# Research Papers — 2026-01 · bundle page 67 of 189

> Full-text markdown of papers #3301–3350 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/67
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/66.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/68.md)

### Learning-augmented smooth integer programs with PAC-learnable oracles

Authors: Hao-Yuan He, Ming Li
Published: 2026-01-22
Categories: cs.DS, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2602.02505v1

This paper investigates learning-augmented algorithms for smooth integer programs, covering canonical problems such as MAX-CUT and MAX-k-SAT. We introduce a framework that incorporates a predictive oracle to construct a linear surrogate of the objective, which is then solved via linear programming followed by a rounding procedure. Crucially, our framework ensures that the solution quality is both consistent and smooth against prediction errors. We demonstrate that this approach effectively extends tractable approximations from the classical dense regime to the near-dense regime. Furthermore, we go beyond the assumption of oracle existence by establishing its PAC-learnability. We prove that the induced algorithm class possesses a bounded pseudo-dimension, thereby ensuring that an oracle with near-optimal expected performance can be learned with polynomial samples.

---

### Impact of LLMs news Sentiment Analysis on Stock Price Movement Prediction

Authors: Walid Siala, Ahmed Khanfir, Mike Papadakis
Published: 2026-01-22
Categories: q-fin.ST, cs.AI, cs.CE
arXiv: https://arxiv.org/abs/2602.00086v3

This paper addresses stock price movement prediction by leveraging LLM-based news sentiment analysis. Earlier works have largely focused on proposing and assessing sentiment analysis models and stock movement prediction methods, however, separately. Although promising results have been achieved, a clear and in-depth understanding of the benefit of the news sentiment to this task, as well as a comprehensive assessment of different architecture types in this context, is still lacking. Herein, we conduct an evaluation study that compares 3 different LLMs, namely, DeBERTa, RoBERTa and FinBERT, for sentiment-driven stock prediction. Our results suggest that DeBERTa outperforms the other two models with an accuracy of 75% and that an ensemble model that combines the three models can increase the accuracy to about 80%. Also, we see that sentiment news features can benefit (slightly) some stock market prediction models, i.e., LSTM-, PatchTST- and tPatchGNN-based classifiers and PatchTST- and TimesNet-based regression tasks models.

---

### CARE-RFT: Confidence-Anchored Reinforcement Finetuning for Reliable Reasoning in Large Language Models

Authors: Shuozhe Li, Jincheng Cao, Bodun Hu, Aryan Mokhtari, Leqi Liu, Amy Zhang
Published: 2026-01-22
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2602.00085v1

Reinforcement finetuning (RFT) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models. However, we identify a critical trade-off: while unconstrained RFT achieves strong reasoning performance, it severely compromises model trustworthiness by amplifying hallucination and worsening calibration; conversely, RKL-constrained RFT preserves trustworthiness but limits reasoning gains due to its unbounded penalty on exploratory deviations. To resolve this tension, we introduce CARE-RFT (Confidence-Anchored Regularized Reinforcement Finetuning), a novel method that replaces standard reverse KL regularization with a skew reverse KL divergence. CARE-RFT provides a confidence-sensitive penalty: it is bounded for confident, consistently rewarded explorations to enable reasoning, while unbounded elsewhere to preserve calibration. Extensive experiments across multiple model scales and RFT algorithms show that CARE-RFT achieves a superior balance, matching the reasoning performance of unconstrained RFT while recovering the trustworthiness and calibration of the base model. Our work establishes that careful, confidence-aware regularization is key to building both capable and trustworthy reasoning models.

---

### Why LoRA Resists Label Noise: A Theoretical Framework for Noise-Robust Parameter-Efficient Fine-Tuning

Authors: Brady Steele
Published: 2026-01-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2602.00084v1

Parameter-efficient fine-tuning methods like Low-Rank Adaptation (LoRA) have become the dominant paradigm for adapting large pretrained models. We present a theoretical framework explaining an underexplored property: LoRA's inherent resistance to label noise. Our analysis reveals three key insights. First, we prove that rank-$r$ LoRA cannot memorize all possible label assignments once the sample size exceeds $O(r(d+k-r))$, limiting its capacity to fit arbitrary noise. Second, we derive an optimal rank balancing approximation bias and noise-induced variance, showing it decreases with noise rate. Third, we establish temporal separation: clean patterns are learned early while noise memorization occurs later. We propose RACT (Rank-Aware Curriculum Training), leveraging rank discrepancy for noise detection. Experiments validate our predictions, with RACT achieving 91.1% F1 for noise detection on AG News while maintaining 91.46% accuracy, competitive with baselines that lack noise detection capability.

---

### SPARC-RAG: Adaptive Sequential-Parallel Scaling with Context Management for Retrieval-Augmented Generation

Authors: Yuxin Yang, Gangda Deng, Ömer Faruk Akgül, Nima Chitsazan, Yash Govilkar, Akasha Tigalappanavara, Shi-Xiong Zhang, Sambit Sahu, Viktor Prasanna
Published: 2026-01-22
Categories: cs.IR, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2602.00083v1

Retrieval-Augmented Generation (RAG) grounds large language model outputs in external evidence, but remains challenged on multi-hop question answering that requires long reasoning. Recent works scale RAG at inference time along two complementary dimensions: sequential depth for iterative refinement and parallel width for coverage expansion. However, naive scaling causes context contamination and scaling inefficiency, leading to diminishing or negative returns despite increased computation. To address these limitations, we propose SPARC-RAG, a multi-agent framework that coordinates sequential and parallel inference-time scaling under a unified context management mechanism. SPARC-RAG employs specialized agents that maintain a shared global context and provide explicit control over the scaling process. It generates targeted, complementary sub-queries for each branch to enable diverse parallel exploration, and explicitly regulates exiting decisions based on answer correctness and evidence grounding. To optimize scaling behavior, we further introduce a lightweight fine-tuning method with process-level verifiable preferences, which improves the efficiency of sequential scaling and effectiveness of parallel scaling. Across single- and multi-hop QA benchmarks, SPARC-RAG consistently outperforms previous RAG baselines, yielding an average +6.2 F1 improvement under lower inference cost.

---

### Design and Empirical Study of a Large Language Model-Based Multi-Agent Investment System for Chinese Public REITs

Authors: Zheng Li
Published: 2026-01-22
Categories: q-fin.ST, cs.AI, q-fin.TR
arXiv: https://arxiv.org/abs/2602.00082v1

This study addresses the low-volatility Chinese Public Real Estate Investment Trusts (REITs) market, proposing a large language model (LLM)-driven trading framework based on multi-agent collaboration. The system constructs four types of analytical agents-announcement, event, price momentum, and market-each conducting analysis from different dimensions; then the prediction agent integrates these multi-source signals to output directional probability distributions across multiple time horizons, then the decision agent generates discrete position adjustment signals based on the prediction results and risk control constraints, thereby forming a closed loop of analysis-prediction-decision-execution. This study further compares two prediction model pathways: for the prediction agent, directly calling the general-purpose large model DeepSeek-R1 versus using a specialized small model Qwen3-8B fine-tuned via supervised fine-tuning and reinforcement learning alignment. In the backtest from October 2024 to October 2025, both agent-based strategies significantly outperformed the buy-and-hold benchmark in terms of cumulative return, Sharpe ratio, and maximum drawdown. The results indicate that the multi-agent framework can effectively enhance the risk-adjusted return of REITs trading, and the fine-tuned small model performs close to or even better than the general-purpose large model in some scenarios.

---

### The GT-Score: A Robust Objective Function for Reducing Overfitting in Data-Driven Trading Strategies

Authors: Alexander Sheppert
Published: 2026-01-22
Categories: q-fin.ST, cs.LG
arXiv: https://arxiv.org/abs/2602.00080v1

Overfitting remains a critical challenge in data-driven financial modeling, where machine learning (ML) systems learn spurious patterns in historical prices and fail out of sample and in deployment. This paper introduces the GT-Score, a composite objective function that integrates performance, statistical significance, consistency, and downside risk to guide optimization toward more robust trading strategies. This approach directly addresses critical pitfalls in quantitative strategy development, specifically data snooping during optimization and the unreliability of statistical inference under non-normal return distributions. Using historical stock data for 50 S&P 500 companies spanning 2010-2024, we conduct an empirical evaluation that includes walk-forward validation with nine sequential time splits and a Monte Carlo study with 15 random seeds across three trading strategies. In walk-forward validation, GT-Score improves the generalization ratio (validation return divided by training return) by 98% relative to baseline objective functions. Paired statistical tests on Monte Carlo out-of-sample returns indicate statistically detectable differences between objective functions (p < 0.01 for comparisons with Sortino and Simple), with small effect sizes. These results suggest that embedding an anti-overfitting structure into the objective can improve the reliability of backtests in quantitative research. Reproducible code and processed result files are provided as supplementary materials.

---

### Embedding Compression via Spherical Coordinates

Authors: Han Xiao
Published: 2026-01-22
Categories: cs.LG, cs.CV
arXiv: https://arxiv.org/abs/2602.00079v4

We present an $ε$-bounded compression method for unit-norm embeddings that achieves 1.5$\times$ compression, 25% better than the best prior lossless method. The method exploits that spherical coordinates of high-dimensional unit vectors concentrate around $π/2$, causing IEEE 754 exponents to collapse to a single value and high-order mantissa bits to become predictable, enabling entropy coding of both. Reconstruction error is bounded by float32 machine epsilon ($1.19 \times 10^{-7}$), making reconstructed values indistinguishable from originals at float32 precision. Evaluation across 26 configurations spanning text, image, and multi-vector embeddings confirms consistent compression improvement with zero measurable retrieval degradation on BEIR benchmarks.

---

### Prediction Markets as Bayesian Inverse Problems: Uncertainty Quantification, Identifiability, and Information Gain from Price-Volume Histories under Latent Types

Authors: Juan Pablo Madrigal-Cianci, Camilo Monsalve Maya, Lachlan Breakey
Published: 2026-01-22
Categories: q-fin.MF, stat.ML
arXiv: https://arxiv.org/abs/2601.18815v1

Prediction markets are often described as mechanisms that ``aggregate information'' into prices, yet the mapping from dispersed private information to observed market histories is typically noisy, endogenous, and shaped by heterogeneous and strategic participation. This paper formulates prediction markets as Bayesian inverse problems in which the unknown event outcome \(Y\in\{0,1\}\) is inferred from an observed history of market-implied probabilities and traded volumes. We introduce a mechanism-agnostic observation model in log-odds space in which price increments conditional on volume arise from a latent mixture of trader types. The resulting likelihood class encompasses informed and uninformed trading, heavy-tailed microstructure noise, and adversarial or manipulative flow, while requiring only price and volume as observables. Within this framework we define posterior uncertainty quantification for \(Y\), provide identifiability and well-posedness criteria in terms of Kullback--Leibler separation between outcome-conditional increment laws, and derive posterior concentration statements and finite-sample error bounds under general regularity assumptions. We further study stability of posterior odds to perturbations of the observed price--volume path and define realized and expected information gain via the posterior-vs-prior KL divergence and mutual information. The inverse-problem formulation yields explicit diagnostics for regimes in which market histories are informative and stable versus regimes in which inference is ill-posed due to type-composition confounding or outcome--nuisance symmetries. Extensive experiments on synthetic data validate our theoretical predictions regarding posterior concentration rates and identifiability thresholds.

---

### Lightweight Quantum-Enhanced ResNet for Coronary Angiography Classification: A Hybrid Quantum-Classical Feature Enhancement Framework

Authors: Jingsong Xia
Published: 2026-01-22
Categories: quant-ph, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18814v1

Background: Coronary angiography (CAG) is the cornerstone imaging modality for evaluating coronary artery stenosis and guiding interventional decision-making. However, interpretation based on single-frame angiographic images remains highly operator-dependent, and conventional deep learning models still face challenges in modeling complex vascular morphology and fine-grained texture patterns.Methods: We propose a Lightweight Quantum-Enhanced ResNet (LQER) for binary classification of coronary angiography images. A pretrained ResNet18 is employed as a classical feature extractor, while a parameterized quantum circuit (PQC) is introduced at the high-level semantic feature space for quantum feature enhancement. The quantum module utilizes data re-uploading and entanglement structures, followed by residual fusion with classical features, enabling end-to-end hybrid optimization with a strictly controlled number of qubits.Results: On an independent test set, the proposed LQER outperformed the classical ResNet18 baseline in accuracy, AUC, and F1-score, achieving a test accuracy exceeding 90%. The results demonstrate that lightweight quantum feature enhancement improves discrimination of positive lesions, particularly under class-imbalanced conditions.Conclusion: This study validates a practical hybrid quantum--classical learning paradigm for coronary angiography analysis, providing a feasible pathway for deploying quantum machine learning in medical imaging applications.

---

### Trademark Search, Artificial Intelligence and the Role of the Private Sector

Authors: Sonia Katyal, Aniket Kesari
Published: 2026-01-22
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.17072v1

Almost every industry today confronts the potential role of artificial intelligence and machine learning in its future. While many studies examine AI in consumer marketing, less attention addresses AI's role in creating and selecting trademarks that are distinctive, recognizable, and meaningful to consumers. Traditional economic approaches to trademarks focus almost exclusively on consumer-based, demand-side considerations regarding search. However, these approaches are incomplete because they fail to account for substantial costs faced not just by consumers, but by trademark applicants as well. Given AI's rapidly increasing role in trademark search and similarity analysis, lawyers and scholars should understand its dramatic implications. This paper proposes that AI should interest anyone studying trademarks and their role in economic decision-making. We examine how machine learning techniques will transform the application and interpretation of foundational trademark doctrines, producing significant implications for the trademark ecosystem. We run empirical experiments regarding trademark search to assess the efficacy of various trademark search engines, many of which employ machine learning methods. Through comparative analysis, we evaluate how these AI-powered tools function in practice. In an age where artificial intelligence increasingly governs trademark selection, the classic division between consumers and trademark owners deserves an updated, supply-side framework. This insight has transformative potential for encouraging both innovation and efficiency in trademark law and practice.

---

### Superpixel-Based Image Segmentation Using Squared 2-Wasserstein Distances

Authors: Jisui Huang, Andreas Alpers, Ke Chen, Na Lei
Published: 2026-01-22
Categories: cs.CV, math.PR
arXiv: https://arxiv.org/abs/2601.17071v1

We present an efficient method for image segmentation in the presence of strong inhomogeneities. The approach can be interpreted as a two-level clustering procedure: pixels are first grouped into superpixels via a linear least-squares assignment problem, which can be viewed as a special case of a discrete optimal transport (OT) problem, and these superpixels are subsequently greedily merged into object-level segments using the squared 2-Wasserstein distance between their empirical distributions. In contrast to conventional superpixel merging strategies based on mean-color distances, our framework employs a distributional OT distance, yielding a mathematically unified formulation across both clustering levels. Numerical experiments demonstrate that this perspective leads to improved segmentation accuracy on challenging images while retaining high computational efficiency.

---

### Multi-Agent Deep Reinforcement Learning Under Constrained Communications

Authors: Shahil Shaik, Jonathon M. Smereka, Yue Wang
Published: 2026-01-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.17069v1

Centralized training with decentralized execution (CTDE) has been the dominant paradigm in multi-agent reinforcement learning (MARL), but its reliance on global state information during training introduces scalability, robustness, and generalization bottlenecks. Moreover, in practical scenarios such as adding/dropping teammates or facing environment dynamics that differ from the training, CTDE methods can be brittle and costly to retrain, whereas distributed approaches allow agents to adapt using only local information and peer-to-peer communication. We present a distributed MARL framework that removes the need for centralized critics or global information. Firstly, we develop a novel Distributed Graph Attention Network (D-GAT) that performs global state inference through multi-hop communication, where agents integrate neighbor features via input-dependent attention weights in a fully distributed manner. Leveraging D-GAT, we develop the distributed graph-attention MAPPO (DG-MAPPO) -- a distributed MARL framework where agents optimize local policies and value functions using local observations, multi-hop communication, and shared/averaged rewards. Empirical evaluation on the StarCraftII Multi-Agent Challenge, Google Research Football, and Multi-Agent Mujoco demonstrates that our method consistently outperforms strong CTDE baselines, achieving superior coordination across a wide range of cooperative tasks with both homogeneous and heterogeneous teams. Our distributed MARL framework provides a principled and scalable solution for robust collaboration, eliminating the need for centralized training or global observability. To the best of our knowledge, DG-MAPPO appears to be the first to fully eliminate reliance on privileged centralized information, enabling agents to learn and act solely through peer-to-peer communication.

---

### A Mechanistic View on Video Generation as World Models: State and Dynamics

Authors: Luozhou Wang, Zhifei Chen, Yihua Du, Dongyu Yan, Wenhang Ge, Guibao Shen, Xinli Xu, Leyi Wu, Man Chen, Tianshuo Xu, Peiran Ren, Xin Tao et al.
Published: 2026-01-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.17067v1

Large-scale video generation models have demonstrated emergent physical coherence, positioning them as potential world models. However, a gap remains between contemporary "stateless" video architectures and classic state-centric world model theories. This work bridges this gap by proposing a novel taxonomy centered on two pillars: State Construction and Dynamics Modeling. We categorize state construction into implicit paradigms (context management) and explicit paradigms (latent compression), while dynamics modeling is analyzed through knowledge integration and architectural reformulation. Furthermore, we advocate for a transition in evaluation from visual fidelity to functional benchmarks, testing physical persistence and causal reasoning. We conclude by identifying two critical frontiers: enhancing persistence via data-driven memory and compressed fidelity, and advancing causality through latent factor decoupling and reasoning-prior integration. By addressing these challenges, the field can evolve from generating visually plausible videos to building robust, general-purpose world simulators.

---

### ThinkTank-ME: A Multi-Expert Framework for Middle East Event Forecasting

Authors: Haoxuan Li, He Chang, Yunshan Ma, Yi Bin, Yang Yang, See-Kiong Ng, Tat-Seng Chua
Published: 2026-01-22
Categories: cs.LG, cs.AI, cs.CL, cs.CY, cs.MA
arXiv: https://arxiv.org/abs/2601.17065v1

Event forecasting is inherently influenced by multifaceted considerations, including international relations, regional historical dynamics, and cultural contexts. However, existing LLM-based approaches employ single-model architectures that generate predictions along a singular explicit trajectory, constraining their ability to capture diverse geopolitical nuances across complex regional contexts. To address this limitation, we introduce ThinkTank-ME, a novel Think Tank framework for Middle East event forecasting that emulates collaborative expert analysis in real-world strategic decision-making. To facilitate expert specialization and rigorous evaluation, we construct POLECAT-FOR-ME, a Middle East-focused event forecasting benchmark. Experimental results demonstrate the superiority of multi-expert collaboration in handling complex temporal geopolitical forecasting tasks. The code is available at https://github.com/LuminosityX/ThinkTank-ME.

---

### Between Search and Platform: ChatGPT Under the DSA

Authors: Toni Lorente, Kathrin Gardhouse
Published: 2026-01-22
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.17064v2

This article examines the applicability of the Digital Services Act (DSA) to ChatGPT, arguing that it should be classified as a hybrid of the two types of hosting services: online search engines and platforms. This requires classifying search engines as hosting services, which we show is appropriate under the DSA, thereby resolving an ambiguity in the legal framework. ChatGPT performs core search functions and stores user-provided inputs and custom GPTs, meeting the definition of hosting service. We compare ChatGPT's systemic risks with those of existing Very Large Online Search Engines (VLOSEs) and Platforms (VLOPs), showing that it raises similarly serious concerns regarding illegal content, fundamental rights, democratic integrity, and public health. Now that ChatGPT has reached the 45 million EU user threshold, it should be subject to the most onerous DSA obligations, requiring the assessment and mitigation of risk emanating from both its online search engine- and platform-like characteristics.

---

### FlashMoE: Reducing SSD I/O Bottlenecks via ML-Based Cache Replacement for Mixture-of-Experts Inference on Edge Devices

Authors: Byeongju Kim, Jungwan Lee, Donghyeon Han, Hoi-Jun Yoo, Sangyeob Kim
Published: 2026-01-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.17063v1

Recently, Mixture-of-Experts (MoE) models have gained attention for efficiently scaling large language models. Although these models are extremely large, their sparse activation enables inference to be performed by accessing only a fraction of the model at a time. This property opens the possibility of on-device inference of MoE, which was previously considered infeasible for such large models. Consequently, various systems have been proposed to leverage this sparsity and enable efficient MoE inference for edge devices. However, previous MoE inference systems like Fiddler(8) or DAOP(13) rely on DRAM-based offloading and are not suitable for memory constrained on-device environments. As recent MoE models grow to hundreds of gigabytes, RAM-offloading solutions become impractical. To address this, we propose FlashMoE, a system that offloads inactive experts to SSD, enabling efficient MoE inference under limited RAM. FlashMoE incorporates a lightweight ML-based caching strategy that adaptively combines recency and frequency signals to maximize expert reuse, significantly reducing storage I/O. In addition, we built a user-grade desktop platform to demonstrate the practicality of FlashMoE. On this real hardware setup, FlashMoE improves cache hit rate by up to 51% over well-known offloading policies such as LRU and LFU, and achieves up to 2.6x speedup compared to existing MoE inference systems.

---

### A Computer Vision Pipeline for Iterative Bullet Hole Tracking in Rifle Zeroing

Authors: Robert M. Belcher, Brendan C. Degryse, Leonard R. Kosta, Christopher J. Lowrance
Published: 2026-01-22
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.17062v1

Adjusting rifle sights, a process commonly called "zeroing," requires shooters to identify and differentiate bullet holes from multiple firing iterations. Traditionally, this process demands physical inspection, introducing delays due to range safety protocols and increasing the risk of human error. We present an end-to-end computer vision system for automated bullet hole detection and iteration-based tracking directly from images taken at the firing line. Our approach combines YOLOv8 for accurate small-object detection with Intersection over Union (IoU) analysis to differentiate bullet holes across sequential images. To address the scarcity of labeled sequential data, we propose a novel data augmentation technique that removes rather than adds objects to simulate realistic firing sequences. Additionally, we introduce a preprocessing pipeline that standardizes target orientation using ORB-based perspective correction, improving model accuracy. Our system achieves 97.0% mean average precision on bullet hole detection and 88.8% accuracy in assigning bullet holes to the correct firing iteration. While designed for rifle zeroing, this framework offers broader applicability in domains requiring the temporal differentiation of visually similar objects.

---

### How Information Evolves: Stability-Driven Assembly and the Emergence of a Natural Genetic Algorithm

Authors: Dan Adler
Published: 2026-01-22
Categories: q-bio.PE, cs.NE, nlin.AO
arXiv: https://arxiv.org/abs/2601.17061v2

Information can evolve as a physical consequence of non-equilibrium dynamics, even in the absence of genes, replication, or predefined fitness functions. We present Stability-Driven Assembly (SDA), a framework in which stochastic assembly combined with differential persistence biases populations toward longer-lived motifs. Assemblies that persist longer become more frequent and are therefore more likely to participate in subsequent interactions, generating feedback that reshapes the population distribution and implements fitness-proportional sampling, realizing evolution as a natural, emergent genetic algorithm (SDA/GA) driven solely by stability. We apply SDA/GA to chemical symbol space using SMILES fragments with recombination, mutation, and a heuristic stability function. Simulations show hallmark features of evolutionary search, including scaffold-level dominance, sustained novelty, and entropy reduction, yielding open-ended dynamics absent from equilibrium models with fixed transition rates. These results motivate an evolutionary ladder hypothesis where persistence-driven selection precedes genetic replication.

---

### Initial results of the Digital Consciousness Model

Authors: Derek Shiller, Laura Duffy, Arvo Muñoz Morán, Adrià Moret, Chris Percy, Hayley Clatterbuck
Published: 2026-01-22
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.17060v3

Artificially intelligent systems have become remarkably sophisticated. They hold conversations, write essays, and seem to understand context in ways that surprise even their creators. This raises a crucial question: Are we creating systems that are conscious? The Digital Consciousness Model (DCM) is a first attempt to assess the evidence for consciousness in AI systems in a systematic, probabilistic way. It provides a shared framework for comparing different AIs and biological organisms, and for tracking how the evidence changes over time as AI develops. Instead of adopting a single theory of consciousness, it incorporates a range of leading theories and perspectives - acknowledging that experts disagree fundamentally about what consciousness is and what conditions are necessary for it. This report describes the structure and initial results of the Digital Consciousness Model. Overall, we find that the evidence is against 2024 LLMs being conscious, but the evidence against 2024 LLMs being conscious is not decisive. The evidence against LLM consciousness is much weaker than the evidence against consciousness in simpler AI systems.

---

### Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

Authors: Wei Zhou, Jun Zhou, Haoyu Wang, Zhenghao Li, Qikang He, Shaokun Han, Guoliang Li, Xuanhe Zhou, Yeye He, Chunwei Liu, Zirui Tang, Bin Wang et al.
Published: 2026-01-22
Categories: cs.DB, cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.17058v1

Data preparation aims to denoise raw datasets, uncover cross-dataset relationships, and extract valuable insights from them, which is essential for a wide range of data-centric applications. Driven by (i) rising demands for application-ready data (e.g., for analytics, visualization, decision-making), (ii) increasingly powerful LLM techniques, and (iii) the emergence of infrastructures that facilitate flexible agent construction (e.g., using Databricks Unity Catalog), LLM-enhanced methods are rapidly becoming a transformative and potentially dominant paradigm for data preparation. By investigating hundreds of recent literature works, this paper presents a systematic review of this evolving landscape, focusing on the use of LLM techniques to prepare data for diverse downstream tasks. First, we characterize the fundamental paradigm shift, from rule-based, model-specific pipelines to prompt-driven, context-aware, and agentic preparation workflows. Next, we introduce a task-centric taxonomy that organizes the field into three major tasks: data cleaning (e.g., standardization, error processing, imputation), data integration (e.g., entity matching, schema matching), and data enrichment (e.g., data annotation, profiling). For each task, we survey representative techniques, and highlight their respective strengths (e.g., improved generalization, semantic understanding) and limitations (e.g., the prohibitive cost of scaling LLMs, persistent hallucinations even in advanced agents, the mismatch between advanced methods and weak evaluation). Moreover, we analyze commonly used datasets and evaluation metrics (the empirical part). Finally, we discuss open research challenges and outline a forward-looking roadmap that emphasizes scalable LLM-data systems, principled designs for reliable agentic workflows, and robust evaluation protocols.

---

### Post-Training Neural Network Pruning using Graph Curvature

Authors: Shuhang Tan, Jayson Sia, Paul Bogdan, Radoslav Ivanov
Published: 2026-01-22
Categories: cs.LG, cs.SC
arXiv: https://arxiv.org/abs/2601.16366v2

This paper provides a fresh view of the neural network (NN) pruning problem through the lens of graph theory. To achieve effective pruning, we aim to identify the main NN data flows and the corresponding NN connections that are most and least important for the performance of the full model. Unlike the standard approach to NN data flow analysis, which is based on information theory, we employ the notion of graph curvature, specifically Ollivier-Ricci curvature (ORC). ORC has been successfully used to identify important graph edges in various domains such as road traffic analysis, biological networks, and social networks. In particular, edges with negative ORC are considered bottlenecks and are therefore critical to the graph's overall connectivity, whereas positive-ORC edges are less essential. We use this intuition for NNs to (1) construct a graph induced by the NN structure and introduce the notion of neural curvature (NC) based on ORC; (2) calculate curvatures based on activation patterns for a set of input examples; and (3) demonstrate that NC can be used to rank edges according to their importance for overall NN functionality. We evaluate our method through pruning experiments on a variety of small and medium size models trained on three image datasets: MNIST, CIFAR-10, and CIFAR-100. The results indicate that our method can identify a larger number of unimportant edges compared to existing pruning methods.

---

### Experience with Single Domain Generalization in Real World Medical Imaging Deployments

Authors: Ayan Banerjee, Komandoor Srivathsan, Sandeep K. S. Gupta
Published: 2026-01-22
Categories: eess.IV, cs.AI, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.16359v1

A desirable property of any deployed artificial intelligence is generalization across domains, i.e. data generation distribution under a specific acquisition condition. In medical imagining applications the most coveted property for effective deployment is Single Domain Generalization (SDG), which addresses the challenge of training a model on a single domain to ensure it generalizes well to unseen target domains. In multi-center studies, differences in scanners and imaging protocols introduce domain shifts that exacerbate variability in rare class characteristics. This paper presents our experience on SDG in real life deployment for two exemplary medical imaging case studies on seizure onset zone detection using fMRI data, and stress electrocardiogram based coronary artery detection. Utilizing the commonly used application of diabetic retinopathy, we first demonstrate that state-of-the-art SDG techniques fail to achieve generalized performance across data domains. We then develop a generic expert knowledge integrated deep learning technique DL+EKE and instantiate it for the DR application and show that DL+EKE outperforms SOTA SDG methods on DR. We then deploy instances of DL+EKE technique on the two real world examples of stress ECG and resting state (rs)-fMRI and discuss issues faced with SDG techniques.

---

### Identity, Cooperation and Framing Effects within Groups of Real and Simulated Humans

Authors: Suhong Moon, Minwoo Kang, Joseph Suh, Mustafa Safdari, John Canny
Published: 2026-01-22
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.16355v2

Humans act via a nuanced process that depends both on rational deliberation and also on identity and contextual factors. In this work, we study how large language models (LLMs) can simulate human action in the context of social dilemma games. While prior work has focused on "steering" (weak binding) of chat models to simulate personas, we analyze here how deep binding of base models with extended backstories leads to more faithful replication of identity-based behaviors. Our study has these findings: simulation fidelity vs human studies is improved by conditioning base LMs with rich context of narrative identities and checking consistency using instruction-tuned models. We show that LLMs can also model contextual factors such as time (year that a study was performed), question framing, and participant pool effects. LLMs, therefore, allow us to explore the details that affect human studies but which are often omitted from experiment descriptions, and which hamper accurate replication.

---

### NOIR: Privacy-Preserving Generation of Code with Open-Source LLMs

Authors: Khoa Nguyen, Khiem Ton, NhatHai Phan, Issa Khalil, Khang Tran, Cristian Borcea, Ruoming Jin, Abdallah Khreishah, My T. Thai
Published: 2026-01-22
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.16354v1

Although boosting software development performance, large language model (LLM)-powered code generation introduces intellectual property and data security risks rooted in the fact that a service provider (cloud) observes a client's prompts and generated code, which can be proprietary in commercial systems. To mitigate this problem, we propose NOIR, the first framework to protect the client's prompts and generated code from the cloud. NOIR uses an encoder and a decoder at the client to encode and send the prompts' embeddings to the cloud to get enriched embeddings from the LLM, which are then decoded to generate the code locally at the client. Since the cloud can use the embeddings to infer the prompt and the generated code, NOIR introduces a new mechanism to achieve indistinguishability, a local differential privacy protection at the token embedding level, in the vocabulary used in the prompts and code, and a data-independent and randomized tokenizer on the client side. These components effectively defend against reconstruction and frequency analysis attacks by an honest-but-curious cloud. Extensive analysis and results using open-source LLMs show that NOIR significantly outperforms existing baselines on benchmarks, including the Evalplus (MBPP and HumanEval, Pass@1 of 76.7 and 77.4), and BigCodeBench (Pass@1 of 38.7, only a 1.77% drop from the original LLM) under strong privacy against attacks.

---

### Regional Bias in Large Language Models

Authors: M P V S Gopinadh, Kappara Lakshmi Sindhu, Soma Sekhar Pandu Ranga Raju P, Yesaswini Swarna
Published: 2026-01-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.16349v1

This study investigates regional bias in large language models (LLMs), an emerging concern in AI fairness and global representation. We evaluate ten prominent LLMs: GPT-3.5, GPT-4o, Gemini 1.5 Flash, Gemini 1.0 Pro, Claude 3 Opus, Claude 3.5 Sonnet, Llama 3, Gemma 7B, Mistral 7B, and Vicuna-13B using a dataset of 100 carefully designed prompts that probe forced-choice decisions between regions under contextually neutral scenarios. We introduce FAZE, a prompt-based evaluation framework that measures regional bias on a 10-point scale, where higher scores indicate a stronger tendency to favor specific regions. Experimental results reveal substantial variation in bias levels across models, with GPT-3.5 exhibiting the highest bias score (9.5) and Claude 3.5 Sonnet scoring the lowest (2.5). These findings indicate that regional bias can meaningfully undermine the reliability, fairness, and inclusivity of LLM outputs in real-world, cross-cultural applications. This work contributes to AI fairness research by highlighting the importance of inclusive evaluation frameworks and systematic approaches for identifying and mitigating geographic biases in language models.

---

### Coarse-to-Fine Non-rigid Multi-modal Image Registration for Historical Panel Paintings based on Crack Structures

Authors: Aline Sindel, Andreas Maier, Vincent Christlein
Published: 2026-01-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.16348v1

Art technological investigations of historical panel paintings rely on acquiring multi-modal image data, including visual light photography, infrared reflectography, ultraviolet fluorescence photography, x-radiography, and macro photography. For a comprehensive analysis, the multi-modal images require pixel-wise alignment, which is still often performed manually. Multi-modal image registration can reduce this laborious manual work, is substantially faster, and enables higher precision. Due to varying image resolutions, huge image sizes, non-rigid distortions, and modality-dependent image content, registration is challenging. Therefore, we propose a coarse-to-fine non-rigid multi-modal registration method efficiently relying on sparse keypoints and thin-plate-splines. Historical paintings exhibit a fine crack pattern, called craquelure, on the paint layer, which is captured by all image systems and is well-suited as a feature for registration. In our one-stage non-rigid registration approach, we employ a convolutional neural network for joint keypoint detection and description based on the craquelure and a graph neural network for descriptor matching in a patch-based manner, and filter matches based on homography reprojection errors in local areas. For coarse-to-fine registration, we introduce a novel multi-level keypoint refinement approach to register mixed-resolution images up to the highest resolution. We created a multi-modal dataset of panel paintings with a high number of keypoint annotations, and a large test set comprising five multi-modal domains and varying image resolutions. The ablation study demonstrates the effectiveness of all modules of our refinement method. Our proposed approaches achieve the best registration results compared to competing keypoint and dense matching methods and refinement methods.

---

### Long-Term Probabilistic Forecast of Vegetation Conditions Using Climate Attributes in the Four Corners Region

Authors: Erika McPhillips, Hyeongseong Lee, Xiangyu Xie, Kathy Baylis, Chris Funk, Mengyang Gu
Published: 2026-01-22
Categories: stat.AP, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.16347v1

Weather conditions can drastically alter the state of crops and rangelands, and in turn, impact the incomes and food security of individuals worldwide. Satellite-based remote sensing offers an effective way to monitor vegetation and climate variables on regional and global scales. The annual peak Normalized Difference Vegetation Index (NDVI), derived from satellite observations, is closely associated with crop development, rangeland biomass, and vegetation growth. Although various machine learning methods have been developed to forecast NDVI over short time ranges, such as one-month-ahead predictions, long-term forecasting approaches, such as one-year-ahead predictions of vegetation conditions, are not yet available. To fill this gap, we develop a two-phase machine learning model to forecast the one-year-ahead peak NDVI over high-resolution grids, using the Four Corners region of the Southwestern United States as a testbed. In phase one, we identify informative climate attributes, including precipitation and maximum vapor pressure deficit, and develop the generalized parallel Gaussian process that captures the relationship between climate attributes and NDVI. In phase two, we forecast these climate attributes using historical data at least one year before the NDVI prediction month, which then serve as inputs to forecast the peak NDVI at each spatial grid. We developed open-source tools that outperform alternative methods for both gross NDVI and grid-based NDVI one-year forecasts, providing information that can help farmers and ranchers make actionable plans a year in advance.

---

### DSGym: A Holistic Framework for Evaluating and Training Data Science Agents

Authors: Fan Nie, Junlin Wang, Harper Hua, Federico Bianchi, Yongchan Kwon, Zhenting Qi, Owen Queen, Shang Zhu, James Zou
Published: 2026-01-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.16344v1

Data science agents promise to accelerate discovery and insight-generation by turning data into executable analyses and findings. Yet existing data science benchmarks fall short due to fragmented evaluation interfaces that make cross-benchmark comparison difficult, narrow task coverage and a lack of rigorous data grounding. In particular, we show that a substantial portion of tasks in current benchmarks can be solved without using the actual data. To address these limitations, we introduce DSGym, a standardized framework for evaluating and training data science agents in self-contained execution environments. Unlike static benchmarks, DSGym provides a modular architecture that makes it easy to add tasks, agent scaffolds, and tools, positioning it as a live, extensible testbed. We curate DSGym-Tasks, a holistic task suite that standardizes and refines existing benchmarks via quality and shortcut solvability filtering. We further expand coverage with (1) DSBio: expert-derived bioinformatics tasks grounded in literature and (2) DSPredict: challenging prediction tasks spanning domains such as computer vision, molecular prediction, and single-cell perturbation. Beyond evaluation, DSGym enables agent training via execution-verified data synthesis pipeline. As a case study, we build a 2,000-example training set and trained a 4B model in DSGym that outperforms GPT-4o on standardized analysis benchmarks. Overall, DSGym enables rigorous end-to-end measurement of whether agents can plan, implement, and validate data analyses in realistic scientific context.

---

### DMAVA: Distributed Multi-Autonomous Vehicle Architecture Using Autoware

Authors: Zubair Islam, Mohamed El-Darieby
Published: 2026-01-22
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.16336v2

Simulating and validating coordination among multiple autonomous vehicles remains challenging, as many existing simulation architectures are limited to single-vehicle operation or rely on centralized control. This paper presents the Distributed Multi-Autonomous Vehicle Architecture (DMAVA), a simulation architecture that enables concurrent execution of multiple independent vehicle autonomy stacks distributed across multiple physical hosts within a shared simulation environment. Each vehicle operates its own complete autonomous driving stack while maintaining coordinated behavior through a data-centric communication layer. The proposed system integrates ROS 2 Humble, Autoware Universe, AWSIM Labs, and Zenoh to support high data accuracy and controllability during multi-vehicle simulation, enabling consistent perception, planning, and control behavior under distributed execution. Experiments conducted on multiple-host configurations demonstrate stable localization, reliable inter-host communication, and consistent closed-loop control under distributed execution. DMAVA also serves as a foundation for Multi-Vehicle Autonomous Valet Parking, demonstrating its extensibility toward higher-level cooperative autonomy. Demo videos and source code are available at: https://github.com/zubxxr/distributed-multi-autonomous-vehicle-architecture.

---

### Where is the multimodal goal post? On the Ability of Foundation Models to Recognize Contextually Important Moments

Authors: Aditya K Surikuchi, Raquel Fernández, Sandro Pezzelle
Published: 2026-01-22
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.16333v2

Foundation models are used for many real-world applications involving language generation from temporally-ordered multimodal events. In this work, we study the ability of models to identify the most important sub-events in a video, which is a fundamental prerequisite for narrating or summarizing multimodal events. Specifically, we focus on football games and evaluate models on their ability to distinguish between important and non-important sub-events in a game. To this end, we construct a new dataset by leveraging human preferences for importance implicit in football game highlight reels, without any additional annotation costs. Using our dataset, we compare several state-of-the-art multimodal models and show that they are not far from chance level performance. Analyses of models beyond standard evaluation metrics reveal their tendency to rely on a single dominant modality and their ineffectiveness in synthesizing necessary information from multiple sources. Our findings underline the importance of modular architectures that can handle sample-level heterogeneity in multimodal data and the need for complementary training procedures that can maximize cross-modal synergy.

---

### Efficient Gaussian process learning via subspace projections

Authors: Elsa Cazelles, Felipe Tobar
Published: 2026-01-22
Categories: cs.LG, eess.SP
arXiv: https://arxiv.org/abs/2601.16332v2

We propose a novel training objective for GPs constructed using lower-dimensional linear projections of the data, referred to as \emph{projected likelihood} (PL). We provide a closed-form expression for the information loss related to the PL and empirically show that it can be reduced with random projections on the unit sphere. We show the superiority of the PL, in terms of accuracy and computational efficiency, over the exact GP training and the variational free energy approach to sparse GPs over different optimisers, kernels and datasets of moderately large sizes.

---

### DMV-AVP: Distributed Multi-Vehicle Autonomous Valet Parking Using Autoware

Authors: Zubair Islam, Mohamed El-Darieby
Published: 2026-01-22
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.16327v2

This paper presents DMV-AVP, a distributed simulation of Multi-Vehicle Autonomous Valet Parking (AVP). The system was implemented as an application of the Distributed Multi-Autonomous Vehicle Architecture (DMAVA) for synchronized multi-host execution. Most existing simulation approaches rely on centralized or non-distributed designs that constrain scalability and limit fully autonomous control. This work introduces two modules built on top of DMAVA: 1) the Multi-Vehicle AVP Coordination Framework, composed of AVP Managers and a per-vehicle AVP Node, is responsible for global parking state tracking, vehicle queuing, parking spot reservation, lifecycle coordination, and conflict resolution across multiple vehicles, and 2) the Unity-Integrated YOLOv5 Parking Spot Detection Module, that provides real-time, vision-based perception within AWSIM Labs. Both modules integrate seamlessly with DMAVA and extend it specifically for multi-vehicle AVP operation, supported by a Zenoh communication layer that ensures high data accuracy and controllability across hosts. Experiments conducted on two- and three-host configurations demonstrate consistent coordination, conflict-free parking behavior, and scalable performance across distributed Autoware instances. The results confirm that the proposed DMV-AVP supports cooperative AVP simulation and establishes a foundation for future real-world and hardware-in-the-loop validation. Demo videos and source code are available at: https://github.com/zubxxr/multi-vehicle-avp

---

### Student Mental Health Screening via Fitbit Data Collected During the COVID-19 Pandemic

Authors: Rebecca Lopez, Avantika Shrestha, ML Tlachac, Kevin Hickey, Xingtong Guo, Shichao Liu, Elke Rundensteiner
Published: 2026-01-22
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.16324v1

College students experience many stressors, resulting in high levels of anxiety and depression. Wearable technology provides unobtrusive sensor data that can be used for the early detection of mental illness. However, current research is limited concerning the variety of psychological instruments administered, physiological modalities, and time series parameters. In this research, we collect the Student Mental and Environmental Health (StudentMEH) Fitbit dataset from students at our institution during the pandemic. We provide a comprehensive assessment of the ability of predictive machine learning models to screen for depression, anxiety, and stress using different Fitbit modalities. Our findings indicate potential in physiological modalities such as heart rate and sleep to screen for mental illness with the F1 scores as high as 0.79 for anxiety, the former modality reaching 0.77 for stress screening, and the latter modality achieving 0.78 for depression. This research highlights the potential of wearable devices to support continuous mental health monitoring, the importance of identifying best data aggregation levels and appropriate modalities for screening for different mental ailments.

---

### EdgeSpot: Efficient and High-Performance Few-Shot Model for Keyword Spotting

Authors: Oguzhan Buyuksolak, Alican Gok, Osman Erman Okman
Published: 2026-01-22
Categories: eess.AS, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.16316v1

We introduce an efficient few-shot keyword spotting model for edge devices, EdgeSpot, that pairs an optimized version of a BC-ResNet-based acoustic backbone with a trainable Per-Channel Energy Normalization frontend and lightweight temporal self-attention. Knowledge distillation is utilized during training by employing a self-supervised teacher model, optimized with Sub-center ArcFace loss. This study demonstrates that the EdgeSpot model consistently provides better accuracy at a fixed false-alarm rate (FAR) than strong BC-ResNet baselines. The largest variant, EdgeSpot-4, improves the 10-shot accuracy at 1% FAR from 73.7% to 82.0%, which requires only 29.4M MACs with 128k parameters.

---

### Machine-Assisted Grading of Nationwide School-Leaving Essay Exams with LLMs and Statistical NLP

Authors: Andres Karjus, Kais Allkivi, Silvia Maine, Katarin Leppik, Krister Kruusmaa, Merilin Aruvee
Published: 2026-01-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.16314v1

Large language models (LLMs) enable rapid and consistent automated evaluation of open-ended exam responses, including dimensions of content and argumentation that have traditionally required human judgment. This is particularly important in cases where a large amount of exams need to be graded in a limited time frame, such as nation-wide graduation exams in various countries. Here, we examine the applicability of automated scoring on two large datasets of trial exam essays of two full national cohorts from Estonia. We operationalize the official curriculum-based rubric and compare LLM and statistical natural language processing (NLP) based assessments with human panel scores. The results show that automated scoring can achieve performance comparable to that of human raters and tends to fall within the human scoring range. We also evaluate bias, prompt injection risks, and LLMs as essay writers. These findings demonstrate that a principled, rubric-driven, human-in-the-loop scoring pipeline is viable for high-stakes writing assessment, particularly relevant for digitally advanced societies like Estonia, which is about to adapt a fully electronic examination system. Furthermore, the system produces fine-grained subscore profiles that can be used to generate systematic, personalized feedback for instruction and exam preparation. The study provides evidence that LLM-assisted assessment can be implemented at a national scale, even in a small-language context, while maintaining human oversight and compliance with emerging educational and regulatory standards.

---

### Teaching and Evaluating LLMs to Reason About Polymer Design Related Tasks

Authors: Dikshya Mohanty, Mohammad Saqib Hasan, Syed Mostofa Monsur, Size Zheng, Benjamin Hsiao, Niranjan Balasubramanian
Published: 2026-01-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.16312v3

Research in AI4Science has shown promise in many science applications, including polymer design. However, current LLMs are ineffective in this problem space because: (i) most models lack polymer-specific knowledge, and (ii) existing aligned models have limited coverage of knowledge and capabilities relevant to polymer design. Addressing this, we introduce PolyBench, a large-scale training and test benchmark dataset of more than 125K polymer design-related tasks, leveraging a knowledge base of more than 13 million data points obtained from experimental and synthetic data sources to ensure broad coverage of polymers and their properties. For effective alignment using PolyBench, we introduce a knowledge-augmented reasoning distillation method that augments this dataset with structured CoT. Furthermore, tasks in PolyBench are organized from simple to complex analytical reasoning problems, enabling generalization tests and diagnostic probes across the problem space. Experiments show that small- and mid- sized language models (SLMs) with 7B to 32BB parameters, trained on PolyBench, outperform similar-sized models and remain competitive with closed-source frontier LLMs on PolyBench's test dataset, while demonstrating performance gains on external polymer benchmarks. Dataset and associated code available at https://github.com/StonyBrookNLP/PolyBench.

---

### A Longitudinal, Multinational, and Multilingual Corpus of News Coverage of the Russo-Ukrainian War

Authors: Dikshya Mohanty, Taisiia Sabadyn, Jelwin Rodrigues, Chenlu Wang, Abhishek Kalugade, Ritwik Banerjee
Published: 2026-01-22
Categories: cs.CL, cs.SI
arXiv: https://arxiv.org/abs/2601.16309v2

We present DNIPRO, a corpus of 246K news articles from the Russo-Ukrainian war (Feb 2022 -- Aug 2024) spanning eleven outlets across five nation-states (Russia, Ukraine, U.S., U.K., China) and three languages. The corpus features comprehensive metadata and human-evaluated annotations for stance, sentiment, and topical framing, enabling systematic analysis of competing geopolitical narratives. It is uniquely suited for empirical studies of narrative divergence, media framing, and information warfare. Our exploratory analyses reveal how media outlets construct incompatible realities through divergent attribution and topical selection without direct refutation of opposing narratives. DNIPRO empowers empirical research on narrative evolution, cross-lingual information flow, and computational detection of implicit contradictions in fragmented information ecosystems.

---

### FeTTL: Federated Template and Task Learning for Multi-Institutional Medical Imaging

Authors: Abhijeet Parida, Antonia Alomar, Zhifan Jiang, Pooneh Roshanitabrizi, Austin Tapp, Ziyue Xu, Syed Muhammad Anwar, Maria J. Ledesma-Carbayo, Holger R. Roth, Marius George Linguraru
Published: 2026-01-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.16302v1

Federated learning enables collaborative model training across geographically distributed medical centers while preserving data privacy. However, domain shifts and heterogeneity in data often lead to a degradation in model performance. Medical imaging applications are particularly affected by variations in acquisition protocols, scanner types, and patient populations. To address these issues, we introduce Federated Template and Task Learning (FeTTL), a novel framework designed to harmonize multi-institutional medical imaging data in federated environments. FeTTL learns a global template together with a task model to align data distributions among clients. We evaluated FeTTL on two challenging and diverse multi-institutional medical imaging tasks: retinal fundus optical disc segmentation and histopathological metastasis classification. Experimental results show that FeTTL significantly outperforms the state-of-the-art federated learning baselines (p-values <0.002) for optical disc segmentation and classification of metastases from multi-institutional data. Our experiments further highlight the importance of jointly learning the template and the task. These findings suggest that FeTTL offers a principled and extensible solution for mitigating distribution shifts in federated learning, supporting robust model deployment in real-world, multi-institutional environments.

---

### Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing

Authors: Dohun Lee, Chun-Hao Paul Huang, Xuelin Chen, Jong Chul Ye, Duygu Ceylan, Hyeonho Jeong
Published: 2026-01-22
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.16296v3

Video-to-video diffusion models achieve impressive single-turn editing performance, but practical editing workflows are inherently iterative. When edits are applied sequentially, existing models treat each turn independently, often causing previously generated regions to drift or be overwritten. We identify this failure mode as the problem of cross-turn consistency in multi-turn video editing. We introduce Memory-V2V, a memory-augmented framework that treats prior edits as structured constraints for subsequent generations. Memory-V2V maintains an external memory of previous outputs, retrieves task-relevant edits, and integrates them through relevance-aware tokenization and adaptive compression. These technical ingredients enable scalable conditioning without linear growth in computation. We demonstrate Memory-V2V on iterative video novel view synthesis and text-guided long video editing. Memory-V2V substantially enhances cross-turn consistency while maintaining visual quality, outperforming strong baselines with modest overhead.

---

### Space Filling Curves is All You Need: Communication-Avoiding Matrix Multiplication Made Simple

Authors: Evangelos Georganas, Alexander Heinecke, Pradeep Dubey
Published: 2026-01-22
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2601.16294v2

General Matrix Multiplication (GEMM) is the cornerstone of HPC workloads and Deep Learning. State-of-the-art vendor libraries tune tensor layouts, parallelization schemes, and cache blocking to minimize data movement across the memory hierarchy and maximize throughput. Optimal settings for these parameters depend on the target platform and matrix shapes, making exhaustive tuning infeasible. We revisit Space Filling Curves (SFC) to alleviate this cumbersome tuning. We partition the Matrix Multiplication using advancements in SFC, and obtain platform-oblivious and shape-oblivious Matrix Multiplication schemes with high degree of data locality. We extend the SFC-based work partitioning to implement Communication-Avoiding (CA) algorithms that provably minimize data movement. The integration of CA-algorithms is seamless with compact code, achieving state-of-the-art results on multiple CPU platforms, outperforming vendor libraries up to 5.5x for a range of GEMM-shapes (1.8x Weighted Harmonic Mean speedup). We show the impact of our work on two real-world applications by leveraging our GEMM as compute backend: i) prefill of LLM inference with speedups up to 1.85x over State-Of-The-Art, and ii) distributed-memory Matrix Multiplication with speedups up to 2.2x.

---

### Active learning for photonic crystals

Authors: Ryan Lopez, Charlotte Loh, Rumen Dangovski, Marin Soljačić
Published: 2026-01-22
Categories: physics.optics, cond-mat.mtrl-sci, cs.LG, physics.app-ph
arXiv: https://arxiv.org/abs/2601.16287v3

Active learning for photonic crystals explores the integration of analytic approximate Bayesian last layer neural networks (LL-BNNs) with uncertainty-driven sample selection to accelerate photonic band gap prediction. We employ an analytic LL-BNN formulation, corresponding to the infinite Monte Carlo sample limit, to obtain uncertainty estimates that are strongly correlated with the true predictive error on unlabeled candidate structures. These uncertainty scores drive an active learning strategy that prioritizes the most informative simulations during training. Applied to the task of predicting band gap sizes in two-dimensional, two-tone photonic crystals, our approach achieves up to a 2.7x reduction on average in required training data compared to a random sampling baseline while maintaining predictive accuracy. The efficiency gains arise from concentrating computational resources on high uncertainty regions of the design space rather than sampling uniformly. Given the substantial cost of full band structure simulations, especially in three dimensions, this data efficiency enables rapid and scalable surrogate modeling. Our results suggest that analytic LL-BNN based active learning can substantially accelerate topological optimization and inverse design workflows for photonic crystals, and more broadly, offers a general framework for data efficient regression across scientific machine learning domains.

---

### SemanticALLI: Caching Reasoning, Not Just Responses, in Agentic Systems

Authors: Varun Chillara, Dylan Kline, Christopher Alvares, Evan Wooten, Huan Yang, Shlok Khetan, Cade Bauer, Tré Guillory, Tanishka Shah, Yashodhara Dhariwal, Volodymyr Pavlov, George Popstefanov
Published: 2026-01-22
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.16286v2

Agentic AI pipelines suffer from a hidden inefficiency: they frequently reconstruct identical intermediate logic, such as metric normalization or chart scaffolding, even when the user's natural language phrasing is entirely novel. Conventional boundary caching fails to capture this inefficiency because it treats inference as a monolithic black box. We introduce SemanticALLI, a pipeline-aware architecture within Alli (PMG's marketing intelligence platform), designed to operationalize redundant reasoning. By decomposing generation into Analytic Intent Resolution (AIR) and Visualization Synthesis (VS), SemanticALLI elevates structured intermediate representations (IRs) to first-class, cacheable artifacts. The impact of caching within the agentic loop is substantial. In our evaluation, baseline monolithic caching caps at a 38.7% hit rate due to linguistic variance. In contrast, our structured approach allows for an additional stage, the Visualization Synthesis stage, to achieve an 83.10% hit rate, bypassing 4,023 LLM calls with a median latency of just 2.66 ms. This internal reuse reduces total token consumption, offering a practical lesson for AI system design: even when users rarely repeat themselves, the pipeline often does, at stable, structured checkpoints where caching is most reliable.

---

### Generating Literature-Driven Scientific Theories at Scale

Authors: Peter Jansen, Peter Clark, Doug Downey, Daniel S. Weld
Published: 2026-01-22
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.16282v1

Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain underexplored. In this work, we formulate the problem of synthesizing theories consisting of qualitative and quantitative laws from large corpora of scientific literature. We study theory generation at scale, using 13.7k source papers to synthesize 2.9k theories, examining how generation using literature-grounding versus parametric knowledge, and accuracy-focused versus novelty-focused generation objectives change theory properties. Our experiments show that, compared to using parametric LLM memory for generation, our literature-supported method creates theories that are significantly better at both matching existing evidence and at predicting future results from 4.6k subsequently-written papers

---

### When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems

Authors: Donghao Huang, Gauri Malwe, Zhaoxia Wang
Published: 2026-01-22
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.16280v1

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic framework that leverages big data analytics to evaluate procedural reliability in intelligent agent systems, addressing critical needs for SME-centric deployment in privacy-sensitive environments. Our approach features a 12-category error taxonomy capturing failure modes across tool initialization, parameter handling, execution, and result interpretation. Through systematic evaluation of 1,980 deterministic test instances spanning both open-weight models (Qwen2.5 series, Functionary) and proprietary alternatives (GPT-4, Claude 3.5/3.7) across diverse edge hardware configurations, we identify actionable reliability thresholds for production deployment. Our analysis reveals that procedural reliability, particularly tool initialization failures, constitutes the primary bottleneck for smaller models, while qwen2.5:32b achieves flawless performance matching GPT-4.1. The framework demonstrates that mid-sized models (qwen2.5:14b) offer practical accuracy-efficiency trade-offs on commodity hardware (96.6\% success rate, 7.3 s latency), enabling cost-effective intelligent agent deployment for resource-constrained organizations. This work establishes foundational infrastructure for systematic reliability evaluation of tool-augmented multi-agent AI systems.

---

### Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification

Authors: Branislav Pecher, Jan Cegin, Robert Belanec, Ivan Srba, Jakub Simko, Maria Bielikova
Published: 2026-01-22
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.16278v1

Large Language Models (LLMs) have demonstrated remarkable multilingual capabilities, making them promising tools in both high- and low-resource languages. One particularly valuable use case is generating synthetic samples that can be used to train smaller models in low-resource scenarios where human-labelled data is scarce. In this work, we investigate whether these synthetic data generation capabilities can serve as a form of distillation, producing smaller models that perform on par with or even better than massive LLMs across languages and tasks. To this end, we use a state-of-the-art multilingual LLM to generate synthetic datasets covering 11 languages and 4 classification tasks. These datasets are then used to train smaller models via fine-tuning or instruction tuning, or as synthetic in-context examples for compact LLMs. Our experiments show that even small amounts of synthetic data enable smaller models to outperform the large generator itself, particularly in low-resource languages. Overall, the results suggest that LLMs are best utilised as generators (teachers) rather than classifiers, producing data that empowers smaller and more efficient multilingual models.

---

### GameTalk: Training LLMs for Strategic Conversation

Authors: Victor Conchello Vendrell, Max Ruiz Luyten, Mihaela van der Schaar
Published: 2026-01-22
Categories: cs.CL, cs.AI, cs.GT, cs.LG, cs.MA
arXiv: https://arxiv.org/abs/2601.16276v1

Strategic decision-making in multi-agent settings is a key challenge for large language models (LLMs), particularly when coordination and negotiation must unfold over extended conversations. While recent work has explored the use of LLMs in isolated decision tasks, little attention has been given to optimizing long-term objectives through dialogue. We introduce \textbf{GameTalk}, a framework for training LLMs to make strategic decisions via multi-turn interactions. Unlike prior work that focuses on single-turn objectives or static action prediction, we train LLMs to optimize a global objective across full conversations. We achieve this by adapting fine-tuning methods like GRPO, DPO, and STaR to incorporate reward signals that depend on the entire interaction. We evaluate this approach on a suite of increasingly complex games, designed to stress different aspects of reasoning, coordination, and opponent modeling. Our results show that GameTalk significantly outperforms untrained models, especially under reward shaping, with DPO consistently yielding the strongest gains. These findings position conversational fine-tuning as a promising path for LLMs to reason, negotiate, and act in interactive environments.

---

### GR3EN: Generative Relighting for 3D Environments

Authors: Xiaoyan Xing, Philipp Henzler, Junhwa Hur, Runze Li, Jonathan T. Barron, Pratul P. Srinivasan, Dor Verbin
Published: 2026-01-22
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.16272v2

We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable to produce high-quality results on complex real-world scenes. Though recent progress in using generative image and video diffusion models for relighting has been promising, these techniques are either limited to 2D image and video relighting or 3D relighting of individual objects. Our approach enables controllable 3D relighting of room-scale scenes by distilling the outputs of a video-to-video relighting diffusion model into a 3D reconstruction. This side-steps the need to solve a difficult inverse rendering problem, and results in a flexible system that can relight 3D reconstructions of complex real-world scenes. We validate our approach on both synthetic and real-world datasets to show that it can faithfully render novel views of scenes under new lighting conditions.

---

### Distributional Computational Graphs: Error Bounds

Authors: Olof Hallqvist Elias, Michael Selby, Phillip Stanley-Marbell
Published: 2026-01-22
Categories: stat.ML, cs.CE, cs.LG, math.NA, math.PR
arXiv: https://arxiv.org/abs/2601.16250v2

We study a general framework of distributional computational graphs: computational graphs whose inputs are probability distributions rather than point values. We analyze the discretization error that arises when these graphs are evaluated using finite approximations of continuous probability distributions. Such an approximation might be the result of representing a continuous real-valued distribution using a discrete representation or from constructing an empirical distribution from samples (or might be the output of another distributional computational graph). We establish non-asymptotic error bounds in terms of the Wasserstein-1 distance, without imposing structural assumptions on the computational graph.

---

### Ordering-based Causal Discovery via Generalized Score Matching

Authors: Vy Vo, He Zhao, Trung Le, Edwin V. Bonilla, Dinh Phung
Published: 2026-01-22
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.16249v3

Learning DAG structures from purely observational data remains a long-standing challenge across scientific domains. An emerging line of research leverages the score of the data distribution to initially identify a topological order of the underlying DAG via leaf node detection and subsequently performs edge pruning for graph recovery. This paper extends the score matching framework for causal discovery, which is originally designated for continuous data, and introduces a novel leaf discriminant criterion based on the discrete score function. Through simulated and real-world experiments, we demonstrate that our theory enables accurate inference of true causal orders from observed discrete data and the identified ordering can significantly boost the accuracy of existing causal discovery baselines on nearly all of the settings.

---