# Research Papers — 2026-01 · bundle page 44 of 189

> Full-text markdown of papers #2151–2200 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/44
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/43.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/45.md)

### Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenes

Authors: Yin Wang, Zhiying Leng, Haitian Liu, Frederick W. B. Li, Mu Li, Xiaohui Liang
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19484v1

Scenes are continuously undergoing dynamic changes in the real world. However, existing human-scene interaction generation methods typically treat the scene as static, which deviates from reality. Inspired by world models, we introduce Dyn-HSI, the first cognitive architecture for dynamic human-scene interaction, which endows virtual humans with three humanoid components. (1)Vision (human eyes): we equip the virtual human with a Dynamic Scene-Aware Navigation, which continuously perceives changes in the surrounding environment and adaptively predicts the next waypoint. (2)Memory (human brain): we equip the virtual human with a Hierarchical Experience Memory, which stores and updates experiential data accumulated during training. This allows the model to leverage prior knowledge during inference for context-aware motion priming, thereby enhancing both motion quality and generalization. (3) Control (human body): we equip the virtual human with Human-Scene Interaction Diffusion Model, which generates high-fidelity interaction motions conditioned on multimodal inputs. To evaluate performance in dynamic scenes, we extend the existing static human-scene interaction datasets to construct a dynamic benchmark, Dyn-Scenes. We conduct extensive qualitative and quantitative experiments to validate Dyn-HSI, showing that our method consistently outperforms existing approaches and generates high-quality human-scene interaction motions in both static and dynamic settings.

---

### Online Regime-aware Calibration for Black-box Social Simulators via Posterior-assisted Evolutionary Dynamic Optimization

Authors: Peng Yang, Zhenhua Yang, Boquan Jiang, Chenkai Wang, Ke Tang, Xin Yao
Published: 2026-01-27
Categories: cs.NE, cs.LG
arXiv: https://arxiv.org/abs/2601.19481v2

Evolutionary dynamic optimization (EDO) commonly assumes that environmental changes can be detected from fitness variations and handled through random re-initialization, historical solutions, or learned transition patterns. Online calibration of black-box simulators introduces a different setting, where the dynamic objective is induced by sequential observations and a changing calibration window, rather than being controlled by explicit variables. Fitness variations therefore cannot be directly attributed to regime changes, while the unknown relationship between successive regimes limits conventional adaptation. We formulate this setting as an observation-driven dynamic optimization problem and propose PosEDO, which augments fitness-based EDO with an observation-conditioned parameter-space signal. PosEDO learns this signal online as a posterior distribution over simulator parameters from parameter-trajectory pairs generated during evolutionary evaluation, using posterior shifts for change detection and posterior samples for population adaptation. The new evaluation records are further utilized for online posterior updating without additional simulator calls. Experiments on nonstationary economic and financial simulators show that PosEDO improves calibration accuracy, optimization performance, and change-detection quality over representative EDO baselines.

---

### Time-to-Injury Forecasting in Elite Female Football: A DeepHit Survival Approach

Authors: Victoria Catterall, Cise Midoglu, Stephen Lynch
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19479v1

Injury occurrence in football poses significant challenges for athletes and teams, carrying personal, competitive, and financial consequences. While machine learning has been applied to injury prediction before, existing approaches often rely on static pre-season data and binary outcomes, limiting their real-world utility. This study investigates the feasibility of using a DeepHit neural network to forecast time-to-injury from longitudinal athlete monitoring data, while providing interpretable predictions. The analysis utilised the publicly available SoccerMon dataset, containing two seasons of training, match, and wellness records from elite female footballers. Data was pre-processed through cleaning, feature engineering, and the application of three imputation strategies. Baseline models (Random Forest, XGBoost, Logistic Regression) were optimised via grid search for benchmarking, while the DeepHit model, implemented with a multilayer perceptron backbone, was evaluated using chronological and leave-one-player-out (LOPO) validation. DeepHit achieved a concordance index of 0.762, outperforming baseline models and delivering individualised, time-varying risk estimates. Shapley Additive Explanations (SHAP) identified clinically relevant predictors consistent with established risk factors, enhancing interpretability. Overall, this study provides a novel proof of concept: survival modelling with DeepHit shows strong potential to advance injury forecasting in football, offering accurate, explainable, and actionable insights for injury prevention across competitive levels.

---

### ROIDS: Robust Outlier-Aware Informed Down-Sampling

Authors: Alina Geiger, Martin Briesch, Dominik Sobania, Franz Rothlauf
Published: 2026-01-27
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.19477v1

Informed down-sampling (IDS) is known to improve performance in symbolic regression when combined with various selection strategies, especially tournament selection. However, recent work found that IDS's gains are not consistent across all problems. Our analysis reveals that IDS performance is worse for problems containing outliers. IDS systematically favors including outliers in subsets which pushes GP towards finding solutions that overfit to outliers. To address this, we introduce ROIDS (Robust Outlier-Aware Informed Down-Sampling), which excludes potential outliers from the sampling process of IDS. With ROIDS it is possible to keep the advantages of IDS without overfitting to outliers and to compete on a wide range of benchmark problems. This is also reflected in our experiments in which ROIDS shows the desired behavior on all studied benchmark problems. ROIDS consistently outperforms IDS on synthetic problems with added outliers as well as on a wide range of complex real-world problems, surpassing IDS on over 80% of the real-world benchmark problems. Moreover, compared to all studied baseline approaches, ROIDS achieves the best average rank across all tested benchmark problems. This robust behavior makes ROIDS a reliable down-sampling method for selection in symbolic regression, especially when outliers may be included in the data set.

---

### On the Expressiveness of State Space Models via Temporal Logics

Authors: Eric Alsmann, Lowejatan Noori, Martin Lange
Published: 2026-01-27
Categories: cs.LO, cs.FL, cs.LG
arXiv: https://arxiv.org/abs/2601.19467v1

We investigate the expressive power of state space models (SSM), which have recently emerged as a potential alternative to transformer architectures in large language models. Building on recent work, we analyse SSM expressiveness through fragments and extensions of linear temporal logic over finite traces. Our results show that the expressive capabilities of SSM vary substantially depending on the underlying gating mechanism. We further distinguish between SSM operating over fixed-width arithmetic (quantised models), whose expressive power remains within regular languages, and SSM with unbounded precision, which can capture counting properties and non-regular languages. In addition, we provide a systematic comparison between these different SSM variants and known results on transformers, thereby clarifying how the two architectures relate in terms of expressive power.

---

### Towards Gold-Standard Depth Estimation for Tree Branches in UAV Forestry: Benchmarking Deep Stereo Matching Methods

Authors: Yida Lin, Bing Xue, Mengjie Zhang, Sam Schofield, Richard Green
Published: 2026-01-27
Categories: cs.CV, cs.RO, eess.IV
arXiv: https://arxiv.org/abs/2601.19461v1

Autonomous UAV forestry operations require robust depth estimation with strong cross-domain generalization, yet existing evaluations focus on urban and indoor scenarios, leaving a critical gap for vegetation-dense environments. We present the first systematic zero-shot evaluation of eight stereo methods spanning iterative refinement, foundation model, diffusion-based, and 3D CNN paradigms. All methods use officially released pretrained weights (trained on Scene Flow) and are evaluated on four standard benchmarks (ETH3D, KITTI 2012/2015, Middlebury) plus a novel 5,313-pair Canterbury Tree Branches dataset ($1920 \times 1080$). Results reveal scene-dependent patterns: foundation models excel on structured scenes (BridgeDepth: 0.23 px on ETH3D; DEFOM: 4.65 px on Middlebury), while iterative methods show variable cross-benchmark performance (IGEV++: 0.36 px on ETH3D but 6.77 px on Middlebury; IGEV: 0.33 px on ETH3D but 4.99 px on Middlebury). Qualitative evaluation on the Tree Branches dataset establishes DEFOM as the gold-standard baseline for vegetation depth estimation, with superior cross-domain consistency (consistently ranking 1st-2nd across benchmarks, average rank 1.75). DEFOM predictions will serve as pseudo-ground-truth for future benchmarking.

---

### APC-RL: Exceeding Data-Driven Behavior Priors with Adaptive Policy Composition

Authors: Finn Rietz, Pedro Zuidberg dos Martires, Johannes Andreas Stork
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19452v1

Incorporating demonstration data into reinforcement learning (RL) can greatly accelerate learning, but existing approaches often assume demonstrations are optimal and fully aligned with the target task. In practice, demonstrations are frequently sparse, suboptimal, or misaligned, which can degrade performance when these demonstrations are integrated into RL. We propose Adaptive Policy Composition (APC), a hierarchical model that adaptively composes multiple data-driven Normalizing Flow (NF) priors. Instead of enforcing strict adherence to the priors, APC estimates each prior's applicability to the target task while leveraging them for exploration. Moreover, APC either refines useful priors, or sidesteps misaligned ones when necessary to optimize downstream reward. Across diverse benchmarks, APC accelerates learning when demonstrations are aligned, remains robust under severe misalignment, and leverages suboptimal demonstrations to bootstrap exploration while avoiding performance degradation caused by overly strict adherence to suboptimal demonstrations.

---

### Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition

Authors: Isha Pandey, Ashish Mittal, Vartul Bahuguna, Ganesh Ramakrishnan
Published: 2026-01-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.19451v1

Recent advances in LLM-based ASR connect frozen speech encoders with Large Language Models (LLMs) via lightweight projectors. While effective in monolingual settings, a single projector struggles to capture the diverse acoustic-to-semantic mappings required for multilingual ASR. To address this, we propose SMEAR-MoE, a stabilized Mixture-of-Experts projector that ensures dense gradient flow to all experts, preventing expert collapse while enabling cross-lingual sharing. We systematically compare monolithic, static multi-projector, and dynamic MoE designs across four Indic languages (Hindi, Marathi, Tamil, Telugu). Our SMEAR-MoE achieves strong performance, delivering upto a 7.6% relative WER reduction over the single-projector baseline, while maintaining comparable runtime efficiency. Analysis of expert routing further shows linguistically meaningful specialization, with related languages sharing experts. These results demonstrate that stable multi-expert projectors are key to scalable and robust multilingual ASR.

---

### Fixed Aggregation Features Can Rival GNNs

Authors: Celia Rubio-Madrigal, Rebekka Burkholz
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19449v2

Graph neural networks (GNNs) are widely believed to excel at node representation learning through trainable neighborhood aggregations. We challenge this view by introducing Fixed Aggregation Features (FAFs), a training-free approach that transforms graph learning tasks into tabular problems. This simple shift enables the use of well-established tabular methods, offering strong interpretability and the flexibility to deploy diverse classifiers. Across 14 benchmarks, well-tuned multilayer perceptrons trained on FAFs rival or outperform state-of-the-art GNNs and graph transformers on 12 tasks -- often using only mean aggregation. The only exceptions are the Roman Empire and Minesweeper datasets, which typically require unusually deep GNNs. To explain the theoretical possibility of non-trainable aggregations, we connect our findings to Kolmogorov-Arnold representations and discuss when mean aggregation can be sufficient. In conclusion, our results call for (i) richer benchmarks benefiting from learning diverse neighborhood aggregations, (ii) strong tabular baselines as standard, and (iii) employing and advancing tabular models for graph data to gain new insights into related tasks.

---

### From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense

Authors: Binyan Xu, Fan Yang, Xilin Dai, Di Tang, Kehuan Zhang
Published: 2026-01-27
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2601.19448v2

Deep Neural Networks remain inherently vulnerable to backdoor attacks. Traditional test-time defenses largely operate under the paradigm of internal diagnosis methods like model repairing or input robustness, yet these approaches are often fragile under advanced attacks as they remain entangled with the victim model's corrupted parameters. We propose a paradigm shift from Internal Diagnosis to External Semantic Auditing, arguing that effective defense requires decoupling safety from the victim model via an independent, semantically grounded auditor. To this end, we present a framework harnessing Universal Vision-Language Models (VLMs) as evolving semantic gatekeepers. We introduce PRISM (Prototype Refinement & Inspection via Statistical Monitoring), which overcomes the domain gap of general VLMs through two key mechanisms: a Hybrid VLM Teacher that dynamically refines visual prototypes online, and an Adaptive Router powered by statistical margin monitoring to calibrate gating thresholds in real-time. Extensive evaluation across 17 datasets and 11 attack types demonstrates that PRISM achieves state-of-the-art performance, suppressing Attack Success Rate to <1% on CIFAR-10 while improving clean accuracy, establishing a new standard for model-agnostic, externalized security.

---

### KG-CRAFT: Knowledge Graph-based Contrastive Reasoning with LLMs for Enhancing Automated Fact-checking

Authors: Vítor N. Lourenço, Aline Paes, Tillman Weyde, Audrey Depeige, Mohnish Dubey
Published: 2026-01-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19447v1

Claim verification is a core component of automated fact-checking systems, aimed at determining the truthfulness of a statement by assessing it against reliable evidence sources such as documents or knowledge bases. This work presents KG-CRAFT, a method that improves automatic claim verification by leveraging large language models (LLMs) augmented with contrastive questions grounded in a knowledge graph. KG-CRAFT first constructs a knowledge graph from claims and associated reports, then formulates contextually relevant contrastive questions based on the knowledge graph structure. These questions guide the distillation of evidence-based reports, which are synthesised into a concise summary that is used for veracity assessment by LLMs. Extensive evaluations on two real-world datasets (LIAR-RAW and RAWFC) demonstrate that our method achieves a new state-of-the-art in predictive performance. Comprehensive analyses validate in detail the effectiveness of our knowledge graph-based contrastive reasoning approach in improving LLMs' fact-checking capabilities.

---

### DSTCS: Dual-Student Teacher Framework with Segment Anything Model for Semi-Supervised Pubic Symphysis Fetal Head Segmentation

Authors: Yalin Luo, Shun Long, Huijin Wang, Jieyun Bai
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19446v1

Segmentation of the pubic symphysis and fetal head (PSFH) is a critical procedure in intrapartum monitoring and is essential for evaluating labor progression and identifying potential delivery complications. However, achieving accurate segmentation remains a significant challenge due to class imbalance, ambiguous boundaries, and noise interference in ultrasound images, compounded by the scarcity of high-quality annotated data. Current research on PSFH segmentation predominantly relies on CNN and Transformer architectures, leaving the potential of more powerful models underexplored. In this work, we propose a Dual-Student and Teacher framework combining CNN and SAM (DSTCS), which integrates the Segment Anything Model (SAM) into a dual student-teacher architecture. A cooperative learning mechanism between the CNN and SAM branches significantly improves segmentation accuracy. The proposed scheme also incorporates a specialized data augmentation strategy optimized for boundary processing and a novel loss function. Extensive experiments on the MICCAI 2023 and 2024 PSFH segmentation benchmarks demonstrate that our method exhibits superior robustness and significantly outperforms existing techniques, providing a reliable segmentation tool for clinical practice.

---

### OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation

Authors: Giuseppe Chiari, Michele Piccoli, Davide Zoni
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19439v1

The automation of analog integrated circuit (IC) design remains a longstanding challenge, primarily due to the intricate interdependencies among physical layout, parasitic effects, and circuit-level performance. These interactions impose complex constraints that are difficult to accurately capture and optimize using conventional design methodologies. Although recent advances in machine learning (ML) have shown promise in automating specific stages of the analog design flow, the development of holistic, end-to-end frameworks that integrate these stages and iteratively refine layouts using post-layout, parasitic-aware performance feedback is still in its early stages. Furthermore, progress in this direction is hindered by the limited availability of open, high-quality datasets tailored to the analog domain, restricting both the benchmarking and the generalizability of ML-based techniques. To address these limitations, we present OSIRIS, a scalable dataset generation pipeline for analog IC design. OSIRIS systematically explores the design space of analog circuits while producing comprehensive performance metrics and metadata, thereby enabling ML-driven research in electronic design automation (EDA). In addition, we release a dataset consisting of 87,100 circuit variations generated with OSIRIS, accompanied by a reinforcement learning (RL)-based baseline method that exploits OSIRIS for analog design optimization.

---

### Ad Insertion in LLM-Generated Responses

Authors: Shengwei Xu, Zhaohua Chen, Xiaotie Deng, Zhiyi Huang, Grant Schoenebeck
Published: 2026-01-27
Categories: cs.GT, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.19435v2

Sustainable monetization of large language models (LLMs) remains a critical open challenge. Traditional search advertising, which relies on static keywords, fails to capture the fleeting, context-dependent user intent---the specific information, goods, or services a user seeks---embedded in conversational flows. Beyond the standard goal of social welfare maximization effective LLM advertising requires contextual coherence (aligning ads semantically with transient user intent), computational efficiency (avoiding user-facing latency), and adherence to ethical and regulatory standards, including privacy preservation and explicit ad disclosure. Although recent solutions have explored bidding at the token and query levels, neither category holistically satisfies these constraints. We propose a framework that resolves these tensions through two decoupling strategies. First, we decouple ad insertion from response generation to facilitate pre-screening and explicit disclosure. Second, we decouple bidding from specific user queries by using ``genres'' (high-level semantic clusters) as a proxy. This allows advertisers to bid on stable categories rather than sensitive real-time responses, reducing computational burden and privacy risks. Applying the VCG auction mechanism to this genre-based framework provides approximate guarantees for dominant-strategy incentive compatibility (DSIC), individual rationality (IR), and social welfare. In synthetic experiments with $10^5$ advertisers and 100 candidate slots, VCG clears in approximately 1.25 seconds on a consumer-grade laptop. Finally, we introduce an ``LLM-as-a-Judge'' metric for estimating contextual coherence. Its predictions correlate with mean human ratings at Spearman's $ρ\approx 0.66$ and have a higher correlation with the leave-one-out group mean than 29 of 36 individual raters (80.6\%).

---

### RoamScene3D: Immersive Text-to-3D Scene Generation via Adaptive Object-aware Roaming

Authors: Jisheng Chu, Wenrui Li, Rui Zhao, Wangmeng Zuo, Shifeng Chen, Xiaopeng Fan
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19433v1

Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D diffusion priors, existing methods suffer from spatial blindness and rely on predefined trajectories that fail to exploit the inner relationships among salient objects. Consequently, these approaches are unable to comprehend the semantic layout, preventing them from exploring the scene adaptively to infer occluded content. Moreover, current inpainting models operate in 2D image space, struggling to plausibly fill holes caused by camera motion. To address these limitations, we propose RoamScene3D, a novel framework that bridges the gap between semantic guidance and spatial generation. Our method reasons about the semantic relations among objects and produces consistent and photorealistic scenes. Specifically, we employ a vision-language model (VLM) to construct a scene graph that encodes object relations, guiding the camera to perceive salient object boundaries and plan an adaptive roaming trajectory. Furthermore, to mitigate the limitations of static 2D priors, we introduce a Motion-Injected Inpainting model that is fine-tuned on a synthetic panoramic dataset integrating authentic camera trajectories, making it adaptive to camera motion. Extensive experiments demonstrate that with semantic reasoning and geometric constraints, our method significantly outperforms state-of-the-art approaches in producing consistent and photorealistic scenes. Our code is available at https://github.com/JS-CHU/RoamScene3D.

---

### Unveiling Perceptual Artifacts: A Fine-Grained Benchmark for Interpretable AI-Generated Image Detection

Authors: Yao Xiao, Weiyan Chen, Jiahao Chen, Zijie Cao, Weijian Deng, Binbin Yang, Ziyi Dong, Xiangyang Ji, Wei Ke, Pengxu Wei, Liang Lin
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19430v1

Current AI-Generated Image (AIGI) detection approaches predominantly rely on binary classification to distinguish real from synthetic images, often lacking interpretable or convincing evidence to substantiate their decisions. This limitation stems from existing AIGI detection benchmarks, which, despite featuring a broad collection of synthetic images, remain restricted in their coverage of artifact diversity and lack detailed, localized annotations. To bridge this gap, we introduce a fine-grained benchmark towards eXplainable AI-Generated image Detection, named X-AIGD, which provides pixel-level, categorized annotations of perceptual artifacts, spanning low-level distortions, high-level semantics, and cognitive-level counterfactuals. These comprehensive annotations facilitate fine-grained interpretability evaluation and deeper insight into model decision-making processes. Our extensive investigation using X-AIGD provides several key insights: (1) Existing AIGI detectors demonstrate negligible reliance on perceptual artifacts, even at the most basic distortion level. (2) While AIGI detectors can be trained to identify specific artifacts, they still substantially base their judgment on uninterpretable features. (3) Explicitly aligning model attention with artifact regions can increase the interpretability and generalization of detectors. The data and code are available at: https://github.com/Coxy7/X-AIGD.

---

### Task-Centric Policy Optimization from Misaligned Motion Priors

Authors: Ziang Zheng, Kai Feng, Yi Nie, Shentao Qin
Published: 2026-01-27
Categories: cs.RO, cs.LG
arXiv: https://arxiv.org/abs/2601.19411v2

Humanoid control often leverages motion priors from human demonstrations to encourage natural behaviors. However, such demonstrations are frequently suboptimal or misaligned with robotic tasks due to embodiment differences, retargeting errors, and task-irrelevant variations, causing naïve imitation to degrade task performance. Conversely, task-only reinforcement learning admits many task-optimal solutions, often resulting in unnatural or unstable motions. This exposes a fundamental limitation of linear reward mixing in adversarial imitation learning. We propose \emph{Task-Centric Motion Priors} (TCMP), a task-priority adversarial imitation framework that treats imitation as a conditional regularizer rather than a co-equal objective. TCMP maximizes task improvement while incorporating imitation signals only when they are compatible with task progress, yielding an adaptive, geometry-aware update that preserves task-feasible descent and suppresses harmful imitation under misalignment. We provide theoretical analysis of gradient conflict and task-priority stationary points, and validate our claims through humanoid control experiments demonstrating robust task performance with consistent motion style under noisy demonstrations.

---

### Do LLMs Truly Benefit from Longer Context in Automatic Post-Editing?

Authors: Ahrii Kim, Seong-heum Kim
Published: 2026-01-27
Categories: cs.CL, cs.HC
arXiv: https://arxiv.org/abs/2601.19410v3

Automatic post-editing (APE) aims to refine machine translations by correcting residual errors. Although recent large language models (LLMs) demonstrate strong translation capabilities, their effectiveness for APE--especially under document-level context--remains insufficiently understood. We present a systematic comparison of proprietary and open-weight LLMs under a naive document-level prompting setup, analyzing APE quality, contextual behavior, robustness, and efficiency. Our results show that proprietary LLMs achieve near human-level APE quality even with simple one-shot prompting, regardless of whether document context is provided. While these models exhibit higher robustness to data poisoning attacks than open-weight counterparts, this robustness also reveals a limitation: they largely fail to exploit document-level context for contextual error correction. Furthermore, standard automatic metrics do not reliably reflect these qualitative improvements, highlighting the continued necessity of human evaluation. Despite their strong performance, the substantial cost and latency overheads of proprietary LLMs render them impractical for real-world APE deployment. Overall, our findings elucidate both the promise and current limitations of LLM-based document-aware APE, and point toward the need for more efficient long-context modeling approaches for translation refinement.

---

### Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation

Authors: Kaipeng Fang, Weiqing Liang, Yuyang Li, Ji Zhang, Pengpeng Zeng, Heng Tao Shen, Jingkuan Song, Lianli Gao
Published: 2026-01-27
Categories: cs.RO, cs.AI
arXiv: https://arxiv.org/abs/2601.19406v2

Real-robot demonstrations are prohibitively expensive, while simulation data and real-world human demonstrations are both scalable but each leaves a distinct gap: simulation suffers from a sim-to-real visual gap, and human data suffers from a human-to-robot embodiment gap. In this work, we identify a natural yet underexplored complementarity between these sources: simulation contributes robot-valid actions absent in human data, while human data provides real-world observations that simulation struggles to render. Building on this insight, we present SimHum, a co-training recipe that extracts kinematic priors from simulation and visual priors from human observations, then fine-tunes on a small real-robot dataset. SimHum exhibits strong scene-generalizable and data-efficient capabilities. With only 80 real-robot episodes per task, it achieves 62.5% success on held-out OOD scenes across four bimanual tabletop tasks, 53.7% higher than Real only in absolute success rate. Moreover, in a controlled data-collection study with matched collection time, SimHum improves over the best single-source pre-training baseline by 35.0% in absolute success rate. Project page: https://kaipengfang.github.io/sim-and-human/

---

### RPO:Reinforcement Fine-Tuning with Partial Reasoning Optimization

Authors: Hongzhu Yi, Xinming Wang, Zhenghao zhang, Tianyu Zong, Yuanxiang Wang, Jun Xie, Tao Yu, Haopeng Jin, Kaixin Xu, Feng Chen, Jiahuan Chen, Yujia Yang et al.
Published: 2026-01-27
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.19404v2

Within the domain of large language models, reinforcement fine-tuning algorithms necessitate the generation of a complete reasoning trajectory beginning from the input query, which incurs significant computational overhead during the rollout phase of training. To address this issue, we analyze the impact of different segments of the reasoning path on the correctness of the final result and, based on these insights, propose Reinforcement Fine-Tuning with Partial Reasoning Optimization (RPO), a plug-and-play reinforcement fine-tuning algorithm. Unlike traditional reinforcement fine-tuning algorithms that generate full reasoning paths, RPO trains the model by generating suffixes of the reasoning path using experience cache. During the rollout phase of training, RPO reduces token generation in this phase by approximately 95%, greatly lowering the theoretical time overhead. Compared with full-path reinforcement fine-tuning algorithms, RPO reduces the training time of the 1.5B model by 90% and the 7B model by 72%. At the same time, it can be integrated with typical algorithms such as GRPO and DAPO, enabling them to achieve training acceleration while maintaining performance comparable to the original algorithms. Our code is open-sourced at https://github.com/yhz5613813/RPO.

---

### Learned split-spectrum metalens for obstruction-free broadband imaging in the visible

Authors: Seungwoo Yoon, Dohyun Kang, Eunsue Choi, Sohyun Lee, Seoyeon Kim, Minho Choi, Hyeonsu Heo, Dong-ha Shin, Suha Kwak, Arka Majumdar, Junsuk Rho, Seung-Hwan Baek
Published: 2026-01-27
Categories: physics.optics, cs.AI, cs.CV, physics.app-ph
arXiv: https://arxiv.org/abs/2601.19403v1

Obstructions such as raindrops, fences, or dust degrade captured images, especially when mechanical cleaning is infeasible. Conventional solutions to obstructions rely on a bulky compound optics array or computational inpainting, which compromise compactness or fidelity. Metalenses composed of subwavelength meta-atoms promise compact imaging, but simultaneous achievement of broadband and obstruction-free imaging remains a challenge, since a metalens that images distant scenes across a broadband spectrum cannot properly defocus near-depth occlusions. Here, we introduce a learned split-spectrum metalens that enables broadband obstruction-free imaging. Our approach divides the spectrum of each RGB channel into pass and stop bands with multi-band spectral filtering and learns the metalens to focus light from far objects through pass bands, while filtering focused near-depth light through stop bands. This optical signal is further enhanced using a neural network. Our learned split-spectrum metalens achieves broadband and obstruction-free imaging with relative PSNR gains of 32.29% and improves object detection and semantic segmentation accuracies with absolute gains of +13.54% mAP, +48.45% IoU, and +20.35% mIoU over a conventional hyperbolic design. This promises robust obstruction-free sensing and vision for space-constrained systems, such as mobile robots, drones, and endoscopes.

---

### PROTEUS: SLA-Aware Routing via Lagrangian RL for Multi-LLM Serving Systems

Authors: Amit Singh Bhatti, Vishal Vaddina, Dagnachew Birru
Published: 2026-01-27
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.19402v3

Production LLM deployments serve diverse workloads where cost and quality requirements vary by customer tier, time of day, and query criticality. Model serving systems accept latency SLOs directly. LLM routers do not. They force operators to tune parameters offline and guess what accuracy might result. The relationship between parameters and outcomes is indirect, non-monotonic, and dataset-dependent. Operators need to specify accuracy targets, not infer them from opaque settings. We present PROTEUS (Polymorphic Router for Operational Target Enforcement with Unified SLA), a router that accepts accuracy targets tau as runtime input. PROTEUS uses Lagrangian dual control. A learned dual variable lambda tracks constraint violations during training and conditions the policy network. This lets the router translate specified tau values into routing decisions that satisfy them. A single trained model serves the full accuracy spectrum without retraining.We evaluate on RouterBench (11 models, 405K queries) and SPROUT (14 models, 45K queries). PROTEUS achieves consistent floor compliance where accuracy meets or exceeds tau. The target-response correlation reaches 0.97 to 0.98. The closest baseline, OmniRouter, meets floors only 22% of the time despite also using Lagrangian optimization. PROTEUS operates across tau in (0.85, 0.95) from a single model. On RouterBench it achieves 90.1% accuracy, within 1.3% of oracle. On SPROUT it achieves 94.0% accuracy, within 4.6% of oracle. Cost savings reach 89.8% versus the best fixed model.

---

### Improved Convergence Rates of Muon Optimizer for Nonconvex Optimization

Authors: Shuntaro Nagashima, Hideaki Iiduka
Published: 2026-01-27
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2601.19400v3

The Muon optimizer has recently attracted attention due to its orthogonalized first-order updates, and a deeper theoretical understanding of its convergence behavior is essential for guiding practical applications; however, existing convergence guarantees are either coarse or obtained under restrictive analytical settings. In this work, we establish sharper convergence guarantees for the Muon optimizer through a direct and simplified analysis that does not rely on restrictive assumptions on the update rule. Our results improve upon existing bounds by achieving faster convergence rates while covering a broader class of problem settings. These findings provide a more accurate theoretical characterization of Muon and offer insights applicable to a broader class of orthogonalized first-order methods.

---

### Residual Tokens Enhance Masked Autoencoders for Speech Modeling

Authors: Samir Sadok, Stéphane Lathuilière, Xavier Alameda-Pineda
Published: 2026-01-27
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.19399v1

Recent speech modeling relies on explicit attributes such as pitch, content, and speaker identity, but these alone cannot capture the full richness of natural speech. We introduce RT-MAE, a novel masked autoencoder framework that augments the supervised attributes-based modeling with unsupervised residual trainable tokens, designed to encode the information not explained by explicit labeled factors (e.g., timbre variations, noise, emotion etc). Experiments show that RT-MAE improves reconstruction quality, preserving content and speaker similarity while enhancing expressivity. We further demonstrate its applicability to speech enhancement, removing noise at inference while maintaining controllability and naturalness.

---

### SEAFormer: A Spatial Proximity and Edge-Aware Transformer for Real-World Vehicle Routing Problems

Authors: Saeed Nasehi Basharzad, Farhana Choudhury, Egemen Tanin
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19395v2

Real-world Vehicle Routing Problems (RWVRPs) require solving complex, sequence-dependent challenges at scale with constraints such as delivery time window, replenishment or recharging stops, asymmetric travel cost, etc. While recent neural methods achieve strong results on large-scale classical VRP benchmarks, they struggle to address RWVRPs because their strategies overlook sequence dependencies and underutilize edge-level information, which are precisely the characteristics that define the complexity of RWVRPs. We present SEAFormer, a novel transformer that incorporates both node-level and edge-level information in decision-making through two key innovations. First, our Clustered Proximity Attention (CPA) exploits locality-aware clustering to reduce the complexity of attention from $O(n^2)$ to $O(n)$ while preserving global perspective, allowing SEAFormer to efficiently train on large instances. Second, our lightweight edge-aware module captures pairwise features through residual fusion, enabling effective incorporation of edge-based information and faster convergence. Extensive experiments across four RWVRP variants with various scales demonstrate that SEAFormer achieves superior results over state-of-the-art methods. Notably, SEAFormer is the first neural method to solve 1,000+ node RWVRPs effectively, while also achieving superior performance on classic VRPs, making it a versatile solution for both research benchmarks and real-world applications.

---

### DSP-Reg: Domain-Sensitive Parameter Regularization for Robust Domain Generalization

Authors: Xudong Han, Senkang Hu, Yihang Tao, Yu Guo, Philip Birch, Sam Tak Wu Kwong, Yuguang Fang
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19394v1

Domain Generalization (DG) is a critical area that focuses on developing models capable of performing well on data from unseen distributions, which is essential for real-world applications. Existing approaches primarily concentrate on learning domain-invariant features, which assume that a model robust to variations in the source domains will generalize well to unseen target domains. However, these approaches neglect a deeper analysis at the parameter level, which makes the model hard to explicitly differentiate between parameters sensitive to domain shifts and those robust, potentially hindering its overall ability to generalize. In order to address these limitations, we first build a covariance-based parameter sensitivity analysis framework to quantify the sensitivity of each parameter in a model to domain shifts. By computing the covariance of parameter gradients across multiple source domains, we can identify parameters that are more susceptible to domain variations, which serves as our theoretical foundation. Based on this, we propose Domain-Sensitive Parameter Regularization (DSP-Reg), a principled framework that guides model optimization by a soft regularization technique that encourages the model to rely more on domain-invariant parameters while suppressing those that are domain-specific. This approach provides a more granular control over the model's learning process, leading to improved robustness and generalization to unseen domains. Extensive experiments on benchmarks, such as PACS, VLCS, OfficeHome, and DomainNet, demonstrate that DSP-Reg outperforms state-of-the-art approaches, achieving an average accuracy of 66.7\% and surpassing all baselines.

---

### High-quality data augmentation for code comment classification

Authors: Thomas Borsani, Andrea Rosani, Giuseppe Di Fatta
Published: 2026-01-27
Categories: cs.SE, cs.LG
arXiv: https://arxiv.org/abs/2601.19383v1

Code comments serve a crucial role in software development for documenting functionality, clarifying design choices, and assisting with issue tracking. They capture developers' insights about the surrounding source code, serving as an essential resource for both human comprehension and automated analysis. Nevertheless, since comments are in natural language, they present challenges for machine-based code understanding. To address this, recent studies have applied natural language processing (NLP) and deep learning techniques to classify comments according to developers' intentions. However, existing datasets for this task suffer from size limitations and class imbalance, as they rely on manual annotations and may not accurately represent the distribution of comments in real-world codebases. To overcome this issue, we introduce new synthetic oversampling and augmentation techniques based on high-quality data generation to enhance the NLBSE'26 challenge datasets. Our Synthetic Quality Oversampling Technique and Augmentation Technique (Q-SYNTH) yield promising results, improving the base classifier by $2.56\%$.

---

### Tri-Reader: An Open-Access, Multi-Stage AI Pipeline for First-Pass Lung Nodule Annotation in Screening CT

Authors: Fakrul Islam Tushar, Joseph Y. Lo
Published: 2026-01-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.19380v2

Using multiple open-access models trained on public datasets, we developed Tri-Reader, a comprehensive, freely available pipeline that integrates lung segmentation, nodule detection, and malignancy classification into a unified tri-stage workflow. The pipeline is designed to prioritize sensitivity while reducing the candidate burden for annotators. To ensure accuracy and generalizability across diverse practices, we evaluated Tri-Reader on multiple internal and external datasets as compared with expert annotations and dataset-provided reference standards.

---

### Optimal Asynchronous Stochastic Nonconvex Optimization under Heavy-Tailed Noise

Authors: Yidong Wu, Luo Luo
Published: 2026-01-27
Categories: math.OC, cs.LG
arXiv: https://arxiv.org/abs/2601.19379v1

This paper considers the problem of asynchronous stochastic nonconvex optimization with heavy-tailed gradient noise and arbitrarily heterogeneous computation times across workers. We propose an asynchronous normalized stochastic gradient descent algorithm with momentum. The analysis show that our method achieves the optimal time complexity under the assumption of bounded $p$th-order central moment with $p\in(1,2)$. We also provide numerical experiments to show the effectiveness of proposed method.

---

### Establishing dermatopathology encyclopedia DermpathNet with Artificial Intelligence-Based Workflow

Authors: Ziyang Xu, Mingquan Lin, Yiliang Zhou, Zihan Xu, Seth J. Orlow, Shane A. Meehan, Alexandra Flamm, Ata S. Moshiri, Yifan Peng
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19378v2

Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and dermatopathology trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6% for the deep learning approach, 61.0% for the keyword-based retrieval method, and 90.4% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.

---

### Teaching Machine Learning Fundamentals with LEGO Robotics

Authors: Viacheslav Sydora, Guner Dilsad Er, Michael Muehlebach
Published: 2026-01-27
Categories: cs.RO, cs.AI, cs.CY, cs.HC, cs.LG
arXiv: https://arxiv.org/abs/2601.19376v2

This paper presents the web-based platform Machine Learning with Bricks and an accompanying two-day course designed to teach machine learning concepts to students aged 12 to 17 through programming-free robotics activities. Machine Learning with Bricks is an open source platform and combines interactive visualizations with LEGO robotics to teach three core algorithms: KNN, linear regression, and Q-learning. Students learn by collecting data, training models, and interacting with robots via a web-based interface. Pre- and post-surveys with 14 students indicate statistically significant improvements in self-reported understanding of machine learning algorithms, changes in AI-related terminology toward more technical language, high platform usability, and increased motivation for continued learning. This work suggests that tangible, visualization-based approaches can make machine learning concepts accessible and engaging for young learners while maintaining technical depth. The platform is freely available at https://learning-and-dynamics.github.io/ml-with-bricks/, with video tutorials guiding students through the experiments at https://youtube.com/playlist?list=PLx1grFu4zAcwfKKJZ1Ux4LwRqaePCOA2J.

---

### Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection

Authors: Quy-Anh Dang, Chris Ngo
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19375v1

Despite significant progress in alignment, large language models (LLMs) remain vulnerable to adversarial attacks that elicit harmful behaviors. Activation steering techniques offer a promising inference-time intervention approach, but existing methods suffer from critical limitations: activation addition requires careful coefficient tuning and is sensitive to layer-specific norm variations, while directional ablation provides only binary control. Recent work on Angular Steering introduces continuous control via rotation in a 2D subspace, but its practical implementation violates norm preservation, causing distribution shift and generation collapse, particularly in models below 7B parameters. We propose Selective Steering, which addresses these limitations through two key innovations: (1) a mathematically rigorous norm-preserving rotation formulation that maintains activation distribution integrity, and (2) discriminative layer selection that applies steering only where feature representations exhibit opposite-signed class alignment. Experiments across nine models demonstrate that Selective Steering achieves 5.5x higher attack success rates than prior methods while maintaining zero perplexity violations and approximately 100\% capability retention on standard benchmarks. Our approach provides a principled, efficient framework for controllable and stable LLM behavior modification. Code: https://github.com/knoveleng/steering

---

### Divergence-Free Diffusion Models for Incompressible Fluid Flows

Authors: Wilfried Genuist, Éric Savin, Filippo Gatti, Didier Clouteau
Published: 2026-01-27
Categories: physics.flu-dyn, stat.ML
arXiv: https://arxiv.org/abs/2601.19368v1

Generative diffusion models are extensively used in unsupervised and self-supervised machine learning with the aim to generate new samples from a probability distribution estimated with a set of known samples. They have demonstrated impressive results in replicating dense, real-world contents such as images, musical pieces, or human languages. This work investigates their application to the numerical simulation of incompressible fluid flows, with a view toward incorporating physical constraints such as incompressibility in the probabilistic forecasting framework enabled by generative networks. For that purpose, we explore different conditional, score-based diffusion models where the divergence-free constraint is imposed by the Leray spectral projector, and autoregressive conditioning is aimed at stabilizing the forecasted flow snapshots at distant time horizons. The proposed models are run on a benchmark turbulence problem, namely a Kolmogorov flow, which allows for a fairly detailed analytical and numerical treatment and thus simplifies the evaluation of the numerical methods used to simulate it. Numerical experiments of increasing complexity are performed in order to compare the advantages and limitations of the diffusion models we have implemented and appraise their performances, including: (i) in-distribution assessment over the same time horizons and for similar physical conditions as the ones seen during training; (ii) rollout predictions over time horizons unseen during training; and (iii) out-of-distribution tests for forecasting flows markedly different from those seen during training. In particular, these results illustrate the ability of diffusion models to reproduce the main statistical characteristics of Kolmogorov turbulence in scenarios departing from the ones they were trained on.

---

### CHEHAB RL: Learning to Optimize Fully Homomorphic Encryption Computations

Authors: Bilel Sefsaf, Abderraouf Dandani, Abdessamed Seddiki, Arab Mohammed, Eduardo Chielle, Michail Maniatakos, Riyadh Baghdadi
Published: 2026-01-27
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.19367v1

Fully Homomorphic Encryption (FHE) enables computations directly on encrypted data, but its high computational cost remains a significant barrier. Writing efficient FHE code is a complex task requiring cryptographic expertise, and finding the optimal sequence of program transformations is often intractable. In this paper, we propose CHEHAB RL, a novel framework that leverages deep reinforcement learning (RL) to automate FHE code optimization. Instead of relying on predefined heuristics or combinatorial search, our method trains an RL agent to learn an effective policy for applying a sequence of rewriting rules to automatically vectorize scalar FHE code while reducing instruction latency and noise growth. The proposed approach supports the optimization of both structured and unstructured code. To train the agent, we synthesize a diverse dataset of computations using a large language model (LLM). We integrate our proposed approach into the CHEHAB FHE compiler and evaluate it on a suite of benchmarks, comparing its performance against Coyote, a state-of-the-art vectorizing FHE compiler. The results show that our approach generates code that is $5.3\times$ faster in execution, accumulates $2.54\times$ less noise, while the compilation process itself is $27.9\times$ faster than Coyote (geometric means).

---

### Pareto-Guided Optimization for Uncertainty-Aware Medical Image Segmentation

Authors: Jinming Zhang, Youpeng Yang, Xi Yang, Haosen Shi, Yuyao Yan, Qiufeng Wang, Guangliang Cheng, Kaizhu Huang
Published: 2026-01-27
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.19365v2

Uncertainty in medical image segmentation is inherently non-uniform, with boundary regions exhibiting substantially higher ambiguity than interior areas. Conventional training treats all pixels equally, leading to unstable optimization during early epochs when predictions are unreliable. We argue that this instability hinders convergence toward Pareto-optimal solutions and propose a region-wise curriculum strategy that prioritizes learning from certain regions and gradually incorporates uncertain ones, reducing gradient variance. Methodologically, we introduce a Pareto-consistent loss that balances trade-offs between regional uncertainties by adaptively reshaping the loss landscape and constraining convergence dynamics between interior and boundary regions; this guides the model toward Pareto-approximate solutions. To address boundary ambiguity, we further develop a fuzzy labeling mechanism that maintains binary confidence in non-boundary areas while enabling smooth transitions near boundaries, stabilizing gradients, and expanding flat regions in the loss surface. Experiments on brain metastasis and non-metastatic tumor segmentation show consistent improvements across multiple configurations, with our method outperforming traditional crisp-set approaches in all tumor subregions.

---

### Revisiting Parameter Server in LLM Post-Training

Authors: Xinyi Wan, Penghui Qi, Guangxing Huang, Chaoyi Ruan, Min Lin, Jialin Li
Published: 2026-01-27
Categories: cs.DC, cs.AI
arXiv: https://arxiv.org/abs/2601.19362v1

Modern data parallel (DP) training favors collective communication over parameter servers (PS) for its simplicity and efficiency under balanced workloads. However, the balanced workload assumption no longer holds in large language model (LLM) post-training due to the high variance in sequence lengths. Under imbalanced workloads, collective communication creates synchronization barriers, leading to under-utilization of devices with smaller workloads. This change in training dynamics calls for a revisit of the PS paradigm for its robustness to such imbalance. We propose \textbf{On-Demand Communication (ODC)}, which adapts PS into Fully Sharded Data Parallel (FSDP) by replacing collective all-gather and reduce-scatter with direct point-to-point communication. Compared to FSDP, ODC reduces the synchronization barrier from once per layer to once per minibatch and decouples the workload on each device so that faster workers are not stalled. It also enables simpler and more effective load balancing at the minibatch level. Across diverse LLM post-training tasks, ODC consistently improves device utilization and training throughput, achieving up to a 36\% speedup over standard FSDP. These results demonstrate that ODC is a superior fit for the prevalent imbalanced workloads in LLM post-training. Our implementation of ODC and integration with FSDP is open-sourced at https://github.com/sail-sg/odc.

---

### Binary Token-Level Classification with DeBERTa for All-Type MWE Identification: A Lightweight Approach with Linguistic Enhancement

Authors: Diego Rossini, Lonneke van der Plas
Published: 2026-01-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.19360v1

We present a comprehensive approach for multiword expression (MWE) identification that combines binary token-level classification, linguistic feature integration, and data augmentation. Our DeBERTa-v3-large model achieves 69.8% F1 on the CoAM dataset, surpassing the best results (Qwen-72B, 57.8% F1) on this dataset by 12 points while using 165x fewer parameters. We achieve this performance by (1) reformulating detection as binary token-level START/END/INSIDE classification rather than span-based prediction, (2) incorporating NP chunking and dependency features that help discontinuous and NOUN-type MWEs identification, and (3) applying oversampling that addresses severe class imbalance in the training data. We confirm the generalization of our method on the STREUSLE dataset, achieving 78.9% F1. These results demonstrate that carefully designed smaller models can substantially outperform LLMs on structured NLP tasks, with important implications for resource-constrained deployments.

---

### GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance

Authors: Zhixiao Wang, Chaofan Zhu, Qihan Feng, Jian Zhang, Xiaobin Rui, Philip S Yu
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19352v1

Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level and the algorithm-level. The former aims to synthesize minority-class nodes to mitigate quantity imbalance, while the latter tries to optimize the learning process to highlight minority classes. However, neither of them addresses the inherently imbalanced graph structure, which is a fundamental factor that incurs majority-class dominance and minority-class assimilation in GNNs. Our theoretical analysis further supports this critical insight. Therefore, we propose GraphSB (Graph Structural Balance), a novel framework that incorporates Structural Balance as a key strategy to address the underlying imbalanced graph structure before node synthesis. Structural Balance performs a two-stage structure optimization: Structure Enhancement that mines hard samples near decision boundaries through dual-view analysis and enhances connectivity for minority classes through adaptive augmentation, and Relation Diffusion that propagates the enhanced minority context while simultaneously capturing higher-order structural dependencies. Thus, GraphSB balances structural distribution before node synthesis, enabling more effective learning in GNNs. Extensive experiments demonstrate that GraphSB significantly outperforms the state-of-the-art methods. More importantly, the proposed Structural Balance can be seamlessly integrated into state-of-the-art methods as a simple plug-and-play module, increasing their accuracy by an average of 4.57%.

---

### Cross-Examination Framework: A Task-Agnostic Diagnostic for Information Fidelity in Text-to-Text Generation

Authors: Tathagata Raha, Clement Christophe, Nada Saadi, Hamza A Javed, Marco AF Pimentel, Ronnie Rajan, Praveenkumar Kanithi
Published: 2026-01-27
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.19350v1

Traditional metrics like BLEU and BERTScore fail to capture semantic fidelity in generative text-to-text tasks. We adapt the Cross-Examination Framework (CEF) for a reference-free, multi-dimensional evaluation by treating the source and candidate as independent knowledge bases. CEF generates verifiable questions from each text and performs a cross-examination to derive three interpretable scores: Coverage, Conformity, and Consistency. Validated across translation, summarization and clinical note-generation, our framework identifies critical errors, such as content omissions and factual contradictions, missed by standard metrics. A key contribution is a systematic robustness analysis to select a stable judge model. Crucially, the strong correlation between our reference-free and with-reference modes validates CEF's reliability without gold references. Furthermore, human expert validation demonstrates that CEF mismatching questions align with meaning-altering semantic errors higher than with non-semantic errors, particularly excelling at identifying entity-based and relational distortions.

---

### AMGFormer: Adaptive Multi-Granular Transformer for Brain Tumor Segmentation with Missing Modalities

Authors: Chengxiang Guo, Jian Wang, Junhua Fei, Xiao Li, Chunling Chen, Yun Jin
Published: 2026-01-27
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.19349v1

Multimodal MRI is essential for brain tumor segmentation, yet missing modalities in clinical practice cause existing methods to exhibit >40% performance variance across modality combinations, rendering them clinically unreliable. We propose AMGFormer, achieving significantly improved stability through three synergistic modules: (1) QuadIntegrator Bridge (QIB) enabling spatially adaptive fusion maintaining consistent predictions regardless of available modalities, (2) Multi-Granular Attention Orchestrator (MGAO) focusing on pathological regions to reduce background sensitivity, and (3) Modality Quality-Aware Enhancement (MQAE) preventing error propagation from corrupted sequences. On BraTS 2018, our method achieves 89.33% WT, 82.70% TC, 67.23% ET Dice scores with <0.5% variance across 15 modality combinations, solving the stability crisis. Single-modality ET segmentation shows 40-81% relative improvements over state-of-the-art methods. The method generalizes to BraTS 2020/2021, achieving up to 92.44% WT, 89.91% TC, 84.57% ET. The model demonstrates potential for clinical deployment with 1.2s inference. Code: https://github.com/guochengxiangives/AMGFormer.

---

### Robust Uncertainty Estimation under Distribution Shift via Difference Reconstruction

Authors: Xinran Xu, Li Rong Wang, Xiuyi Fan
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19341v1

Estimating uncertainty in deep learning models is critical for reliable decision-making in high-stakes applications such as medical imaging. Prior research has established that the difference between an input sample and its reconstructed version produced by an auxiliary model can serve as a useful proxy for uncertainty. However, directly comparing reconstructions with the original input is degraded by information loss and sensitivity to superficial details, which limits its effectiveness. In this work, we propose Difference Reconstruction Uncertainty Estimation (DRUE), a method that mitigates this limitation by reconstructing inputs from two intermediate layers and measuring the discrepancy between their outputs as the uncertainty score. To evaluate uncertainty estimation in practice, we follow the widely used out-of-distribution (OOD) detection paradigm, where in-distribution (ID) training data are compared against datasets with increasing domain shift. Using glaucoma detection as the ID task, we demonstrate that DRUE consistently achieves superior AUC and AUPR across multiple OOD datasets, highlighting its robustness and reliability under distribution shift. This work provides a principled and effective framework for enhancing model reliability in uncertain environments.

---

### SETA: Statistical Fault Attribution for Compound AI Systems

Authors: Sayak Chowdhury, Meenakshi D'Souza
Published: 2026-01-27
Categories: cs.AI, cs.LG, cs.SE
arXiv: https://arxiv.org/abs/2601.19337v1

Modern AI systems increasingly comprise multiple interconnected neural networks to tackle complex inference tasks. Testing such systems for robustness and safety entails significant challenges. Current state-of-the-art robustness testing techniques, whether black-box or white-box, have been proposed and implemented for single-network models and do not scale well to multi-network pipelines. We propose a modular robustness testing framework that applies a given set of perturbations to test data. Our testing framework supports (1) a component-wise system analysis to isolate errors and (2) reasoning about error propagation across the neural network modules. The testing framework is architecture and modality agnostic and can be applied across domains. We apply the framework to a real-world autonomous rail inspection system composed of multiple deep networks and successfully demonstrate how our approach enables fine-grained robustness analysis beyond conventional end-to-end metrics.

---

### From Observations to Events: Event-Aware World Model for Reinforcement Learning

Authors: Zhao-Han Peng, Shaohui Li, Zhi Li, Shulan Ruan, Yu Liu, You He
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19336v1

While model-based reinforcement learning (MBRL) improves sample efficiency by learning world models from raw observations, existing methods struggle to generalize across structurally similar scenes and remain vulnerable to spurious variations such as textures or color shifts. From a cognitive science perspective, humans segment continuous sensory streams into discrete events and rely on these key events for decision-making. Motivated by this principle, we propose the Event-Aware World Model (EAWM), a general framework that learns event-aware representations to streamline policy learning without requiring handcrafted labels. EAWM employs an automated event generator to derive events from raw observations and introduces a Generic Event Segmentor (GES) to identify event boundaries, which mark the start and end time of event segments. Through event prediction, the representation space is shaped to capture meaningful spatio-temporal transitions. Beyond this, we present a unified formulation of seemingly distinct world model architectures and show the broad applicability of our methods. Experiments on Atari 100K, Craftax 1M, and DeepMind Control 500K, DMC-GB2 500K demonstrate that EAWM consistently boosts the performance of strong MBRL baselines by 10%-45%, setting new state-of-the-art results across benchmarks. Our code is released at https://github.com/MarquisDarwin/EAWM.

---

### When Benchmarks Leak: Inference-Time Decontamination for LLMs

Authors: Jianzhe Chai, Yu Zhe, Jun Sakuma
Published: 2026-01-27
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.19334v1

Benchmark-based evaluation is the de facto standard for comparing large language models (LLMs). However, its reliability is increasingly threatened by test set contamination, where test samples or their close variants leak into training data and artificially inflate reported performance. To address this issue, prior work has explored two main lines of mitigation. One line attempts to identify and remove contaminated benchmark items before evaluation, but this inevitably alters the evaluation set itself and becomes unreliable when contamination is moderate or severe. The other line preserves the benchmark and instead suppresses contaminated behavior at evaluation time; however, such interventions often interfere with normal inference and lead to noticeable performance degradation on clean inputs. We propose DeconIEP, a decontamination framework that operates entirely during evaluation by applying small, bounded perturbations in the input embedding space. Guided by a relatively less-contaminated reference model, DeconIEP learns an instance-adaptive perturbation generator that steers the evaluated model away from memorization-driven shortcut pathways. Across multiple open-weight LLMs and benchmarks, extensive empirical results show that DeconIEP achieves strong decontamination effectiveness while incurring only minimal degradation in benign utility.

---

### Metric $k$-clustering using only Weak Comparison Oracles

Authors: Rahul Raychaudhury, Aryan Esmailpour, Sainyam Galhotra, Stavros Sintos
Published: 2026-01-27
Categories: cs.LG, cs.DS
arXiv: https://arxiv.org/abs/2601.19333v1

Clustering is a fundamental primitive in unsupervised learning. However, classical algorithms for $k$-clustering (such as $k$-median and $k$-means) assume access to exact pairwise distances -- an unrealistic requirement in many modern applications. We study clustering in the \emph{Rank-model (R-model)}, where access to distances is entirely replaced by a \emph{quadruplet oracle} that provides only relative distance comparisons. In practice, such an oracle can represent learned models or human feedback, and is expected to be noisy and entail an access cost. Given a metric space with $n$ input items, we design randomized algorithms that, using only a noisy quadruplet oracle, compute a set of $O(k \cdot \mathsf{polylog}(n))$ centers along with a mapping from the input items to the centers such that the clustering cost of the mapping is at most constant times the optimum $k$-clustering cost. Our method achieves a query complexity of $O(n\cdot k \cdot \mathsf{polylog}(n))$ for arbitrary metric spaces and improves to $O((n+k^2) \cdot \mathsf{polylog}(n))$ when the underlying metric has bounded doubling dimension. When the metric has bounded doubling dimension we can further improve the approximation from constant to $1+\varepsilon$, for any arbitrarily small constant $\varepsilon\in(0,1)$, while preserving the same asymptotic query complexity. Our framework demonstrates how noisy, low-cost oracles, such as those derived from large language models, can be systematically integrated into scalable clustering algorithms.

---

### Innovator-VL: A Multimodal Large Language Model for Scientific Discovery

Authors: Zichen Wen, Boxue Yang, Shuang Chen, Yaojie Zhang, Yuhang Han, Junlong Ke, Cong Wang, Yicheng Fu, Jiawang Zhao, Jiangchao Yao, Xi Fang, Zhen Wang et al.
Published: 2026-01-27
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.19325v1

We present Innovator-VL, a scientific multimodal large language model designed to advance understanding and reasoning across diverse scientific domains while maintaining excellent performance on general vision tasks. Contrary to the trend of relying on massive domain-specific pretraining and opaque pipelines, our work demonstrates that principled training design and transparent methodology can yield strong scientific intelligence with substantially reduced data requirements. (i) First, we provide a fully transparent, end-to-end reproducible training pipeline, covering data collection, cleaning, preprocessing, supervised fine-tuning, reinforcement learning, and evaluation, along with detailed optimization recipes. This facilitates systematic extension by the community. (ii) Second, Innovator-VL exhibits remarkable data efficiency, achieving competitive performance on various scientific tasks using fewer than five million curated samples without large-scale pretraining. These results highlight that effective reasoning can be achieved through principled data selection rather than indiscriminate scaling. (iii) Third, Innovator-VL demonstrates strong generalization, achieving competitive performance on general vision, multimodal reasoning, and scientific benchmarks. This indicates that scientific alignment can be integrated into a unified model without compromising general-purpose capabilities. Our practices suggest that efficient, reproducible, and high-performing scientific multimodal models can be built even without large-scale data, providing a practical foundation for future research.

---

### Predictive Accuracy versus Interpretability in Energy Markets: A Copula-Enhanced TVP-SVAR Analysis

Authors: Fredy Pokou, Jules Sadefo Kamdem, Kpante Emmanuel Gnandi
Published: 2026-01-27
Categories: q-fin.CP, q-fin.ST, stat.ML
arXiv: https://arxiv.org/abs/2601.19321v1

This paper investigates whether structural econometric models can rival machine learning in forecasting energy--macro dynamics while retaining causal interpretability. Using monthly data from 1999 to 2025, we develop a unified framework that integrates Time-Varying Parameter Structural VARs (TVP-SVAR) with advanced dependence structures, including DCC-GARCH, t-copulas, and mixed Clayton--Frank--Gumbel copulas. These models are empirically evaluated against leading machine learning techniques Gaussian Process Regression (GPR), Artificial Neural Networks, Random Forests, and Support Vector Regression across seven macro-financial and energy variables, with Brent crude oil as the central asset. The findings reveal three major insights. First, TVP-SVAR consistently outperforms standard VAR models, confirming structural instability in energy transmission channels. Second, copula-based extensions capture non-linear and tail dependence more effectively than symmetric DCC models, particularly during periods of macroeconomic stress. Third, despite their methodological differences, copula-enhanced econometric models and GPR achieve statistically equivalent predictive accuracy (t-test p = 0.8444). However, only the econometric approach provides interpretable impulse responses, regime shifts, and tail-risk diagnostics. We conclude that machine learning can replicate predictive performance but cannot substitute the explanatory power of structural econometrics. This synthesis offers a pathway where AI accuracy and economic interpretability jointly inform energy policy and risk management.

---

### StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths

Authors: Tianyi Chen, Sihan Chen, Xiaoyi Qu, Dan Zhao, Ruomei Yan, Jongwoo Ko, Luming Liang, Pashmina Cameron
Published: 2026-01-27
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.19320v2

Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints, yet achieving stable and robust optimization at ultra-low bitwidths remains challenging. Common approaches based on the straight-through estimator (STE) or soft quantizers often suffer from gradient mismatch, instability, or high computational overhead. As such, we propose StableQAT, a unified and efficient QAT framework that stabilizes training in ultra low-bit settings via a novel, lightweight, and theoretically grounded surrogate for backpropagation derived from a discrete Fourier analysis of the rounding operator. StableQAT strictly generalizes STE as the latter arises as a special case of our more expressive surrogate family, yielding smooth, bounded, and inexpensive gradients that improve QAT training performance and stability across various hyperparameter choices. In experiments, StableQAT exhibits stable and efficient QAT at 2-4 bit regimes, demonstrating improved training stability, robustness, and superior performance with negligible training overhead against standard QAT techniques. Our code is available at https://github.com/microsoft/StableQAT.

---

### Perception-to-Pursuit: Track-Centric Temporal Reasoning for Open-World Drone Detection and Autonomous Chasing

Authors: Venkatakrishna Reddy Oruganti
Published: 2026-01-27
Categories: cs.RO, cs.CV
arXiv: https://arxiv.org/abs/2601.19318v2

Autonomous drone pursuit requires not only detecting drones but also predicting their trajectories in a manner that enables kinematically feasible interception. Existing tracking methods optimize for prediction accuracy but ignore pursuit feasibility, resulting in trajectories that are physically impossible to intercept 99.9% of the time. We propose Perception-to-Pursuit (P2P), a track-centric temporal reasoning framework that bridges detection and actionable pursuit planning. Our method represents drone motion as compact 8-dimensional tokens capturing velocity, acceleration, scale, and smoothness, enabling a 12-frame causal transformer to reason about future behavior. We introduce the Intercept Success Rate (ISR) metric to measure pursuit feasibility under realistic interceptor constraints. Evaluated on the Anti-UAV-RGBT dataset with 226 real drone sequences, P2P achieves 28.12 pixel average displacement error and 0.597 ISR, representing a 77% improvement in trajectory prediction and 597x improvement in pursuit feasibility over tracking-only baselines, while maintaining perfect drone classification accuracy (100%). Our work demonstrates that temporal reasoning over motion patterns enables both accurate prediction and actionable pursuit planning.

---

### Generalizable IoT Traffic Representations for Cross-Network Device Identification

Authors: Arunan Sivanathan, David Warren, Deepak Mishra, Sushmita Ruj, Natasha Fernandes, Quan Z. Sheng, Minh Tran, Ben Luo, Daniel Coscia, Gustavo Batista, Hassan Habibi Gharakaheili
Published: 2026-01-27
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.19315v1

Machine learning models have demonstrated strong performance in classifying network traffic and identifying Internet-of-Things (IoT) devices, enabling operators to discover and manage IoT assets at scale. However, many existing approaches rely on end-to-end supervised pipelines or task-specific fine-tuning, resulting in traffic representations that are tightly coupled to labeled datasets and deployment environments, which can limit generalizability. In this paper, we study the problem of learning generalizable traffic representations for IoT device identification. We design compact encoder architectures that learn per-flow embeddings from unlabeled IoT traffic and evaluate them using a frozen-encoder protocol with a simple supervised classifier. Our specific contributions are threefold. (1) We develop unsupervised encoder--decoder models that learn compact traffic representations from unlabeled IoT network flows and assess their quality through reconstruction-based analysis. (2) We show that these learned representations can be used effectively for IoT device-type classification using simple, lightweight classifiers trained on frozen embeddings. (3) We provide a systematic benchmarking study against the state-of-the-art pretrained traffic encoders, showing that larger models do not necessarily yield more robust representations for IoT traffic. Using more than 18 million real IoT traffic flows collected across multiple years and deployment environments, we learn traffic representations from unlabeled data and evaluate device-type classification on disjoint labeled subsets, achieving macro F1-scores exceeding 0.9 for device-type classification and demonstrating robustness under cross-environment deployment.

---