# Research Papers — 2026-01 · bundle page 185 of 189

> Full-text markdown of papers #9201–9250 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/185
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/184.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/186.md)

### CSSBench: Evaluating the Safety of Lightweight LLMs against Chinese-Specific Adversarial Patterns

Authors: Zhenhong Zhou, Shilinlu Yan, Chuanpu Liu, Qiankun Li, Kun Wang, Zhigang Zeng
Published: 2026-01-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.00588v1

Large language models (LLMs) are increasingly deployed in cost-sensitive and on-device scenarios, and safety guardrails have advanced mainly in English. However, real-world Chinese malicious queries typically conceal intent via homophones, pinyin, symbol-based splitting, and other Chinese-specific patterns. These Chinese-specific adversarial patterns create the safety evaluation gap that is not well captured by existing benchmarks focused on English. This gap is particularly concerning for lightweight models, which may be more vulnerable to such specific adversarial perturbations. To bridge this gap, we introduce the Chinese-Specific Safety Benchmark (CSSBench) that emphasizes these adversarial patterns and evaluates the safety of lightweight LLMs in Chinese. Our benchmark covers six domains that are common in real Chinese scenarios, including illegal activities and compliance, privacy leakage, health and medical misinformation, fraud and hate, adult content, and public and political safety, and organizes queries into multiple task types. We evaluate a set of popular lightweight LLMs and measure over-refusal behavior to assess safety-induced performance degradation. Our results show that the Chinese-specific adversarial pattern is a critical challenge for lightweight LLMs. This benchmark offers a comprehensive evaluation of LLM safety in Chinese, assisting robust deployments in practice.

---

### GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval

Authors: Mingyu Jeon, Sunjae Yoon, Jonghee Kim, Junyeoung Kim
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00584v1

Zero-shot video moment retrieval (ZVMR) is the task of localizing a temporal moment within an untrimmed video using a natural language query without relying on task-specific training data. The primary challenge in this setting lies in the mismatch in semantic granularity between textual queries and visual content. Previous studies in ZVMR have attempted to achieve alignment by leveraging high-quality pre-trained knowledge that represents video and language in a joint space. However, these approaches failed to balance the semantic granularity between the pre-trained knowledge provided by each modality for a given scene. As a result, despite the high quality of each modality's representations, the mismatch in granularity led to inaccurate retrieval. In this paper, we propose a training-free framework, called Granularity-Aware Alignment (GranAlign), that bridges this gap between coarse and fine semantic representations. Our approach introduces two complementary techniques: granularity-based query rewriting to generate varied semantic granularities, and query-aware caption generation to embed query intent into video content. By pairing multi-level queries with both query-agnostic and query-aware captions, we effectively resolve semantic mismatches. As a result, our method sets a new state-of-the-art across all three major benchmarks (QVHighlights, Charades-STA, ActivityNet-Captions), with a notable 3.23% mAP@avg improvement on the challenging QVHighlights dataset.

---

### HFedMoE: Resource-aware Heterogeneous Federated Learning with Mixture-of-Experts

Authors: Zihan Fang, Zheng Lin, Senkang Hu, Yanan Ma, Yihang Tao, Yiqin Deng, Xianhao Chen, Yuguang Fang
Published: 2026-01-02
Categories: cs.LG, cs.AI, cs.NI
arXiv: https://arxiv.org/abs/2601.00583v1

While federated learning (FL) enables fine-tuning of large language models (LLMs) without compromising data privacy, the substantial size of an LLM renders on-device training impractical for resource-constrained clients, such as mobile devices. Thus, Mixture-of-Experts (MoE) models have emerged as a computation-efficient solution, which activates only a sparse subset of experts during model training to reduce computing burden without sacrificing performance. Though integrating MoE into FL fine-tuning holds significant potential, it still encounters three key challenges: i) selecting appropriate experts for clients remains challenging due to the lack of a reliable metric to measure each expert's impact on local fine-tuning performance, ii) the heterogeneous computing resources across clients severely hinder MoE-based LLM fine-tuning, as dynamic expert activations across diverse input samples can overwhelm resource-constrained devices, and iii) client-specific expert subsets and routing preference undermine global aggregation, where misaligned expert updates and inconsistent gating networks in troduce destructive interference. To address these challenges, we propose HFedMoE, a heterogeneous MoE-based FL fine-tuning framework that customizes a subset of experts to each client for computation-efficient LLM fine-tuning. Specifically, HFedMoE identifies the expert importance based on its contributions to fine-tuning performance, and then adaptively selects a subset of experts from an information bottleneck perspective to align with each client' s computing budget. A sparsity-aware model aggregation strategy is also designed to aggregate the actively fine-tuned experts and gating parameters with importance weighted contributions. Extensive experiments demonstrate that HFedMoE outperforms state-of-the-art benchmarks in training accuracy and convergence speed.

---

### AceFF: A State-of-the-Art Machine Learning Potential for Small Molecules

Authors: Stephen E. Farr, Stefan Doerr, Antonio Mirarchi, Francesc Sabanes Zariquiey, Gianni De Fabritiis
Published: 2026-01-02
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2601.00581v2

We introduce AceFF, a pre-trained machine learning interatomic potential (MLIP) optimized for small molecule drug discovery. While MLIPs have emerged as efficient alternatives to Density Functional Theory (DFT), generalizability across diverse chemical spaces remains difficult. AceFF addresses this via a refined TensorNet2 architecture trained on a comprehensive dataset of drug-like compounds. This approach yields a force field that balances high-throughput inference speed with DFT-level accuracy. \mbox{AceFF} fully supports the essential medicinal chemistry elements (H, B, C, N, O, F, Si, P, S, Cl, Br, I) and is explicitly trained to handle charged states. Validation against rigorous benchmarks, including complex torsional energy scans, molecular dynamics trajectories, batched minimizations, and tests of force and energy accuracy, demonstrates that AceFF is state-of-the-art for organic molecules in the accuracy and speed regime important for drug discovery. The AceFF-2 model weights and inference code are available at https://huggingface.co/Acellera/AceFF-2.0.

---

### AceFF: A State-of-the-Art Machine Learning Potential for Small Molecules

Authors: Stephen E. Farr, Stefan Doerr, Antonio Mirarchi, Francesc Sabanes Zariquiey, Gianni De Fabritiis
Published: 2026-01-02
Categories: physics.chem-ph, cs.LG
arXiv: https://arxiv.org/abs/2601.00581v1

We introduce AceFF, a pre-trained machine learning interatomic potential (MLIP) optimized for small molecule drug discovery. While MLIPs have emerged as efficient alternatives to Density Functional Theory (DFT), generalizability across diverse chemical spaces remains difficult. AceFF addresses this via a refined TensorNet2 architecture trained on a comprehensive dataset of drug-like compounds. This approach yields a force field that balances high-throughput inference speed with DFT-level accuracy. AceFF fully supports the essential medicinal chemistry elements (H, B, C, N, O, F, Si, P, S, Cl, Br, I) and is explicitly trained to handle charged states. Validation against rigorous benchmarks, including complex torsional energy scans, molecular dynamics trajectories, batched minimizations, and forces and anergy accuracy demonstrates that AceFF establishes a new state-of-the-art for organic molecules. The AceFF-2 model weights and inference code are available at https://huggingface.co/Acellera/AceFF-2.0.

---

### Priority-Aware Multi-Robot Coverage Path Planning

Authors: Kanghoon Lee, Hyeonjun Kim, Jiachen Li, Jinkyoo Park
Published: 2026-01-02
Categories: cs.RO, cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.00580v1

Multi-robot systems are widely used for coverage tasks that require efficient coordination across large environments. In Multi-Robot Coverage Path Planning (MCPP), the objective is typically to minimize the makespan by generating non-overlapping paths for full-area coverage. However, most existing methods assume uniform importance across regions, limiting their effectiveness in scenarios where some zones require faster attention. We introduce the Priority-Aware MCPP (PA-MCPP) problem, where a subset of the environment is designated as prioritized zones with associated weights. The goal is to minimize, in lexicographic order, the total priority-weighted latency of zone coverage and the overall makespan. To address this, we propose a scalable two-phase framework combining (1) greedy zone assignment with local search, spanning-tree-based path planning, and (2) Steiner-tree-guided residual coverage. Experiments across diverse scenarios demonstrate that our method significantly reduces priority-weighted latency compared to standard MCPP baselines, while maintaining competitive makespan. Sensitivity analyses further show that the method scales well with the number of robots and that zone coverage behavior can be effectively controlled by adjusting priority weights.

---

### Learning to be Reproducible: Custom Loss Design for Robust Neural Networks

Authors: Waqas Ahmed, Sheeba Samuel, Kevin Coakley, Birgitta Koenig-Ries, Odd Erik Gundersen
Published: 2026-01-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.00578v1

To enhance the reproducibility and reliability of deep learning models, we address a critical gap in current training methodologies: the lack of mechanisms that ensure consistent and robust performance across runs. Our empirical analysis reveals that even under controlled initialization and training conditions, the accuracy of the model can exhibit significant variability. To address this issue, we propose a Custom Loss Function (CLF) that reduces the sensitivity of training outcomes to stochastic factors such as weight initialization and data shuffling. By fine-tuning its parameters, CLF explicitly balances predictive accuracy with training stability, leading to more consistent and reliable model performance. Extensive experiments across diverse architectures for both image classification and time series forecasting demonstrate that our approach significantly improves training robustness without sacrificing predictive performance. These results establish CLF as an effective and efficient strategy for developing more stable, reliable and trustworthy neural networks.

---

### Adversarial Samples Are Not Created Equal

Authors: Jennifer Crawford, Amol Khanna, Fred Lu, Amy R. Wagoner, Stella Biderman, Andre T. Nguyen, Edward Raff
Published: 2026-01-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00577v1

Over the past decade, numerous theories have been proposed to explain the widespread vulnerability of deep neural networks to adversarial evasion attacks. Among these, the theory of non-robust features proposed by Ilyas et al. has been widely accepted, showing that brittle but predictive features of the data distribution can be directly exploited by attackers. However, this theory overlooks adversarial samples that do not directly utilize these features. In this work, we advocate that these two kinds of samples - those which use use brittle but predictive features and those that do not - comprise two types of adversarial weaknesses and should be differentiated when evaluating adversarial robustness. For this purpose, we propose an ensemble-based metric to measure the manipulation of non-robust features by adversarial perturbations and use this metric to analyze the makeup of adversarial samples generated by attackers. This new perspective also allows us to re-examine multiple phenomena, including the impact of sharpness-aware minimization on adversarial robustness and the robustness gap observed between adversarially training and standard training on robust datasets.

---

### InfoSynth: Information-Guided Benchmark Synthesis for LLMs

Authors: Ishir Garg, Neel Kolhe, Xuandong Zhao, Dawn Song
Published: 2026-01-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.00575v2

Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation, but efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on manual human effort, which is expensive and time-consuming. Furthermore, existing benchmarks often contaminate LLM training data, necessitating novel and diverse benchmarks to accurately assess their genuine capabilities. This work introduces InfoSynth, a novel framework for automatically generating and evaluating reasoning benchmarks guided by information-theoretic principles. We propose metrics based on KL-divergence and entropy to quantify benchmark novelty and diversity without relying on costly model evaluations. Building on this framework, we develop an end-to-end pipeline that synthesizes robust Python coding problems from seed datasets using genetic algorithms and iterative code feedback. Our method generates accurate test cases and solutions to new problems 97% of the time, and the synthesized benchmarks consistently exhibit higher difficulty compared to prior works. Moreover, our algorithm provides a method for controlling the novelty/diversity and difficulty of generated problems. InfoSynth offers a scalable, self-verifying pipeline for constructing high-quality, challenging coding benchmarks for LLMs. Project Page: https://ishirgarg.github.io/infosynth_web/

---

### InfoSynth: Information-Guided Benchmark Synthesis for LLMs

Authors: Ishir Garg, Neel Kolhe, Xuandong Zhao, Dawn Song
Published: 2026-01-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.00575v1

Large language models (LLMs) have demonstrated significant advancements in reasoning and code generation. However, efficiently creating new benchmarks to evaluate these capabilities remains a challenge. Traditional benchmark creation relies on manual human effort, a process that is both expensive and time-consuming. Furthermore, existing benchmarks often contaminate LLM training data, necessitating novel and diverse benchmarks to accurately assess their genuine capabilities. This work introduces InfoSynth, a novel framework for automatically generating and evaluating reasoning benchmarks guided by information-theoretic principles. We propose metrics based on KL-divergence and entropy to quantify benchmark novelty and diversity without relying on costly model evaluations. Building on this framework, we develop an end-to-end pipeline that synthesizes robust Python coding problems from seed datasets using genetic algorithms and iterative code feedback. Our method generates accurate test cases and solutions to new problems 97% of the time, and the synthesized benchmarks consistently exhibit higher novelty and diversity compared to their seed datasets. Moreover, our algorithm provides a method for controlling the novelty/diversity and difficulty of generated problems. InfoSynth offers a scalable, self-verifying pipeline for constructing high-quality, novel and diverse benchmarks for LLMs. Project Page: https://ishirgarg.github.io/infosynth_web/

---

### Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models

Authors: Yihe Wang, Zhiqiao Kang, Bohan Chen, Yu Zhang, Xiang Zhang
Published: 2026-01-02
Categories: cs.NE, cs.CE
arXiv: https://arxiv.org/abs/2601.00573v2

Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the brain's processing of specific cognitive tasks. ERP plays a critical role in cognitive analysis, the detection of neurological diseases, and the assessment of psychological states. Recent years have seen substantial advances in deep learning-based methods for spontaneous EEG and other non-time-locked task-related EEG signals. However, their effectiveness on ERP data remains underexplored, and many existing ERP studies still rely heavily on manually extracted features. In this paper, we conduct a comprehensive benchmark study that systematically compares traditional manual features (followed by a linear classifier), deep learning models, and pre-trained EEG foundation models for ERP analysis. We establish a unified data preprocessing and training pipeline and evaluate these approaches on two representative tasks, ERP stimulus classification and ERP-based brain disease detection, across 12 publicly available datasets. Furthermore, we investigate various token-embedding strategies within advanced Transformer architectures to identify embedding designs that better suit ERP data. Our study provides a landmark framework to guide method selection and tailored model design for future ERP analysis. The code is available at https://github.com/DL4mHealth/ERP-Benchmark

---

### Benchmarking ERP Analysis: Manual Features, Deep Learning, and Foundation Models

Authors: Yihe Wang, Zhiqiao Kang, Bohan Chen, Yu Zhang, Xiang Zhang
Published: 2026-01-02
Categories: cs.NE, cs.CE
arXiv: https://arxiv.org/abs/2601.00573v1

Event-related potential (ERP), a specialized paradigm of electroencephalographic (EEG), reflects neurological responses to external stimuli or events, generally associated with the brain's processing of specific cognitive tasks. ERP plays a critical role in cognitive analysis, the detection of neurological diseases, and the assessment of psychological states. Recent years have seen substantial advances in deep learning-based methods for spontaneous EEG and other non-time-locked task-related EEG signals. However, their effectiveness on ERP data remains underexplored, and many existing ERP studies still rely heavily on manually extracted features. In this paper, we conduct a comprehensive benchmark study that systematically compares traditional manual features (followed by a linear classifier), deep learning models, and pre-trained EEG foundation models for ERP analysis. We establish a unified data preprocessing and training pipeline and evaluate these approaches on two representative tasks, ERP stimulus classification and ERP-based brain disease detection, across 12 publicly available datasets. Furthermore, we investigate various patch-embedding strategies within advanced Transformer architectures to identify embedding designs that better suit ERP data. Our study provides a landmark framework to guide method selection and tailored model design for future ERP analysis. The code is available at https://github.com/DL4mHealth/ERP-Benchmark.

---

### Improving Scientific Document Retrieval with Academic Concept Index

Authors: Jeyun Lee, Junhyoung Lee, Wonbin Kweon, Bowen Jin, Yu Zhang, Susik Yoon, Dongha Lee, Hwanjo Yu, Jiawei Han, Seongku Kang
Published: 2026-01-02
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.00567v2

Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index, which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation (CCQGen), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts (CCExpand), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.

---

### Improving Scientific Document Retrieval with Academic Concept Index

Authors: Jeyun Lee, Junhyoung Lee, Wonbin Kweon, Bowen Jin, Yu Zhang, Susik Yoon, Dongha Lee, Hwanjo Yu, Jiawei Han, Seongku Kang
Published: 2026-01-02
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.00567v1

Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in vocabulary and information needs. Recent approaches address these issues through two independent directions that leverage large language models (LLMs): (1) generating synthetic queries for fine-tuning, and (2) generating auxiliary contexts to support relevance matching. However, both directions overlook the diverse academic concepts embedded within scientific documents, often producing redundant or conceptually narrow queries and contexts. To address this limitation, we introduce an academic concept index, which extracts key concepts from papers and organizes them guided by an academic taxonomy. This structured index serves as a foundation for improving both directions. First, we enhance the synthetic query generation with concept coverage-based generation (CCQGen), which adaptively conditions LLMs on uncovered concepts to generate complementary queries with broader concept coverage. Second, we strengthen the context augmentation with concept-focused auxiliary contexts (CCExpand), which leverages a set of document snippets that serve as concise responses to the concept-aware CCQGen queries. Extensive experiments show that incorporating the academic concept index into both query generation and context augmentation leads to higher-quality queries, better conceptual alignment, and improved retrieval performance.

---

### A Cascaded Information Interaction Network for Precise Image Segmentation

Authors: Hewen Xiao, Jie Mei, Guangfu Ma, Weiren Wu
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00562v1

Visual perception plays a pivotal role in enabling autonomous behavior, offering a cost-effective and efficient alternative to complex multi-sensor systems. However, robust segmentation remains a challenge in complex scenarios. To address this, this paper proposes a cascaded convolutional neural network integrated with a novel Global Information Guidance Module. This module is designed to effectively fuse low-level texture details with high-level semantic features across multiple layers, thereby overcoming the inherent limitations of single-scale feature extraction. This architectural innovation significantly enhances segmentation accuracy, particularly in visually cluttered or blurred environments where traditional methods often fail. Experimental evaluations on benchmark image segmentation datasets demonstrate that the proposed framework achieves superior precision, outperforming existing state-of-the-art methods. The results highlight the effectiveness of the approach and its promising potential for deployment in practical robotic applications.

---

### AEGIS: Exploring the Limit of World Knowledge Capabilities for Unified Mulitmodal Models

Authors: Jintao Lin, Bowen Dong, Weikang Shi, Chenyang Lei, Suiyun Zhang, Rui Liu, Xihui Liu
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00561v1

The capability of Unified Multimodal Models (UMMs) to apply world knowledge across diverse tasks remains a critical, unresolved challenge. Existing benchmarks fall short, offering only siloed, single-task evaluations with limited diagnostic power. To bridge this gap, we propose AEGIS (\emph{i.e.}, \textbf{A}ssessing \textbf{E}diting, \textbf{G}eneration, \textbf{I}nterpretation-Understanding for \textbf{S}uper-intelligence), a comprehensive multi-task benchmark covering visual understanding, generation, editing, and interleaved generation. AEGIS comprises 1,050 challenging, manually-annotated questions spanning 21 topics (including STEM, humanities, daily life, etc.) and 6 reasoning types. To concretely evaluate the performance of UMMs in world knowledge scope without ambiguous metrics, we further propose Deterministic Checklist-based Evaluation (DCE), a protocol that replaces ambiguous prompt-based scoring with atomic ``Y/N'' judgments, to enhance evaluation reliability. Our extensive experiments reveal that most UMMs exhibit severe world knowledge deficits and that performance degrades significantly with complex reasoning. Additionally, simple plug-in reasoning modules can partially mitigate these vulnerabilities, highlighting a promising direction for future research. These results highlight the importance of world-knowledge-based reasoning as a critical frontier for UMMs.

---

### Cracking IoT Security: Can LLMs Outsmart Static Analysis Tools?

Authors: Jason Quantrill, Noura Khajehnouri, Zihan Guo, Manar H. Alalfi
Published: 2026-01-02
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.00559v1

Smart home IoT platforms such as openHAB rely on Trigger Action Condition (TAC) rules to automate device behavior, but the interplay among these rules can give rise to interaction threats, unintended or unsafe behaviors emerging from implicit dependencies, conflicting triggers, or overlapping conditions. Identifying these threats requires semantic understanding and structural reasoning that traditionally depend on symbolic, constraint-driven static analysis. This work presents the first comprehensive evaluation of Large Language Models (LLMs) across a multi-category interaction threat taxonomy, assessing their performance on both the original openHAB (oHC/IoTB) dataset and a structurally challenging Mutation dataset designed to test robustness under rule transformations. We benchmark Llama 3.1 8B, Llama 70B, GPT-4o, Gemini-2.5-Pro, and DeepSeek-R1 across zero-, one-, and two-shot settings, comparing their results against oHIT's manually validated ground truth. Our findings show that while LLMs exhibit promising semantic understanding, particularly on action- and condition-related threats, their accuracy degrades significantly for threats requiring cross-rule structural reasoning, especially under mutated rule forms. Model performance varies widely across threat categories and prompt settings, with no model providing consistent reliability. In contrast, the symbolic reasoning baseline maintains stable detection across both datasets, unaffected by rule rewrites or structural perturbations. These results underscore that LLMs alone are not yet dependable for safety critical interaction-threat detection in IoT environments. We discuss the implications for tool design and highlight the potential of hybrid architectures that combine symbolic analysis with LLM-based semantic interpretation to reduce false positives while maintaining structural rigor.

---

### A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR

Authors: Yuang Zheng, Dongxu Chen, Yuxiang Mei, Dongxing Xu, Jie Chen, Yanhua Long
Published: 2026-01-02
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.00557v2

Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs, limiting their deployment on resource-constrained edge devices. In this study, we propose a lightweight and language-agnostic multilingual ASR system based on a CTC architecture with domain adaptation. Specifically, we introduce a Language-agnostic Hierarchical LoRA-MoE (HLoRA) framework integrated into an mHuBERT-CTC model, enabling end-to-end decoding via LID-posterior-driven LoRA routing. The hierarchical design consists of a multilingual shared LoRA for learning language-invariant acoustic representations and language-specific LoRA experts for modeling language-dependent characteristics. The proposed routing mechanism removes the need for prior language identity information or explicit language labels during inference, achieving true language-agnostic decoding. Experiments on MSR-86K and the MLC-SLM 2025 Challenge datasets demonstrate that HLoRA achieves comparable performance to two-stage inference approaches while reducing RTF by 11.7% and 8.2%, respectively, leading to improved decoding efficiency for low-resource mASR applications.

---

### A Language-Agnostic Hierarchical LoRA-MoE Architecture for CTC-based Multilingual ASR

Authors: Yuang Zheng, Yuxiang Mei, Dongxing Xu, Jie Chen, Yanhua Long
Published: 2026-01-02
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.00557v1

Large-scale multilingual ASR (mASR) models such as Whisper achieve strong performance but incur high computational and latency costs, limiting their deployment on resource-constrained edge devices. In this study, we propose a lightweight and language-agnostic multilingual ASR system based on a CTC architecture with domain adaptation. Specifically, we introduce a Language-agnostic Hierarchical LoRA-MoE (HLoRA) framework integrated into an mHuBERT-CTC model, enabling end-to-end decoding via LID-posterior-driven LoRA routing. The hierarchical design consists of a multilingual shared LoRA for learning language-invariant acoustic representations and language-specific LoRA experts for modeling language-dependent characteristics. The proposed routing mechanism removes the need for prior language identity information or explicit language labels during inference, achieving true language-agnostic decoding. Experiments on MSR-86K and the MLC-SLM 2025 Challenge datasets demonstrate that HLoRA achieves competitive performance with state-of-the-art two-stage inference methods using only single-pass decoding, significantly improving decoding efficiency for low-resource mASR applications.

---

### Entropy Production in Machine Learning Under Fokker-Planck Probability Flow

Authors: Lennon Shikhman
Published: 2026-01-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00554v3

Machine learning models deployed in nonstationary environments inevitably experience performance degradation due to data drift. While numerous drift detection heuristics exist, most lack a dynamical interpretation and provide limited guidance on how retraining decisions should be balanced against operational cost. In this work, we propose an entropy-based retraining framework grounded in nonequilibrium statistical physics. Interpreting drift as probability flow governed by a Fokker-Planck equation, we quantify model-data mismatch using relative entropy and show that its time derivative admits an entropy-balance decomposition featuring a nonnegative entropy production term driven by probability currents. Guided by this theory, we implement an entropy-triggered retraining policy using an exponentially weighted moving-average (EWMA) control statistic applied to a streaming kernel density estimator of the Kullback-Leibler divergence. We evaluate this approach across multiple nonstationary data streams. In synthetic, financial, and web-traffic domains, entropy-based retraining achieves predictive performance comparable to frequent retraining while reducing retraining frequency by one to two orders of magnitude. However, in a challenging biomedical ECG setting, the entropy-based trigger underperforms the maximum-frequency baseline, highlighting limitations of feature-space entropy monitoring under complex label-conditional drift.

---

### Entropy Production in Machine Learning Under Fokker-Planck Probability Flow

Authors: Lennon Shikhman
Published: 2026-01-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00554v1

Machine learning models deployed in nonstationary environments experience performance degradation due to data drift. While many drift detection heuristics exist, most lack a principled dynamical interpretation and provide limited guidance on how retraining frequency should be balanced against operational cost. In this work, we propose an entropy--based retraining framework grounded in nonequilibrium stochastic dynamics. Modeling deployment--time data drift as probability flow governed by a Fokker--Planck equation, we quantify model--data mismatch using a time--evolving Kullback--Leibler divergence. We show that the time derivative of this mismatch admits an entropy--balance decomposition featuring a nonnegative entropy production term driven by probability currents. This interpretation motivates entropy--triggered retraining as a label--free intervention strategy that responds to accumulated mismatch rather than delayed performance collapse. In a controlled nonstationary classification experiment, entropy--triggered retraining achieves predictive performance comparable to high--frequency retraining while reducing retraining events by an order of magnitude relative to daily and label--based policies.

---

### A Comprehensive Dataset for Human vs. AI Generated Image Detection

Authors: Rajarshi Roy, Ashhar Aziz, Shashwat Bajpai, Nasrin Imanpour, Gurpreet Singh, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte et al.
Published: 2026-01-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.00553v2

Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, we release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.

---

### A Comprehensive Dataset for Human vs. AI Generated Image Detection

Authors: Rajarshi Roy, Nasrin Imanpour, Ashhar Aziz, Shashwat Bajpai, Gurpreet Singh, Shwetangshu Biswas, Kapil Wanaskar, Parth Patwa, Subhankar Ghosh, Shreyas Dixit, Nilesh Ranjan Pal, Vipula Rawte et al.
Published: 2026-01-02
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.00553v1

Multimodal generative AI systems like Stable Diffusion, DALL-E, and MidJourney have fundamentally changed how synthetic images are created. These tools drive innovation but also enable the spread of misleading content, false information, and manipulated media. As generated images become harder to distinguish from photographs, detecting them has become an urgent priority. To combat this challenge, We release MS COCOAI, a novel dataset for AI generated image detection consisting of 96000 real and synthetic datapoints, built using the MS COCO dataset. To generate synthetic images, we use five generators: Stable Diffusion 3, Stable Diffusion 2.1, SDXL, DALL-E 3, and MidJourney v6. Based on the dataset, we propose two tasks: (1) classifying images as real or generated, and (2) identifying which model produced a given synthetic image. The dataset is available at https://huggingface.co/datasets/Rajarshi-Roy-research/Defactify_Image_Dataset.

---

### SlingBAG Pro: Accelerating point cloud-based iterative reconstruction for 3D photoacoustic imaging with arbitrary array geometries

Authors: Shuang Li, Yibing Wang, Jian Gao, Chulhong Kim, Seongwook Choi, Yu Zhang, Qian Chen, Yao Yao, Changhui Li
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00551v2

High-quality three-dimensional (3D) photoacoustic imaging (PAI) is gaining increasing attention in clinical applications. To address the challenges of limited space and high costs, irregular geometric transducer arrays that conform to specific imaging regions are promising for achieving high-quality 3D PAI with fewer transducers. However, traditional iterative reconstruction algorithms struggle with irregular array configurations, suffering from high computational complexity, substantial memory requirements, and lengthy reconstruction times. In this work, we introduce SlingBAG Pro, an advanced reconstruction algorithm based on the point cloud iteration concept of the Sliding ball adaptive growth (SlingBAG) method, while extending its compatibility to arbitrary array geometries. SlingBAG Pro maintains high reconstruction quality, reduces the number of required transducers, and employs a hierarchical optimization strategy that combines zero-gradient filtering with progressively increased temporal sampling rates during iteration. This strategy rapidly removes redundant spatial point clouds, accelerates convergence, and significantly shortens overall reconstruction time. Compared to the original SlingBAG algorithm, SlingBAG Pro achieves up to a 2.2-fold speed improvement in point cloud-based 3D PA reconstruction under irregular array geometries. The proposed method is validated through both simulation and in vivo mouse experiments, and the source code is publicly available at https://github.com/JaegerCQ/SlingBAG_Pro.

---

### SingBAG Pro: Accelerating point cloud-based iterative reconstruction for 3D photoacoustic imaging under arbitrary array

Authors: Shuang Li, Yibing Wang, Jian Gao, Chulhong Kim, Seongwook Choi, Yu Zhang, Qian Chen, Yao Yao, Changhui Li
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00551v1

High-quality three-dimensional (3D) photoacoustic imaging (PAI) is gaining increasing attention in clinical applications. To address the challenges of limited space and high costs, irregular geometric transducer arrays that conform to specific imaging regions are promising for achieving high-quality 3D PAI with fewer transducers. However, traditional iterative reconstruction algorithms struggle with irregular array configurations, suffering from high computational complexity, substantial memory requirements, and lengthy reconstruction times. In this work, we introduce SlingBAG Pro, an advanced reconstruction algorithm based on the point cloud iteration concept of the Sliding ball adaptive growth (SlingBAG) method, while extending its compatibility to arbitrary array geometries. SlingBAG Pro maintains high reconstruction quality, reduces the number of required transducers, and employs a hierarchical optimization strategy that combines zero-gradient filtering with progressively increased temporal sampling rates during iteration. This strategy rapidly removes redundant spatial point clouds, accelerates convergence, and significantly shortens overall reconstruction time. Compared to the original SlingBAG algorithm, SlingBAG Pro achieves up to a 2.2-fold speed improvement in point cloud-based 3D PA reconstruction under irregular array geometries. The proposed method is validated through both simulation and in vivo mouse experiments, and the source code is publicly available at https://github.com/JaegerCQ/SlingBAG_Pro.

---

### CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge

Authors: Zhiheng Guo, Zhaoyang Liu, Zihan Cen, Chenyuan Feng, Xinghua Sun, Xiang Chen, Tony Q. S. Quek, Xijun Wang
Published: 2026-01-02
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2601.00549v3

The deployment of large-scale neural networks within the Open Radio Access Network (O-RAN) architecture is pivotal for enabling native edge intelligence. However, this paradigm faces two critical bottlenecks: the prohibitive memory footprint required for local training on resource-constrained gNBs, and the saturation of bandwidth-limited backhaul links during the global aggregation of high-dimensional model updates. To address these challenges, we propose CoCo-Fed, a novel Compression and Combination-based Federated learning framework that unifies local memory efficiency and global communication reduction. Locally, CoCo-Fed breaks the memory wall by performing a double-dimension down-projection of gradients, adapting the optimizer to operate on low-rank structures without introducing additional inference parameters/latency. Globally, we introduce a transmission protocol based on orthogonal subspace superposition, where layer-wise updates are projected and superimposed into a single consolidated matrix per gNB, drastically reducing the backhaul traffic. Beyond empirical designs, we establish a rigorous theoretical foundation, proving the convergence of CoCo-Fed even under unsupervised learning conditions suitable for wireless sensing tasks. Extensive simulations on an angle-of-arrival estimation task demonstrate that CoCo-Fed significantly outperforms state-of-the-art baselines in both memory and communication efficiency while maintaining robust convergence under non-IID settings.

---

### CoCo-Fed: A Unified Framework for Memory- and Communication-Efficient Federated Learning at the Wireless Edge

Authors: Zhiheng Guo, Zhaoyang Liu, Zihan Cen, Chenyuan Feng, Xinghua Sun, Xiang Chen, Tony Q. S. Quek, Xijun Wang
Published: 2026-01-02
Categories: cs.IT, cs.AI
arXiv: https://arxiv.org/abs/2601.00549v1

The deployment of large-scale neural networks within the Open Radio Access Network (O-RAN) architecture is pivotal for enabling native edge intelligence. However, this paradigm faces two critical bottlenecks: the prohibitive memory footprint required for local training on resource-constrained gNBs, and the saturation of bandwidth-limited backhaul links during the global aggregation of high-dimensional model updates. To address these challenges, we propose CoCo-Fed, a novel Compression and Combination-based Federated learning framework that unifies local memory efficiency and global communication reduction. Locally, CoCo-Fed breaks the memory wall by performing a double-dimension down-projection of gradients, adapting the optimizer to operate on low-rank structures without introducing additional inference parameters/latency. Globally, we introduce a transmission protocol based on orthogonal subspace superposition, where layer-wise updates are projected and superimposed into a single consolidated matrix per gNB, drastically reducing the backhaul traffic. Beyond empirical designs, we establish a rigorous theoretical foundation, proving the convergence of CoCo-Fed even under unsupervised learning conditions suitable for wireless sensing tasks. Extensive simulations on an angle-of-arrival estimation task demonstrate that CoCo-Fed significantly outperforms state-of-the-art baselines in both memory and communication efficiency while maintaining robust convergence under non-IID settings.

---

### ECR: Manifold-Guided Semantic Cues for Compact Language Models

Authors: Chung-Wei Victor Yuan
Published: 2026-01-02
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.00543v1

Compact models often lose the structure of their embedding space. The issue shows up when the capacity is tight or the data spans several languages. Such collapse makes it difficult for downstream tasks to build on the resulting representation. Existing compression methods focus on aligning model outputs at a superficial level but fail to preserve the underlying manifold structure. This mismatch often leads to semantic drift in the compact model, causing both task behavior and linguistic properties to deviate from the reference model. To address those issues, we provide a new framework called Embedding Consistency Regulation (ECR). This framework first derives a set of semantic anchors from teacher embeddings (computed once offline). Then, the compact model learns to maintain consistent geometry around these anchors, without relying on matching logits or internal features. ECR adds only a small projection step at inference, without altering the decoding architecture or its runtime behavior. In experiments on a 100K multilingual corpus, ECR consistently stabilizes training and preserves semantic structure across tasks and languages. It also produces a more compact and task-aligned representation space, enabling low-capacity models to learn cleaner manifolds than conventional baselines. ECR works without teacher outputs and is compatible with, but independent of, distillation. Taken together, our results show that ECR helps compact models better follow task requirements and makes them easier to deploy under strict efficiency or privacy limits.

---

### DynaDrag: Dynamic Drag-Style Image Editing by Motion Prediction

Authors: Jiacheng Sui, Yujie Zhou, Li Niu
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00542v1

To achieve pixel-level image manipulation, drag-style image editing which edits images using points or trajectories as conditions is attracting widespread attention. Most previous methods follow move-and-track framework, in which miss tracking and ambiguous tracking are unavoidable challenging issues. Other methods under different frameworks suffer from various problems like the huge gap between source image and target edited image as well as unreasonable intermediate point which can lead to low editability. To avoid these problems, we propose DynaDrag, the first dragging method under predict-and-move framework. In DynaDrag, Motion Prediction and Motion Supervision are performed iteratively. In each iteration, Motion Prediction first predicts where the handle points should move, and then Motion Supervision drags them accordingly. We also propose to dynamically adjust the valid handle points to further improve the performance. Experiments on face and human datasets showcase the superiority over previous works.

---

### Parametrized Sharing for Multi-Agent Hybrid DRL for Multiple Multi-Functional RISs-Aided Downlink NOMA Networks

Authors: Chi-Te Kuo, Li-Hsiang Shen, Jyun-Jhe Huang
Published: 2026-01-02
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2601.00538v2

Multi-functional reconfigurable intelligent surface (MF-RIS) is conceived to address the communication efficiency thanks to its extended signal coverage from its active RIS capability and self-sustainability from energy harvesting (EH). We investigate the architecture of multi-MF-RISs to assist non-orthogonal multiple access (NOMA) downlink networks. We formulate an energy efficiency (EE) maximization problem by optimizing power allocation, transmit beamforming and MF-RIS configurations of amplitudes, phase-shifts and EH ratios, as well as the position of MF-RISs, while satisfying constraints of available power, user rate requirements, and self-sustainability property. We design a parametrized sharing scheme for multi-agent hybrid deep reinforcement learning (PMHRL), where the multi-agent proximal policy optimization (PPO) and deep-Q network (DQN) handle continuous and discrete variables, respectively. The simulation results have demonstrated that proposed PMHRL has the highest EE compared to other benchmarks, including cases without parametrized sharing, pure PPO and DQN. Moreover, the proposed multi-MF-RISs-aided downlink NOMA achieves the highest EE compared to scenarios of no-EH/amplification, traditional RISs, and deployment without RISs/MF-RISs under different multiple access.

---

### Parametrized Sharing for Multi-Agent Hybrid DRL for Multiple Multi-Functional RISs-Aided Downlink NOMA Networks

Authors: Chi-Te Kuo, Li-Hsiang Shen, Jyun-Jhe Huang
Published: 2026-01-02
Categories: eess.SP, cs.AI
arXiv: https://arxiv.org/abs/2601.00538v1

Multi-functional reconfigurable intelligent surface (MF-RIS) is conceived to address the communication efficiency thanks to its extended signal coverage from its active RIS capability and self-sustainability from energy harvesting (EH). We investigate the architecture of multi-MF-RISs to assist non-orthogonal multiple access (NOMA) downlink networks. We formulate an energy efficiency (EE) maximization problem by optimizing power allocation, transmit beamforming and MF-RIS configurations of amplitudes, phase-shifts and EH ratios, as well as the position of MF-RISs, while satisfying constraints of available power, user rate requirements, and self-sustainability property. We design a parametrized sharing scheme for multi-agent hybrid deep reinforcement learning (PMHRL), where the multi-agent proximal policy optimization (PPO) and deep-Q network (DQN) handle continuous and discrete variables, respectively. The simulation results have demonstrated that proposed PMHRL has the highest EE compared to other benchmarks, including cases without parametrized sharing, pure PPO and DQN. Moreover, the proposed multi-MF-RISs-aided downlink NOMA achieves the highest EE compared to scenarios of no-EH/amplification, traditional RISs, and deployment without RISs/MF-RISs under different multiple access.

---

### Boosting Segment Anything Model to Generalize Visually Non-Salient Scenarios

Authors: Guangqian Guo, Pengfei Chen, Yong Guo, Huafeng Chen, Boqiang Zhang, Shan Gao
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00537v1

Segment Anything Model (SAM), known for its remarkable zero-shot segmentation capabilities, has garnered significant attention in the community. Nevertheless, its performance is challenged when dealing with what we refer to as visually non-salient scenarios, where there is low contrast between the foreground and background. In these cases, existing methods often cannot capture accurate contours and fail to produce promising segmentation results. In this paper, we propose Visually Non-Salient SAM (VNS-SAM), aiming to enhance SAM's perception of visually non-salient scenarios while preserving its original zero-shot generalizability. We achieve this by effectively exploiting SAM's low-level features through two designs: Mask-Edge Token Interactive decoder and Non-Salient Feature Mining module. These designs help the SAM decoder gain a deeper understanding of non-salient characteristics with only marginal parameter increments and computational requirements. The additional parameters of VNS-SAM can be optimized within 4 hours, demonstrating its feasibility and practicality. In terms of data, we established VNS-SEG, a unified dataset for various VNS scenarios, with more than 35K images, in contrast to previous single-task adaptations. It is designed to make the model learn more robust VNS features and comprehensively benchmark the model's segmentation performance and generalizability on VNS scenarios. Extensive experiments across various VNS segmentation tasks demonstrate the superior performance of VNS-SAM, particularly under zero-shot settings, highlighting its potential for broad real-world applications. Codes and datasets are publicly available at https://guangqian-guo.github.io/VNS-SAM.

---

### Retrieval--Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical Trends

Authors: Yuelyu Ji, Zhuochun Li, Rui Meng, Daqing He
Published: 2026-01-02
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.00536v1

Multi-hop question answering (QA) requires systems to iteratively retrieve evidence and reason across multiple hops. While recent RAG and agentic methods report strong results, the underlying retrieval--reasoning \emph{process} is often left implicit, making procedural choices hard to compare across model families. This survey takes the execution procedure as the unit of analysis and introduces a four-axis framework covering (A) overall execution plan, (B) index structure, (C) next-step control (strategies and triggers), and (D) stop/continue criteria. Using this schema, we map representative multi-hop QA systems and synthesize reported ablations and tendencies on standard benchmarks (e.g., HotpotQA, 2WikiMultiHopQA, MuSiQue), highlighting recurring trade-offs among effectiveness, efficiency, and evidence faithfulness. We conclude with open challenges for retrieval--reasoning agents, including structure-aware planning, transferable control policies, and robust stopping under distribution shift.

---

### FreeText: Training-Free Text Rendering in Diffusion Transformers via Attention Localization and Spectral Glyph Injection

Authors: Ruiqiang Zhang, Hengyi Wang, Chang Liu, Guanjie Wang, Zehua Ma, Weiming Zhang
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00535v1

Large-scale text-to-image (T2I) diffusion models excel at open-domain synthesis but still struggle with precise text rendering, especially for multi-line layouts, dense typography, and long-tailed scripts such as Chinese. Prior solutions typically require costly retraining or rigid external layout constraints, which can degrade aesthetics and limit flexibility. We propose \textbf{FreeText}, a training-free, plug-and-play framework that improves text rendering by exploiting intrinsic mechanisms of \emph{Diffusion Transformer (DiT)} models. \textbf{FreeText} decomposes the problem into \emph{where to write} and \emph{what to write}. For \emph{where to write}, we localize writing regions by reading token-wise spatial attribution from endogenous image-to-text attention, using sink-like tokens as stable spatial anchors and topology-aware refinement to produce high-confidence masks. For \emph{what to write}, we introduce Spectral-Modulated Glyph Injection (SGMI), which injects a noise-aligned glyph prior with frequency-domain band-pass modulation to strengthen glyph structure and suppress semantic leakage (rendering the concept instead of the word). Extensive experiments on Qwen-Image, FLUX.1-dev, and SD3 variants across longText-Benchmark, CVTG, and our CLT-Bench show consistent gains in text readability while largely preserving semantic alignment and aesthetic quality, with modest inference overhead.

---

### All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations

Authors: Wenrui Li, Hongtao Chen, Yao Xiao, Wangmeng Zuo, Jiantao Zhou, Yonghong Tian, Xiaopeng Fan
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00533v2

All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task to videos faces unique challenges. Existing approaches primarily focus on frame-wise degradation variation, overlooking the temporal continuity that naturally exists in real-world degradation processes. In practice, degradation types and intensities evolve smoothly over time, and multiple degradations may coexist or transition gradually. In this paper, we introduce the Smoothly Evolving Unknown Degradations (SEUD) scenario, where both the active degradation set and degradation intensity change continuously over time. To support this scenario, we design a flexible synthesis pipeline that generates temporally coherent videos with single, compound, and evolving degradations. To address the challenges in the SEUD scenario, we propose an all-in-One Recurrent Conditional and Adaptive prompting Network (ORCANet). First, a Coarse Intensity Estimation Dehazing (CIED) module estimates haze intensity using physical priors and provides coarse dehazed features as initialization. Second, a Flow Prompt Generation (FPG) module extracts degradation features. FPG generates both static prompts that capture segment-level degradation types and dynamic prompts that adapt to frame-level intensity variations. Furthermore, a label-aware supervision mechanism improves the discriminability of static prompt representations under different degradations. Extensive experiments show that ORCANet achieves superior restoration quality, temporal consistency, and robustness over image and video-based baselines. Code is available at https://github.com/Friskknight/ORCANet-SEUD.

---

### All-in-One Video Restoration under Smoothly Evolving Unknown Weather Degradations

Authors: Wenrui Li, Hongtao Chen, Yao Xiao, Wangmeng Zuo, Jiantao Zhou, Yonghong Tian, Xiaopeng Fan
Published: 2026-01-02
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.00533v1

All-in-one image restoration aims to recover clean images from diverse unknown degradations using a single model. But extending this task to videos faces unique challenges. Existing approaches primarily focus on frame-wise degradation variation, overlooking the temporal continuity that naturally exists in real-world degradation processes. In practice, degradation types and intensities evolve smoothly over time, and multiple degradations may coexist or transition gradually. In this paper, we introduce the Smoothly Evolving Unknown Degradations (SEUD) scenario, where both the active degradation set and degradation intensity change continuously over time. To support this scenario, we design a flexible synthesis pipeline that generates temporally coherent videos with single, compound, and evolving degradations. To address the challenges in the SEUD scenario, we propose an all-in-One Recurrent Conditional and Adaptive prompting Network (ORCANet). First, a Coarse Intensity Estimation Dehazing (CIED) module estimates haze intensity using physical priors and provides coarse dehazed features as initialization. Second, a Flow Prompt Generation (FPG) module extracts degradation features. FPG generates both static prompts that capture segment-level degradation types and dynamic prompts that adapt to frame-level intensity variations. Furthermore, a label-aware supervision mechanism improves the discriminability of static prompt representations under different degradations. Extensive experiments show that ORCANet achieves superior restoration quality, temporal consistency, and robustness over image and video-based baselines. Code is available at https://github.com/Friskknight/ORCANet-SEUD.

---

### Cloud-Native Generative AI for Automated Planogram Synthesis: A Diffusion Model Approach for Multi-Store Retail Optimization

Authors: Ravi Teja Pagidoju, Shriya Agarwal
Published: 2026-01-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00527v1

Planogram creation is a significant challenge for retail, requiring an average of 30 hours per complex layout. This paper introduces a cloud-native architecture using diffusion models to automatically generate store-specific planograms. Unlike conventional optimization methods that reorganize existing layouts, our system learns from successful shelf arrangements across multiple retail locations to create new planogram configurations. The architecture combines cloud-based model training via AWS with edge deployment for real-time inference. The diffusion model integrates retail-specific constraints through a modified loss function. Simulation-based analysis demonstrates the system reduces planogram design time by 98.3% (from 30 to 0.5 hours) while achieving 94.4% constraint satisfaction. Economic analysis reveals a 97.5% reduction in creation expenses with a 4.4-month break-even period. The cloud-native architecture scales linearly, supporting up to 10,000 concurrent store requests. This work demonstrates the viability of generative AI for automated retail space optimization.

---

### Federated Customization of Large Models: Approaches, Experiments, and Insights

Authors: Yuchuan Ye, Ming Ding, Youjia Chen, Peng Cheng, Dusit Niyato
Published: 2026-01-02
Categories: cs.LG, cs.DC
arXiv: https://arxiv.org/abs/2601.00526v1

In this article, we explore federated customization of large models and highlight the key challenges it poses within the federated learning framework. We review several popular large model customization techniques, including full fine-tuning, efficient fine-tuning, prompt engineering, prefix-tuning, knowledge distillation, and retrieval-augmented generation. Then, we discuss how these techniques can be implemented within the federated learning framework. Moreover, we conduct experiments on federated prefix-tuning, which, to the best of our knowledge, is the first trial to apply prefix-tuning in the federated learning setting. The conducted experiments validate its feasibility with performance close to centralized approaches. Further comparison with three other federated customization methods demonstrated its competitive performance, satisfactory efficiency, and consistent robustness.

---

### Optimizing LSTM Neural Networks for Resource-Constrained Retail Sales Forecasting: A Model Compression Study

Authors: Ravi Teja Pagidoju
Published: 2026-01-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.00525v1

Standard LSTM(Long Short-Term Memory) neural networks provide accurate predictions for sales data in the retail industry, but require a lot of computing power. It can be challenging especially for mid to small retail industries. This paper examines LSTM model compression by gradually reducing the number of hidden units from 128 to 16. We used the Kaggle Store Item Demand Forecasting dataset, which has 913,000 daily sales records from 10 stores and 50 items, to look at the trade-off between model size and how accurate the predictions are. Experiments show that lowering the number of hidden LSTM units to 64 maintains the same level of accuracy while also improving it. The mean absolute percentage error (MAPE) ranges from 23.6% for the full 128-unit model to 12.4% for the 64-unit model. The optimized model is 73% smaller (from 280KB to 76KB) and 47% more accurate. These results show that larger models do not always achieve better results.

---

### Probability-Aware Parking Selection

Authors: Cameron Hickert, Sirui Li, Zhengbing He, Cathy Wu
Published: 2026-01-02
Categories: eess.SY, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2601.00521v2

Current navigation systems conflate time-to-drive with the true time-to-arrive by ignoring parking search duration and the final walking leg. Such underestimation can significantly affect user experience, mode choice, congestion, and emissions. To address this issue, this paper introduces the probability-aware parking selection problem, which aims to direct drivers to the best parking location rather than straight to their destination. An adaptable dynamic programming framework is proposed that leverages probabilistic, lot-level availability to minimize the expected time-to-arrive. Closed-form analysis determines when it is optimal to target a specific parking lot or explore alternatives, as well as the expected time cost. Sensitivity analysis and three illustrative cases are examined, demonstrating the model's ability to account for the dynamic nature of parking availability. Given the high cost of permanent sensing infrastructure, we assess the error rates of using stochastic observations to estimate availability. Experiments with real-world data from the US city of Seattle indicate this approach's viability, with mean absolute error decreasing from 7% to below 2% as observation frequency increases. In data-based simulations, probability-aware strategies demonstrate time savings up to 66% relative to probability-unaware baselines, yet still take up to 123% longer than time-to-drive estimates.

---

### Probability-Aware Parking Selection

Authors: Cameron Hickert, Sirui Li, Zhengbing He, Cathy Wu
Published: 2026-01-02
Categories: eess.SY, cs.AI, stat.AP
arXiv: https://arxiv.org/abs/2601.00521v1

Current parking navigation systems often underestimate total travel time by failing to account for the time spent searching for a parking space, which significantly affects user experience, mode choice, congestion, and emissions. To address this issue, this paper introduces the probability-aware parking selection problem, which aims to direct drivers to the best parking location rather than straight to their destination. An adaptable dynamic programming framework is proposed for decision-making based on probabilistic information about parking availability at the parking lot level. Closed-form analysis determines when it is optimal to target a specific parking lot or explore alternatives, as well as the expected time cost. Sensitivity analysis and three illustrative cases are examined, demonstrating the model's ability to account for the dynamic nature of parking availability. Acknowledging the financial costs of permanent sensing infrastructure, the paper provides analytical and empirical assessments of errors incurred when leveraging stochastic observations to estimate parking availability. Experiments with real-world data from the US city of Seattle indicate this approach's viability, with mean absolute error decreasing from 7% to below 2% as observation frequency grows. In data-based simulations, probability-aware strategies demonstrate time savings up to 66% relative to probability-unaware baselines, yet still take up to 123% longer than direct-to-destination estimates.

---

### A Sparse-Attention Deep Learning Model Integrating Heterogeneous Multimodal Features for Parkinson's Disease Severity Profiling

Authors: Dristi Datta, Tanmoy Debnath, Minh Chau, Manoranjan Paul, Gourab Adhikary, Md Geaur Rahman
Published: 2026-01-02
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.00519v1

Characterising the heterogeneous presentation of Parkinson's disease (PD) requires integrating biological and clinical markers within a unified predictive framework. While multimodal data provide complementary information, many existing computational models struggle with interpretability, class imbalance, or effective fusion of high-dimensional imaging and tabular clinical features. To address these limitations, we propose the Class-Weighted Sparse-Attention Fusion Network (SAFN), an interpretable deep learning framework for robust multimodal profiling. SAFN integrates MRI cortical thickness, MRI volumetric measures, clinical assessments, and demographic variables using modality-specific encoders and a symmetric cross-attention mechanism that captures nonlinear interactions between imaging and clinical representations. A sparsity-constrained attention-gating fusion layer dynamically prioritises informative modalities, while a class-balanced focal loss (beta = 0.999, gamma = 1.5) mitigates dataset imbalance without synthetic oversampling. Evaluated on 703 participants (570 PD, 133 healthy controls) from the Parkinson's Progression Markers Initiative using subject-wise five-fold cross-validation, SAFN achieves an accuracy of 0.98 plus or minus 0.02 and a PR-AUC of 1.00 plus or minus 0.00, outperforming established machine learning and deep learning baselines. Interpretability analysis shows a clinically coherent decision process, with approximately 60 percent of predictive weight assigned to clinical assessments, consistent with Movement Disorder Society diagnostic principles. SAFN provides a reproducible and transparent multimodal modelling paradigm for computational profiling of neurodegenerative disease.

---

### Generative Conditional Missing Imputation Networks

Authors: George Sun, Yi-Hui Zhou
Published: 2026-01-02
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.00517v1

In this study, we introduce a sophisticated generative conditional strategy designed to impute missing values within datasets, an area of considerable importance in statistical analysis. Specifically, we initially elucidate the theoretical underpinnings of the Generative Conditional Missing Imputation Networks (GCMI), demonstrating its robust properties in the context of the Missing Completely at Random (MCAR) and the Missing at Random (MAR) mechanisms. Subsequently, we enhance the robustness and accuracy of GCMI by integrating a multiple imputation framework using a chained equations approach. This innovation serves to bolster model stability and improve imputation performance significantly. Finally, through a series of meticulous simulations and empirical assessments utilizing benchmark datasets, we establish the superior efficacy of our proposed methods when juxtaposed with other leading imputation techniques currently available. This comprehensive evaluation not only underscores the practicality of GCMI but also affirms its potential as a leading-edge tool in the field of statistical data analysis.

---

### Trajectory Guard -- A Lightweight, Sequence-Aware Model for Real-Time Anomaly Detection in Agentic AI

Authors: Laksh Advani
Published: 2026-01-02
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.00516v1

Autonomous LLM agents generate multi-step action plans that can fail due to contextual misalignment or structural incoherence. Existing anomaly detection methods are ill-suited for this challenge: mean-pooling embeddings dilutes anomalous steps, while contrastive-only approaches ignore sequential structure. Standard unsupervised methods on pre-trained embeddings achieve F1-scores no higher than 0.69. We introduce Trajectory Guard, a Siamese Recurrent Autoencoder with a hybrid loss function that jointly learns task-trajectory alignment via contrastive learning and sequential validity via reconstruction. This dual objective enables unified detection of both "wrong plan for this task" and "malformed plan structure." On benchmarks spanning synthetic perturbations and real-world failures from security audits (RAS-Eval) and multi-agent systems (Who\&When), we achieve F1-scores of 0.88-0.94 on balanced sets and recall of 0.86-0.92 on imbalanced external benchmarks. At 32 ms inference latency, our approach runs 17-27$\times$ faster than LLM Judge baselines, enabling real-time safety verification in production deployments.

---

### The Illusion of Insight in Reasoning Models

Authors: Liv G. d'Aliberti, Manoel Horta Ribeiro
Published: 2026-01-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.00514v2

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear whether such intrinsic shifts in reasoning strategy actually improve performance. Here, we study mid-reasoning shifts and instrument training runs to detect them. Our analysis spans 1M+ reasoning traces, hundreds of training checkpoints, three reasoning domains, and multiple decoding temperatures and model architectures. We find that reasoning shifts are rare, do not become more frequent with training, and seldom improve accuracy, indicating that they do not correspond to prior perceptions of model insight. However, their effect varies with model uncertainty. Building on this finding, we show that artificially triggering extrinsic shifts under high entropy reliably improves accuracy. Our results show that mid-reasoning shifts are symptoms of unstable inference behavior rather than an intrinsic mechanism for self-correction.

---

### The Illusion of Insight in Reasoning Models

Authors: Liv G. d'Aliberti, Manoel Horta Ribeiro
Published: 2026-01-02
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.00514v1

Do reasoning models have "Aha!" moments? Prior work suggests that models like DeepSeek-R1-Zero undergo sudden mid-trace realizations that lead to accurate outputs, implying an intrinsic capacity for self-correction. Yet, it remains unclear whether such intrinsic shifts in reasoning strategy actually improve performance. Here, we study mid-reasoning shifts and instrument training runs to detect them. Our analysis spans 1M+ reasoning traces, hundreds of training checkpoints, three reasoning domains, and multiple decoding temperatures and model architectures. We find that reasoning shifts are rare, do not become more frequent with training, and seldom improve accuracy, indicating that they do not correspond to prior perceptions of model insight. However, their effect varies with model uncertainty. Building on this finding, we show that artificially triggering extrinsic shifts under high entropy reliably improves accuracy. Our results show that mid-reasoning shifts are symptoms of unstable inference behavior rather than an intrinsic mechanism for self-correction.

---

### Traffic Simulation in Ad Hoc Network of Flying UAVs with Generative AI Adaptation

Authors: Andrii Grekhov, Volodymyr Kharchenko, Vasyl Kondratiuk
Published: 2026-01-01
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2602.13200v1

The purpose of this paper is to model traffic in Ad Hoc network of Unmanned Aerial Vehicles and demonstrate a way for adapting communication channel using Artificial Intelligence. The modeling was based on the original model of Ad Hoc network including 20 Unmanned Aerial Vehicles. The dependences of packet loss on the packet size for different transmission powers, on the packet size for different frequencies, on Unmanned Aerial Vehicles flight area and on the number of Unmanned Aerial Vehicles were obtained and analyzed. The implementation of adaptive data transmission is presented in the program code. The dependences of packet loss, power and transaction size on time during Artificial Intelligence adaptation are shown.

---

### Simulation-Based Study of AI-Assisted Channel Adaptation in UAV-Enabled Cellular Networks

Authors: Andrii Grekhov, Volodymyr Kharchenko, Vasyl Kondratiuk
Published: 2026-01-01
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2602.13199v1

This paper presents a simulation based study of Artificial Intelligence assisted communication channel adaptation in Unmanned Aerial Vehicle enabled cellular networks. The considered system model includes communication channel Ground Base Station Aerial Repeater UAV Base Station Cluster of Cellular Network Users. The primary objective of the study is to investigate the impact of adaptive channel parameter control on communication performance under dynamically changing interference conditions. A lightweight supervised machine learning approach based on linear regression is employed to implement cognitive channel adaptation. The AI model operates on packet level performance indicators and enables real time adjustment of Transaction Size in response to variations in Bit Error Rate and effective Data Rate. A custom simulation environment is developed to generate training and testing datasets and to evaluate system behavior under both static and adaptive channel configurations.

---

### Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics

Authors: Pierrick Lorang
Published: 2026-01-01
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.16985v1

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow adaptation, and catastrophic forgetting. We present a neuro-symbolic framework integrating hierarchical abstractions, task and motion planning (TAMP), and reinforcement learning to enable rapid adaptation in robotics. Our architecture combines symbolic goal-oriented learning and world model-based exploration to facilitate rapid adaptation to environmental changes. Validated in robotic manipulation and autonomous driving, our approach achieves faster convergence, improved sample efficiency, and superior robustness over state-of-the-art hybrid methods, demonstrating its potential for real-world deployment.

---

### Entropic Context Shaping: Information-Theoretic Filtering for Context-Aware LLM Agents

Authors: Hyunjun Kim
Published: 2026-01-01
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.11585v1

Context engineering for large language model (LLM) agents requires distinguishing pragmatically useful information from misleading distractors. We introduce Entropic Context Shaping (ECS), an information-theoretic framework that measures context utility via the shift in the model's answer distribution toward the correct answer. Unlike lexical similarity methods that rely on word overlap, ECS captures pragmatic utility -- whether a passage actually helps answer the question. We formalize utility as the signed change in answer probability and provide theoretical analysis showing that task-irrelevant updates yield near-zero distribution shift. We evaluate on multi-turn context selection tasks using LongMemEval (session-level) and LoCoMo (turn-level) benchmarks. On fine-grained turn selection, ECS with Llama-3.1-8B achieves F1=0.265, a 71.83% relative improvement over TF-IDF (F1=0.154), demonstrating that pragmatic utility outperforms lexical similarity when precise context selection matters. Code and data are available in the supplementary materials.

---