# Research Papers — 2026-01 · bundle page 182 of 189

> Full-text markdown of papers #9051–9100 of 9403 published in 2026-01, newest first. AI-readable mirrors of the full 9403-paper 2026-01 archive (50 papers per file).

Canonical page: https://aipod.dev/papers/archive/2026-01/page/182
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/181.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/183.md)

### Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs

Authors: Jing Wang, Peng Zhao, Zhi-Hua Zhou
Published: 2026-01-03
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.01069v1

Non-stationary parametric bandits have attracted much attention recently. There are three principled ways to deal with non-stationarity, including sliding-window, weighted, and restart strategies. As many non-stationary environments exhibit gradual drifting patterns, the weighted strategy is commonly adopted in real-world applications. However, previous theoretical studies show that its analysis is more involved and the algorithms are either computationally less efficient or statistically suboptimal. This paper revisits the weighted strategy for non-stationary parametric bandits. In linear bandits (LB), we discover that this undesirable feature is due to an inadequate regret analysis, which results in an overly complex algorithm design. We propose a \emph{refined analysis framework}, which simplifies the derivation and, importantly, produces a simpler weight-based algorithm that is as efficient as window/restart-based algorithms while retaining the same regret as previous studies. Furthermore, our new framework can be used to improve regret bounds of other parametric bandits, including Generalized Linear Bandits (GLB) and Self-Concordant Bandits (SCB). For example, we develop a simple weighted GLB algorithm with an $\tilde{O}(k_μ^{5/4} c_μ^{-3/4} d^{3/4} P_T^{1/4}T^{3/4})$ regret, improving the $\tilde{O}(k_μ^{2} c_μ^{-1}d^{9/10} P_T^{1/5}T^{4/5})$ bound in prior work, where $k_μ$ and $c_μ$ characterize the reward model's nonlinearity, $P_T$ measures the non-stationarity, $d$ and $T$ denote the dimension and time horizon. Moreover, we extend our framework to non-stationary Markov Decision Processes (MDPs) with function approximation, focusing on Linear Mixture MDP and Multinomial Logit (MNL) Mixture MDP. For both classes, we propose algorithms based on the weighted strategy and establish dynamic regret guarantees using our analysis framework.

---

### Tiny Machine Learning for Real-Time Aquaculture Monitoring: A Case Study in Morocco

Authors: Achraf Hsain, Yahya Zaki, Othman Abaakil, Hibat-allah Bekkar, Yousra Chtouki
Published: 2026-01-03
Categories: cs.LG, eess.SP, eess.SY
arXiv: https://arxiv.org/abs/2601.01065v1

Aquaculture, the farming of aquatic organisms, is a rapidly growing industry facing challenges such as water quality fluctuations, disease outbreaks, and inefficient feed management. Traditional monitoring methods often rely on manual labor and are time consuming, leading to potential delays in addressing issues. This paper proposes the integration of low-power edge devices using Tiny Machine Learning (TinyML) into aquaculture systems to enable real-time automated monitoring and control, such as collecting data and triggering alarms, and reducing labor requirements. The system provides real-time data on the required parameters such as pH levels, temperature, dissolved oxygen, and ammonia levels to control water quality, nutrient levels, and environmental conditions enabling better maintenance, efficient resource utilization, and optimal management of the enclosed aquaculture space. The system enables alerts in case of anomaly detection. The data collected by the sensors over time can serve for important decision-making regarding optimizing water treatment processes, feed distribution, feed pattern analysis and improve feed efficiency, reducing operational costs. This research explores the feasibility of developing TinyML-based solutions for aquaculture monitoring, considering factors such as sensor selection, algorithm design, hardware constraints, and ethical considerations. By demonstrating the potential benefits of TinyML in aquaculture, our aim is to contribute to the development of more sustainable and efficient farming practices.

---

### Efficient Hyperspectral Image Reconstruction Using Lightweight Separate Spectral Transformers

Authors: Jianan Li, Wangcai Zhao, Tingfa Xu
Published: 2026-01-03
Categories: cs.CV, eess.IV
arXiv: https://arxiv.org/abs/2601.01064v1

Hyperspectral imaging (HSI) is essential across various disciplines for its capacity to capture rich spectral information. However, efficiently reconstructing hyperspectral images from compressive sensing measurements presents significant challenges. To tackle these, we adopt a divide-and-conquer strategy that capitalizes on the unique spectral and spatial characteristics of hyperspectral images. We introduce the Lightweight Separate Spectral Transformer (LSST), an innovative architecture tailored for efficient hyperspectral image reconstruction. This architecture consists of Separate Spectral Transformer Blocks (SSTB) for modeling spectral relationships and Lightweight Spatial Convolution Blocks (LSCB) for spatial processing. The SSTB employs Grouped Spectral Self-attention and a Spectrum Shuffle operation to effectively manage both local and non-local spectral relationships. Simultaneously, the LSCB utilizes depth-wise separable convolutions and strategic ordering to enhance spatial information processing. Furthermore, we implement the Focal Spectrum Loss, a novel loss weighting mechanism that dynamically adjusts during training to improve reconstruction across spectrally complex bands. Extensive testing demonstrates that our LSST achieves superior performance while requiring fewer FLOPs and parameters, underscoring its efficiency and effectiveness. The source code is available at: https://github.com/wcz1124/LSST.

---

### SPoRC-VIST: A Benchmark for Evaluating Generative Natural Narrative in Vision-Language Models

Authors: Yunlin Zeng
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.01062v1

Vision-Language Models (VLMs) have achieved remarkable success in descriptive tasks such as image captioning and visual question answering (VQA). However, their ability to generate engaging, long-form narratives -- specifically multi-speaker podcast dialogues -- remains under-explored and difficult to evaluate. Standard metrics like BLEU and ROUGE fail to capture the nuances of conversational naturalness, personality, and narrative flow, often rewarding safe, repetitive outputs over engaging storytelling. In this work, we present a novel pipeline for end-to-end visual podcast generation, and fine-tune a Qwen3-VL-32B model on a curated dataset of 4,000 image-dialogue pairs. Crucially, we use a synthetic-to-real training strategy: we train on high-quality podcast dialogues from the Structured Podcast Research Corpus (SPoRC) paired with synthetically generated imagery, and evaluate on real-world photo sequences from the Visual Storytelling Dataset (VIST). This rigorous setup tests the model's ability to generalize from synthetic training data to real-world visual domains. We propose a comprehensive evaluation framework that moves beyond textual overlap, and use AI-as-a-judge (Gemini 3 Pro, Claude Opus 4.5, GPT 5.2) and novel style metrics (average turn length, speaker switch rate) to assess quality. Our experiments demonstrate that our fine-tuned 32B model significantly outperforms a 235B base model in conversational naturalness ($>$80\% win rate) and narrative depth (+50\% turn length), while maintaining identical visual grounding capabilities (CLIPScore: 20.39).

---

### A UCB Bandit Algorithm for General ML-Based Estimators

Authors: Yajing Liu, Erkao Bao, Linqi Song
Published: 2026-01-03
Categories: cs.LG, cs.AI, math.PR
arXiv: https://arxiv.org/abs/2601.01061v2

We present ML-UCB, a generalized upper confidence bound algorithm that integrates arbitrary machine learning models into multi-armed bandit frameworks. A fundamental challenge in deploying sophisticated ML models for sequential decision-making is the lack of tractable concentration inequalities required for principled exploration. We overcome this limitation by directly modeling the learning curve behavior of the underlying estimator. Specifically, assuming the Mean Squared Error decreases as a power law in the number of training samples, we derive a generalized concentration inequality and prove that ML-UCB achieves sublinear regret. This framework enables the principled integration of any ML model whose learning curve can be empirically characterized, eliminating the need for model-specific theoretical analysis. We validate our approach through experiments on a collaborative filtering recommendation system using online matrix factorization with synthetic data designed to simulate a simplified two-tower model, demonstrating substantial improvements over LinUCB

---

### Unsupervised Text Style Transfer for Controllable Intensity

Authors: Shuhuan Gu, Wenbiao Tao, Xinchen Ma, Kangkang He, Ye Guo, Xiang Li, Yunshi Lan
Published: 2026-01-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01060v1

Unsupervised Text Style Transfer (UTST) aims to build a system to transfer the stylistic properties of a given text without parallel text pairs. Compared with text transfer between style polarities, UTST for controllable intensity is more challenging due to the subtle differences in stylistic features across different intensity levels. Faced with the challenges posed by the lack of parallel data and the indistinguishability between adjacent intensity levels, we propose a SFT-then-PPO paradigm to fine-tune an LLM. We first fine-tune the LLM with synthesized parallel data. Then, we further train the LLM with PPO, where the rewards are elaborately designed for distinguishing the stylistic intensity in hierarchical levels. Both the global and local stylistic features are considered to formulate the reward functions. The experiments on two UTST benchmarks showcase that both rewards have their advantages and applying them to LLM fine-tuning can effectively improve the performance of an LLM backbone based on various evaluation metrics. Even for close levels of intensity, we can still observe the noticeable stylistic difference between the generated text.

---

### Enhancing Histopathological Image Classification via Integrated HOG and Deep Features with Robust Noise Performance

Authors: Ifeanyi Ezuma, Ugochukwu Ugwu
Published: 2026-01-03
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01056v1

The era of digital pathology has advanced histopathological examinations, making automated image analysis essential in clinical practice. This study evaluates the classification performance of machine learning and deep learning models on the LC25000 dataset, which includes five classes of histopathological images. We used the fine-tuned InceptionResNet-v2 network both as a classifier and for feature extraction. Our results show that the fine-tuned InceptionResNet-v2 achieved a classification accuracy of 96.01\% and an average AUC of 96.8\%. Models trained on deep features from InceptionResNet-v2 outperformed those using only the pre-trained network, with the Neural Network model achieving an AUC of 99.99\% and accuracy of 99.84\%. Evaluating model robustness under varying SNR conditions revealed that models using deep features exhibited greater resilience, particularly GBM and KNN. The combination of HOG and deep features showed enhanced performance, however, less so in noisy environments.

---

### Fibonacci-Driven Recursive Ensembles: Algorithms, Convergence, and Learning Dynamics

Authors: Ernest Fokoué
Published: 2026-01-03
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.01055v1

This paper develops the algorithmic and dynamical foundations of recursive ensemble learning driven by Fibonacci-type update flows. In contrast with classical boosting Freund and Schapire (1997); Friedman (2001), where the ensemble evolves through first-order additive updates, we study second-order recursive architectures in which each predictor depends on its two immediate predecessors. These Fibonacci flows induce a learning dynamic with memory, allowing ensembles to integrate past structure while adapting to new residual information. We introduce a general family of recursive weight-update algorithms encompassing Fibonacci, tribonacci, and higher-order recursions, together with continuous-time limits that yield systems of differential equations governing ensemble evolution. We establish global convergence conditions, spectral stability criteria, and non-asymptotic generalization bounds under Rademacher Bartlett and Mendelson (2002) and algorithmic stability analyses. The resulting theory unifies recursive ensembles, structured weighting, and dynamical systems viewpoints in statistical learning. Experiments with kernel ridge regression Rasmussen and Williams (2006), spline smoothers Wahba (1990), and random Fourier feature models Rahimi and Recht (2007) demonstrate that recursive flows consistently improve approximation and generalization beyond static weighting. These results complete the trilogy begun in Papers I and II: from Fibonacci weighting, through geometric weighting theory, to fully dynamical recursive ensemble learning systems.

---

### Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure

Authors: Milad Rahmati, Nima Rahmati
Published: 2026-01-03
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.01053v1

The proliferation of Internet of Things devices in critical infrastructure has created unprecedented cybersecurity challenges, necessitating collaborative threat detection mechanisms that preserve data privacy while maintaining robustness against sophisticated attacks. Traditional federated learning approaches for IoT security suffer from two critical vulnerabilities: susceptibility to Byzantine attacks where malicious participants poison model updates, and inadequacy against future quantum computing threats that can compromise cryptographic aggregation protocols. This paper presents a novel Byzantine-robust federated learning framework integrated with post-quantum secure aggregation specifically designed for real-time threat intelligence sharing across critical IoT infrastructure. The proposed framework combines a adaptive weighted aggregation mechanism with lattice-based cryptographic protocols to simultaneously defend against model poisoning attacks and quantum adversaries. We introduce a reputation-based client selection algorithm that dynamically identifies and excludes Byzantine participants while maintaining differential privacy guarantees. The secure aggregation protocol employs CRYSTALS-Kyber for key encapsulation and homomorphic encryption to ensure confidentiality during parameter updates. Experimental evaluation on industrial IoT intrusion detection datasets demonstrates that our framework achieves 96.8% threat detection accuracy while successfully mitigating up to 40% Byzantine attackers, with only 18% computational overhead compared to non-secure federated approaches. The framework maintains sub-second aggregation latency suitable for real-time applications and provides 256-bit post-quantum security level.

---

### EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos

Authors: Hongming Fu, Wenjia Wang, Xiaozhen Qiao, Rolandos Alexandros Potamias, Taku Komura, Shuo Yang, Zheng Liu, Bo Zhao
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.GR
arXiv: https://arxiv.org/abs/2601.01050v2

We propose EgoGrasp, the first method to reconstruct world-space hand-object interactions (W-HOI) from dynamic egoview videos, supporting open-vocabulary objects. Accurate W-HOI reconstruction is critical for embodied intelligence yet remains challenging. Existing HOI methods are largely restricted to local camera coordinates or single frames, failing to capture global temporal dynamics. While some recent approaches attempt world-space hand estimation, they overlook object poses and HOI constraints. Moreover, previous HOI estimation methods either fail to handle open-set categories due to their reliance on object templates or employ differentiable rendering that requires per-instance optimization, resulting in prohibitive computational costs. Finally, frequent occlusions in egocentric videos severely degrade performance. To overcome these challenges, we propose a multi-stage framework: (i) a robust pre-processing pipeline leveraging vision foundation models for initial 3D scene, hand and object reconstruction; (ii) a body-guided diffusion model that incorporates explicit egocentric body priors for hand pose estimation; and (iii) an HOI-prior-informed diffusion model for hand-aware 6DoF pose infilling, ensuring physically plausible and temporally consistent W-HOI estimation. We experimentally demonstrate that EgoGrasp can achieve state-of-the-art performance in W-HOI reconstruction, handling multiple and open vocabulary objects robustly.

---

### KV-Embedding: Training-free Text Embedding via Internal KV Re-routing in Decoder-only LLMs

Authors: Yixuan Tang, Yi Yang
Published: 2026-01-03
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01046v1

While LLMs are powerful embedding backbones, their application in training-free settings faces two structural challenges: causal attention restricts early tokens from accessing subsequent context, and the next-token prediction objective biases representations toward generation rather than semantic compression. To address these limitations, we propose KV-Embedding, a framework that activates the latent representation power of frozen LLMs. Our method leverages the observation that the key-value (KV) states of the final token at each layer encode a compressed view of the sequence. By re-routing these states as a prepended prefix, we enable all tokens to access sequence-level context within a single forward pass. To ensure model-agnostic applicability, we introduce an automated layer selection strategy based on intrinsic dimensionality. Evaluations on MTEB across Qwen, Mistral, and Llama backbones show that KV-Embedding outperforms existing training-free baselines by up to 10%, while maintaining robust performance on sequences up to 4,096 tokens. These results demonstrate that internal state manipulation offers an efficient alternative to input modification, and we hope this work encourages further exploration of LLM internals for representation learning.

---

### Coarse-Grained Kullback--Leibler Control of Diffusion-Based Generative AI

Authors: Tatsuaki Tsuruyama
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01045v2

Diffusion models and score-based generative models provide a powerful framework for synthesizing high-quality images from noise. However, there is still no satisfactory theory that describes how coarse-grained quantities, such as blockwise intensity or class proportions after partitioning an image into spatial blocks, are preserved and evolve along the reverse diffusion dynamics. In previous work, the author introduced an information-theoretic Lyapunov function V for non-ergodic Markov processes on a state space partitioned into blocks, defined as the minimal Kullback-Leibler divergence to the set of stationary distributions reachable from a given initial condition, and showed that a leak-tolerant potential V-delta with a prescribed tolerance for block masses admits a closed-form expression as a scaling-and-clipping operation on block masses. In this paper, I transplant this framework to the reverse diffusion process in generative models and propose a reverse diffusion scheme that is projected by the potential V-delta (referred to as the V-delta projected reverse diffusion). I extend the monotonicity of V to time-inhomogeneous block-preserving Markov kernels and show that, under small leakage and the V-delta projection, V-delta acts as an approximate Lyapunov function. Furthermore, using a toy model consisting of block-constant images and a simplified reverse kernel, I numerically demonstrate that the proposed method keeps the block-mass error and the leak-tolerant potential within the prescribed tolerance, while achieving pixel-wise accuracy and visual quality comparable to the non-projected dynamics. This study reinterprets generative sampling as a decrease of an information potential from noise to data, and provides a design principle for reverse diffusion processes with explicit control of coarse-grained quantities.

---

### Evaluating transfer learning strategies for improving dairy cattle body weight prediction in small farms using depth-image and point-cloud data

Authors: Jin Wang, Angelo De Castro, Yuxi Zhang, Lucas Basolli Borsatto, Yuechen Guo, Victoria Bastos Primo, Ana Beatriz Montevecchio Bernardino, Gota Morota, Ricardo C Chebel, Haipeng Yu
Published: 2026-01-03
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.01044v1

Computer vision provides automated, non-invasive, and scalable tools for monitoring dairy cattle, thereby supporting management, health assessment, and phenotypic data collection. Although transfer learning is commonly used for predicting body weight from images, its effectiveness and optimal fine-tuning strategies remain poorly understood in livestock applications, particularly beyond the use of pretrained ImageNet or COCO weights. In addition, while both depth images and three-dimensional point-cloud data have been explored for body weight prediction, direct comparisons of these two modalities in dairy cattle are limited. Therefore, the objectives of this study were to 1) evaluate whether transfer learning from a large farm enhances body weight prediction on a small farm with limited data, and 2) compare the predictive performance of depth-image- and point-cloud-based approaches under three experimental designs. Top-view depth images and point-cloud data were collected from 1,201, 215, and 58 cows at large, medium, and small dairy farms, respectively. Four deep learning models were evaluated: ConvNeXt and MobileViT for depth images, and PointNet and DGCNN for point clouds. Transfer learning markedly improved body weight prediction on the small farm across all four models, outperforming single-source learning and achieving gains comparable to or greater than joint learning. These results indicate that pretrained representations generalize well across farms with differing imaging conditions and dairy cattle populations. No consistent performance difference was observed between depth-image- and point-cloud-based models. Overall, these findings suggest that transfer learning is well suited for small farm prediction scenarios where cross-farm data sharing is limited by privacy, logistical, or policy constraints, as it requires access only to pretrained model weights rather than raw data.

---

### Generalizable Deepfake Detection Based on Forgery-aware Layer Masking and Multi-artifact Subspace Decomposition

Authors: Xiang Zhang, Wenliang Weng, Daoyong Fu, Beijing Chen, Ziqiang Li, Ziwen He, Zhangjie Fu
Published: 2026-01-03
Categories: cs.CV, cs.MM
arXiv: https://arxiv.org/abs/2601.01041v3

Deepfake detection remains highly challenging, particularly in cross-dataset scenarios and complex real-world settings. This challenge mainly arises because artifact patterns vary substantially across different forgery methods, whereas adapting pretrained models to such artifacts often overemphasizes forgery-specific cues and disturbs semantic representations, thereby weakening generalization. Existing approaches typically rely on full-parameter fine-tuning or auxiliary supervision to improve discrimination. However, they often struggle to model diverse forgery artifacts without compromising pretrained representations. To address these limitations, we propose FMSD, a deepfake detection framework built upon Forgery-aware Layer Masking and Multi-Artifact Subspace Decomposition. Specifically, Forgery-aware Layer Masking evaluates the bias-variance characteristics of layer-wise gradients to identify forgery-sensitive layers, thereby selectively updating them while reducing unnecessary disturbance to pretrained representations. Building upon this, Multi-Artifact Subspace Decomposition further decomposes the selected layer weights via Singular Value Decomposition (SVD) into a semantic subspace and multiple learnable artifact subspaces. These subspaces are optimized to capture heterogeneous and complementary forgery artifacts, enabling effective modeling of diverse forgery patterns while preserving pretrained semantic representations. Furthermore, orthogonality and spectral consistency constraints are imposed to regularize the artifact subspaces, reducing redundancy across them while preserving the overall spectral structure of pretrained weights.

---

### Multi-Dimensional Prompt Chaining to Improve Open-Domain Dialogue Generation

Authors: Livia Leong Hui Teng
Published: 2026-01-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01037v1

Small language models (SLMs) offer significant deployment advantages but often struggle to match the dialogue quality of larger models in open-domain settings. In this paper, we propose a multi-dimensional prompt-chaining framework that integrates Naturalness, Coherence, and Engagingness dimensions to enhance human-likeness in open-domain dialogue generation. We apply the framework to two SLMs, TinyLlama and Llama-2-7B, and benchmark their performance against responses generated by substantially larger models, including Llama-2-70B and GPT-3.5 Turbo. We then employ automatic and human evaluation to assess the responses based on diversity, contextual coherence, as well as overall quality. Results show that the full framework improves response diversity by up to 29%, contextual coherence by up to 28%, and engagingness as well as naturalness by up to 29%. Notably, Llama-2-7B achieves performance comparable to substantially larger models, including Llama-2-70B and GPT-3.5 Turbo. Overall, the findings demonstrate that carefully designed prompt-based strategies provide an effective and resource-efficient pathway to improving open-domain dialogue quality in SLMs.

---

### Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising

Authors: Kiet Dang Vu, Trung Thai Tran, Kien Nguyen Do Trung, Duc Dung Nguyen
Published: 2026-01-03
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01036v1

While DETR-like architectures have demonstrated significant potential for monocular 3D object detection, they are often hindered by a critical limitation: the exclusion of 3D attributes from the bipartite matching process. This exclusion arises from the inherent ill-posed nature of 3D estimation from monocular image, which introduces instability during training. Consequently, high-quality 3D predictions can be erroneously suppressed by 2D-only matching criteria, leading to suboptimal results. To address this, we propose Mono3DV, a novel Transformer-based framework. Our approach introduces three key innovations. First, we develop a 3D-Aware Bipartite Matching strategy that directly incorporates 3D geometric information into the matching cost, resolving the misalignment caused by purely 2D criteria. Second, it is important to stabilize the Bipartite Matching to resolve the instability occurring when integrating 3D attributes. Therefore, we propose 3D-DeNoising scheme in the training phase. Finally, recognizing the gradient vanishing issue associated with conventional denoising techniques, we propose a novel Variational Query DeNoising mechanism to overcome this limitation, which significantly enhances model performance. Without leveraging any external data, our method achieves state-of-the-art results on the KITTI 3D object detection benchmark.

---

### Beyond Demand Estimation: Consumer Surplus Evaluation via Cumulative Propensity Weights

Authors: Zeyu Bian, Max Biggs, Ruijiang Gao, Zhengling Qi
Published: 2026-01-03
Categories: stat.ML, cs.AI, cs.LG, math.ST
arXiv: https://arxiv.org/abs/2601.01029v1

This paper develops a practical framework for using observational data to audit the consumer surplus effects of AI-driven decisions, specifically in targeted pricing and algorithmic lending. Traditional approaches first estimate demand functions and then integrate to compute consumer surplus, but these methods can be challenging to implement in practice due to model misspecification in parametric demand forms and the large data requirements and slow convergence of flexible nonparametric or machine learning approaches. Instead, we exploit the randomness inherent in modern algorithmic pricing, arising from the need to balance exploration and exploitation, and introduce an estimator that avoids explicit estimation and numerical integration of the demand function. Each observed purchase outcome at a randomized price is an unbiased estimate of demand and by carefully reweighting purchase outcomes using novel cumulative propensity weights (CPW), we are able to reconstruct the integral. Building on this idea, we introduce a doubly robust variant named the augmented cumulative propensity weighting (ACPW) estimator that only requires one of either the demand model or the historical pricing policy distribution to be correctly specified. Furthermore, this approach facilitates the use of flexible machine learning methods for estimating consumer surplus, since it achieves fast convergence rates by incorporating an estimate of demand, even when the machine learning estimate has slower convergence rates. Neither of these estimators is a standard application of off-policy evaluation techniques as the target estimand, consumer surplus, is unobserved. To address fairness, we extend this framework to an inequality-aware surplus measure, allowing regulators and firms to quantify the profit-equity trade-off. Finally, we validate our methods through comprehensive numerical studies.

---

### A Platform for Interactive AI Character Experiences

Authors: Rafael Wampfler, Chen Yang, Dillon Elste, Nikola Kovacevic, Philine Witzig, Markus Gross
Published: 2026-01-03
Categories: cs.HC, cs.AI, cs.CL, cs.GR
arXiv: https://arxiv.org/abs/2601.01027v1

From movie characters to modern science fiction - bringing characters into interactive, story-driven conversations has captured imaginations across generations. Achieving this vision is highly challenging and requires much more than just language modeling. It involves numerous complex AI challenges, such as conversational AI, maintaining character integrity, managing personality and emotions, handling knowledge and memory, synthesizing voice, generating animations, enabling real-world interactions, and integration with physical environments. Recent advancements in the development of foundation models, prompt engineering, and fine-tuning for downstream tasks have enabled researchers to address these individual challenges. However, combining these technologies for interactive characters remains an open problem. We present a system and platform for conveniently designing believable digital characters, enabling a conversational and story-driven experience while providing solutions to all of the technical challenges. As a proof-of-concept, we introduce Digital Einstein, which allows users to engage in conversations with a digital representation of Albert Einstein about his life, research, and persona. While Digital Einstein exemplifies our methods for a specific character, our system is flexible and generalizes to any story-driven or conversational character. By unifying these diverse AI components into a single, easy-to-adapt platform, our work paves the way for immersive character experiences, turning the dream of lifelike, story-based interactions into a reality.

---

### Enhanced Leukemic Cell Classification Using Attention-Based CNN and Data Augmentation

Authors: Douglas Costa Braga, Daniel Oliveira Dantas
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2601.01026v1

We present a reproducible deep learning pipeline for leukemic cell classification, focusing on system architecture, experimental robustness, and software design choices for medical image analysis. Acute lymphoblastic leukemia (ALL) is the most common childhood cancer, requiring expert microscopic diagnosis that suffers from inter-observer variability and time constraints. The proposed system integrates an attention-based convolutional neural network combining EfficientNetV2-B3 with Squeeze-and-Excitation mechanisms for automated ALL cell classification. Our approach employs comprehensive data augmentation, focal loss for class imbalance, and patient-wise data splitting to ensure robust and reproducible evaluation. On the C-NMC 2019 dataset (12,528 original images from 62 patients), the system achieves a 97.89% F1-score and 97.89% accuracy on the test set, with statistical validation through 100-iteration Monte Carlo experiments confirming significant improvements (p < 0.001) over baseline methods. The proposed pipeline outperforms existing approaches by up to 4.67% while using 89% fewer parameters than VGG16 (15.2M vs. 138M). The attention mechanism provides interpretable visualizations of diagnostically relevant cellular features, demonstrating that modern attention-based architectures can improve leukemic cell classification while maintaining computational efficiency suitable for clinical deployment.

---

### ITSELF: Attention Guided Fine-Grained Alignment for Vision-Language Retrieval

Authors: Tien-Huy Nguyen, Huu-Loc Tran, Thanh Duc Ngo
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2601.01024v1

Vision Language Models (VLMs) have rapidly advanced and show strong promise for text-based person search (TBPS), a task that requires capturing fine-grained relationships between images and text to distinguish individuals. Previous methods address these challenges through local alignment, yet they are often prone to shortcut learning and spurious correlations, yielding misalignment. Moreover, injecting prior knowledge can distort intra-modality structure. Motivated by our finding that encoder attention surfaces spatially precise evidence from the earliest training epochs, and to alleviate these issues, we introduceITSELF, an attention-guided framework for implicit local alignment. At its core, Guided Representation with Attentive Bank (GRAB) converts the model's own attention into an Attentive Bank of high-saliency tokens and applies local objectives on this bank, learning fine-grained correspondences without extra supervision. To make the selection reliable and non-redundant, we introduce Multi-Layer Attention for Robust Selection (MARS), which aggregates attention across layers and performs diversity-aware top-k selection; and Adaptive Token Scheduler (ATS), which schedules the retention budget from coarse to fine over training, preserving context early while progressively focusing on discriminative details. Extensive experiments on three widely used TBPS benchmarks showstate-of-the-art performance and strong cross-dataset generalization, confirming the effectiveness and robustness of our approach without additional prior supervision. Our project is publicly available at https://trhuuloc.github.io/itself

---

### Wireless Dataset Similarity: Measuring Distances in Supervised and Unsupervised Machine Learning

Authors: João Morais, Sadjad Alikhani, Akshay Malhotra, Shahab Hamidi-Rad, Ahmed Alkhateeb
Published: 2026-01-03
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.01023v1

This paper introduces a task- and model-aware framework for measuring similarity between wireless datasets, enabling applications such as dataset selection/augmentation, simulation-to-real (sim2real) comparison, task-specific synthetic data generation, and informing decisions on model training/adaptation to new deployments. We evaluate candidate dataset distance metrics by how well they predict cross-dataset transferability: if two datasets have a small distance, a model trained on one should perform well on the other. We apply the framework on an unsupervised task, channel state information (CSI) compression, using autoencoders. Using metrics based on UMAP embeddings, combined with Wasserstein and Euclidean distances, we achieve Pearson correlations exceeding 0.85 between dataset distances and train-on-one/test-on-another task performance. We also apply the framework to a supervised beam prediction in the downlink using convolutional neural networks. For this task, we derive a label-aware distance by integrating supervised UMAP and penalties for dataset imbalance. Across both tasks, the resulting distances outperform traditional baselines and consistently exhibit stronger correlations with model transferability, supporting task-relevant comparisons between wireless datasets.

---

### Decoupling Amplitude and Phase Attention in Frequency Domain for RGB-Event based Visual Object Tracking

Authors: Shiao Wang, Xiao Wang, Haonan Zhao, Jiarui Xu, Bo Jiang, Lin Zhu, Xin Zhao, Yonghong Tian, Jin Tang
Published: 2026-01-03
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01022v1

Existing RGB-Event visual object tracking approaches primarily rely on conventional feature-level fusion, failing to fully exploit the unique advantages of event cameras. In particular, the high dynamic range and motion-sensitive nature of event cameras are often overlooked, while low-information regions are processed uniformly, leading to unnecessary computational overhead for the backbone network. To address these issues, we propose a novel tracking framework that performs early fusion in the frequency domain, enabling effective aggregation of high-frequency information from the event modality. Specifically, RGB and event modalities are transformed from the spatial domain to the frequency domain via the Fast Fourier Transform, with their amplitude and phase components decoupled. High-frequency event information is selectively fused into RGB modality through amplitude and phase attention, enhancing feature representation while substantially reducing backbone computation. In addition, a motion-guided spatial sparsification module leverages the motion-sensitive nature of event cameras to capture the relationship between target motion cues and spatial probability distribution, filtering out low-information regions and enhancing target-relevant features. Finally, a sparse set of target-relevant features is fed into the backbone network for learning, and the tracking head predicts the final target position. Extensive experiments on three widely used RGB-Event tracking benchmark datasets, including FE108, FELT, and COESOT, demonstrate the high performance and efficiency of our method. The source code of this paper will be released on https://github.com/Event-AHU/OpenEvTracking

---

### Expanding the Chaos: Neural Operator for Stochastic (Partial) Differential Equations

Authors: Dai Shi, Lequan Lin, Andi Han, Luke Thompson, José Miguel Hernández-Lobato, Zhiyong Wang, Junbin Gao
Published: 2026-01-03
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01021v2

Stochastic differential equations (SDEs) and stochastic partial differential equations (SPDEs) are fundamental for modeling stochastic dynamics across the natural sciences and modern machine learning. Learning their solution operators with deep learning models promises fast solvers and new perspectives on classical learning tasks. In this work, we build on Wiener-chaos expansions (WCE) to design neural operator (NO) architectures for SDEs and SPDEs: we project driving noise paths onto orthonormal Wick-Hermite features and use NOs to parameterize the resulting chaos coefficients, enabling reconstruction of full trajectories from noise in a single forward pass. We also make the underlying WCE structure explicit for multi-dimensional SDEs and semilinear SPDEs by showing the coupled deterministic ODE/PDE systems governing these coefficients. Empirically, we achieve competitive accuracy across several tasks, including standard SPDE benchmarks and SDE-based diffusion one-step image sampling, topological graph interpolation, financial extrapolation, parameter estimation, and manifold SDE flood forecasting. These results suggest WCE-based neural operators are a practical and scalable approach to learning SDE/SPDE solution operators across domains.

---

### Improving Variational Autoencoder using Random Fourier Transformation: An Aviation Safety Anomaly Detection Case-Study

Authors: Ata Akbari Asanjan, Milad Memarzadeh, Bryan Matthews, Nikunj Oza
Published: 2026-01-03
Categories: cs.LG, cs.AI, eess.SY
arXiv: https://arxiv.org/abs/2601.01016v3

In this study, we focus on the training process and inference improvements of deep neural networks (DNNs), specifically Autoencoders (AEs) and Variational Autoencoders (VAEs), using Random Fourier Transformation (RFT). We further explore the role of RFT in model training behavior using Frequency Principle (F-Principle) analysis and show that models with RFT turn to learn low frequency and high frequency at the same time, whereas conventional DNNs start from low frequency and gradually learn (if successful) high-frequency features. We focus on reconstruction-based anomaly detection using autoencoder and variational autoencoder and investigate the RFT's role. We also introduced a trainable variant of RFT that uses the existing computation graph to train the expansion of RFT instead of it being random. We showcase our findings with two low-dimensional synthetic datasets for data representation, and an aviation safety dataset, called Dashlink, for high-dimensional reconstruction-based anomaly detection. The results indicate the superiority of models with Fourier transformation compared to the conventional counterpart and remain inconclusive regarding the benefits of using trainable Fourier transformation in contrast to the Random variant.

---

### HyperJoin: LLM-augmented Hypergraph Link Prediction for Joinable Table Discovery

Authors: Shiyuan Liu, Jianwei Wang, Xuemin Lin, Lu Qin, Wenjie Zhang, Ying Zhang
Published: 2026-01-03
Categories: cs.CL, cs.DB
arXiv: https://arxiv.org/abs/2601.01015v1

As a pivotal task in data lake management, joinable table discovery has attracted widespread interest. While existing language model-based methods achieve remarkable performance by combining offline column representation learning with online ranking, their design insufficiently accounts for the underlying structural interactions: (1) offline, they directly model tables into isolated or pairwise columns, thereby struggling to capture the rich inter-table and intra-table structural information; and (2) online, they rank candidate columns based solely on query-candidate similarity, ignoring the mutual interactions among the candidates, leading to incoherent result sets. To address these limitations, we propose HyperJoin, a large language model (LLM)-augmented Hypergraph framework for Joinable table discovery. Specifically, we first construct a hypergraph to model tables using both the intra-table hyperedges and the LLM-augmented inter-table hyperedges. Consequently, the task of joinable table discovery is formulated as link prediction on this constructed hypergraph. We then design HIN, a Hierarchical Interaction Network that learns expressive column representations through bidirectional message passing over columns and hyperedges. To strengthen coherence and internal consistency in the result columns, we cast online ranking as a coherence-aware top-k column selection problem. We then introduce a reranking module that leverages a maximum spanning tree algorithm to prune noisy connections and maximize coherence. Experiments demonstrate the superiority of HyperJoin, achieving average improvements of 21.4% (Precision@15) and 17.2% (Recall@15) over the best baseline.

---

### Geometric and Dynamic Scaling in Deep Transformers

Authors: Haoran Su, Chenyu You
Published: 2026-01-03
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.01014v3

Despite their empirical success, pushing Transformer architectures to extreme depth often leads to a paradoxical failure: representations become increasingly redundant, lose rank, and ultimately collapse. Existing explanations largely attribute this phenomenon to optimization instability or vanishing gradients, yet such accounts fail to explain why collapse persists even under modern normalization and initialization schemes. In this paper, we argue that the collapse of deep Transformers is fundamentally a geometric problem. Standard residual updates implicitly assume that feature accumulation is always beneficial, but offer no mechanism to constrain update directions or to erase outdated information. As depth increases, this leads to systematic drift off the semantic manifold and monotonic feature accumulation, causing representational degeneracy. We propose a unified geometric framework that addresses these failures through two orthogonal principles. First, manifold-constrained hyper-connections restrict residual updates to valid local tangent directions, preventing uncontrolled manifold drift. Second, deep delta learning introduces data-dependent, non-monotonic updates that enable reflection and erasure of redundant features rather than their unconditional accumulation. Together, these mechanisms decouple the direction and sign of feature updates, yielding a stable geometric evolution across depth. We term the resulting architecture the Manifold-Geometric Transformer (MGT). Our analysis predicts that enforcing geometric validity while allowing dynamic erasure is essential for avoiding rank collapse in ultra-deep networks. We outline an evaluation protocol for Transformers exceeding 100 layers to test the hypothesis that geometry, rather than depth itself, is the key limiting factor in deep representation learning.

---

### Intention Collapse: Intention-Level Metrics for Reasoning in Language Models

Authors: Patricio Vera
Published: 2026-01-03
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01011v2

Language generation maps a rich, high-dimensional internal state to a single token sequence. We study this many-to-one mapping through the lens of intention collapse: the projection from an internal intention space I to an external language space L. We introduce three cheap, model-agnostic metrics computed on a pre-collapse state I: (i) intention entropy Hint(I), (ii) effective dimensionality deff(I), and (iii) recoverability Recov(I), operationalized as probe AUROC for predicting eventual success. We evaluate these metrics in a 3x3 study across models (Mistral-7B, LLaMA-3.1-8B, Qwen-2.5-7B) and benchmarks (GSM8K, ARC-Challenge, AQUA-RAT), comparing baseline, chain-of-thought (CoT), and a babble control (n=200 items per cell). CoT increases average accuracy from 34.2% to 47.3% (+13.1 pp), driven by large gains on GSM8K but consistent degradations on ARC-Challenge. Across models, CoT induces distinct entropy regimes relative to baseline, dH = Hint(CoT) - Hint(Base): Mistral shows dH < 0 (lower-entropy CoT), whereas LLaMA shows dH > 0 (higher-entropy CoT), highlighting heterogeneity in CoT-induced internal uncertainty. Finally, probe AUROC is significantly above chance in a subset of settings and can dissociate from behavioral accuracy (e.g., high AUROC alongside lower CoT accuracy on ARC-Challenge for Qwen), suggesting that informative internal signal is not always reliably converted into a final discrete decision under constrained response formats.

---

### Disordered Dynamics in High Dimensions: Connections to Random Matrices and Machine Learning

Authors: Blake Bordelon, Cengiz Pehlevan
Published: 2026-01-03
Categories: cond-mat.dis-nn, stat.ML
arXiv: https://arxiv.org/abs/2601.01010v2

We provide an overview of high dimensional dynamical systems driven by random matrices, focusing on applications to simple models of learning and generalization in machine learning theory. Using both cavity method arguments and path integrals, we review how the behavior of a coupled infinite dimensional system can be characterized as a stochastic process for each single site of the system. We provide a pedagogical treatment of dynamical mean field theory (DMFT), a framework that can be flexibly applied to these settings. The DMFT single site stochastic process is fully characterized by a set of (two-time) correlation and response functions. For linear time-invariant systems, we illustrate connections between random matrix resolvents and the DMFT response. We demonstrate applications of these ideas to machine learning models such as gradient flow, stochastic gradient descent on random feature models and deep linear networks in the feature learning regime trained on random data. We demonstrate how bias and variance decompositions (analysis of ensembling/bagging etc) can be computed by averaging over subsets of the DMFT noise variables. From our formalism we also investigate how linear systems driven with random non-Hermitian matrices (such as random feature models) can exhibit non-monotonic loss curves with training time, while Hermitian matrices with the matching spectra do not, highlighting a different mechanism for non-monotonicity than small eigenvalues causing instability to label noise. Lastly, we provide asymptotic descriptions of the training and test loss dynamics for randomly initialized deep linear neural networks trained in the feature learning regime with high-dimensional random data. In this case, the time translation invariance structure is lost and the hidden layer weights are characterized as spiked random matrices.

---

### Data-Driven Assessment of Concrete Mixture Compositions on Chloride Transport via Standalone Machine Learning Algorithms

Authors: Mojtaba Aliasghar-Mamaghani, Mohammadreza Khalafi
Published: 2026-01-03
Categories: cs.LG, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2601.01009v1

This paper employs a data-driven approach to determine the impact of concrete mixture compositions on the temporal evolution of chloride in concrete structures. This is critical for assessing the service life of civil infrastructure subjected to aggressive environments. The adopted methodology relies on several simple and complex standalone machine learning (ML) algorithms, with the primary objective of establishing confidence in the unbiased prediction of the underlying hidden correlations. The simple algorithms include linear regression (LR), k-nearest neighbors (KNN) regression, and kernel ridge regression (KRR). The complex algorithms entail support vector regression (SVR), Gaussian process regression (GPR), and two families of artificial neural networks, including a feedforward network (multilayer perceptron, MLP) and a gated recurrent unit (GRU). The MLP architecture cannot explicitly handle sequential data, a limitation addressed by the GRU. A comprehensive dataset is considered. The performance of ML algorithms is evaluated, with KRR, GPR, and MLP exhibiting high accuracy. Given the diversity of the adopted concrete mixture proportions, the GRU was unable to accurately reproduce the response in the test set. Further analyses elucidate the contributions of mixture compositions to the temporal evolution of chloride. The results obtained from the GPR model unravel latent correlations through clear and explainable trends. The MLP, SVR, and KRR also provide acceptable estimates of the overall trends. The majority of mixture components exhibit an inverse relation with chloride content, while a few components demonstrate a direct correlation. These findings highlight the potential of surrogate approaches for describing the physical processes involved in chloride ingress and the associated correlations, toward the ultimate goal of enhancing the service life of civil infrastructure.

---

### An Explainable Agentic AI Framework for Uncertainty-Aware and Abstention-Enabled Acute Ischemic Stroke Imaging Decisions

Authors: Md Rashadul Islam
Published: 2026-01-03
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.01008v1

Artificial intelligence models have shown strong potential in acute ischemic stroke imaging, particularly for lesion detection and segmentation using computed tomography and magnetic resonance imaging. However, most existing approaches operate as black box predictors, producing deterministic outputs without explicit uncertainty awareness or structured mechanisms to abstain under ambiguous conditions. This limitation raises serious safety and trust concerns in high risk emergency radiology settings. In this paper, we propose an explainable agentic AI framework for uncertainty aware and abstention enabled decision support in acute ischemic stroke imaging. The framework follows a modular agentic pipeline in which a perception agent performs lesion aware image analysis, an uncertainty estimation agent computes slice level predictive reliability, and a decision agent determines whether to issue a prediction or abstain based on predefined uncertainty thresholds. Unlike prior stroke imaging systems that primarily focus on improving segmentation or classification accuracy, the proposed framework explicitly prioritizes clinical safety, transparency, and clinician aligned decision behavior. Qualitative and case based analyses across representative stroke imaging scenarios demonstrate that uncertainty driven abstention naturally emerges in diagnostically ambiguous regions and low information slices. The framework further integrates visual explanation mechanisms to support both predictive and abstention decisions, addressing a key limitation of existing uncertainty aware medical imaging systems. Rather than introducing a new performance benchmark, this work presents agentic control, uncertainty awareness, and selective abstention as essential design principles for developing safe and trustworthy medical imaging AI systems.

---

### FinRetrieval: A Benchmark for Financial Data Retrieval by AI Agents

Authors: Eric Y. Kim, Jie Huang
Published: 2026-01-02
Categories: cs.IR, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2603.04403v1

AI agents increasingly assist with financial research, yet no benchmark evaluates their ability to retrieve specific numeric values from structured databases. We introduce FinRetrieval, a benchmark of 500 financial retrieval questions with ground truth answers, agent responses from 14 configurations across three frontier providers (Anthropic, OpenAI, Google), and complete tool call execution traces. Our evaluation reveals that tool availability dominates performance: Claude Opus achieves 90.8% accuracy with structured data APIs but only 19.8% with web search alone--a 71 percentage point gap that exceeds other providers by 3-4x. We find that reasoning mode benefits vary inversely with base capability (+9.0pp for OpenAI vs +2.8pp for Claude), explained by differences in base-mode tool utilization rather than reasoning ability. Geographic performance gaps (5.6pp US advantage) stem from fiscal year naming conventions, not model limitations. We release the dataset, evaluation code, and tool traces to enable research on financial AI systems.

---

### SearchGym: A Modular Infrastructure for Cross-Platform Benchmarking and Hybrid Search Orchestration

Authors: Jerome Tze-Hou Hsu
Published: 2026-01-02
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2603.04402v1

The rapid growth of Retrieval-Augmented Generation (RAG) has created a proliferation of toolkits, yet a fundamental gap remains between experimental prototypes and robust, production-ready systems. We present SearchGym, a modular infrastructure designed for cross-platform benchmarking and hybrid search orchestration. Unlike existing model-centric frameworks, SearchGym decouples data representation, embedding strategies, and retrieval logic into stateful abstractions: Dataset, VectorSet, and App. This separation enables a Compositional Config Algebra, allowing designers to synthesize entire systems from hierarchical configurations while ensuring perfect reproducibility. Moreover, we analyze the "Top-$k$ Cognizance" in hybrid retrieval pipelines, demonstrating that the optimal sequence of semantic ranking and structured filtering is highly dependent on filter strength. Evaluated on the LitSearch expert-annotated benchmark, SearchGym achieves a 70% Top-100 retrieval rate. SearchGym reveals a design tension between generalizability and optimizability, presenting the potential where engineering optimization may serve as a tool for uncovering the causal mechanisms inherent in information retrieval across heterogeneous domains. An open-source implementation of SearchGym is available at: https://github.com/JeromeTH/search-gym

---

### ChiEngMixBench: Evaluating Large Language Models on Expert-Style Chinese-English Terminology Mixing

Authors: Qingyan Yang, Tongxi Wang, Yunsheng Luo
Published: 2026-01-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.16217v2

Large language models increasingly mediate multilingual professional communication, where useful generation requires adapting to community conventions about which expressions are retained, translated, or mixed. Existing benchmarks rarely isolate such community-conditioned choices. We introduce ChiEngMixBench, a controlled benchmark for Chinese AI/CS discourse, where Chinese frames routinely incorporate established English technical terms. Built from public technical discussions, it contains 1,706 source-derived candidate pairs covering 1,344 non-empty normalized terms, including a 1,167-pair strict subset that fixes the Chinese prefix and syntactic position while varying only the terminology form. The benchmark combines paired likelihood comparisons with a transparent reference-profile diagnostic for open-ended responses. Across nine open-weight models, Chinese equivalents receive higher likelihood on most pairs, revealing a gap between source-attested usage and model preference. Specialized terms show a small directional lift that is not robust after frequency and length controls and multiple-comparison correction. Human evaluation and baseline analyses show that reference-profile conformity is informative under the intended mixed-style rubric but does not reliably predict holistic response preference. ChiEngMixBench provides a reusable testbed for community-specific multilingual conventions with explicit diagnostic boundaries.

---

### Entropy-Tree: Tree-Based Decoding with Entropy-Guided Exploration

Authors: Longxuan Wei, Yubo Zhang, Zijiao Zhang, Zhihu Wang, Shiwan Zhao, Tianyu Huang, Huiting Zhao, Chenfei Liu, Shenao Zhang, Junchi Yan
Published: 2026-01-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.15296v1

Large language models achieve strong reasoning performance, yet existing decoding strategies either explore blindly (random sampling) or redundantly (independent multi-sampling). We propose Entropy-Tree, a tree-based decoding method that exploits entropy as a signal for branching decisions--expanding the search tree only at positions where the model exhibits genuine uncertainty. Entropy-Tree shows superior accuracy and calibration in reasoning tasks: it achieves better pass@k than Multi-chain across multiple models and datasets, and its predictive entropy demonstrates better AUROC compared to several traditional metrics. Entropy-Tree unifies efficient structured exploration and reliable uncertainty estimation within a single decoding procedure.

---

### Opening the Black Box: A Survey on the Mechanisms of Multi-Step Reasoning in Large Language Models

Authors: Liangming Pan, Jason Liang, Jiaran Ye, Minglai Yang, Xinyuan Lu, Fengbin Zhu
Published: 2026-01-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.14270v1

Large Language Models (LLMs) have demonstrated remarkable abilities to solve problems requiring multiple reasoning steps, yet the internal mechanisms enabling such capabilities remain elusive. Unlike existing surveys that primarily focus on engineering methods to enhance performance, this survey provides a comprehensive overview of the mechanisms underlying LLM multi-step reasoning. We organize the survey around a conceptual framework comprising seven interconnected research questions, from how LLMs execute implicit multi-hop reasoning within hidden activations to how verbalized explicit reasoning remodels the internal computation. Finally, we highlight five research directions for future mechanistic studies.

---

### The Slow Drift of Support: Boundary Failures in Multi-Turn Mental Health LLM Dialogues

Authors: Youyou Cheng, Zhuangwei Kang, Kerry Jiang, Chenyu Sun, Qiyang Pan
Published: 2026-01-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.14269v1

Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output prohibited words in single-turn conversations, neglecting the gradual erosion of safety boundaries in long dialogues. Examples include making definitive guarantees, assuming responsibility, and playing professional roles. We believe that with the evolution of mainstream LLMs, words with obvious safety risks are easily filtered by their underlying systems, while the real danger lies in the gradual transgression of boundaries during multi-turn interactions, driven by the LLM's attempts at comfort and empathy. This paper proposes a multi-turn stress testing framework and conducts long-dialogue safety tests on three cutting-edge LLMs using two pressure methods: static progression and adaptive probing. We generated 50 virtual patient profiles and stress-tested each model through up to 20 rounds of virtual psychiatric dialogues. The experimental results show that violations are common, and both pressure modes produced similar violation rates. However, adaptive probing significantly advanced the time at which models crossed boundaries, reducing the average number of turns from 9.21 in static progression to 4.64. Under both mechanisms, making definitive or zero-risk promises was the primary way in which boundaries were breached. These findings suggest that the robustness of LLM safety boundaries cannot be inferred solely through single-turn tests; it is necessary to fully consider the wear and tear on safety boundaries caused by different interaction pressures and characteristics in extended dialogues.

---

### Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs

Authors: Andrew Kiruluta
Published: 2026-01-02
Categories: cs.LG, cs.CL, cs.IT
arXiv: https://arxiv.org/abs/2601.06100v1

We present a theory-first framework that interprets inference-time adaptation in large language models (LLMs) as online Bayesian state estimation. Rather than modeling rapid adaptation as implicit optimization or meta-learning, we formulate task- and context-specific learning as the sequential inference of a low-dimensional latent adaptation state governed by a linearized state-space model. Under Gaussian assumptions, adaptation follows a Kalman recursion with closed-form updates for both the posterior mean and covariance. This perspective elevates epistemic uncertainty to an explicit dynamical variable. We show that inference-time learning is driven by covariance collapse, i.e., rapid contraction of posterior uncertainty induced by informative tokens, which typically precedes convergence of the posterior mean. Using observability conditions on token-level Jacobians, we establish stability of the Bayesian filter, prove exponential covariance contraction rates, and derive mean-square error bounds. Gradient descent, natural-gradient methods, and meta-learning updates arise as singular, noise-free limits of the filtering dynamics, positioning optimization-based adaptation as a degenerate approximation of Bayesian inference. The resulting theory provides a unified probabilistic account of in-context learning, parameter-efficient adaptation, and test-time learning without parameter updates. It yields explicit guarantees on stability and sample efficiency, offers a principled interpretation of prompt informativeness via information accumulation, and clarifies the role of uncertainty dynamics absent from existing accounts. Minimal illustrative experiments corroborate the qualitative predictions of the theory.

---

### Automatic Question Generation for Intuitive Learning Utilizing Causal Graph Guided Chain of Thought Reasoning

Authors: Nicholas X. Wang, Neel V. Parpia, Aaryan D. Parikh, Aggelos K. Katsaggelos
Published: 2026-01-02
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06098v1

Intuitive learning is crucial for developing deep conceptual understanding, especially in STEM education, where students often struggle with abstract and interconnected concepts. Automatic question generation has become an effective strategy for personalized and adaptive learning. However, its effectiveness is hindered by hallucinations in large language models (LLMs), which may generate factually incorrect, ambiguous, or pedagogically inconsistent questions. To address this issue, we propose a novel framework that combines causal-graph-guided Chain-of-Thought (CoT) reasoning with a multi-agent LLM architecture. This approach ensures the generation of accurate, meaningful, and curriculum-aligned questions. Causal graphs provide an explicit representation of domain knowledge, while CoT reasoning facilitates a structured, step-by-step traversal of related concepts. Dedicated LLM agents are assigned specific tasks such as graph pathfinding, reasoning, validation, and output, all working within domain constraints. A dual validation mechanism-at both the conceptual and output stages-greatly reduces hallucinations. Experimental results demonstrate up to a 70% improvement in quality compared to reference methods and yielded highly favorable outcomes in subjective evaluations.

---

### Semantic Event Graphs for Long-Form Video Question Answering

Authors: Aradhya Dixit, Tianxi Liang
Published: 2026-01-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06097v1

Long-form video question answering remains challenging for modern vision-language models, which struggle to reason over hour-scale footage without exceeding practical token and compute budgets. Existing systems typically downsample frames or feed dense visual embeddings to large-context language models, trading off temporal coverage against cost. We propose Semantic Event Graphs (SEG), a lightweight symbolic interface between video and language that replaces raw frames with compact temporal interaction logs. Our pipeline detects and tracks objects with YOLOv11, converts proximity patterns into START/END human-object events, and organizes them into a Temporal Scene Graph (TSG). At inference time, a query-aware pruning module identifies anchor entities and lexically relevant events, returning only a small subgraph which is verbalized and passed to Gemini 2.5 Flash for answer generation. On five YouTube videos (300-500 interactions each) and 120 automatically generated long-horizon questions, SEG achieves 65.0% accuracy using only 3.47k tokens per query, closely matching a full-log baseline (62.5% at 40.39k tokens) while reducing token usage by 91.4%. A short-context baseline restricted to the last 30 seconds collapses to 2.5% accuracy, underscoring the need for explicit temporal memory. These results show that symbolic temporal graphs can serve as an effective, plug-and-play memory layer for off-the-shelf vision-language models, preserving long-range reasoning ability while making long-form video question answering substantially more token- and cost-efficient. Code, logs, and event-extraction tools will be released for reproducibility.

---

### Feedback Indices to Evaluate LLM Responses to Rebuttals for Multiple Choice Type Questions

Authors: Justin C. Dunlap, Anne-Simone Parent, Ralf Widenhorn
Published: 2026-01-02
Categories: physics.ed-ph, cs.AI
arXiv: https://arxiv.org/abs/2601.03285v1

We present a systematic framework of indices designed to characterize Large Language Model (LLM) responses when challenged with rebuttals during a chat. Assessing how LLMs respond to user dissent is crucial for understanding their reliability and behavior patterns, yet the complexity of human-LLM interactions makes systematic evaluation challenging. Our approach employs a fictitious-response rebuttal method that quantifies LLM behavior when presented with multiple-choice questions followed by deliberate challenges to their fictitious previous response. The indices are specifically designed to detect and measure what could be characterized as sycophantic behavior (excessive agreement with user challenges) or stubborn responses (rigid adherence to the fictitious response in the chat history) from LLMs. These metrics allow investigation of the relationships between sycophancy, stubbornness, and the model's actual mastery of the subject matter. We demonstrate the utility of these indices using two physics problems as test scenarios with various OpenAI models. The framework is intentionally generalizable to any multiple-choice format question, including on topics without universally accepted correct answers. Our results reveal measurable differences across OpenAI model generations, with trends indicating that newer models and those employing greater "Reasoning Effort" exhibit reduced sycophantic behavior. The FR pairing method combined with our proposed indices provides a practical, adaptable toolkit for systematically comparing LLM dialogue behaviors across different models and contexts.

---

### AI-Guided Discovery of Novel Ionic Liquid Solvents for Industrial CO2 Capture

Authors: Davide Garbelotto, Alexander Lobo, Urvi Awasthi, Oleg Medvedev, Srayanta Mukherjee, Anton Aristov, Konstantin Polunin, Alex De Mur, Leonid Zhukov, Azad Huseynov, Murad Abdullayev
Published: 2026-01-02
Categories: physics.chem-ph, cond-mat.mtrl-sci, cs.AI
arXiv: https://arxiv.org/abs/2601.03284v1

We present an AI-driven approach to discover compounds with optimal properties for CO2 capture from flue gas-refinery emissions' primary source. Focusing on ionic liquids (ILs) as alternatives to traditional amine-based solvents, we successfully identify new IL candidates with high working capacity, manageable viscosity, favorable regeneration energy, and viable synthetic routes. Our approach follows a five-stage pipeline. First, we generate IL candidates by pairing available cation and anion molecules, then predict temperature- and pressure-dependent CO2 solubility and viscosity using a GNN-based molecular property prediction model. Next, we convert solubility to working capacity and regeneration energy via Van't Hoff modeling, and then find the best set of candidates using Pareto optimization, before finally filtering those based on feasible synthesis routes. We identify 36 feasible candidates that could enable 5-10% OPEX savings and up to 10% CAPEX reductions through lower regeneration energy requirements and reduced corrosivity-offering a novel carbon-capture strategy for refineries moving forward.

---

### Socially-Aware Recommender Systems Mitigate Opinion Clusterization

Authors: Lukas Schüepp, Carmen Amo Alonso, Florian Dörfler, Giulia De Pasquale
Published: 2026-01-02
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.02412v1

Recommender systems shape online interactions by matching users with creators content to maximize engagement. Creators, in turn, adapt their content to align with users preferences and enhance their popularity. At the same time, users preferences evolve under the influence of both suggested content from the recommender system and content shared within their social circles. This feedback loop generates a complex interplay between users, creators, and recommender algorithms, which is the key cause of filter bubbles and opinion polarization. We develop a social network-aware recommender system that explicitly accounts for this user-creators feedback interaction and strategically exploits the topology of the user's own social network to promote diversification. Our approach highlights how accounting for and exploiting user's social network in the recommender system design is crucial to mediate filter bubble effects while balancing content diversity with personalization. Provably, opinion clusterization is positively correlated with the influence of recommended content on user opinions. Ultimately, the proposed approach shows the power of socially-aware recommender systems in combating opinion polarization and clusterization phenomena.

---

### SpikySpace: A Spiking State Space Model for Energy-Efficient Time Series Forecasting

Authors: Kaiwen Tang, Jiaqi Zheng, Yuze Jin, Yupeng Qiu, Guangda Sun, Zhanglu Yan, Weng-Fai Wong
Published: 2026-01-02
Categories: cs.NE, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.02411v2

Time-series forecasting in domains like traffic management and industrial monitoring often requires real-time, energy-efficient processing on edge devices with limited resources. Spiking neural networks (SNNs) offer event-driven computation and ultra-low power and have been proposed for use in this space. Unfortunately, existing SNN-based time-series forecasters often use complex transformer blocks. To address this issue, we propose SpikySpace, a spiking state-space model (SSM) that reduces the quadratic cost in the attention block to linear time via spiking selective scanning. Further, we introduce PTsoftplus and PTSiLU, two efficient approximations of SiLU and Softplus that replace costly exponential and division operations with simple bit-shifts. Evaluated on four multivariate time-series benchmarks, SpikySpace outperforms the leading SNN in terms of accuracy by up to 3.0% while reducing energy consumption by over 96.1%. As the first fully spiking state-space model, SpikySpace bridges neuromorphic efficiency with modern sequence modeling, opening a practical path toward efficient time series forecasting systems. Our code is available at https://anonymous.4open.science/r/SpikySpace.

---

### The Vibe-Check Protocol: Quantifying Cognitive Offloading in AI Programming

Authors: Aizierjiang Aiersilan
Published: 2026-01-02
Categories: cs.SE, cs.AI, cs.CY, cs.GR
arXiv: https://arxiv.org/abs/2601.02410v1

The integration of Large Language Models (LLMs) into software engineering education has driven the emergence of ``Vibe Coding,'' a paradigm where developers articulate high-level intent through natural language and delegate implementation to AI agents. While proponents argue this approach modernizes pedagogy by emphasizing conceptual design over syntactic memorization, accumulating empirical evidence raises concerns regarding skill retention and deep conceptual understanding. This paper proposes a theoretical framework to investigate the research question: \textit{Is Vibe Coding a better way to learn software engineering?} We posit a divergence in student outcomes between those leveraging AI for acceleration versus those using it for cognitive offloading. To evaluate these educational trade-offs, we propose the \textbf{Vibe-Check Protocol (VCP)}, a systematic benchmarking framework incorporating three quantitative metrics: the \textit{Cold Start Refactor} ($M_{CSR}$) for modeling skill decay; \textit{Hallucination Trap Detection} ($M_{HT}$) based on signal detection theory to evaluate error identification; and the \textit{Explainability Gap} ($E_{gap}$) for quantifying the divergence between code complexity and conceptual comprehension. Through controlled comparisons, VCP aims to provide a quantitative basis for educators to determine the optimal pedagogical boundary: identifying contexts where Vibe Coding fosters genuine mastery and contexts where it introduces hidden technical debt and superficial competence.

---

### Expert-Guided Explainable Few-Shot Learning with Active Sample Selection for Medical Image Analysis

Authors: Longwei Wang, Ifrat Ikhtear Uddin, KC Santosh
Published: 2026-01-02
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.02409v1

Medical image analysis faces two critical challenges: scarcity of labeled data and lack of model interpretability, both hindering clinical AI deployment. Few-shot learning (FSL) addresses data limitations but lacks transparency in predictions. Active learning (AL) methods optimize data acquisition but overlook interpretability of acquired samples. We propose a dual-framework solution: Expert-Guided Explainable Few-Shot Learning (EGxFSL) and Explainability-Guided AL (xGAL). EGxFSL integrates radiologist-defined regions-of-interest as spatial supervision via Grad-CAM-based Dice loss, jointly optimized with prototypical classification for interpretable few-shot learning. xGAL introduces iterative sample acquisition prioritizing both predictive uncertainty and attention misalignment, creating a closed-loop framework where explainability guides training and sample selection synergistically. On the BraTS (MRI), VinDr-CXR (chest X-ray), and SIIM-COVID-19 (chest X-ray) datasets, we achieve accuracies of 92\%, 76\%, and 62\%, respectively, consistently outperforming non-guided baselines across all datasets. Under severe data constraints, xGAL achieves 76\% accuracy with only 680 samples versus 57\% for random sampling. Grad-CAM visualizations demonstrate guided models focus on diagnostically relevant regions, with generalization validated on breast ultrasound confirming cross-modality applicability.

---

### Scale-aware Adaptive Supervised Network with Limited Medical Annotations

Authors: Zihan Li, Dandan Shan, Yunxiang Li, Paul E. Kinahan, Qingqi Hong
Published: 2026-01-02
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.01005v1

Medical image segmentation faces critical challenges in semi-supervised learning scenarios due to severe annotation scarcity requiring expert radiological knowledge, significant inter-annotator variability across different viewpoints and expertise levels, and inadequate multi-scale feature integration for precise boundary delineation in complex anatomical structures. Existing semi-supervised methods demonstrate substantial performance degradation compared to fully supervised approaches, particularly in small target segmentation and boundary refinement tasks. To address these fundamental challenges, we propose SASNet (Scale-aware Adaptive Supervised Network), a dual-branch architecture that leverages both low-level and high-level feature representations through novel scale-aware adaptive reweight mechanisms. Our approach introduces three key methodological innovations, including the Scale-aware Adaptive Reweight strategy that dynamically weights pixel-wise predictions using temporal confidence accumulation, the View Variance Enhancement mechanism employing 3D Fourier domain transformations to simulate annotation variability, and segmentation-regression consistency learning through signed distance map algorithms for enhanced boundary precision. These innovations collectively address the core limitations of existing semi-supervised approaches by integrating spatial, temporal, and geometric consistency principles within a unified optimization framework. Comprehensive evaluation across LA, Pancreas-CT, and BraTS datasets demonstrates that SASNet achieves superior performance with limited labeled data, surpassing state-of-the-art semi-supervised methods while approaching fully supervised performance levels. The source code for SASNet is available at https://github.com/HUANGLIZI/SASNet.

---

### Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations

Authors: Amin Abyaneh, Charlotte Morissette, Mohamad H. Danesh, Anas El Houssaini, David Meger, Gregory Dudek, Hsiu-Chin Lin
Published: 2026-01-02
Categories: cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.01003v2

Diffusion policies have emerged as powerful generative models for offline policy learning, whose sampling process can be rigorously characterized by a score function guiding a stochastic differential equation (SDE). However, the same score-based SDE modeling that grants diffusion policies the flexibility to learn diverse behavior also incurs solver and score-matching errors, large data requirements, and inconsistencies in action generation. While less critical in image generation, these inaccuracies compound and lead to failure in continuous control settings. We introduce contractive diffusion policies (CDPs) to induce contractive behavior in the diffusion sampling dynamics. Contraction pulls nearby flows closer to enhance robustness against solver and score-matching errors while reducing unwanted action variance. We develop an in-depth theoretical analysis along with a practical implementation recipe to incorporate CDPs into existing diffusion policy architectures with minimal modification and computational cost. We evaluate CDPs for offline learning by conducting extensive experiments in simulation and real-world settings. Across benchmarks, CDPs often outperform baseline policies, with pronounced benefits under data scarcity.

---

### Lightweight Channel Attention for Efficient CNNs

Authors: Prem Babu Kanaparthi, Tulasi Venkata Sri Varshini Padamata
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01002v1

Attention mechanisms have become integral to modern convolutional neural networks (CNNs), delivering notable performance improvements with minimal computational overhead. However, the efficiency accuracy trade off of different channel attention designs remains underexplored. This work presents an empirical study comparing Squeeze and Excitation (SE), Efficient Channel Attention (ECA), and a proposed Lite Channel Attention (LCA) module across ResNet 18 and MobileNetV2 architectures on CIFAR 10. LCA employs adaptive one dimensional convolutions with grouped operations to reduce parameter usage while preserving effective attention behavior. Experimental results show that LCA achieves competitive accuracy, reaching 94.68 percent on ResNet 18 and 93.10 percent on MobileNetV2, while matching ECA in parameter efficiency and maintaining favorable inference latency. Comprehensive benchmarks including FLOPs, parameter counts, and GPU latency measurements are provided, offering practical insights for deploying attention enhanced CNNs in resource constrained environments.

---

### Dynamic Accuracy Estimation in a Wi-Fi-based Positioning System

Authors: Marcin Kolakowski, Vitomir Djaja-Josko
Published: 2026-01-02
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2601.00999v1

The paper presents a concept of a dynamic accuracy estimation method, in which the localization errors are derived based on the measurement results used by the positioning algorithm. The concept was verified experimentally in a Wi\nobreakdash-Fi based indoor positioning system, where several regression methods were tested (linear regression, random forest, k-nearest neighbors, and neural networks). The highest positioning error estimation accuracy was achieved for random forest regression, with a mean absolute error of 0.72 m.

---

### DVGBench: Implicit-to-Explicit Visual Grounding Benchmark in UAV Imagery with Large Vision-Language Models

Authors: Yue Zhou, Jue Chen, Zilun Zhang, Penghui Huang, Ran Ding, Zhentao Zou, PengFei Gao, Yuchen Wei, Ke Li, Xue Yang, Xue Jiang, Hongxin Yang et al.
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00998v1

Remote sensing (RS) large vision-language models (LVLMs) have shown strong promise across visual grounding (VG) tasks. However, existing RS VG datasets predominantly rely on explicit referring expressions-such as relative position, relative size, and color cues-thereby constraining performance on implicit VG tasks that require scenario-specific domain knowledge. This article introduces DVGBench, a high-quality implicit VG benchmark for drones, covering six major application scenarios: traffic, disaster, security, sport, social activity, and productive activity. Each object provides both explicit and implicit queries. Based on the dataset, we design DroneVG-R1, an LVLM that integrates the novel Implicit-to-Explicit Chain-of-Thought (I2E-CoT) within a reinforcement learning paradigm. This enables the model to take advantage of scene-specific expertise, converting implicit references into explicit ones and thus reducing grounding difficulty. Finally, an evaluation of mainstream models on both explicit and implicit VG tasks reveals substantial limitations in their reasoning capabilities. These findings provide actionable insights for advancing the reasoning capacity of LVLMs for drone-based agents. The code and datasets will be released at https://github.com/zytx121/DVGBench

---