struggle to maintain coherent, revisable spatial beliefs during active exploration.

---

### AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization

Authors: Ashutosh Chaubey, Jiacheng Pang, Maksim Siniukov, Mohammad Soleymani
Published: 2026-02-04
Categories: cs.LG, cs.CV, cs.HC
arXiv: https://arxiv.org/abs/2602.07054v1

Emotion understanding is essential for building socially intelligent agents. Although recent multimodal large language models have shown strong performance on this task, two key challenges remain - spurious associations between emotions and irrelevant audiovisual cues, and hallucinations of audiovisual cues driven by text priors in the language model backbone. To quantify and understand these issues, we introduce EmoReAlM, a benchmark designed to evaluate MLLMs for cue-emotion associations, hallucinations and modality agreement. We then propose AVEm-DPO, a preference optimization technique that aligns model responses with both audiovisual inputs and emotion-centric queries. Specifically, we construct preferences over responses exhibiting spurious associations or hallucinations, and audiovisual input pairs guided by textual prompts. We also include a regularization term that penalizes reliance on text priors, thereby mitigating modality-specific cue hallucinations. Experimental results on DFEW, RAVDESS and EMER demonstrate that our method significantly improves the performance of the reference baseline models with 6-19% of relative performance gains in zero-shot settings. By providing both a rigorous benchmark and a robust optimization framework, this work enables principled evaluation and improvement of MLLMs for emotion understanding and social AI. Code, models and benchmark will be released at https://avere-iclr.github.io.

---

### Markerless Head Tracking for Accurate and Accessible Neuronavigation

Authors: Ziye Xie, Oded Schlesinger, Raj Kundu, Jessica Y. Choi, Pablo Iturralde, Dennis A. Turner, Stefan M. Goetz, Guillermo Sapiro, Angel V. Peterchev, J. Matias Di Martino
Published: 2026-02-04
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2602.07052v2

Neuronavigation is widely used in biomedical research and interventions to guide the precise placement of instruments around the head to support procedures such as transcranial magnetic stimulation. Traditional systems, however, rely on subject-mounted markers that require manual registration, may shift during procedures, and can cause discomfort. We introduce and evaluate markerless approaches that replace expensive hardware and physical markers with low-cost visible and infrared light cameras incorporating stereo and depth sensing, combined with algorithmic modeling of the facial geometry. Validation with 50 human subjects yielded a median tracking discrepancy of only 2.32 mm and 2.01$^\circ$ for the best markerless algorithm compared to a conventional marker-based system, which indicates sufficient accuracy for transcranial magnetic stimulation and a substantial improvement over prior markerless results. The study also suggests that integration of the data from the various camera sensors can improve the overall accuracy further. The proposed markerless neuronavigation methods can reduce setup cost and complexity, improve patient comfort, and expand access to neuronavigation in clinical and research settings.

---

### Neural Sentinel: Unified Vision Language Model (VLM) for License Plate Recognition with Human-in-the-Loop Continual Learning

Authors: Karthik Sivakoti
Published: 2026-02-04
Categories: cs.CV, cs.AI, cs.LG, cs.NE
arXiv: https://arxiv.org/abs/2602.07051v1

Traditional Automatic License Plate Recognition (ALPR) systems employ multi-stage pipelines consisting of object detection networks followed by separate Optical Character Recognition (OCR) modules, introducing compounding errors, increased latency, and architectural complexity. This research presents Neural Sentinel, a novel unified approach that leverages Vision Language Models (VLMs) to perform license plate recognition, state classification, and vehicle attribute extraction through a single forward pass. Our primary contribution lies in demonstrating that a fine-tuned PaliGemma 3B model, adapted via Low-Rank Adaptation (LoRA), can simultaneously answer multiple visual questions about vehicle images, achieving 92.3% plate recognition accuracy, which is a 14.1% improvement over EasyOCR and 9.9% improvement over PaddleOCR baselines. We introduce a Human-in-the-Loop (HITL) continual learning framework that incorporates user corrections while preventing catastrophic forgetting through experience replay, maintaining a 70:30 ratio of original training data to correction samples. The system achieves a mean inference latency of 152ms with an Expected Calibration Error (ECE) of 0.048, indicating well calibrated confidence estimates. Additionally, the VLM first architecture enables zero-shot generalization to auxiliary tasks including vehicle color detection (89%), seatbelt detection (82%), and occupancy counting (78%) without task specific training. Through extensive experimentation on real world toll plaza imagery, we demonstrate that unified vision language approaches represent a paradigm shift in ALPR systems, offering superior accuracy, reduced architectural complexity, and emergent multi-task capabilities that traditional pipeline approaches cannot achieve.

---

### Interpreting Physics in Video World Models

Authors: Sonia Joseph, Quentin Garrido, Randall Balestriero, Matthew Kowal, Thomas Fel, Shahab Bakhtiari, Blake Richards, Mike Rabbat
Published: 2026-02-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07050v1

A long-standing question in physical reasoning is whether video-based models need to rely on factorized representations of physical variables in order to make physically accurate predictions, or whether they can implicitly represent such variables in a task-specific, distributed manner. While modern video world models achieve strong performance on intuitive physics benchmarks, it remains unclear which of these representational regimes they implement internally. Here, we present the first interpretability study to directly examine physical representations inside large-scale video encoders. Using layerwise probing, subspace geometry, patch-level decoding, and targeted attention ablations, we characterize where physical information becomes accessible and how it is organized within encoder-based video transformers. Across architectures, we identify a sharp intermediate-depth transition -- which we call the Physics Emergence Zone -- at which physical variables become accessible. Physics-related representations peak shortly after this transition and degrade toward the output layers. Decomposing motion into explicit variables, we find that scalar quantities such as speed and acceleration are available from early layers onwards, whereas motion direction becomes accessible only at the Physics Emergence Zone. Notably, we find that direction is encoded through a high-dimensional population structure with circular geometry, requiring coordinated multi-feature intervention to control. These findings suggest that modern video models do not use factorized representations of physical variables like a classical physics engine. Instead, they use a distributed representation that is nonetheless sufficient for making physical predictions.

---

### Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead

Authors: Jindong Li, Dario Zanca, Vincent Christlein, Tim Hamann, Jens Barth, Peter Kämpf, Björn Eskofier
Published: 2026-02-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.07049v2

Online handwriting recognition using inertial measurement units opens up handwriting on paper as input for digital devices. Doing it on edge hardware improves privacy and lowers latency, but entails memory constraints. To address this, we propose Error-enhanced Contrastive Handwriting Recognition (ECHWR), a training framework designed to improve feature representation and recognition accuracy without increasing inference costs. ECHWR utilizes a temporary auxiliary branch that aligns sensor signals with semantic text embeddings during the training phase. This alignment is maintained through a dual contrastive objective: an in-batch contrastive loss for general modality alignment and a novel error-based contrastive loss that distinguishes between correct signals and synthetic hard negatives. The auxiliary branch is discarded after training, which allows the deployed model to keep its original, efficient architecture. Evaluations on the OnHW-Words500 dataset show that ECHWR significantly outperforms state-of-the-art baselines, reducing character error rates by up to 7.4% on the writer-independent split and 10.4% on the writer-dependent split. Finally, although our ablation studies indicate that solving specific challenges require specific architectural and objective configurations, error-based contrastive loss shows its effectiveness for handling unseen writing styles.

---

### ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees

Authors: Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda
Published: 2026-02-04
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2602.07047v3

Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their learned representations. However, existing hierarchical Shapley approaches do not exploit the multiscale structure of image data, leading to slow convergence and weak alignment with the actual morphological features. Moreover, no prior Shapley method has leveraged data-aware hierarchies for Computer Vision tasks, leaving a gap in model interpretability of structured visual data. To address this, this paper introduces ShapBPT, a novel data-aware XCV method based on the hierarchical Shapley formula. ShapBPT assigns Shapley coefficients to a multiscale hierarchical structure tailored for images, the Binary Partition Tree (BPT). By using this data-aware hierarchical partitioning, ShapBPT ensures that feature attributions align with intrinsic image morphology, effectively prioritizing relevant regions while reducing computational overhead. This advancement connects hierarchical Shapley methods with image data, providing a more efficient and semantically meaningful approach to visual interpretability. Experimental results confirm ShapBPT's effectiveness, demonstrating superior alignment with image structures and improved efficiency over existing XCV methods, and a 20-subject user study confirming that ShapBPT explanations are preferred by humans.

---

### VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

Authors: Zhiming Luo, Di Wang, Haonan Guo, Jing Zhang, Bo Du
Published: 2026-02-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07045v2

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,000 question-answer pairs with an average question length of 130.19 words, spanning 14 tasks and up to eight temporal phases. VLRS-Bench is constructed via a specialized pipeline that integrates RS-specific priors and expert knowledge to ensure geospatial realism and reasoning complexity. Experimental results reveal significant bottlenecks in existing state-of-the-art MLLMs, providing critical insights for advancing multimodal reasoning within the remote sensing community. The project repository is available at https://github.com/MiliLab/VLRS-Bench.

---

### PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging

Authors: Tianyi Qu, Songxiao Yang, Haolin Wang, Huadong Song, Xiaoting Guo, Wenguang Hu, Guanlin Liu, Honghe Chen, Yafei Ou
Published: 2026-02-04
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2602.07044v4

Pipeline integrity is critical to industrial safety and environmental protection, with Magnetic Flux Leakage (MFL) detection being a primary non-destructive testing technology. Despite the promise of deep learning for automating MFL interpretation, progress toward reliable models has been constrained by the absence of a large-scale public dataset and benchmark, making fair comparison and reproducible evaluation difficult. We introduce \textbf{PipeMFL-240K}, a large-scale, meticulously annotated dataset and benchmark for complex object detection in pipeline MFL pseudo-color images. PipeMFL-240K reflects real-world inspection complexity and poses several unique challenges: (i) an extremely long-tailed distribution over \textbf{12} categories, (ii) a high prevalence of tiny objects that often comprise only a handful of pixels and (iii) substantial intra-class variability. The dataset contains \textbf{249,320} images and \textbf{200,020} high-quality bounding-box annotations, collected from 12 pipelines spanning approximately \textbf{1,530} km. Extensive experiments are conducted with state-of-the-art object detectors to establish baselines. Results show that modern detectors still struggle with the intrinsic properties of MFL data, highlighting considerable headroom for improvement, while PipeMFL-240K provides a reliable and challenging testbed to drive future research. As the first public dataset and the first benchmark of this scale and scope for pipeline MFL inspection, it provides a critical foundation for efficient pipeline diagnostics as well as maintenance planning and is expected to accelerate algorithmic innovation and reproducible research in MFL-based pipeline integrity assessment.

---

### COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification

Authors: Magesh Rajasekaran, Md Saiful Islam Sajol, Frej Berglind, Supratik Mukhopadhyay, Kamalika Das
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.07042v1

Identifying out-of-distribution (OOD) data at inference time is crucial for many machine learning applications, especially for automation. We present a novel unsupervised semi-parametric framework COMBOOD for OOD detection with respect to image recognition. Our framework combines signals from two distance metrics, nearest-neighbor and Mahalanobis, to derive a confidence score for an inference point to be out-of-distribution. The former provides a non-parametric approach to OOD detection. The latter provides a parametric, simple, yet effective method for detecting OOD data points, especially, in the far OOD scenario, where the inference point is far apart from the training data set in the embedding space. However, its performance is not satisfactory in the near OOD scenarios that arise in practical situations. Our COMBOOD framework combines the two signals in a semi-parametric setting to provide a confidence score that is accurate both for the near-OOD and far-OOD scenarios. We show experimental results with the COMBOOD framework for different types of feature extraction strategies. We demonstrate experimentally that COMBOOD outperforms state-of-the-art OOD detection methods on the OpenOOD (both version 1 and most recent version 1.5) benchmark datasets (for both far-OOD and near-OOD) as well as on the documents dataset in terms of accuracy. On a majority of the benchmark datasets, the improvements in accuracy resulting from the COMBOOD framework are statistically significant. COMBOOD scales linearly with the size of the embedding space, making it ideal for many real-life applications.

---

### Point Virtual Transformer

Authors: Veerain Sood, Bnalin, Gaurav Pandey
Published: 2026-02-04
Categories: cs.CV
arXiv: https://arxiv.org/abs/2602.06406v1

LiDAR-based 3D object detectors often struggle to detect far-field objects due to the sparsity of point clouds at long ranges, which limits the availability of reliable geometric cues. To address this, prior approaches augment LiDAR data with depth-completed virtual points derived from RGB images; however, directly incorporating all virtual points leads to increased computational cost and introduces challenges in effectively fusing real and virtual information. We present Point Virtual Transformer (PointViT), a transformer-based 3D object detection framework that jointly reasons over raw LiDAR points and selectively sampled virtual points. The framework examines multiple fusion strategies, ranging from early point-level fusion to BEV-based gated fusion, and analyses their trade-offs in terms of accuracy and efficiency. The fused point cloud is voxelized and encoded using sparse convolutions to form a BEV representation, from which a compact set of high-confidence object queries is initialised and refined through a transformer-based context aggregation module. Experiments on the KITTI benchmark report 91.16% 3D AP, 95.94% BEV AP, and 99.36% AP on the KITTI 2D detection benchmark for the Car class.

---

### Communication Enhances LLMs' Stability in Strategic Thinking

Authors: Nunzio Lore, Babak Heydari
Published: 2026-02-04
Categories: cs.MA, cs.AI, cs.GT
arXiv: https://arxiv.org/abs/2602.06081v1

Large Language Models (LLMs) often exhibit pronounced context-dependent variability that undermines predictable multi-agent behavior in tasks requiring strategic thinking. Focusing on models that range from 7 to 9 billion parameters in size engaged in a ten-round repeated Prisoner's Dilemma, we evaluate whether short, costless pre-play messages emulating the cheap-talk paradigm affect strategic stability. Our analysis uses simulation-level bootstrap resampling and nonparametric inference to compare cooperation trajectories fitted with LOWESS regression across both the messaging and the no-messaging condition. We demonstrate consistent reductions in trajectory noise across a majority of the model-context pairings being studied. The stabilizing effect persists across multiple prompt variants and decoding regimes, though its magnitude depends on model choice and contextual framing, with models displaying higher baseline volatility gaining the most. While communication rarely produces harmful instability, we document a few context-specific exceptions and identify the limited domains in which communication harms stability. These findings position cheap-talk style communication as a low-cost, practical tool for improving the predictability and reliability of strategic behavior in multi-agent LLM systems.

---

### Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers

Authors: Liangyu Wang, Siqi Zhang, Junjie Wang, Yiming Dong, Bo Zheng, Zihan Qiu, Shengkun Tang, Di Wang, Rui Men, Dayiheng Liu
Published: 2026-02-04
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2602.06079v1

The scaling of Large Language Models (LLMs) drives interest in matrix-based optimizers (e.g., Shampoo, Muon, SOAP) for their convergence efficiency; yet their requirement for holistic updates conflicts with the tensor fragmentation in distributed frameworks like Megatron. Existing solutions are suboptimal: synchronous approaches suffer from computational redundancy, while layer-wise partitioning fails to reconcile this conflict without violating the geometric constraints of efficient communication primitives. To bridge this gap, we propose Canzona, a Unified, Asynchronous, and Load-Balanced framework that decouples logical optimizer assignment from physical parameter distribution. For Data Parallelism, we introduce an alpha-Balanced Static Partitioning strategy that respects atomicity while neutralizing the load imbalance. For Tensor Parallelism, we design an Asynchronous Compute pipeline utilizing Micro-Group Scheduling to batch fragmented updates and hide reconstruction overhead. Extensive evaluations on the Qwen3 model family (up to 32B parameters) on 256 GPUs demonstrate that our approach preserves the efficiency of established parallel architectures, achieving a 1.57x speedup in end-to-end iteration time and reducing optimizer step latency by 5.8x compared to the baseline.

---

### Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking

Authors: Elliot L. Epstein, Rajat Dwaraknath, John Winnicki, Thanawat Sornwanee
Published: 2026-02-04
Categories: cs.DL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.06078v1

This paper argues that large ML conferences should allocate marginal review capacity primarily to papers near the acceptance boundary, rather than spreading extra reviews via random or affinity-driven heuristics. We propose using LLM-based comparative ranking (via pairwise comparisons and a Bradley--Terry model) to identify a borderline band \emph{before} human reviewing and to allocate \emph{marginal} reviewer capacity at assignment time. Concretely, given a venue-specific minimum review target (e.g., 3 or 4), we use this signal to decide which papers receive one additional review (e.g., a 4th or 5th), without conditioning on any human reviews and without using LLM outputs for accept/reject. We provide a simple expected-impact calculation in terms of (i) the overlap between the predicted and true borderline sets ($ρ$) and (ii) the incremental value of an extra review near the boundary ($Δ$), and we provide retrospective proxies to estimate these quantities.

---

### CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAG

Authors: Nengbo Wang, Tuo Liang, Vikash Singh, Chaoda Song, Van Yang, Yu Yin, Jing Ma, Jagdip Singh, Vipin Chaudhary
Published: 2026-02-04
Categories: cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2602.05143v2

Retrieval augmented generation (RAG) has enhanced large language models by enabling access to external knowledge, with graph-based RAG emerging as a powerful paradigm for structured retrieval and reasoning. However, existing graph-based methods often over-rely on entity-centric node matching and lack explicit causal modeling, leading to unfaithful or spurious answers. Prior attempts to incorporate causality are typically limited to local or single-document contexts and also suffer from information isolation that arises from modular graph structures, which hinders scalability and cross-module causal reasoning. To address these challenges, we propose CausalRAG2, a framework that rethinks knowledge organization for graph-based RAG through causal gating across hierarchical modules. CausalRAG2 explicitly models causal relationships to suppress spurious correlations while enabling scalable reasoning over large-scale knowledge graphs. We also introduce HolisQA, a benchmark for holistic comprehension beyond entity-centric matching. Extensive experiments demonstrate that CausalRAG2 consistently outperforms competitive graph-based RAG baselines across multiple datasets and evaluation metrics. Our work establishes a principled foundation for structured, scalable, and causally grounded RAG systems. Our code and HolisQA benchmark are available at https://github.com/Pwnb/CausalRAG2.

---

### Adaptive Exploration for Latent-State Bandits

Authors: Jikai Jin, Kenneth Hung, Sanath Kumar Krishnamurthy, Baoyi Shi, Congshan Zhang
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05139v3

We study bandits whose rewards depend on an unobserved Markov state that evolves independently of the learner's actions. The optimal arm can change even though the learner observes only past actions and rewards. We propose algorithms that feed LinUCB with two summaries of the hidden state: a lagged action-reward pair and, when available, a probe fingerprint formed from rewards of multiple arms. The adaptive variants refresh the fingerprint using residual, margin, and staleness tests. In synthetic stress tests over state count, transition rate, noise, and horizon, these methods reduce dynamic regret relative to standard, adversarial, and non-stationary bandit baselines when the summaries distinguish states and are updated often enough. Ablations and misspecification tests identify the main failure modes: weak fingerprint separation, high noise, and state changes during sequential probes.

---

### Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers

Authors: Hao Chen, Jinghui Yuan, Hanmin Zhang
Published: 2026-02-04
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.05136v1

Is the standard weight decay in AdamW truly optimal? Although AdamW decouples weight decay from adaptive gradient scaling, a fundamental conflict remains: the Radial Tug-of-War. In deep learning, gradients tend to increase parameter norms to expand effective capacity while steering directions to learn features, whereas weight decay indiscriminately suppresses norm growth. This push--pull interaction induces radial oscillations, injecting noise into Adam's second-moment estimates and potentially degrading delicate tangential feature learning. We argue that magnitude and direction play distinct roles and should be decoupled in optimizer dynamics. We propose Orthogonal Dynamics Decoupling and instantiate it as AdamO: an SGD-style update handles the one-dimensional norm control, while Adam's adaptive preconditioning is confined to the tangential subspace. AdamO further incorporates curvature-adaptive radial step sizing and architecture-aware rules and projections for scale-invariant layers and low-dimensional parameters. Experiments on vision and language tasks show that AdamO improves generalization and stability over AdamW without introducing additional complex constraints.

---

### SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines

Authors: Olga Ovcharenko, Matthias Boehm, Sebastian Schelter
Published: 2026-02-04
Categories: cs.LG, cs.DB
arXiv: https://arxiv.org/abs/2602.05134v1

Real-world machine learning on tabular data relies on complex data preparation pipelines for prediction, data integration, augmentation, and debugging. Designing these pipelines requires substantial domain expertise and engineering effort, motivating the question of how large language models (LLMs) can support tabular ML through code synthesis. We introduce SemPipes, a novel declarative programming model that integrates LLM-powered semantic data operators into tabular ML pipelines. Semantic operators specify data transformations in natural language while delegating execution to a runtime system. During training, SemPipes synthesizes custom operator implementations based on data characteristics, operator instructions, and pipeline context. This design enables the automatic optimization of data operations in a pipeline via LLM-based code synthesis guided by evolutionary search. We evaluate SemPipes across diverse tabular ML tasks and show that semantic operators substantially improve end-to-end predictive performance for both expert-designed and agent-generated pipelines, while reducing pipeline complexity. We implement SemPipes in Python and release it at https://github.com/deem-data/sempipes/tree/v1.

---