# Research Papers — 2026-01 · bundle page 175 of 189

> Full-text markdown of papers #8701–8750 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/175
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/174.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/176.md)

### Clinical Knowledge Graph Construction and Evaluation with Multi-LLMs via Retrieval-Augmented Generation

Authors: Udiptaman Das, Krishnasai B. Atmakuri, Duy Ho, Chi Lee, Yugyung Lee
Published: 2026-01-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01844v1

Large language models (LLMs) offer new opportunities for constructing knowledge graphs (KGs) from unstructured clinical narratives. However, existing approaches often rely on structured inputs and lack robust validation of factual accuracy and semantic consistency, limitations that are especially problematic in oncology. We introduce an end-to-end framework for clinical KG construction and evaluation directly from free text using multi-agent prompting and a schema-constrained Retrieval-Augmented Generation (KG-RAG) strategy. Our pipeline integrates (1) prompt-driven entity, attribute, and relation extraction; (2) entropy-based uncertainty scoring; (3) ontology-aligned RDF/OWL schema generation; and (4) multi-LLM consensus validation for hallucination detection and semantic refinement. Beyond static graph construction, the framework supports continuous refinement and self-supervised evaluation, enabling iterative improvement of graph quality. Applied to two oncology cohorts (PDAC and BRCA), our method produces interpretable, SPARQL-compatible, and clinically grounded knowledge graphs without relying on gold-standard annotations. Experimental results demonstrate consistent gains in precision, relevance, and ontology compliance over baseline methods.

---

### Towards Automated Lexicography: Generating and Evaluating Definitions for Learner's Dictionaries

Authors: Yusuke Ide, Adam Nohejl, Joshua Tanner, Hitomi Yanaka, Christopher Lindsay, Taro Watanabe
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01842v2

Dictionary definitions are an essential resource for learning word senses, but manually creating them is costly. We thus study dictionary definition generation (DDG), i.e., the generation of non-contextualized definitions for given headwords. Specifically, we address learner's dictionary definition generation (LDDG), where definitions should be written using simple vocabulary. First, we introduce a reliable evaluation approach for DDG, based on newly proposed evaluation criteria and powered by an LLM-as-a-judge. To provide reference definitions for the evaluation, we construct a dataset of Japanese dictionary definitions in collaboration with a professional lexicographer. Validation results demonstrate that our evaluation approach agrees with human annotators at a level comparable to inter-annotator agreement. Second, we propose an LLM-based LDDG approach that employs iterative simplification. Experimental results show that our approach yields definitions that achieve high scores on the proposed criteria and exhibit high lexical simplicity.

---

### Tackling Resource-Constrained and Data-Heterogeneity in Federated Learning with Double-Weight Sparse Pack

Authors: Qiantao Yang, Liquan Chen, Mingfu Xue, Songze Li
Published: 2026-01-05
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2601.01840v1

Federated learning has drawn widespread interest from researchers, yet the data heterogeneity across edge clients remains a key challenge, often degrading model performance. Existing methods enhance model compatibility with data heterogeneity by splitting models and knowledge distillation. However, they neglect the insufficient communication bandwidth and computing power on the client, failing to strike an effective balance between addressing data heterogeneity and accommodating limited client resources. To tackle this limitation, we propose a personalized federated learning method based on cosine sparsification parameter packing and dual-weighted aggregation (FedCSPACK), which effectively leverages the limited client resources and reduces the impact of data heterogeneity on model performance. In FedCSPACK, the client packages model parameters and selects the most contributing parameter packages for sharing based on cosine similarity, effectively reducing bandwidth requirements. The client then generates a mask matrix anchored to the shared parameter package to improve the alignment and aggregation efficiency of sparse updates on the server. Furthermore, directional and distribution distance weights are embedded in the mask to implement a weighted-guided aggregation mechanism, enhancing the robustness and generalization performance of the global model. Extensive experiments across four datasets using ten state-of-the-art methods demonstrate that FedCSPACK effectively improves communication and computational efficiency while maintaining high model accuracy.

---

### The Machine Learning Canvas: Empirical Findings on Why Strategy Matters More Than AI Code Generation

Authors: Martin Prause
Published: 2026-01-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.01839v1

Despite the growing popularity of AI coding assistants, over 80% of machine learning (ML) projects fail to deliver real business value. This study creates and tests a Machine Learning Canvas, a practical framework that combines business strategy, software engineering, and data science in order to determine the factors that lead to the success of ML projects. We surveyed 150 data scientists and analyzed their responses using statistical modeling. We identified four key success factors: Strategy (clear goals and planning), Process (how work gets done), Ecosystem (tools and infrastructure), and Support (organizational backing and resources). Our results show that these factors are interconnected - each one affects the next. For instance, strong organizational support results in a clearer strategy (β= 0.432, p < 0.001), which improves work processes (β= 0.428, p < 0.001) and builds better infrastructure (β= 0.547, p < 0.001). Together, these elements determine whether a project succeeds. The surprising finding? Although AI assistants make coding faster, they don't guarantee project success. AI assists with the "how" of coding but cannot replace the "why" and "what" of strategic thinking.

---

### COMPASS: A Framework for Evaluating Organization-Specific Policy Alignment in LLMs

Authors: Dasol Choi, DongGeon Lee, Brigitta Jesica Kartono, Helena Berndt, Taeyoun Kwon, Joonwon Jang, Haon Park, Hwanjo Yu, Minsuk Kahng
Published: 2026-01-05
Categories: cs.AI, cs.CY
arXiv: https://arxiv.org/abs/2601.01836v1

As large language models are deployed in high-stakes enterprise applications, from healthcare to finance, ensuring adherence to organization-specific policies has become essential. Yet existing safety evaluations focus exclusively on universal harms. We present COMPASS (Company/Organization Policy Alignment Assessment), the first systematic framework for evaluating whether LLMs comply with organizational allowlist and denylist policies. We apply COMPASS to eight diverse industry scenarios, generating and validating 5,920 queries that test both routine compliance and adversarial robustness through strategically designed edge cases. Evaluating seven state-of-the-art models, we uncover a fundamental asymmetry: models reliably handle legitimate requests (>95% accuracy) but catastrophically fail at enforcing prohibitions, refusing only 13-40% of adversarial denylist violations. These results demonstrate that current LLMs lack the robustness required for policy-critical deployments, establishing COMPASS as an essential evaluation framework for organizational AI safety.

---

### RSwinV2-MD: An Enhanced Residual SwinV2 Transformer for Monkeypox Detection from Skin Images

Authors: Rashid Iqbal, Saddam Hussain Khan
Published: 2026-01-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01835v2

In this paper, a deep learning approach for Mpox diagnosis named Customized Residual SwinTransformerV2 (RSwinV2) has been proposed, trying to enhance the capability of lesion classification by employing the RSwinV2 tool-assisted vision approach. In the RSwinV2 method, a hierarchical structure of the transformer has been customized based on the input dimensionality, embedding structure, and output targeted by the method. In this RSwinV2 approach, the input image has been split into non-overlapping patches and processed using shifted windows and attention in these patches. This process has helped the method link all the windows efficiently by avoiding the locality issues of non-overlapping regions in attention, while being computationally efficient. RSwinV2 has further developed based on SwinTransformer and has included patch and position embeddings to take advantage of the transformer global-linking capability by employing multi-head attention in these embeddings. Furthermore, RSwinV2 has developed and incorporated the Inverse Residual Block (IRB) into this method, which utilizes convolutional skip connections with these inclusive designs to address the vanishing gradient issues during processing. RSwinV2 inclusion of IRB has therefore facilitated this method to link global patterns as well as local patterns; hence, its integrity has helped improve lesion classification capability by minimizing variability of Mpox and increasing differences of Mpox, chickenpox, measles, and cowpox. In testing SwinV2, its accuracy of 96.51 and an F1score of 96.13 have been achieved on the Kaggle public dataset, which has outperformed standard CNN models and SwinTransformers; the RSwinV2 vector has thus proved its validity as a computer-assisted tool for Mpox lesion observation interpretation.

---

### FAROS: Robust Federated Learning with Adaptive Scaling against Backdoor Attacks

Authors: Chenyu Hu, Qiming Hu, Sinan Chen, Nianyu Li, Mingyue Zhang, Jialong Li
Published: 2026-01-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01833v1

Federated Learning (FL) enables multiple clients to collaboratively train a shared model without exposing local data. However, backdoor attacks pose a significant threat to FL. These attacks aim to implant a stealthy trigger into the global model, causing it to mislead on inputs that possess a specific trigger while functioning normally on benign data. Although pre-aggregation detection is a main defense direction, existing state-of-the-art defenses often rely on fixed defense parameters. This reliance makes them vulnerable to single-point-of-failure risks, rendering them less effective against sophisticated attackers. To address these limitations, we propose FAROS, an enhanced FL framework that incorporates Adaptive Differential Scaling (ADS) and Robust Core-set Computing (RCC). The ADS mechanism adjusts the defense's sensitivity dynamically, based on the dispersion of uploaded gradients by clients in each round. This allows it to counter attackers who strategically shift between stealthiness and effectiveness. Furthermore, the RCC effectively mitigates the risk of single-point failure by computing the centroid of a core set comprising clients with the highest confidence. We conducted extensive experiments across various datasets, models, and attack scenarios. The results demonstrate that our method outperforms current defenses in both attack success rate and main task accuracy.

---

### Yukthi Opus: A Multi-Chain Hybrid Metaheuristic for Large-Scale NP-Hard Optimization

Authors: SB Danush Vikraman, Hannah Abigail, Prasanna Kesavraj, Gajanan V Honnavar
Published: 2026-01-05
Categories: cs.NE, cs.AI
arXiv: https://arxiv.org/abs/2601.01832v3

We present Yukthi Opus (YO), a multi-chain hybrid metaheuristic designed for NP-hard optimization under explicit evaluation budget constraints. YO integrates three complementary mechanisms in a structured two-phase architecture: Markov Chain Monte Carlo (MCMC) for global exploration, greedy local search for exploitation, and simulated annealing with adaptive reheating to enable controlled escape from local minima. A dedicated burn-in phase allocates evaluations to probabilistic exploration, after which a hybrid optimization loop refines promising candidates. YO further incorporates a spatial blacklist mechanism to avoid repeated evaluation of poor regions and a multi-chain execution strategy to improve robustness and reduce sensitivity to initialization. We evaluate YO on three benchmarks: the Rastrigin function (5D) with ablation studies, the Traveling Salesman Problem with 50 to 200 cities, and the Rosenbrock function (5D) with comparisons against established optimizers including CMA-ES, Bayesian optimization, and accelerated particle swarm optimization. Results show that MCMC exploration and greedy refinement are critical for solution quality, while simulated annealing and multi-chain execution primarily improve stability and variance reduction. Overall, YO achieves competitive performance on large and multimodal problems while maintaining predictable evaluation budgets, making it suitable for expensive black-box optimization settings.

---

### ARIES: A Scalable Multi-Agent Orchestration Framework for Real-Time Epidemiological Surveillance and Outbreak Monitoring

Authors: Aniket Wattamwar, Sampson Akwafuo
Published: 2026-01-05
Categories: cs.MA, cs.AI, cs.IR, cs.SE
arXiv: https://arxiv.org/abs/2601.01831v1

Global health surveillance is currently facing a challenge of Knowledge Gaps. While general-purpose AI has proliferated, it remains fundamentally unsuited for the high-stakes epidemiological domain due to chronic hallucinations and an inability to navigate specialized data silos. This paper introduces ARIES (Agentic Retrieval Intelligence for Epidemiological Surveillance), a specialized, autonomous multi-agent framework designed to move beyond static, disease-specific dashboards toward a dynamic intelligence ecosystem. Built on a hierarchical command structure, ARIES utilizes GPTs to orchestrate a scalable swarm of sub-agents capable of autonomously querying World Health Organization (WHO), Center for Disease Control and Prevention (CDC), and peer-reviewed research papers. By automating the extraction and logical synthesis of surveillance data, ARIES provides a specialized reasoning that identifies emergent threats and signal divergence in near real-time. This modular architecture proves that a task-specific agentic swarm can outperform generic models, offering a robust, extensible for next-generation outbreak response and global health intelligence.

---

### RealPDEBench: A Benchmark for Complex Physical Systems with Real-World Data

Authors: Peiyan Hu, Haodong Feng, Hongyuan Liu, Tongtong Yan, Wenhao Deng, Tianrun Gao, Rong Zheng, Haoren Zheng, Chenglei Yu, Chuanrui Wang, Kaiwen Li, Zhi-Ming Ma et al.
Published: 2026-01-05
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.01829v2

Predicting the evolution of complex physical systems remains a central problem in science and engineering. Despite rapid progress in scientific Machine Learning (ML) models, a critical bottleneck is the lack of expensive real-world data, resulting in most current models being trained and validated on simulated data. Beyond limiting the development and evaluation of scientific ML, this gap also hinders research into essential tasks such as sim-to-real transfer. We introduce RealPDEBench, the first benchmark for scientific ML that integrates real-world measurements with paired numerical simulations. RealPDEBench consists of five datasets, three tasks, eight metrics, and ten baselines. We first present five real-world measured datasets with paired simulated datasets across different complex physical systems. We further define three tasks, which allow comparisons between real-world and simulated data, and facilitate the development of methods to bridge the two. Moreover, we design eight evaluation metrics, spanning data-oriented and physics-oriented metrics, and finally benchmark ten representative baselines, including state-of-the-art models, pretrained PDE foundation models, and a traditional method. Experiments reveal significant discrepancies between simulated and real-world data, while showing that pretraining with simulated data consistently improves both accuracy and convergence. In this work, we hope to provide insights from real-world data, advancing scientific ML toward bridging the sim-to-real gap and real-world deployment. Our benchmark, datasets, and instructions are available at https://realpdebench.github.io/.

---

### Emergent Introspective Awareness in Large Language Models

Authors: Jack Lindsey
Published: 2026-01-05
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.01828v1

We investigate whether large language models can introspect on their internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model's activations, and measuring the influence of these manipulations on the model's self-reported states. We find that models can, in certain scenarios, notice the presence of injected concepts and accurately identify them. Models demonstrate some ability to recall prior internal representations and distinguish them from raw text inputs. Strikingly, we find that some models can use their ability to recall prior intentions in order to distinguish their own outputs from artificial prefills. In all these experiments, Claude Opus 4 and 4.1, the most capable models we tested, generally demonstrate the greatest introspective awareness; however, trends across models are complex and sensitive to post-training strategies. Finally, we explore whether models can explicitly control their internal representations, finding that models can modulate their activations when instructed or incentivized to "think about" a concept. Overall, our results indicate that current language models possess some functional introspective awareness of their own internal states. We stress that in today's models, this capacity is highly unreliable and context-dependent; however, it may continue to develop with further improvements to model capabilities.

---

### Aspect Extraction from E-Commerce Product and Service Reviews

Authors: Valiant Lance D. Dionela, Fatima Kriselle S. Dy, Robin James M. Hombrebueno, Aaron Rae M. Nicolas, Charibeth K. Cheng, Raphael W. Gonda
Published: 2026-01-05
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.01827v1

Aspect Extraction (AE) is a key task in Aspect-Based Sentiment Analysis (ABSA), yet it remains difficult to apply in low-resource and code-switched contexts like Taglish, a mix of Tagalog and English commonly used in Filipino e-commerce reviews. This paper introduces a comprehensive AE pipeline designed for Taglish, combining rule-based, large language model (LLM)-based, and fine-tuning techniques to address both aspect identification and extraction. A Hierarchical Aspect Framework (HAF) is developed through multi-method topic modeling, along with a dual-mode tagging scheme for explicit and implicit aspects. For aspect identification, four distinct models are evaluated: a Rule-Based system, a Generative LLM (Gemini 2.0 Flash), and two Fine-Tuned Gemma-3 1B models trained on different datasets (Rule-Based vs. LLM-Annotated). Results indicate that the Generative LLM achieved the highest performance across all tasks (Macro F1 0.91), demonstrating superior capability in handling implicit aspects. In contrast, the fine-tuned models exhibited limited performance due to dataset imbalance and architectural capacity constraints. This work contributes a scalable and linguistically adaptive framework for enhancing ABSA in diverse, code-switched environments.

---

### CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning

Authors: Yaxin Cui, Yuanqiang Zeng, Jiapeng Yan, Keling Lin, Kai Ji, Jianhui Zeng, Sheng Zhang, Xin Luo, Binzhu Su, Chaolai Shen, Jiahao Yu
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01825v1

Large Language Models (LLMs) have achieved remarkable success in general benchmarks, yet their competence in commodity supply chains (CSCs) -- a domain governed by institutional rule systems and feasibility constraints -- remains under-explored. CSC decisions are shaped jointly by process stages (e.g., planning, procurement, delivery), variety-specific rules (e.g., contract specifications and delivery grades), and reasoning depth (from retrieval to multi-step analysis and decision selection). We introduce CSCBench, a 2.3K+ single-choice benchmark for CSC reasoning, instantiated through our PVC 3D Evaluation Framework (Process, Variety, and Cognition). The Process axis aligns tasks with SCOR+Enable; the Variety axis operationalizes commodity-specific rule systems under coupled material-information-financial constraints, grounded in authoritative exchange guidebooks/rulebooks and industry reports; and the Cognition axis follows Bloom's revised taxonomy. Evaluating representative LLMs under a direct prompting setting, we observe strong performance on the Process and Cognition axes but substantial degradation on the Variety axis, especially on Freight Agreements. CSCBench provides a diagnostic yardstick for measuring and improving LLM capabilities in this high-stakes domain.

---

### DisCo-FLoc: Semantic-Free Floorplan Localization via $SE(2)$-Aware Contrastive Disambiguation

Authors: Ping Zhong, Shiyong Meng, Bolei Chen, Tao Zou, Chaoxu Mu, Jianxin Wang
Published: 2026-01-05
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.01822v3

Visual Floorplan Localization (FLoc) struggles with severe structural aliasing caused by repetitive minimalist layouts. This occurs because physically distant poses share highly similar visual-geometric features, which degrades spatial separability and angular discriminability. While existing methods attempt to mitigate these ambiguities by relying on costly semantic annotations, the resulting performance gains remain inherently limited. To address the above issues, we propose DisCo-FLoc, a semantic-free method for visual-geometric Contrastive Disambiguation. First, we introduce a depth-aware Ray Regression Predictor (RRP) that serves as a dense-to-ray geometric projector. By explicitly suppressing visual clutter along the vertical dimension, RRP projects monocular RGB images into 2D ray primitives, which are matched with floorplans to produce geometry-aware FLoc candidates. Second, to resolve the remaining ambiguity among these candidates, we propose a spatially perturbed contrastive objective to align RGB images with local floorplan structures and formulate a visual-geometric compatibility function. In particular, we meticulously construct positive and negative samples at both positional and directional levels through $SE(2)$ pose perturbations for contrastive learning, effectively achieving pose smoothness, spatial separability, and angular discriminability. The compatibility function enables DisCo-FLoc to disambiguate FLoc by using richer visual context beyond pure geometric layouts, without requiring any semantic annotations. Extensive experiments on two challenging visual FLoc benchmarks demonstrate that DisCo-FLoc significantly outperforms state-of-the-art semantic-based methods, especially narrowing the performance gap between positional and directional FLoc accuracy.

---

### Robust Egocentric Visual Attention Prediction Through Language-guided Scene Context-aware Learning

Authors: Sungjune Park, Hongda Mao, Qingshuang Chen, Yong Man Ro, Yelin Kim
Published: 2026-01-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01818v1

As the demand for analyzing egocentric videos grows, egocentric visual attention prediction, anticipating where a camera wearer will attend, has garnered increasing attention. However, it remains challenging due to the inherent complexity and ambiguity of dynamic egocentric scenes. Motivated by evidence that scene contextual information plays a crucial role in modulating human attention, in this paper, we present a language-guided scene context-aware learning framework for robust egocentric visual attention prediction. We first design a context perceiver which is guided to summarize the egocentric video based on a language-based scene description, generating context-aware video representations. We then introduce two training objectives that: 1) encourage the framework to focus on the target point-of-interest regions and 2) suppress distractions from irrelevant regions which are less likely to attract first-person attention. Extensive experiments on Ego4D and Aria Everyday Activities (AEA) datasets demonstrate the effectiveness of our approach, achieving state-of-the-art performance and enhanced robustness across diverse, dynamic egocentric scenarios.

---

### Admissibility Alignment

Authors: Chris Duffey
Published: 2026-01-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01816v1

This paper introduces Admissibility Alignment: a reframing of AI alignment as a property of admissible action and decision selection over distributions of outcomes under uncertainty, evaluated through the behavior of candidate policies. We present MAP-AI (Monte Carlo Alignment for Policy) as a canonical system architecture for operationalizing admissibility alignment, formalizing alignment as a probabilistic, decision-theoretic property rather than a static or binary condition. MAP-AI, a new control-plane system architecture for aligned decision-making under uncertainty, enforces alignment through Monte Carlo estimation of outcome distributions and admissibility-controlled policy selection rather than static model-level constraints. The framework evaluates decision policies across ensembles of plausible futures, explicitly modeling uncertainty, intervention effects, value ambiguity, and governance constraints. Alignment is assessed through distributional properties including expected utility, variance, tail risk, and probability of misalignment rather than accuracy or ranking performance. This approach distinguishes probabilistic prediction from decision reasoning under uncertainty and provides an executable methodology for evaluating trust and alignment in enterprise and institutional AI systems. The result is a practical foundation for governing AI systems whose impact is determined not by individual forecasts, but by policy behavior across distributions and tail events. Finally, we show how distributional alignment evaluation can be integrated into decision-making itself, yielding an admissibility-controlled action selection mechanism that alters policy behavior under uncertainty without retraining or modifying underlying models.

---

### Spatio-temporal modeling and forecasting with Fourier neural operators

Authors: Pratik Nag, Andrew Zammit-Mangion, Sumeetpal Singh, Noel Cressie
Published: 2026-01-05
Categories: stat.ME, stat.ML
arXiv: https://arxiv.org/abs/2601.01813v1

Spatio-temporal process models are often used for modeling dynamic physical and biological phenomena that evolve across space and time. These phenomena may exhibit environmental heterogeneity and complex interactions that are difficult to capture using traditional statistical process models such as Gaussian processes. This work proposes the use of Fourier neural operators (FNOs) for constructing statistical dynamical spatio-temporal models for forecasting. An FNO is a flexible mapping of functions that approximates the solution operator of possibly unknown linear or non-linear partial differential equations (PDEs) in a computationally efficient manner. It does so using samples of inputs and their respective outputs, and hence explicit knowledge of the underlying PDE is not required. Through simulations from a nonlinear PDE with known solution, we compare FNO forecasts to those from state-of-the-art statistical spatio-temporal-forecasting methods. Further, using sea surface temperature data over the Atlantic Ocean and precipitation data across Europe, we demonstrate the ability of FNO-based dynamic spatio-temporal (DST) statistical modeling to capture complex real-world spatio-temporal dependencies. Using collections of testing instances, we show that the FNO-DST forecasts are accurate with valid uncertainty quantification.

---

### Adaptive Hybrid Optimizer based Framework for Lumpy Skin Disease Identification

Authors: Ubaidullah, Muhammad Abid Hussain, Mohsin Raza Jafri, Rozi Khan, Moid Sandhu, Abd Ullah Khan, Hyundong Shin
Published: 2026-01-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01807v1

Lumpy Skin Disease (LSD) is a contagious viral infection that significantly deteriorates livestock health, thereby posing a serious threat to the global economy and food security. Owing to its rapid spread characteristics, early and precise identification is crucial to prevent outbreaks and ensure timely intervention. In this paper, we propose a hybrid deep learning-based approach called LUMPNet for the early detection of LSD. LUMPNet utilizes image data to detect and classify skin nodules -- the primary indicator of LSD. To this end, LUMPNet uses YOLOv11, EfficientNet-based CNN classifier with compound scaling, and a novel adaptive hybrid optimizer. More precisely, LUMPNet detects and localizes LSD skin nodules and lesions on cattle images. It exploits EfficientNet to classify the localized cattle images into LSD-affected or healthy categories. To stabilize and accelerate the training of YOLOv11 and EfficientNet hybrid model, a novel adaptive hybrid optimizer is proposed and utilized. We evaluate LUMPNet at various stages of LSD using a publicly available dataset. Results indicate that the proposed scheme achieves 99% LSD detection training accuracy, and outperforms existing schemes. The model also achieves validation accuracy of 98%. Moreover, for further evaluation, we conduct a case study using an optimized EfficientNet-B0 model trained with the AdamW optimizer, and compare its performance with LUMPNet. The results show that LUMPNet achieves superior performance.

---

### V-CORE: Temporally Consistent Video Understanding for Video-LLM

Authors: Zhengjian Kang, Qi Chen, Rui Liu, Kangtong Mo, Xingyu Zhang, Xiaoyu Deng, Ye Zhang
Published: 2026-01-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01804v3

Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient Video-LLMs rely on unconstrained bidirectional projectors to model inter-frame interactions, which can blur temporal ordering by allowing later frames to influence earlier representations, without explicit architectural mechanisms to respect the directional nature of video reasoning. To address this limitation, we propose V-CORE, a parameter-efficient framework that introduces explicit temporal ordering constraints for video understanding. V-CORE consists of two key components: (1) Learnable Spatial Aggregation (LSA), which adaptively selects salient spatial tokens to reduce redundancy, and (2) a Causality-Aware Temporal Projector (CATP), which enforces structured unidirectional information flow via block-causal attention and a terminal dynamic summary token acting as a causal sink. This design preserves intra-frame spatial interactions while ensuring that temporal information is aggregated in a strictly ordered manner. With 4-bit QLoRA and a frozen LLM backbone, V-CORE can be trained efficiently on a single consumer GPU. Experiments show that V-CORE achieves strong performance on the challenging NExT-QA benchmark, reaching 61.2% accuracy, and remains competitive across MSVD-QA, MSRVTT-QA, and TGIF-QA, with gains concentrated in temporal and causal reasoning subcategories (+3.5% and +5.2% respectively), directly validating the importance of explicit temporal ordering constraints.

---

### Causality-Aware Temporal Projection for Video Understanding in Video-LLMs

Authors: Zhengjian Kang, Qi Chen, Rui Liu, Kangtong Mo, Xingyu Zhang, Xiaoyu Deng, Ye Zhang
Published: 2026-01-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01804v1

Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient Video-LLMs rely on unconstrained bidirectional projectors to model inter-frame interactions, which can blur temporal ordering by allowing later frames to influence earlier representations, without explicit architectural mechanisms to respect the directional nature of video reasoning. To address this limitation, we propose V-CORE, a parameter-efficient framework that introduces explicit temporal ordering constraints for video understanding. V-CORE consists of two key components: (1) Learnable Spatial Aggregation (LSA), which adaptively selects salient spatial tokens to reduce redundancy, and (2) a Causality-Aware Temporal Projector (CATP), which enforces structured unidirectional information flow via block-causal attention and a terminal dynamic summary token acting as a causal sink. This design preserves intra-frame spatial interactions while ensuring that temporal information is aggregated in a strictly ordered manner. With 4-bit QLoRA and a frozen LLM backbone, V-CORE can be trained efficiently on a single consumer GPU. Experiments show that V-CORE achieves strong performance on the challenging NExT-QA benchmark, reaching 61.2% accuracy, and remains competitive across MSVD-QA, MSRVTT-QA, and TGIF-QA, with gains concentrated in temporal and causal reasoning subcategories (+3.5% and +5.2% respectively), directly validating the importance of explicit temporal ordering constraints.

---

### Moments Matter:Stabilizing Policy Optimization using Return Distributions

Authors: Dennis Jabs, Aditya Mohan, Marius Lindauer
Published: 2026-01-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.01803v1

Deep Reinforcement Learning (RL) agents often learn policies that achieve the same episodic return yet behave very differently, due to a combination of environmental (random transitions, initial conditions, reward noise) and algorithmic (minibatch selection, exploration noise) factors. In continuous control tasks, even small parameter shifts can produce unstable gaits, complicating both algorithm comparison and real-world transfer. Previous work has shown that such instability arises when policy updates traverse noisy neighborhoods and that the spread of post-update return distribution $R(θ)$, obtained by repeatedly sampling minibatches, updating $θ$, and measuring final returns, is a useful indicator of this noise. Although explicitly constraining the policy to maintain a narrow $R(θ)$ can improve stability, directly estimating $R(θ)$ is computationally expensive in high-dimensional settings. We propose an alternative that takes advantage of environmental stochasticity to mitigate update-induced variability. Specifically, we model state-action return distribution through a distributional critic and then bias the advantage function of PPO using higher-order moments (skewness and kurtosis) of this distribution. By penalizing extreme tail behaviors, our method discourages policies from entering parameter regimes prone to instability. We hypothesize that in environments where post-update critic values align poorly with post-update returns, standard PPO struggles to produce a narrow $R(θ)$. In such cases, our moment-based correction narrows $R(θ)$, improving stability by up to 75% in Walker2D, while preserving comparable evaluation returns.

---

### PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism AI Psychological Counselor

Authors: Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, Jingyuan Zhao, Qin Chen, Ningning Zhou, Kai Chen et al.
Published: 2026-01-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01802v3

To develop a reliable AI for psychological assessment, we introduce \texttt{PsychEval}, a multi-session, multi-therapy, and highly realistic benchmark designed to address three key challenges: \textbf{1) Can we train a highly realistic AI counselor?} Realistic counseling is a longitudinal task requiring sustained memory and dynamic goal tracking. We propose a multi-session benchmark (spanning 6-10 sessions across three distinct stages) that demands critical capabilities such as memory continuity, adaptive reasoning, and longitudinal planning. The dataset is annotated with extensive professional skills, comprising over 677 meta-skills and 4577 atomic skills. \textbf{2) How to train a multi-therapy AI counselor?} While existing models often focus on a single therapy, complex cases frequently require flexible strategies among various therapies. We construct a diverse dataset covering five therapeutic modalities (Psychodynamic, Behaviorism, CBT, Humanistic Existentialist, and Postmodernist) alongside an integrative therapy with a unified three-stage clinical framework across six core psychological topics. \textbf{3) How to systematically evaluate an AI counselor?} We establish a holistic evaluation framework with 18 therapy-specific and therapy-shared metrics across Client-Level and Counselor-Level dimensions. To support this, we also construct over 2,000 diverse client profiles. Extensive experimental analysis fully validates the superior quality and clinical fidelity of our dataset. Crucially, \texttt{PsychEval} transcends static benchmarking to serve as a high-fidelity reinforcement learning environment that enables the self-evolutionary training of clinically responsible and adaptive AI counselors.

---

### PsychEval: A Multi-Session and Multi-Therapy Benchmark for High-Realism and Comprehensive AI Psychological Counselor

Authors: Qianjun Pan, Junyi Wang, Jie Zhou, Yutao Yang, Junsong Li, Kaiyin Xu, Yougen Zhou, Yihan Li, Jingyuan Zhao, Qin Chen, Ningning Zhou, Kai Chen et al.
Published: 2026-01-05
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.01802v1

To develop a reliable AI for psychological assessment, we introduce \texttt{PsychEval}, a multi-session, multi-therapy, and highly realistic benchmark designed to address three key challenges: \textbf{1) Can we train a highly realistic AI counselor?} Realistic counseling is a longitudinal task requiring sustained memory and dynamic goal tracking. We propose a multi-session benchmark (spanning 6-10 sessions across three distinct stages) that demands critical capabilities such as memory continuity, adaptive reasoning, and longitudinal planning. The dataset is annotated with extensive professional skills, comprising over 677 meta-skills and 4577 atomic skills. \textbf{2) How to train a multi-therapy AI counselor?} While existing models often focus on a single therapy, complex cases frequently require flexible strategies among various therapies. We construct a diverse dataset covering five therapeutic modalities (Psychodynamic, Behaviorism, CBT, Humanistic Existentialist, and Postmodernist) alongside an integrative therapy with a unified three-stage clinical framework across six core psychological topics. \textbf{3) How to systematically evaluate an AI counselor?} We establish a holistic evaluation framework with 18 therapy-specific and therapy-shared metrics across Client-Level and Counselor-Level dimensions. To support this, we also construct over 2,000 diverse client profiles. Extensive experimental analysis fully validates the superior quality and clinical fidelity of our dataset. Crucially, \texttt{PsychEval} transcends static benchmarking to serve as a high-fidelity reinforcement learning environment that enables the self-evolutionary training of clinically responsible and adaptive AI counselors.

---

### Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving

Authors: Qi Wei, Junchao Fan, Zhao Yang, Jianhua Wang, Jingkai Mao, Xiaolin Chang
Published: 2026-01-05
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.01800v1

Reinforcement learning (RL) has shown considerable potential in autonomous driving (AD), yet its vulnerability to perturbations remains a critical barrier to real-world deployment. As a primary countermeasure, adversarial training improves policy robustness by training the AD agent in the presence of an adversary that deliberately introduces perturbations. Existing approaches typically model the interaction as a zero-sum game with continuous attacks. However, such designs overlook the inherent asymmetry between the agent and the adversary and then fail to reflect the sparsity of safety-critical risks, rendering the achieved robustness inadequate for practical AD scenarios. To address these limitations, we introduce criticality-aware robust RL (CARRL), a novel adversarial training approach for handling sparse, safety-critical risks in autonomous driving. CARRL consists of two interacting components: a risk exposure adversary (REA) and a risk-targeted robust agent (RTRA). We model the interaction between the REA and RTRA as a general-sum game, allowing the REA to focus on exposing safety-critical failures (e.g., collisions) while the RTRA learns to balance safety with driving efficiency. The REA employs a decoupled optimization mechanism to better identify and exploit sparse safety-critical moments under a constrained budget. However, such focused attacks inevitably result in a scarcity of adversarial data. The RTRA copes with this scarcity by jointly leveraging benign and adversarial experiences via a dual replay buffer and enforces policy consistency under perturbations to stabilize behavior. Experimental results demonstrate that our approach reduces the collision rate by at least 22.66\% across all cases compared to state-of-the-art baseline methods.

---

### VerLM: Explaining Face Verification Using Natural Language

Authors: Syed Abdul Hannan, Hazim Bukhari, Thomas Cantalapiedra, Eman Ansar, Massa Baali, Rita Singh, Bhiksha Raj
Published: 2026-01-05
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.01798v1

Face verification systems have seen substantial advancements; however, they often lack transparency in their decision-making processes. In this paper, we introduce an innovative Vision-Language Model (VLM) for Face Verification, which not only accurately determines if two face images depict the same individual but also explicitly explains the rationale behind its decisions. Our model is uniquely trained using two complementary explanation styles: (1) concise explanations that summarize the key factors influencing its decision, and (2) comprehensive explanations detailing the specific differences observed between the images. We adapt and enhance a state-of-the-art modeling approach originally designed for audio-based differentiation to suit visual inputs effectively. This cross-modal transfer significantly improves our model's accuracy and interpretability. The proposed VLM integrates sophisticated feature extraction techniques with advanced reasoning capabilities, enabling clear articulation of its verification process. Our approach demonstrates superior performance, surpassing baseline methods and existing models. These findings highlight the immense potential of vision language models in face verification set up, contributing to more transparent, reliable, and explainable face verification systems.

---

### Distributed Federated Learning by Alternating Periods of Training

Authors: Shamik Bhattacharyya, Rachel Kalpana Kalaimani
Published: 2026-01-05
Categories: cs.LG, eess.SY
arXiv: https://arxiv.org/abs/2601.01793v1

Federated learning is a privacy-focused approach towards machine learning where models are trained on client devices with locally available data and aggregated at a central server. However, the dependence on a single central server is challenging in the case of a large number of clients and even poses the risk of a single point of failure. To address these critical limitations of scalability and fault-tolerance, we present a distributed approach to federated learning comprising multiple servers with inter-server communication capabilities. While providing a fully decentralized approach, the designed framework retains the core federated learning structure where each server is associated with a disjoint set of clients with server-client communication capabilities. We propose a novel DFL (Distributed Federated Learning) algorithm which uses alternating periods of local training on the client data followed by global training among servers. We show that the DFL algorithm, under a suitable choice of parameters, ensures that all the servers converge to a common model value within a small tolerance of the ideal model, thus exhibiting effective integration of local and global training models. Finally, we illustrate our theoretical claims through numerical simulations.

---

### HyperCLOVA X 8B Omni

Authors: NAVER Cloud HyperCLOVA X Team
Published: 2026-01-05
Categories: cs.LG, cs.AI, cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.01792v1

In this report, we present HyperCLOVA X 8B Omni, the first any-to-any omnimodal model in the HyperCLOVA X family that supports text, audio, and vision as both inputs and outputs. By consolidating multimodal understanding and generation into a single model rather than separate modality-specific pipelines, HyperCLOVA X 8B Omni serves as an 8B-scale omni-pathfinding point toward practical any-to-any omni assistants. At a high level, the model unifies modalities through a shared next-token prediction interface over an interleaved multimodal sequence, while vision and audio encoders inject continuous embeddings for fine-grained understanding and grounding. Empirical evaluations demonstrate competitive performance against comparably sized models across diverse input-output combinations spanning text, audio, and vision, in both Korean and English. We anticipate that the open-weight release of HyperCLOVA X 8B Omni will support a wide range of research and deployment scenarios.

---

### UnPII: Unlearning Personally Identifiable Information with Quantifiable Exposure Risk

Authors: Intae Jeon, Yujeong Kwon, Hyungjoon Koo
Published: 2026-01-05
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2601.01786v1

The ever-increasing adoption of Large Language Models in critical sectors like finance, healthcare, and government raises privacy concerns regarding the handling of sensitive Personally Identifiable Information (PII) during training. In response, regulations such as European Union's General Data Protection Regulation (GDPR) mandate the deletion of PII upon requests, underscoring the need for reliable and cost-effective data removal solutions. Machine unlearning has emerged as a promising direction for selectively forgetting data points. However, existing unlearning techniques typically apply a uniform forgetting strategy that neither accounts for the varying privacy risks posed by different PII attributes nor reflects associated business risks. In this work, we propose UnPII, the first PII-centric unlearning approach that prioritizes forgetting based on the risk of individual or combined PII attributes. To this end, we introduce the PII risk index (PRI), a composite metric that incorporates multiple dimensions of risk factors: identifiability, sensitivity, usability, linkability, permanency, exposability, and compliancy. The PRI enables a nuanced evaluation of privacy risks associated with PII exposures and can be tailored to align with organizational privacy policies. To support realistic assessment, we systematically construct a synthetic PII dataset (e.g., 1,700 PII instances) that simulates realistic exposure scenarios. UnPII seamlessly integrates with established unlearning algorithms, such as Gradient Ascent, Negative Preference Optimization, and Direct Preference Optimization, without modifying their underlying principles. Our experimental results demonstrate that UnPII achieves the improvements of accuracy up to 11.8%, utility up to 6.3%, and generalizability up to 12.4%, respectively, while incurring a modest fine-tuning overhead of 27.5% on average during unlearning.

---

### SRAS: A Lightweight Reinforcement Learning-based Document Selector for Edge-Native RAG Pipelines

Authors: Rajiv Chaitanya Muttur
Published: 2026-01-05
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.01785v1

Retrieval-Augmented Generation (RAG) systems often rely on fixed top-k document selection mechanisms that ignore downstream generation quality and impose computational overheads. We propose SRAS (Sparse Reward-Aware Selector), a lightweight document selector trained via reinforcement learning (RL) for edge-native RAG deployment. Unlike prior RL-based retrievers that assume large memory and latency budgets, SRAS learns a compact (~0.76MB) policy using Proximal Policy Optimization (PPO), guided by a hybrid reward signal combining Relaxed F1 and BERTScore. Our method operates under tight token and compute constraints, maintaining <1s latency on CPU. SRAS outperforms supervised and random selectors on a synthetic QA benchmark, and generalizes to real-world data, achieving BERTScore F1 of 0.8546 on SQuAD v2 without domain-specific tuning. This work is the first to demonstrate that RL-based document selection can be made ultra-lightweight, latency-aware, and effective for on-device RAG pipelines.

---

### DDNet: A Dual-Stream Graph Learning and Disentanglement Framework for Temporal Forgery Localization

Authors: Boyang Zhao, Xin Liao, Jiaxin Chen, Xiaoshuai Wu, Yufeng Wu
Published: 2026-01-05
Categories: cs.CV, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2601.01784v1

The rapid evolution of AIGC technology enables misleading viewers by tampering mere small segments within a video, rendering video-level detection inaccurate and unpersuasive. Consequently, temporal forgery localization (TFL), which aims to precisely pinpoint tampered segments, becomes critical. However, existing methods are often constrained by \emph{local view}, failing to capture global anomalies. To address this, we propose a \underline{d}ual-stream graph learning and \underline{d}isentanglement framework for temporal forgery localization (DDNet). By coordinating a \emph{Temporal Distance Stream} for local artifacts and a \emph{Semantic Content Stream} for long-range connections, DDNet prevents global cues from being drowned out by local smoothness. Furthermore, we introduce Trace Disentanglement and Adaptation (TDA) to isolate generic forgery fingerprints, alongside Cross-Level Feature Embedding (CLFE) to construct a robust feature foundation via deep fusion of hierarchical features. Experiments on ForgeryNet and TVIL benchmarks demonstrate that our method outperforms state-of-the-art approaches by approximately 9\% in AP@0.95, with significant improvements in cross-domain robustness.

---

### Subimage Overlap Prediction: Task-Aligned Self-Supervised Pretraining For Semantic Segmentation In Remote Sensing Imagery

Authors: Lakshay Sharma, Alex Marin
Published: 2026-01-05
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.01781v1

Self-supervised learning (SSL) methods have become a dominant paradigm for creating general purpose models whose capabilities can be transferred to downstream supervised learning tasks. However, most such methods rely on vast amounts of pretraining data. This work introduces Subimage Overlap Prediction, a novel self-supervised pretraining task to aid semantic segmentation in remote sensing imagery that uses significantly lesser pretraining imagery. Given an image, a sub-image is extracted and the model is trained to produce a semantic mask of the location of the extracted sub-image within the original image. We demonstrate that pretraining with this task results in significantly faster convergence, and equal or better performance (measured via mIoU) on downstream segmentation. This gap in convergence and performance widens when labeled training data is reduced. We show this across multiple architecture types, and with multiple downstream datasets. We also show that our method matches or exceeds performance while requiring significantly lesser pretraining data relative to other SSL methods. Code and model weights are provided at \href{https://github.com/sharmalakshay93/subimage-overlap-prediction}{github.com/sharmalakshay93/subimage-overlap-prediction}.

---

### LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment

Authors: Arsham Khosravani, Alireza Hoseinpour, Arshia Akhavan, Mehdi Keshani, Abbas Heydarnoori
Published: 2026-01-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.01780v2

Issue assignment is a critical process in software maintenance, where new issue reports are validated and assigned to suitable developers. However, manual issue assignment is often inconsistent and error-prone, especially in large open-source projects where thousands of new issues are reported monthly. Existing automated approaches have shown promise, but many rely heavily on large volumes of project-specific training data or relational information that is often sparse and noisy, which limits their effectiveness. To address these challenges, we propose LIA (LLM-based Issue Assignment), which employs supervised fine-tuning to adapt an LLM, DeepSeek-R1-Distill-Llama-8B in this work, for automatic issue assignment. By leveraging the LLM's pretrained semantic understanding of natural language and software-related text, LIA learns to generate ranked developer recommendations directly from issue titles and descriptions. The ranking is based on the model's learned understanding of historical issue-to-developer assignments, using patterns from past tasks to infer which developers are most likely to handle new issues. Through comprehensive evaluation, we show that LIA delivers substantial improvements over both its base pretrained model and state-of-the-art baselines. It achieves up to +187.8% higher Hit@1 compared to the DeepSeek-R1-Distill-Llama-8B pretrained base model, and outperforms four leading issue assignment methods by as much as +211.2% in Hit@1 score. These results highlight the effectiveness of domain-adapted LLMs for software maintenance tasks and establish LIA as a practical, high-performing solution for issue assignment.

---

### LIA: Supervised Fine-Tuning of Large Language Models for Automatic Issue Assignment

Authors: Arsham Khosravani, Alireza Hosseinpour, Arshia Akhavan, Mehdi Keshani, Abbas Heydarnoori
Published: 2026-01-05
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.01780v1

Issue assignment is a critical process in software maintenance, where new issue reports are validated and assigned to suitable developers. However, manual issue assignment is often inconsistent and error-prone, especially in large open-source projects where thousands of new issues are reported monthly. Existing automated approaches have shown promise, but many rely heavily on large volumes of project-specific training data or relational information that is often sparse and noisy, which limits their effectiveness. To address these challenges, we propose LIA (LLM-based Issue Assignment), which employs supervised fine-tuning to adapt an LLM, DeepSeek-R1-Distill-Llama-8B in this work, for automatic issue assignment. By leveraging the LLM's pretrained semantic understanding of natural language and software-related text, LIA learns to generate ranked developer recommendations directly from issue titles and descriptions. The ranking is based on the model's learned understanding of historical issue-to-developer assignments, using patterns from past tasks to infer which developers are most likely to handle new issues. Through comprehensive evaluation, we show that LIA delivers substantial improvements over both its base pretrained model and state-of-the-art baselines. It achieves up to +187.8% higher Hit@1 compared to the DeepSeek-R1-Distill-Llama-8B pretrained base model, and outperforms four leading issue assignment methods by as much as +211.2% in Hit@1 score. These results highlight the effectiveness of domain-adapted LLMs for software maintenance tasks and establish LIA as a practical, high-performing solution for issue assignment.

---

### Machine learning modularity

Authors: Yi Fan, Vishnu Jejjala, Yang Lei
Published: 2026-01-05
Categories: hep-th, cs.LG
arXiv: https://arxiv.org/abs/2601.01779v2

Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$θ$ function and the elliptic Gamma function. The model learns to apply algebraic identities, particularly the SL$(2,\mathbb{Z})$ and SL$(3,\mathbb{Z})$ modular transformations, to reduce heavily scrambled expressions to their canonical forms. Experimental results show that the model achieves over 99\% accuracy on in-distribution tests and maintains robust performance (exceeding 90\% accuracy) under significant extrapolation, such as with deeper scrambling depths. This demonstrates that the model has internalized the underlying algebraic rules of modular transformations rather than merely memorizing training patterns. Our work presents the first successful application of machine learning to perform symbolic simplification using modular identities, offering a new automated tool for computations with special functions in quantum field theory and the string theory.

---

### Machine learning modularity

Authors: Yi Fan, Vishnu Jejjala, Yang Lei
Published: 2026-01-05
Categories: hep-th, cs.LG
arXiv: https://arxiv.org/abs/2601.01779v1

Based on a transformer based sequence-to-sequence architecture combined with a dynamic batching algorithm, this work introduces a machine learning framework for automatically simplifying complex expressions involving multiple elliptic Gamma functions, including the $q$-$θ$ function and the elliptic Gamma function. The model learns to apply algebraic identities, particularly the SL$(2,\mathbb{Z})$ and SL$(3,\mathbb{Z})$ modular transformations, to reduce heavily scrambled expressions to their canonical forms. Experimental results show that the model achieves over 99\% accuracy on in-distribution tests and maintains robust performance (exceeding 90\% accuracy) under significant extrapolation, such as with deeper scrambling depths. This demonstrates that the model has internalized the underlying algebraic rules of modular transformations rather than merely memorizing training patterns. Our work presents the first successful application of machine learning to perform symbolic simplification using modular identities, offering a new automated tool for computations with special functions in quantum field theory and the string theory.

---

### BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali

Authors: Jakir Hasan, Shrestha Datta, Md Saiful Islam, Shubhashis Roy Dipta, Ameya Debnath
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01778v2

Despite its widespread use, Bengali lacks a robust automated International Phonetic Alphabet (IPA) transcription system that effectively supports both standard language and regional dialectal texts. Existing approaches struggle to handle regional variations, numerical expressions, and generalize poorly to previously unseen words. To address these limitations, we propose BanglaIPA, a novel IPA generation system that integrates a character-based vocabulary with word-level alignment. The proposed system accurately handles Bengali numerals and demonstrates strong performance across regional dialects. BanglaIPA improves inference efficiency by leveraging a precomputed word-to-IPA mapping dictionary for previously observed words. The system is evaluated on the standard Bengali and six regional variations of the DUAL-IPA dataset. Experimental results show that BanglaIPA outperforms baseline IPA transcription models by 58.4-78.7% and achieves an overall mean word error rate of 11.4%, highlighting its robustness in phonetic transcription generation for the Bengali language.

---

### BanglaIPA: Towards Robust Text-to-IPA Transcription with Contextual Rewriting in Bengali

Authors: Jakir Hasan, Shrestha Datta, Md Saiful Islam, Shubhashis Roy Dipta, Ameya Debnath
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01778v1

Despite its widespread use, Bengali lacks a robust automated International Phonetic Alphabet (IPA) transcription system that effectively supports both standard language and regional dialectal texts. Existing approaches struggle to handle regional variations, numerical expressions, and generalize poorly to previously unseen words. To address these limitations, we propose BanglaIPA, a novel IPA generation system that integrates a character-based vocabulary with word-level alignment. The proposed system accurately handles Bengali numerals and demonstrates strong performance across regional dialects. BanglaIPA improves inference efficiency by leveraging a precomputed word-to-IPA mapping dictionary for previously observed words. The system is evaluated on the standard Bengali and six regional variations of the DUAL-IPA dataset. Experimental results show that BanglaIPA outperforms baseline IPA transcription models by 58.4-78.7% and achieves an overall mean word error rate of 11.4%, highlighting its robustness in phonetic transcription generation for the Bengali language.

---

### Can Large Language Models Solve Engineering Equations? A Systematic Comparison of Direct Prediction and Solver-Assisted Approaches

Authors: Sai Varun Kodathala, Rakesh Vunnam
Published: 2026-01-05
Categories: cs.AI, cs.CE, math.NA
arXiv: https://arxiv.org/abs/2601.01774v1

Transcendental equations requiring iterative numerical solution pervade engineering practice, from fluid mechanics friction factor calculations to orbital position determination. We systematically evaluate whether Large Language Models can solve these equations through direct numerical prediction or whether a hybrid architecture combining LLM symbolic manipulation with classical iterative solvers proves more effective. Testing six state-of-the-art models (GPT-5.1, GPT-5.2, Gemini-3-Flash, Gemini-2.5-Lite, Claude-Sonnet-4.5, Claude-Opus-4.5) on 100 problems spanning seven engineering domains, we compare direct prediction against solver-assisted computation where LLMs formulate governing equations and provide initial conditions while Newton-Raphson iteration performs numerical solution. Direct prediction yields mean relative errors of 0.765 to 1.262 across models, while solver-assisted computation achieves 0.225 to 0.301, representing error reductions of 67.9% to 81.8%. Domain-specific analysis reveals dramatic improvements in Electronics (93.1%) due to exponential equation sensitivity, contrasted with modest gains in Fluid Mechanics (7.2%) where LLMs exhibit effective pattern recognition. These findings establish that contemporary LLMs excel at symbolic manipulation and domain knowledge retrieval but struggle with precision-critical iterative arithmetic, suggesting their optimal deployment as intelligent interfaces to classical numerical solvers rather than standalone computational engines.

---

### CTIS-QA: Clinical Template-Informed Slide-level Question Answering for Pathology

Authors: Hao Lu, Ziniu Qian, Yifu Li, Yang Zhou, Bingzheng Wei, Yan Xu
Published: 2026-01-05
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.01769v1

In this paper, we introduce a clinical diagnosis template-based pipeline to systematically collect and structure pathological information. In collaboration with pathologists and guided by the the College of American Pathologists (CAP) Cancer Protocols, we design a Clinical Pathology Report Template (CPRT) that ensures comprehensive and standardized extraction of diagnostic elements from pathology reports. We validate the effectiveness of our pipeline on TCGA-BRCA. First, we extract pathological features from reports using CPRT. These features are then used to build CTIS-Align, a dataset of 80k slide-description pairs from 804 WSIs for vision-language alignment training, and CTIS-Bench, a rigorously curated VQA benchmark comprising 977 WSIs and 14,879 question-answer pairs. CTIS-Bench emphasizes clinically grounded, closed-ended questions (e.g., tumor grade, receptor status) that reflect real diagnostic workflows, minimize non-visual reasoning, and require genuine slide understanding. We further propose CTIS-QA, a Slide-level Question Answering model, featuring a dual-stream architecture that mimics pathologists' diagnostic approach. One stream captures global slide-level context via clustering-based feature aggregation, while the other focuses on salient local regions through attention-guided patch perception module. Extensive experiments on WSI-VQA, CTIS-Bench, and slide-level diagnostic tasks show that CTIS-QA consistently outperforms existing state-of-the-art models across multiple metrics. Code and data are available at https://github.com/HLSvois/CTIS-QA.

---

### Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation

Authors: Meiman Xiao, Ante Wang, Qingguo Hu, Zhongjian Miao, Huangjun Shen, Longyue Wang, Weihua Luo, Jinsong Su
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01768v2

Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In this work, we demonstrate that LLMs often fail to accurately measure their response lengths, leading to poor adherence to length constraints. To address this issue, we propose a novel length regulation approach that incorporates dynamic length feedback during generation, enabling adaptive adjustments to meet target lengths. Experiments on summarization and biography tasks show our training-free approach significantly improves precision in achieving target token, word, or sentence counts without compromising quality. Additionally, we demonstrate that further supervised fine-tuning allows our method to generalize effectively to broader text-generation tasks.

---

### Can LLMs Track Their Output Length? A Dynamic Feedback Mechanism for Precise Length Regulation

Authors: Meiman Xiao, Ante Wang, Qingguo Hu, Zhongjian Miao, Huangjun Shen, Longyue Wang, Weihua Luo, Jinsong Su
Published: 2026-01-05
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.01768v1

Precisely controlling the length of generated text is a common requirement in real-world applications. However, despite significant advancements in following human instructions, Large Language Models (LLMs) still struggle with this task. In this work, we demonstrate that LLMs often fail to accurately measure input text length, leading to poor adherence to length constraints. To address this issue, we propose a novel length regulation approach that incorporates dynamic length feedback during generation, enabling adaptive adjustments to meet target lengths. Experiments on summarization and biography tasks show our training-free approach significantly improves precision in achieving target token, word, or sentence counts without compromising quality. Additionally, we demonstrate that further supervised fine-tuning allows our method to generalize effectively to broader text-generation tasks.

---

### A New Benchmark for the Appropriate Evaluation of RTL Code Optimization

Authors: Yao Lu, Shang Liu, Hangan Zhou, Wenji Fang, Qijun Zhang, Zhiyao Xie
Published: 2026-01-05
Categories: cs.AI, cs.SE
arXiv: https://arxiv.org/abs/2601.01765v1

The rapid progress of artificial intelligence increasingly relies on efficient integrated circuit (IC) design. Recent studies have explored the use of large language models (LLMs) for generating Register Transfer Level (RTL) code, but existing benchmarks mainly evaluate syntactic correctness rather than optimization quality in terms of power, performance, and area (PPA). This work introduces RTL-OPT, a benchmark for assessing the capability of LLMs in RTL optimization. RTL-OPT contains 36 handcrafted digital designs that cover diverse implementation categories including combinational logic, pipelined datapaths, finite state machines, and memory interfaces. Each task provides a pair of RTL codes, a suboptimal version and a human-optimized reference that reflects industry-proven optimization patterns not captured by conventional synthesis tools. Furthermore, RTL-OPT integrates an automated evaluation framework to verify functional correctness and quantify PPA improvements, enabling standardized and meaningful assessment of generative models for hardware design optimization.

---

### AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

Authors: Yanhao Wu, Haoyang Zhang, Fei He, Rui Wu, Yanhu Shan, Congpei Qiu, Liang Gao, Wei Ke, Tong Zhang
Published: 2026-01-05
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.01762v4

Practical autonomous driving requires models that generalize by reasoning through spatial-temporal possibilities to exclude unsafe outcomes. While state-of-the-art (SOTA) methods use parallel planning architectures, they fail to explicitly couple speed decisions with agent behavior along the driving path, leading to suboptimal coordination. To address this, we propose a cascaded framework that transforms longitudinal planning from an independent prediction task into a path-conditioned reasoning process. On the model side, we introduce an anchor-based regression design that conditions longitudinal prediction on the lateral drive path, and reformulate longitudinal planning as 1D displacement prediction along the path. This reduces geometric uncertainty and sharpens the model's focus on interaction-driven dynamics. On the data side, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events by programmatically inserting agents and relabeling longitudinal targets to enforce collision avoidance. Evaluated on the challenging Bench2Drive benchmark, our method achieves SOTA performance with a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety. Further evaluation on Fail2Drive confirms strong generalization to rare edge cases where parallel formulations typically fail. Project page:https://yanhaowu.github.io/AlignDrive/.

---

### AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

Authors: Yanhao Wu, Haoyang Zhang, Fei He, Rui Wu, Congpei Qiu, Liang Gao, Wei Ke, Tong Zhang
Published: 2026-01-05
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.01762v1

End-to-end autonomous driving has rapidly progressed, enabling joint perception and planning in complex environments. In the planning stage, state-of-the-art (SOTA) end-to-end autonomous driving models decouple planning into parallel lateral and longitudinal predictions. While effective, this parallel design can lead to i) coordination failures between the planned path and speed, and ii) underutilization of the drive path as a prior for longitudinal planning, thus redundantly encoding static information. To address this, we propose a novel cascaded framework that explicitly conditions longitudinal planning on the drive path, enabling coordinated and collision-aware lateral and longitudinal planning. Specifically, we introduce a path-conditioned formulation that explicitly incorporates the drive path into longitudinal planning. Building on this, the model predicts longitudinal displacements along the drive path rather than full 2D trajectory waypoints. This design simplifies longitudinal reasoning and more tightly couples it with lateral planning. Additionally, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events, such as vehicle cut-ins, by adding agents and relabeling longitudinal targets to avoid collision. Evaluated on the challenging Bench2Drive benchmark, our method sets a new SOTA, achieving a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety

---

### Sparse Convex Biclustering

Authors: Jiakun Jiang, Dewei Xiang, Chenliang Gu, Wei Liu, Binhuan Wang
Published: 2026-01-05
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.01757v1

Biclustering is an essential unsupervised machine learning technique for simultaneously clustering rows and columns of a data matrix, with widespread applications in genomics, transcriptomics, and other high-dimensional omics data. Despite its importance, existing biclustering methods struggle to meet the demands of modern large-scale datasets. The challenges stem from the accumulation of noise in high-dimensional features, the limitations of non-convex optimization formulations, and the computational complexity of identifying meaningful biclusters. These issues often result in reduced accuracy and stability as the size of the dataset increases. To overcome these challenges, we propose Sparse Convex Biclustering (SpaCoBi), a novel method that penalizes noise during the biclustering process to improve both accuracy and robustness. By adopting a convex optimization framework and introducing a stability-based tuning criterion, SpaCoBi achieves an optimal balance between cluster fidelity and sparsity. Comprehensive numerical studies, including simulations and an application to mouse olfactory bulb data, demonstrate that SpaCoBi significantly outperforms state-of-the-art methods in accuracy. These results highlight SpaCoBi as a robust and efficient solution for biclustering in high-dimensional and large-scale datasets.

---

### A Wachspress-based transfinite formulation for exactly enforcing Dirichlet boundary conditions on convex polygonal domains in physics-informed neural networks

Authors: N. Sukumar, Ritwick Roy
Published: 2026-01-05
Categories: math.NA, cs.NE
arXiv: https://arxiv.org/abs/2601.01756v3

In this paper, we present a Wachspress-based transfinite formulation on convex polygonal domains for exact enforcement of Dirichlet boundary conditions in physics-informed neural networks. This approach leverages prior advances in geometric design such as blending functions and transfinite interpolation over convex domains. For prescribed Dirichlet boundary function $\mathcal{B}$, the transfinite interpolant of $\mathcal{B}$, $g : \bar P \to C^0(\bar P)$, $\textit{lifts}$ functions from the boundary of a two-dimensional polygonal domain to its interior. The transfinite trial function is expressed as the difference between the neural network's output and the extension of its boundary restriction into the interior of the domain, with $g$ added to it. This ensures kinematic admissibility of the trial function in the deep Ritz method. Wachspress coordinates for an $n$-gon are used in the transfinite formula, which generalizes bilinear Coons transfinite interpolation on rectangles to convex polygons. Since Wachspress coordinates are smooth, the neural network trial function has a bounded Laplacian, thereby overcoming a limitation in a previous contribution where approximate distance functions were used to exactly enforce Dirichlet boundary conditions. For a point $\boldsymbol{x} \in \bar{P}$, Wachspress coordinates, $\boldsymbolλ : \bar P \to (0,1)^n$, serve as a geometric feature map for the neural network: $\boldsymbolλ$ encodes the boundary edges of the polygonal domain. This offers a framework for solving problems on parametrized convex geometries using neural networks. The accuracy of physics-informed neural networks is successfully assessed on forward problems (linear and nonlinear), an inverse heat conduction problem, and a parametrized geometric Poisson boundary-value problem.

---

### A Wachspress-based transfinite formulation for exactly enforcing Dirichlet boundary conditions on convex polygonal domains in physics-informed neural networks

Authors: N. Sukumar, Ritwick Roy
Published: 2026-01-05
Categories: math.NA, cs.NE
arXiv: https://arxiv.org/abs/2601.01756v1

In this paper, we present a Wachspress-based transfinite formulation on convex polygonal domains for exact enforcement of Dirichlet boundary conditions in physics-informed neural networks. This approach leverages prior advances in geometric design such as blending functions and transfinite interpolation over convex domains. For prescribed Dirichlet boundary function $\mathcal{B}$, the transfinite interpolant of $\mathcal{B}$, $g : \bar P \to C^0(\bar P)$, $\textit{lifts}$ functions from the boundary of a two-dimensional polygonal domain to its interior. The trial function is expressed as the difference between the neural network's output and the extension of its boundary restriction into the interior of the domain, with $g$ added to it. This ensures kinematic admissibility of the trial function in the deep Ritz method. Wachspress coordinates for an $n$-gon are used in the transfinite formula, which generalizes bilinear Coons transfinite interpolation on rectangles to convex polygons. The neural network trial function has a bounded Laplacian, thereby overcoming a limitation in a previous contribution where approximate distance functions were used to exactly enforce Dirichlet boundary conditions. For a point $\boldsymbol{x} \in \bar{P}$, Wachspress coordinates, $\boldsymbolλ : \bar P \to (0,1)^n$, serve as a geometric feature map for the neural network: $\boldsymbolλ$ encodes the boundary edges of the polygonal domain. This offers a framework for solving problems on parametrized convex geometries using neural networks. The accuracy of physics-informed neural networks and deep Ritz is assessed on forward, inverse, and parametrized geometric Poisson boundary-value problems.

---

### Context-Free Recognition with Transformers

Authors: Selim Jerad, Anej Svete, Sophie Hao, Ryan Cotterell, William Merrill
Published: 2026-01-05
Categories: cs.LG, cs.CC, cs.CL, cs.FL
arXiv: https://arxiv.org/abs/2601.01754v3

Transformers excel empirically on tasks that process well-formed inputs according to some grammar, such as natural language and code. However, it remains unclear how they can process grammatical syntax. In fact, under standard complexity conjectures, standard transformers cannot recognize context-free languages (CFLs), a canonical formalism to describe syntax, or even regular languages, a subclass of CFLs. Past work has shown that $\mathcal{O}(\log(N))$ looping layers (w.r.t. input length $N$) allow transformers to recognize regular languages, but the question of context-free recognition with looped transformers remained open. In this work, we show that looped transformers with $\mathcal{O}(\log(N))$ looping layers and $\mathcal{O}(N^6)$ padding symbols can recognize all CFLs. However, training and inference with $\mathcal{O}(N^6)$ padding symbols is potentially impractical. Fortunately, we show that, for natural subclasses such as unambiguous CFLs, the recognition problem on transformers becomes more tractable, requiring $\mathcal{O}(N^3)$ padding. Empirically, looped and padded transformers perform better than fixed-depth transformers in recognizing CFLs. Overall, our results shed light on the intricacy of CFL recognition by transformers: while general recognition may require an intractable amount of padding, natural constraints such as unambiguity yield efficient recognition algorithms.

---

### Context-Free Recognition with Transformers

Authors: Selim Jerad, Anej Svete, Sophie Hao, Ryan Cotterell, William Merrill
Published: 2026-01-05
Categories: cs.LG, cs.CC, cs.CL, cs.FL
arXiv: https://arxiv.org/abs/2601.01754v1

Transformers excel on tasks that process well-formed inputs according to some grammar, such as natural language and code. However, it remains unclear how they can process grammatical syntax. In fact, under standard complexity conjectures, standard transformers cannot recognize context-free languages (CFLs), a canonical formalism to describe syntax, or even regular languages, a subclass of CFLs (Merrill et al., 2022). Merrill & Sabharwal (2024) show that $\mathcal{O}(\log n)$ looping layers (w.r.t. input length $n$) allows transformers to recognize regular languages, but the question of context-free recognition remained open. In this work, we show that looped transformers with $\mathcal{O}(\log n)$ looping layers and $\mathcal{O}(n^6)$ padding tokens can recognize all CFLs. However, training and inference with $\mathcal{O}(n^6)$ padding tokens is potentially impractical. Fortunately, we show that, for natural subclasses such as unambiguous CFLs, the recognition problem on transformers becomes more tractable, requiring $\mathcal{O}(n^3)$ padding. We empirically validate our results and show that looping helps on a language that provably requires logarithmic depth. Overall, our results shed light on the intricacy of CFL recognition by transformers: While general recognition may require an intractable amount of padding, natural constraints such as unambiguity yield efficient recognition algorithms.

---

### MergeRec: Model Merging for Data-Isolated Cross-Domain Sequential Recommendation

Authors: Hyunsoo Kim, Jaewan Moon, Seongmin Park, Jongwuk Lee
Published: 2026-01-05
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.01753v1

Modern recommender systems trained on domain-specific data often struggle to generalize across multiple domains. Cross-domain sequential recommendation has emerged as a promising research direction to address this challenge; however, existing approaches face fundamental limitations, such as reliance on overlapping users or items across domains, or unrealistic assumptions that ignore privacy constraints. In this work, we propose a new framework, MergeRec, based on model merging under a new and realistic problem setting termed data-isolated cross-domain sequential recommendation, where raw user interaction data cannot be shared across domains. MergeRec consists of three key components: (1) merging initialization, (2) pseudo-user data construction, and (3) collaborative merging optimization. First, we initialize a merged model using training-free merging techniques. Next, we construct pseudo-user data by treating each item as a virtual sequence in each domain, enabling the synthesis of meaningful training samples without relying on real user interactions. Finally, we optimize domain-specific merging weights through a joint objective that combines a recommendation loss, which encourages the merged model to identify relevant items, and a distillation loss, which transfers collaborative filtering signals from the fine-tuned source models. Extensive experiments demonstrate that MergeRec not only preserves the strengths of the original models but also significantly enhances generalizability to unseen domains. Compared to conventional model merging methods, MergeRec consistently achieves superior performance, with average improvements of up to 17.21% in Recall@10, highlighting the potential of model merging as a scalable and effective approach for building universal recommender systems. The source code is available at https://github.com/DIALLab-SKKU/MergeRec.

---