# Research Papers — 2026-01 · bundle page 74 of 189 > Full-text markdown of papers #3651–3700 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/74 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/73.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/75.md) ### USDs: A universal stabilizer decoder framework using symmetry Authors: Hoshitaro Ohnishi, Hideo Mukai Published: 2026-01-21 Categories: quant-ph, cs.LG arXiv: https://arxiv.org/abs/2601.15361v2 Quantum error correction is indispensable to achieving reliable quantum computation. When quantum information is encoded redundantly, a larger Hilbert space is constructed using multiple physical qubits, and the computation is performed within a designated subspace. When applying deep learning to the decoding of quantum error-correcting codes, a key challenge arises from the non-uniqueness between the syndrome measurements provided to the decoder and the corresponding error patterns that constitute the ground-truth labels. Building upon prior work that addressed this issue for the toric code by re-optimizing the decoder with respect to the symmetry inherent in the parity-check structure, we generalize this approach to arbitrary stabilizer codes. In our experiments, we employed multilayer perceptrons to approximate continuous functions that complement the syndrome measurements of the Color code and the Golay code. Using these models, we performed decoder re-optimization for each code. For the Color code, we achieved an improvement of approximately 0.8% in decoding accuracy at a physical error rate of 5%, while for the Golay code the accuracy increased by about 0.1%. Furthermore, from the evaluation of the geometric and algebraic structures in the continuous function approximation for each code, we showed that the design of generalized continuous functions is advantageous for learning the geometric structure inherent in the code. Our results also indicate that approximations that faithfully reproduce the code structure can have a significant impact on the effectiveness of reoptimization. This study demonstrates that the re-optimization technique previously shown to be effective for the Toric code can be generalized to address the challenge of label degeneracy that arises when applying deep learning to the decoding of stabilizer codes. --- ### Robust X-Learner: Breaking the Curse of Imbalance and Heavy Tails via Robust Cross-Imputation Authors: Eichi Uehara Published: 2026-01-21 Categories: stat.ML, cs.LG, econ.EM, stat.ME arXiv: https://arxiv.org/abs/2601.15360v1 Estimating Heterogeneous Treatment Effects (HTE) in industrial applications such as AdTech and healthcare presents a dual challenge: extreme class imbalance and heavy-tailed outcome distributions. While the X-Learner framework effectively addresses imbalance through cross-imputation, we demonstrate that it is fundamentally vulnerable to "Outlier Smearing" when reliant on Mean Squared Error (MSE) minimization. In this failure mode, the bias from a few extreme observations ("whales") in the minority group is propagated to the entire majority group during the imputation step, corrupting the estimated treatment effect structure. To resolve this, we propose the Robust X-Learner (RX-Learner). This framework integrates a redescending γ-divergence objective -- structurally equivalent to the Welsch loss under Gaussian assumptions -- into the gradient boosting machinery. We further stabilize the non-convex optimization using a Proxy Hessian strategy grounded in Majorization-Minimization (MM) principles. Empirical evaluation on a semi-synthetic Criteo Uplift dataset demonstrates that the RX-Learner reduces the Precision in Estimation of Heterogeneous Effect (PEHE) metric by 98.6% compared to the standard X-Learner, effectively decoupling the stable "Core" population from the volatile "Periphery". --- ### High-Fidelity 3D Tooth Reconstruction by Fusing Intraoral Scans and CBCT Data via a Deep Implicit Representation Authors: Yi Zhu, Razmig Kechichian, Raphaël Richert, Satoshi Ikehata, Sébastien Valette Published: 2026-01-21 Categories: eess.IV, cs.CV arXiv: https://arxiv.org/abs/2601.15358v1 High-fidelity 3D tooth models are essential for digital dentistry, but must capture both the detailed crown and the complete root. Clinical imaging modalities are limited: Cone-Beam Computed Tomography (CBCT) captures the root but has a noisy, low-resolution crown, while Intraoral Scanners (IOS) provide a high-fidelity crown but no root information. A naive fusion of these sources results in unnatural seams and artifacts. We propose a novel, fully-automated pipeline that fuses CBCT and IOS data using a deep implicit representation. Our method first segments and robustly registers the tooth instances, then creates a hybrid proxy mesh combining the IOS crown and the CBCT root. The core of our approach is to use this noisy proxy to guide a class-specific DeepSDF network. This optimization process projects the input onto a learned manifold of ideal tooth shapes, generating a seamless, watertight, and anatomically coherent model. Qualitative and quantitative evaluations show our method uniquely preserves both the high-fidelity crown from IOS and the patient-specific root morphology from CBCT, overcoming the limitations of each modality and naive stitching. --- ### Q-Probe: Scaling Image Quality Assessment to High Resolution via Context-Aware Agentic Probing Authors: Xiang Li, Xueheng Li, Yu Wang, Xuanhua He, Zhangchi Hu, Chengjun Xie Published: 2026-01-21 Categories: eess.IV, cs.AI arXiv: https://arxiv.org/abs/2601.15356v6 Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior human preference alignment in Image Quality Assessment (IQA). However, existing RL-based IQA models typically rely on coarse-grained global views, failing to capture subtle local degradations in high-resolution scenarios. While emerging "Thinking with Images" paradigms enable multi-scale visual perception via zoom-in mechanisms, their direct adaptation to IQA induces spurious "cropping-implies-degradation" biases and misinterprets natural depth-of-field as artifacts. To address these challenges, we propose Q-Probe, the first agentic IQA framework designed to scale IQA to high resolution via context-aware probing. First, we construct Vista-Bench, a pioneering benchmark tailored for fine-grained local degradation analysis in high-resolution IQA settings. Furthermore, we propose a three-stage training paradigm that progressively aligns the model with human preferences, while simultaneously eliminating causal bias through a novel context-aware cropping strategy. Extensive experiments demonstrate that Q-Probe achieves state-of-the-art performance in high-resolution settings while maintaining superior efficacy across resolution scales. --- ### Reinforcement Learning in the Real World: A Survey of Statistical Challenges and Future Directions Authors: Asim H. Gazi, Yongyi Guo, Daiqi Gao, Ziping Xu, Kelly W. Zhang, Susan A. Murphy Published: 2026-01-21 Categories: stat.AP, cs.LG, stat.ML arXiv: https://arxiv.org/abs/2601.15353v2 Reinforcement learning (RL) has achieved remarkable success in real-world decision-making across diverse domains, including gaming, robotics, online advertising, public health, and natural language processing. Despite these advances, a substantial gap remains between RL research and its deployment in many practical settings. Two recurring challenges often underlie this gap. First, many settings offer limited opportunity for the agent to interact extensively with the target environment due to practical constraints. Second, many target environments often undergo substantial changes, requiring redesign and redeployment of RL systems (e.g., advancements in science and technology that change the landscape of healthcare delivery). Addressing these challenges and bridging the gap between basic research and application requires theory and methodology that directly inform the design, implementation, and continual improvement of RL systems in real-world settings. In this paper, we frame the application of RL in practice as a three-component process: (i) online learning and optimization during deployment, (ii) post- or between-deployment offline analyses, and (iii) repeated cycles of deployment and redeployment to continually improve the RL system. We provide a narrative review of recent advances that address the statistical challenges arising across these three components, including methods for enhancing sample efficiency during online deployment, maximizing data utility for post- or between-deployment inference, and designing sequences of deployments for continual improvement. We also outline future research directions in RL that are use-inspired -- aiming for impactful application of RL in practice. --- ### OmniSpectra: A Unified Foundation Model for Native Resolution Astronomical Spectra Authors: Md Khairul Islam, Judy Fox Published: 2026-01-21 Categories: astro-ph.IM, cs.AI arXiv: https://arxiv.org/abs/2601.15351v1 We present OmniSpectra, the first native-resolution foundation model for astronomy spectra. Unlike traditional models, which are limited to fixed-length input sizes or configurations, OmniSpectra handles spectra of any length at their original size, without resampling or interpolation. Despite the large-scale spectroscopic data from diverse surveys fueling the rapid growth of astronomy, existing foundation models are limited to a fixed wavelength range and specific instruments. OmniSpectra is the first foundation model to learn simultaneously from multiple real-world spectra surveys with different configurations at a large scale. We achieve this by designing a novel architecture with adaptive patching across variable lengths, sinusoidal global wavelength encoding, local positional embeddings through depthwise convolution, and validity-aware self-attention masks. Allowing us to learn multi-scale spatial patterns while skipping attention for invalid patches. Even with a limited training example, OmniSpectra demonstrates excellent zero-shot generalization compared to methods tailored for specific tasks. This transfer learning capability makes this model the state-of-the-art across various astronomy tasks, including source classification, redshift estimation, and properties prediction for stars and galaxies. OmniSpectra reduces the need for training individual models for different tasks from scratch, establishing itself as the next-generation astronomy foundation model. --- ### Abusive music and song transformation using GenAI and LLMs Authors: Jiyang Choi, Rohitash Chandra Published: 2026-01-21 Categories: cs.SD, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.15348v1 Repeated exposure to violence and abusive content in music and song content can influence listeners' emotions and behaviours, potentially normalising aggression or reinforcing harmful stereotypes. In this study, we explore the use of generative artificial intelligence (GenAI) and Large Language Models (LLMs) to automatically transform abusive words (vocal delivery) and lyrical content in popular music. Rather than simply muting or replacing a single word, our approach transforms the tone, intensity, and sentiment, thus not altering just the lyrics, but how it is expressed. We present a comparative analysis of four selected English songs and their transformed counterparts, evaluating changes through both acoustic and sentiment-based lenses. Our findings indicate that Gen-AI significantly reduces vocal aggressiveness, with acoustic analysis showing improvements in Harmonic to Noise Ratio, Cepstral Peak Prominence, and Shimmer. Sentiment analysis reduced aggression by 63.3-85.6\% across artists, with major improvements in chorus sections (up to 88.6\% reduction). The transformed versions maintained musical coherence while mitigating harmful content, offering a promising alternative to traditional content moderation that avoids triggering the "forbidden fruit" effect, where the censored content becomes more appealing simply because it is restricted. This approach demonstrates the potential for GenAI to create safer listening experiences while preserving artistic expression. --- ### Logic Programming on Knowledge Graph Networks And its Application in Medical Domain Authors: Chuanqing Wang, Zhenmin Zhao, Shanshan Du, Chaoqun Fei, Songmao Zhang, Ruqian Lu Published: 2026-01-21 Categories: cs.AI, cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.15347v1 The rash development of knowledge graph research has brought big driving force to its application in many areas, including the medicine and healthcare domain. However, we have found that the application of some major information processing techniques on knowledge graph still lags behind. This defect includes the failure to make sufficient use of advanced logic reasoning, advanced artificial intelligence techniques, special-purpose programming languages, modern probabilistic and statistic theories et al. on knowledge graphs development and application. In particular, the multiple knowledge graphs cooperation and competition techniques have not got enough attention from researchers. This paper develops a systematic theory, technique and application of the concept 'knowledge graph network' and its application in medical and healthcare domain. Our research covers its definition, development, reasoning, computing and application under different conditions such as unsharp, uncertain, multi-modal, vectorized, distributed, federated. Almost in each case we provide (real data) examples and experiment results. Finally, a conclusion of innovation is provided. --- ### APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping Authors: Jiwon Kang, Yeji Choi, JoungBin Lee, Wooseok Jang, Jinhyeok Choi, Taekeun Kang, Yongjae Park, Myungin Kim, Seungryong Kim Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15288v2 Face swapping aims to transfer the identity of a source face onto a target face while preserving target-specific attributes such as pose, expression, lighting, skin tone, and makeup. However, since real ground truth for face swapping is unavailable, achieving both accurate identity transfer and high-quality attribute preservation remains challenging. Recent diffusion-based approaches attempt to improve visual fidelity through conditional inpainting on masked target images, but the masked condition removes crucial appearance cues, resulting in plausible yet misaligned attributes. To address this limitation, we propose APPLE (Attribute-Preserving Pseudo-Labeling), a fully diffusion-based teacher-student framework for attribute-preserving face swapping. Our approach introduces a teacher design to produce pseudo-labels aligned with the target attributes through (1) a conditional deblurring formulation that improves the preservation of global attributes such as skin tone and illumination, and (2) an attribute-aware inversion scheme that further enhances fine-grained attribute preservation such as makeup. APPLE conditions the student on clean pseudo-labels rather than degraded masked inputs, enabling more faithful attribute preservation. As a result, APPLE achieves state-of-the-art performance in attribute preservation while maintaining competitive identity transferability. --- ### Towards Understanding Best Practices for Quantization of Vision-Language Models Authors: Gautom Das, Vincent La, Ethan Lau, Abhinav Shrivastava, Matthew Gwilliam Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15287v1 Large language models (LLMs) deliver impressive results for a variety of tasks, but state-of-the-art systems require fast GPUs with large amounts of memory. To reduce both the memory and latency of these systems, practitioners quantize their learned parameters, typically at half precision. A growing body of research focuses on preserving the model performance with more aggressive bit widths, and some work has been done to apply these strategies to other models, like vision transformers. In our study we investigate how a variety of quantization methods, including state-of-the-art GPTQ and AWQ, can be applied effectively to multimodal pipelines comprised of vision models, language models, and their connectors. We address how performance on captioning, retrieval, and question answering can be affected by bit width, quantization method, and which portion of the pipeline the quantization is used for. Results reveal that ViT and LLM exhibit comparable importance in model performance, despite significant differences in parameter size, and that lower-bit quantization of the LLM achieves high accuracy at reduced bits per weight (bpw). These findings provide practical insights for efficient deployment of MLLMs and highlight the value of exploration for understanding component sensitivities in multimodal models. Our code is available at https://github.com/gautomdas/mmq. --- ### Iterative Refinement Improves Compositional Image Generation Authors: Shantanu Jaiswal, Mihir Prabhudesai, Nikash Bhardwaj, Zheyang Qin, Amir Zadeh, Chuan Li, Katerina Fragkiadaki, Deepak Pathak Published: 2026-01-21 Categories: cs.CV, cs.AI, cs.LG, cs.RO arXiv: https://arxiv.org/abs/2601.15286v1 Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as parallel sampling with verifiers or simply increasing denoising steps, can improve prompt alignment but remain inadequate for richly compositional settings where many constraints must be satisfied. Inspired by the success of chain-of-thought reasoning in large language models, we propose an iterative test-time strategy in which a T2I model progressively refines its generations across multiple steps, guided by feedback from a vision-language model as the critic in the loop. Our approach is simple, requires no external tools or priors, and can be flexibly applied to a wide range of image generators and vision-language models. Empirically, we demonstrate consistent gains on image generation across benchmarks: a 16.9% improvement in all-correct rate on ConceptMix (k=7), a 13.8% improvement on T2I-CompBench (3D-Spatial category) and a 12.5% improvement on Visual Jenga scene decomposition compared to compute-matched parallel sampling. Beyond quantitative gains, iterative refinement produces more faithful generations by decomposing complex prompts into sequential corrections, with human evaluators preferring our method 58.7% of the time over 41.3% for the parallel baseline. Together, these findings highlight iterative self-correction as a broadly applicable principle for compositional image generation. Results and visualizations are available at https://iterative-img-gen.github.io/ --- ### Walk through Paintings: Egocentric World Models from Internet Priors Authors: Anurag Bagchi, Zhipeng Bao, Homanga Bharadhwaj, Yu-Xiong Wang, Pavel Tokmakov, Martial Hebert Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15284v2 What if a video generation model could not only imagine a plausible future, but the correct one -- accurately reflecting how the world changes with each action? We answer this by presenting the Egocentric World Model (EgoWM), a simple, architecture-agnostic method that transforms any pre-trained video diffusion model into an action-conditioned world model, enabling precisely controllable future prediction. Rather than training from scratch, we repurpose the rich world priors of Internet-scale video models by injecting appropriately compressed motor commands through lightweight conditioning layers. This allows our model to follow actions faithfully while preserving generalization and realism. Our approach scales naturally across embodiments and action spaces -- from 3-DoF mobile robots to 25-DoF humanoids, where predicting egocentric joint-angle-driven dynamics is substantially more challenging. The model produces coherent rollouts for both navigation and manipulation, requiring only modest fine-tuning. To evaluate physical correctness independent of appearance, we introduce the Structural Consistency Score (SCS), which measures whether stable scene elements evolve consistently with the provided actions. Our method improves SCS by up to 65\% over the prior state of the art, Navigation World Models; applies seamlessly to three different video diffusion model architectures; and effectively utilizes Internet priors to generalize to unseen environments, including navigation and manipulation inside paintings. Finally, we demonstrate the applicability of EgoWM to robotic planning. --- ### LuxRemix: Lighting Decomposition and Remixing for Indoor Scenes Authors: Ruofan Liang, Norman Müller, Ethan Weber, Duncan Zauss, Nandita Vijaykumar, Peter Kontschieder, Christian Richardt Published: 2026-01-21 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2601.15283v2 We present a novel approach for interactive light editing in indoor scenes from a single multi-view scene capture. Our method leverages a generative image-based light decomposition model that factorizes complex indoor scene illumination into its constituent light sources. This factorization enables independent manipulation of individual light sources, specifically allowing control over their state (on/off), chromaticity, and intensity. We further introduce multi-view lighting harmonization to ensure consistent propagation of the lighting decomposition across all scene views. This is integrated into a relightable 3D Gaussian splatting representation, providing real-time interactive control over the individual light sources. Our results demonstrate highly photorealistic lighting decomposition and relighting outcomes across diverse indoor scenes. We evaluate our method on both synthetic and real-world datasets and provide a quantitative and qualitative comparison to state-of-the-art techniques. For video results and interactive demos, see https://luxremix.github.io. --- ### Rethinking Video Generation Model for the Embodied World Authors: Yufan Deng, Zilin Pan, Hongyu Zhang, Xiaojie Li, Ruoqing Hu, Yufei Ding, Yiming Zou, Yan Zeng, Daquan Zhou Published: 2026-01-21 Categories: cs.CV, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.15282v1 Video generation models have significantly advanced embodied intelligence, unlocking new possibilities for generating diverse robot data that capture perception, reasoning, and action in the physical world. However, synthesizing high-quality videos that accurately reflect real-world robotic interactions remains challenging, and the lack of a standardized benchmark limits fair comparisons and progress. To address this gap, we introduce a comprehensive robotics benchmark, RBench, designed to evaluate robot-oriented video generation across five task domains and four distinct embodiments. It assesses both task-level correctness and visual fidelity through reproducible sub-metrics, including structural consistency, physical plausibility, and action completeness. Evaluation of 25 representative models highlights significant deficiencies in generating physically realistic robot behaviors. Furthermore, the benchmark achieves a Spearman correlation coefficient of 0.96 with human evaluations, validating its effectiveness. While RBench provides the necessary lens to identify these deficiencies, achieving physical realism requires moving beyond evaluation to address the critical shortage of high-quality training data. Driven by these insights, we introduce a refined four-stage data pipeline, resulting in RoVid-X, the largest open-source robotic dataset for video generation with 4 million annotated video clips, covering thousands of tasks and enriched with comprehensive physical property annotations. Collectively, this synergistic ecosystem of evaluation and data establishes a robust foundation for rigorous assessment and scalable training of video models, accelerating the evolution of embodied AI toward general intelligence. --- ### StableWorld: Towards Stable and Consistent Long Interactive Video Generation Authors: Ying Yang, Zhengyao Lv, Yujia Zeng, Tianlin Pan, Haofan Wang, Yueming Lyu, Binxin Yang, Hubery Yin, Chen Li, Jing Lyu, Ziwei Liu, Chenyang Si Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15281v2 In this paper, we explore the overlooked challenge of stability and temporal consistency in interactive video generation, which synthesizes dynamic and controllable video worlds through interactive behaviors such as camera movements and text prompts. Despite remarkable progress in world modeling, current methods still suffer from severe instability and temporal degradation, often leading to spatial drift and scene collapse during long-horizon interactions. To better understand this issue, we initially investigate the underlying causes of instability and identify that the major source of error accumulation originates from the same scene, where generated frames gradually deviate from the initial clean state and propagate errors to subsequent frames. Building upon this observation, we propose a simple yet effective method, \textbf{StableWorld}, a Dynamic Frame Eviction Mechanism. By continuously filtering out degraded frames while retaining geometrically consistent ones, StableWorld effectively prevents cumulative drift at its source, leading to more stable and temporal consistency of interactive generation. Promising results on multiple interactive video models, \eg, Matrix-Game, Open-Oasis, and Hunyuan-GameCraft, demonstrate that StableWorld is model-agnostic and can be applied to different interactive video generation frameworks to substantially improve stability, temporal consistency, and generalization across diverse interactive scenarios. --- ### LLM-based Multimodal Feedback Produces Equivalent Learning and Better Student Perceptions than Educator Feedback Authors: Chloe Qianhui Zhao, Jie Cao, Jionghao Lin, Kenneth R. Koedinger Published: 2026-01-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.15280v1 Providing timely, targeted, and multimodal feedback helps students quickly correct errors, build deep understanding and stay motivated, yet making it at scale remains a challenge. This study introduces a real-time AI-facilitated multimodal feedback system that integrates structured textual explanations with dynamic multimedia resources, including the retrieved most relevant slide page references and streaming AI audio narration. In an online crowdsourcing experiment, we compared this system against fixed business-as-usual feedback by educators across three dimensions: (1) learning effectiveness, (2) learner engagement, (3) perceived feedback quality and value. Results showed that AI multimodal feedback achieved learning gains equivalent to original educator feedback while significantly outperforming it on perceived clarity, specificity, conciseness, motivation, satisfaction, and reducing cognitive load, with comparable correctness, trust, and acceptance. Process logs revealed distinct engagement patterns: for multiple-choice questions, educator feedback encouraged more submissions; for open-ended questions, AI-facilitated targeted suggestions lowered revision barriers and promoted iterative improvement. These findings highlight the potential of AI multimodal feedback to provide scalable, real-time, and context-aware support that both reduces instructor workload and enhances student experience. --- ### MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs Authors: Christoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi, Philipp Seidl, Günter Klambauer, Sohvi Luukkonen Published: 2026-01-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.15279v1 A molecule's properties are fundamentally determined by its composition and structure encoded in its molecular graph. Thus, reasoning about molecular properties requires the ability to parse and understand the molecular graph. Large Language Models (LLMs) are increasingly applied to chemistry, tackling tasks such as molecular name conversion, captioning, text-guided generation, and property or reaction prediction. Most existing benchmarks emphasize general chemical knowledge, rely on literature or surrogate labels that risk leakage or bias, or reduce evaluation to multiple-choice questions. We introduce MolecularIQ, a molecular structure reasoning benchmark focused exclusively on symbolically verifiable tasks. MolecularIQ enables fine-grained evaluation of reasoning over molecular graphs and reveals capability patterns that localize model failures to specific tasks and molecular structures. This provides actionable insights into the strengths and limitations of current chemistry LLMs and guides the development of models that reason faithfully over molecular structure. --- ### Robust Fake News Detection using Large Language Models under Adversarial Sentiment Attacks Authors: Sahar Tahmasebi, Eric Müller-Budack, Ralph Ewerth Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15277v1 Misinformation and fake news have become a pressing societal challenge, driving the need for reliable automated detection methods. Prior research has highlighted sentiment as an important signal in fake news detection, either by analyzing which sentiments are associated with fake news or by using sentiment and emotion features for classification. However, this poses a vulnerability since adversaries can manipulate sentiment to evade detectors especially with the advent of large language models (LLMs). A few studies have explored adversarial samples generated by LLMs, but they mainly focus on stylistic features such as writing style of news publishers. Thus, the crucial vulnerability of sentiment manipulation remains largely unexplored. In this paper, we investigate the robustness of state-of-the-art fake news detectors under sentiment manipulation. We introduce AdSent, a sentiment-robust detection framework designed to ensure consistent veracity predictions across both original and sentiment-altered news articles. Specifically, we (1) propose controlled sentiment-based adversarial attacks using LLMs, (2) analyze the impact of sentiment shifts on detection performance. We show that changing the sentiment heavily impacts the performance of fake news detection models, indicating biases towards neutral articles being real, while non-neutral articles are often classified as fake content. (3) We introduce a novel sentiment-agnostic training strategy that enhances robustness against such perturbations. Extensive experiments on three benchmark datasets demonstrate that AdSent significantly outperforms competitive baselines in both accuracy and robustness, while also generalizing effectively to unseen datasets and adversarial scenarios. --- ### RayRoPE: Projective Ray Positional Encoding for Multi-view Attention Authors: Yu Wu, Minsik Jeon, Jen-Hao Rick Chang, Oncel Tuzel, Shubham Tulsiani Published: 2026-01-21 Categories: cs.CV, cs.LG arXiv: https://arxiv.org/abs/2601.15275v3 We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency similarity, and can adapt to the geometry of the underlying 3D scene. We find that prior (absolute or relative) encoding schemes for multi-view attention do not meet these desiderata, and present RayRoPE to address this gap. RayRoPE represents patch positions based on associated rays and computes query-frame projective coordinates to ensure SE(3) invariance. To adapt to scene geometry, RayRoPE predicts (without direct supervision) a per-token depth to obtain its position along the corresponding ray, while also modeling uncertainty and analytically computing the expected positional encoding. We validate our method on the tasks of novel-view synthesis, stereo depth estimation, and feed-forward 3DGS reconstruction. While remaining efficient, RayRoPE consistently improves over alternate position encoding schemes (e.g., 24% relative improvement on LPIPS in RE10K). --- ### Evaluation of Large Language Models in Legal Applications: Challenges, Methods, and Future Directions Authors: Yiran Hu, Huanghai Liu, Chong Wang, Kunran Li, Tien-Hsuan Wu, Haitao Li, Xinran Xu, Siqing Huo, Weihang Su, Ning Zheng, Siyuan Zheng, Qingyao Ai et al. Published: 2026-01-21 Categories: cs.CY, cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.15267v1 Large language models (LLMs) are being increasingly integrated into legal applications, including judicial decision support, legal practice assistance, and public-facing legal services. While LLMs show strong potential in handling legal knowledge and tasks, their deployment in real-world legal settings raises critical concerns beyond surface-level accuracy, involving the soundness of legal reasoning processes and trustworthy issues such as fairness and reliability. Systematic evaluation of LLM performance in legal tasks has therefore become essential for their responsible adoption. This survey identifies key challenges in evaluating LLMs for legal tasks grounded in real-world legal practice. We analyze the major difficulties involved in assessing LLM performance in the legal domain, including outcome correctness, reasoning reliability, and trustworthiness. Building on these challenges, we review and categorize existing evaluation methods and benchmarks according to their task design, datasets, and evaluation metrics. We further discuss the extent to which current approaches address these challenges, highlight their limitations, and outline future research directions toward more realistic, reliable, and legally grounded evaluation frameworks for LLMs in legal domains. --- ### DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integration Authors: Dominik Rößle, Xujun Xie, Adithya Mohan, Venkatesh Thirugnana Sambandham, Daniel Cremers, Torsten Schön Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15260v2 Perception is a cornerstone of autonomous driving, enabling vehicles to understand their surroundings and make safe, reliable decisions. Developing robust perception algorithms requires large-scale, high-quality datasets that cover diverse driving conditions and support thorough evaluation. Existing datasets often lack a high-fidelity digital twin, limiting systematic testing, edge-case simulation, sensor modification, and sim-to-real evaluations. To address this gap, we present DrivIng, a large-scale multimodal dataset with a complete geo-referenced digital twin of a ~18 km route spanning urban, suburban, and highway segments. Our dataset provides continuous recordings from six RGB cameras, one LiDAR, and high-precision ADMA-based localization, captured across day, dusk, and night. All sequences are annotated at 10 Hz with 3D bounding boxes and track IDs across 12 classes, yielding ~1.2 million annotated instances. Alongside the benefits of a digital twin, DrivIng enables a 1-to-1 transfer of real traffic into simulation, preserving agent interactions while enabling realistic and flexible scenario testing. To support reproducible research and robust validation, we benchmark DrivIng with state-of-the-art perception models and publicly release the dataset, digital twin, HD map, and codebase. --- ### Many Experiments, Few Repetitions, Unpaired Data, and Sparse Effects: Is Causal Inference Possible? Authors: Felix Schur, Niklas Pfister, Peng Ding, Sach Mukherjee, Jonas Peters Published: 2026-01-21 Categories: stat.ML, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.15254v1 We study the problem of estimating causal effects under hidden confounding in the following unpaired data setting: we observe some covariates $X$ and an outcome $Y$ under different experimental conditions (environments) but do not observe them jointly; we either observe $X$ or $Y$. Under appropriate regularity conditions, the problem can be cast as an instrumental variable (IV) regression with the environment acting as a (possibly high-dimensional) instrument. When there are many environments but only a few observations per environment, standard two-sample IV estimators fail to be consistent. We propose a GMM-type estimator based on cross-fold sample splitting of the instrument-covariate sample and prove that it is consistent as the number of environments grows but the sample size per environment remains constant. We further extend the method to sparse causal effects via $\ell_1$-regularized estimation and post-selection refitting. --- ### The Effect of Scripts and Formats on LLM Numeracy Authors: Varshini Reddy, Craig W. Schmidt, Seth Ebner, Adam Wiemerslage, Yuval Pinter, Chris Tanner Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15251v2 Large language models (LLMs) have achieved impressive proficiency in basic arithmetic, rivaling human-level performance on standard numerical tasks. However, little attention has been given to how these models perform when numerical expressions deviate from the prevailing conventions present in their training corpora. In this work, we investigate numerical reasoning across a wide range of numeral scripts and formats. We show that LLM accuracy drops substantially when numerical inputs are rendered in underrepresented scripts or formats, despite the underlying mathematical reasoning being identical. We further demonstrate that targeted prompting strategies, such as few-shot prompting and explicit numeral mapping, can greatly narrow this gap. Our findings highlight an overlooked challenge in multilingual numerical reasoning and provide actionable insights for working with LLMs to reliably interpret, manipulate, and generate numbers across diverse numeral scripts and formatting styles. --- ### FlowSSC: Universal Generative Monocular Semantic Scene Completion via One-Step Latent Diffusion Authors: Zichen Xi, Hao-Xiang Chen, Nan Xue, Hongyu Yan, Qi-Yuan Feng, Levent Burak Kara, Joaquim Jorge, Qun-Ce Xu Published: 2026-01-21 Categories: cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.15250v1 Semantic Scene Completion (SSC) from monocular RGB images is a fundamental yet challenging task due to the inherent ambiguity of inferring occluded 3D geometry from a single view. While feed-forward methods have made progress, they often struggle to generate plausible details in occluded regions and preserve the fundamental spatial relationships of objects. Such accurate generative reasoning capability for the entire 3D space is critical in real-world applications. In this paper, we present FlowSSC, the first generative framework applied directly to monocular semantic scene completion. FlowSSC treats the SSC task as a conditional generation problem and can seamlessly integrate with existing feed-forward SSC methods to significantly boost their performance. To achieve real-time inference without compromising quality, we introduce Shortcut Flow-matching that operates in a compact triplane latent space. Unlike standard diffusion models that require hundreds of steps, our method utilizes a shortcut mechanism to achieve high-fidelity generation in a single step, enabling practical deployment in autonomous systems. Extensive experiments on SemanticKITTI demonstrate that FlowSSC achieves state-of-the-art performance, significantly outperforming existing baselines. --- ### Recommending Best Paper Awards for ML/AI Conferences via the Isotonic Mechanism Authors: Garrett G. Wen, Buxin Su, Natalie Collina, Zhun Deng, Weijie Su Published: 2026-01-21 Categories: cs.LG, cs.AI, cs.GT, stat.ME arXiv: https://arxiv.org/abs/2601.15249v2 Machine learning and artificial intelligence conferences such as NeurIPS and ICML now regularly receive tens of thousands of submissions, posing significant challenges to maintaining the quality and consistency of the peer review process. This challenge is particularly acute for best paper awards, which are an important part of the peer review process, yet whose selection has increasingly become a subject of debate in recent years. In this paper, we introduce an author-assisted mechanism to facilitate the selection of best paper awards. Our method employs the Isotonic Mechanism for eliciting authors' assessments of their own submissions in the form of a ranking, which is subsequently utilized to adjust the raw review scores for optimal estimation of the submissions' ground-truth quality. We demonstrate that authors are incentivized to report truthfully when their utility is a convex additive function of the adjusted scores, and we validate this convexity assumption for best paper awards using publicly accessible review data of ICLR from 2019 to 2023 and NeurIPS from 2021 to 2023. Crucially, in the special case where an author has a single quota -- that is, may nominate only one paper -- we prove that truthfulness holds even when the utility function is merely nondecreasing and additive. This finding represents a substantial relaxation of the assumptions required in prior work. For practical implementation, we extend our mechanism to accommodate the common scenario of overlapping authorship. Finally, simulation results demonstrate that our mechanism significantly improves the quality of papers selected for awards. --- ### Taxonomy-Aligned Risk Extraction from 10-K Filings with Autonomous Improvement Using LLMs Authors: Rian Dolphin, Joe Dursun, Jarrett Blankenship, Katie Adams, Quinton Pike Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15247v1 We present a methodology for extracting structured risk factors from corporate 10-K filings while maintaining adherence to a predefined hierarchical taxonomy. Our three-stage pipeline combines LLM extraction with supporting quotes, embedding-based semantic mapping to taxonomy categories, and LLM-as-a-judge validation that filters spurious assignments. To evaluate our approach, we extract 10,688 risk factors from S&P 500 companies and examine risk profile similarity across industry clusters. Beyond extraction, we introduce autonomous taxonomy maintenance where an AI agent analyzes evaluation feedback to identify problematic categories, diagnose failure patterns, and propose refinements, achieving 104.7% improvement in embedding separation in a case study. External validation confirms the taxonomy captures economically meaningful structure: same-industry companies exhibit 63% higher risk profile similarity than cross-industry pairs (Cohen's d=1.06, AUC 0.82, p<0.001). The methodology generalizes to any domain requiring taxonomy-aligned extraction from unstructured text, with autonomous improvement enabling continuous quality maintenance and enhancement as systems process more documents. --- ### Feasibility Preservation under Monotone Retrieval Truncation Authors: Sean Plummer Published: 2026-01-21 Categories: cs.LO, cs.AI arXiv: https://arxiv.org/abs/2601.15241v1 Retrieval-based systems approximate access to a corpus by exposing only a truncated subset of available evidence. Even when relevant information exists in the corpus, truncation can prevent compatible evidence from co-occurring, leading to failures that are not captured by relevance-based evaluation. This paper studies retrieval from a structural perspective, modeling query answering as a feasibility problem under truncation. We formalize retrieval as a sequence of candidate evidence sets and characterize conditions under which feasibility in the limit implies feasibility at finite retrieval depth. We show that monotone truncation suffices to guarantee finite witnessability for individual queries. For classes of queries, we identify finite generation of witness certificates as the additional condition required to obtain a uniform retrieval bound, and we show that this condition is necessary. We further exhibit sharp counterexamples demonstrating failure under non-monotone truncation, non-finitely-generated query classes, and purely slotwise coverage. Together, these results isolate feasibility preservation as a correctness criterion for retrieval independent of relevance scoring or optimization, and clarify structural limitations inherent to truncation-based retrieval. --- ### Multi-context principal component analysis Authors: Kexin Wang, Salil Bhate, João M. Pereira, Joe Kileel, Matylda Figlerowicz, Anna Seigal Published: 2026-01-21 Categories: stat.ML, cs.LG, math.ST arXiv: https://arxiv.org/abs/2601.15239v1 Principal component analysis (PCA) is a tool to capture factors that explain variation in data. Across domains, data are now collected across multiple contexts (for example, individuals with different diseases, cells of different types, or words across texts). While the factors explaining variation in data are undoubtedly shared across subsets of contexts, no tools currently exist to systematically recover such factors. We develop multi-context principal component analysis (MCPCA), a theoretical and algorithmic framework that decomposes data into factors shared across subsets of contexts. Applied to gene expression, MCPCA reveals axes of variation shared across subsets of cancer types and an axis whose variability in tumor cells, but not mean, is associated with lung cancer progression. Applied to contextualized word embeddings from language models, MCPCA maps stages of a debate on human nature, revealing a discussion between science and fiction over decades. These axes are not found by combining data across contexts or by restricting to individual contexts. MCPCA is a principled generalization of PCA to address the challenge of understanding factors underlying data across contexts. --- ### MAPLE: Metadata Conditioned LLM Pretraining for Locale-Aware Question Answering Authors: Anjishnu Mukherjee, Ziwei Zhu, Antonios Anastasopoulos Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15236v3 Large language models can memorize competing locale-specific facts yet fail to select among them when the locale changes, defaulting instead to a single globally dominant answer. We formalize this as localized knowledge disambiguation and introduce LocalNewsQA, an 18,700-item English-news benchmark that pairs the same question across two locales and scores whether a model actually switches its answer when the locale changes. We also introduce MAPLE, a controlled family of decoder-only models pretrained with document-level geographic metadata (source URL, country, and continent) already present in the training corpus, and compare it to metadata-free controls trained on identical data with the same token budget, architecture, and optimization. In controlled experiments at 1B and 3B, with inference-time metadata fixed, pretraining with metadata in MAPLE produces measurable switching and improves accuracy on questions whose correct answer depends on locale. Ablations and external-benchmark evaluations further suggest that locale-conditioned prediction benefits from geographic provenance learned during pretraining and that these benefits strengthen at larger model sizes. --- ### Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification Authors: Fabi Nahian Madhurja, Rusab Sarmun, Muhammad E. H. Chowdhury, Adam Mushtak, Israa Al-Hashimi, Sohaib Bassam Zoghoul Published: 2026-01-21 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.15235v4 Cervical spine fractures require rapid and accurate diagnosis, yet automatic CT interpretation remains challenging as subtle injuries must be assessed across large 3D volumes. We ask whether full 3D vertebra segmentation is necessary for automated fracture recognition, or whether vertebra masks approximated from 2D projections can preserve sufficient diagnostic context. We propose an end-to-end pipeline that localizes the cervical spine, estimates C1-C7 vertebra masks from optimized 2D projections, and uses the resulting vertebra-level volumes for downstream fracture classification. A YOLOv8 detector first localizes spine regions of interest from multi-view variance projections, achieving a 3D mean Intersection over Union of 94.45%. Multi-label vertebra segmentation is then performed with a DenseNet121-Unet on energy-based sagittal and coronal projections, attaining a mean Dice score of 87.86%. The predicted 2D masks are back-projected and fused into approximate 3D masks for each vertebra to extract volumes of interest from the original CT. These volumes are analyzed by an ensemble of 2.5D spatio-sequential CNN-Transformer models, yielding vertebra-level and patient-level F1 scores of 68.15 and 82.26, area under the receiver operating characteristic curve of 91.62 and 90.95, and area under the precision-recall curve of 75.60 and 92.00, respectively. The projection-derived volumes achieved fracture-recognition performance comparable to a full 3D-segmentation baseline, while shifting the vertebra segmentation stage into a lower-dimensional domain. Saliency-based explainability and interobserver variability analysis further examine interpretability and reliability. Overall, the results indicate that projection-based mask approximation is a viable proxy for full 3D vertebra segmentation in cervical fracture recognition. --- ### PROGRESSLM: Towards Progress Reasoning in Vision-Language Models Authors: Jianshu Zhang, Chengxuan Qian, Haosen Sun, Haoran Lu, Dingcheng Wang, Letian Xue, Han Liu Published: 2026-01-21 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.15224v2 Estimating task progress requires reasoning over long-horizon dynamics rather than recognizing static visual content. While modern Vision-Language Models (VLMs) excel at describing what is visible, it remains unclear whether they can infer how far a task has progressed from partial observations. To this end, we introduce Progress-Bench, a benchmark for systematically evaluating progress reasoning in VLMs. Beyond benchmarking, we further explore a human-inspired two-stage progress reasoning paradigm through both training-free prompting and training-based approach based on curated dataset ProgressLM-45K. Experiments on 14 VLMs show that most models are not yet ready for task progress estimation, exhibiting sensitivity to demonstration modality and viewpoint changes, as well as poor handling of unanswerable cases. While training-free prompting that enforces structured progress reasoning yields limited and model-dependent gains, the training-based ProgressLM-3B achieves consistent improvements even at a small model scale, despite being trained on a task set fully disjoint from the evaluation tasks. Further analyses reveal characteristic error patterns and clarify when and why progress reasoning succeeds or fails. Website: https://progresslm.github.io/ProgressLM/ --- ### ScenDi: 3D-to-2D Scene Diffusion Cascades for Urban Generation Authors: Hanlei Guo, Jiahao Shao, Xinya Chen, Xiyang Tan, Sheng Miao, Yujun Shen, Yiyi Liao Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15221v1 Recent advancements in 3D object generation using diffusion models have achieved remarkable success, but generating realistic 3D urban scenes remains challenging. Existing methods relying solely on 3D diffusion models tend to suffer a degradation in appearance details, while those utilizing only 2D diffusion models typically compromise camera controllability. To overcome this limitation, we propose ScenDi, a method for urban scene generation that integrates both 3D and 2D diffusion models. We first train a 3D latent diffusion model to generate 3D Gaussians, enabling the rendering of images at a relatively low resolution. To enable controllable synthesis, this 3DGS generation process can be optionally conditioned by specifying inputs such as 3d bounding boxes, road maps, or text prompts. Then, we train a 2D video diffusion model to enhance appearance details conditioned on rendered images from the 3D Gaussians. By leveraging the coarse 3D scene as guidance for 2D video diffusion, ScenDi generates desired scenes based on input conditions and successfully adheres to accurate camera trajectories. Experiments on two challenging real-world datasets, Waymo and KITTI-360, demonstrate the effectiveness of our approach. --- ### Privacy Collapse: Benign Fine-Tuning Can Break Contextual Privacy in Language Models Authors: Anmol Goel, Cornelius Emde, Sangdoo Yun, Seong Joon Oh, Martin Gubri Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15220v2 We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for helpfulness, exposure to user information, emotional and subjective dialogue, and debugging code printing internal variables, among others. Fine-tuned models lose their ability to reason about contextual privacy norms, share information inappropriately with tools, and violate memory boundaries across contexts. Privacy collapse is a ``silent failure'' because models maintain high performance on standard safety and utility benchmarks whilst exhibiting severe privacy vulnerabilities. Our experiments show evidence of privacy collapse across six models (closed and open weight), five fine-tuning datasets (real-world and controlled data), and two task categories (agentic and memory-based). Our mechanistic analysis reveals that privacy representations are uniquely fragile to fine-tuning, compared to task-relevant features which are preserved. Our results reveal a critical gap in current safety evaluations, in particular for the deployment of specialised agents. --- ### ZENITH: Automated Gradient Norm Informed Stochastic Optimization Authors: Dhrubo Saha Published: 2026-01-21 Categories: cs.LG, cs.CV arXiv: https://arxiv.org/abs/2601.15212v2 Training deep computer vision models requires manual oversight or hyperparameter tuning of the learning rate (LR) schedule. While existing adaptive optimizers schedule the LR automatically, they suffer from computational and memory overhead, incompatibility with regularization, and suboptimal LR choices. In this work, we introduce the ZENITH (Zero-overhead Evolution using Norm-Informed Training History) optimizer, which adapts the LR using the temporal evolution of the gradient norm. Image classification experiments spanning 6 CNN architectures and 6 benchmarks demonstrate that ZENITH achieves higher test accuracy in lower wall-clock time than baselines. It also yielded superior mAP in object detection, keypoint detection, and instance segmentation on MS COCO using the R-CNN family of models. Furthermore, its compatibility with regularization enables even better generalization. --- ### Deaf and Hard of Hearing Access to Intelligent Personal Assistants: Comparison of Voice-Based Options with an LLM-Powered Touch Interface Authors: Paige S. DeVries, Michaela Okosi, Ming Li, Nora Dunphy, Gidey Gezae, Dante Conway, Abraham Glasser, Raja Kushalnagar, Christian Vogler Published: 2026-01-21 Categories: cs.HC, cs.AI arXiv: https://arxiv.org/abs/2601.15209v2 We investigate intelligent personal assistants (IPAs) accessibility for deaf and hard of hearing (DHH) people who can use their voice in everyday communication. The inability of IPAs to understand diverse accents including deaf speech renders them largely inaccessible to non-signing and speaking DHH individuals. Using an Echo Show, we compare the usability of natural language input via spoken English; with Alexa's automatic speech recognition and a Wizard-of-Oz setting with a trained facilitator re-speaking commands against that of a large language model (LLM)-assisted touch interface in a mixed-methods study. The touch method was navigated through an LLM-powered "task prompter," which integrated the user's history and smart environment to suggest contextually-appropriate commands. Quantitative results showed no significant differences across both spoken English conditions vs LLM-assisted touch. Qualitative results showed variability in opinions on the usability of each method. Ultimately, it will be necessary to have robust deaf-accented speech recognized natively by IPAs. --- ### A Computer Vision Hybrid Approach: CNN and Transformer Models for Accurate Alzheimer's Detection from Brain MRI Scans Authors: Md Mahmudul Hoque, Shuvo Karmaker, Md. Hadi Al-Amin, Md Modabberul Islam, Jisun Junayed, Farha Ulfat Mahi Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15202v1 Early and accurate classification of Alzheimers disease (AD) from brain MRI scans is essential for timely clinical intervention and improved patient outcomes. This study presents a comprehensive comparative analysis of five CNN architectures (EfficientNetB0, ResNet50, DenseNet201, MobileNetV3, VGG16), five Transformer-based models (ViT, ConvTransformer, PatchTransformer, MLP-Mixer, SimpleTransformer), and a proposed hybrid model named Evan_V2. All models were evaluated on a four-class AD classification task comprising Mild Dementia, Moderate Dementia, Non-Demented, and Very Mild Dementia categories. Experimental findings show that CNN architectures consistently achieved strong performance, with ResNet50 attaining 98.83% accuracy. Transformer models demonstrated competitive generalization capabilities, with ViT achieving the highest accuracy among them at 95.38%. However, individual Transformer variants exhibited greater class-specific instability. The proposed Evan_V2 hybrid model, which integrates outputs from ten CNN and Transformer architectures through feature-level fusion, achieved the best overall performance with 99.99% accuracy, 0.9989 F1-score, and 0.9968 ROC AUC. Confusion matrix analysis further confirmed that Evan_V2 substantially reduced misclassification across all dementia stages, outperforming every standalone model. These findings highlight the potential of hybrid ensemble strategies in producing highly reliable and clinically meaningful diagnostic tools for Alzheimers disease classification. --- ### BBoxMaskPose v2: Expanding Mutual Conditioning to 3D Authors: Miroslav Purkrabek, Constantin Kolomiiets, Jiri Matas Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15200v1 Most 2D human pose estimation benchmarks are nearly saturated, with the exception of crowded scenes. We introduce PMPose, a top-down 2D pose estimator that incorporates the probabilistic formulation and the mask-conditioning. PMPose improves crowded pose estimation without sacrificing performance on standard scenes. Building on this, we present BBoxMaskPose v2 (BMPv2) integrating PMPose and an enhanced SAM-based mask refinement module. BMPv2 surpasses state-of-the-art by 1.5 average precision (AP) points on COCO and 6 AP points on OCHuman, becoming the first method to exceed 50 AP on OCHuman. We demonstrate that BMP's 2D prompting of 3D model improves 3D pose estimation in crowded scenes and that advances in 2D pose quality directly benefit 3D estimation. Results on the new OCHuman-Pose dataset show that multi-person performance is more affected by pose prediction accuracy than by detection. The code, models, and data are available on https://MiraPurkrabek.github.io/BBox-Mask-Pose/. --- ### LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queries Authors: Shijie Lian, Bin Yu, Xiaopeng Lin, Laurence T. Yang, Zhaolong Shen, Changti Wu, Yuzhuo Miao, Cong Huang, Kai Chen Published: 2026-01-21 Categories: cs.AI, cs.CL, cs.CV, cs.RO arXiv: https://arxiv.org/abs/2601.15197v7 Vision-Language-Action (VLA) models have shown promise in robot manipulation but often struggle to generalize to new instructions or complex multi-task scenarios. We identify a critical pathology in current training paradigms where goal-driven data collection creates a dataset bias. In such datasets, language instructions are highly predictable from visual observations alone, causing the conditional mutual information between instructions and actions to vanish, a phenomenon we term Information Collapse. Consequently, models degenerate into vision-only policies that ignore language constraints and fail in out-of-distribution (OOD) settings. To address this, we propose LangForce, a novel framework that enforces instruction following via Bayesian decomposition. By introducing learnable Latent Action Queries, we construct a dual-branch architecture to estimate both a vision-only prior $p(a \mid v)$ and a language-conditioned posterior $π(a \mid v, \ell)$. We then optimize the policy to maximize the conditional Pointwise Mutual Information (PMI) between actions and instructions. This objective effectively penalizes the vision shortcut and rewards actions that explicitly explain the language command. Without requiring new data, LangForce significantly improves generalization. Extensive experiments across on SimplerEnv and RoboCasa demonstrate substantial gains, including an 11.3% improvement on the challenging OOD SimplerEnv benchmark, validating the ability of our approach to robustly ground language in action. --- ### Where Do AI Coding Agents Fail? An Empirical Study of Failed Agentic Pull Requests in GitHub Authors: Ramtin Ehsani, Sakshi Pathak, Shriya Rawal, Abdullah Al Mujahid, Mia Mohammad Imran, Preetha Chatterjee Published: 2026-01-21 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.15195v1 AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known about how they behave in practice and why many of them fail to be merged. In this paper, we conduct a large-scale study of 33k agent-authored PRs made by five coding agents across GitHub. (RQ1) We first quantitatively characterize merged and not-merged PRs along four broad dimensions: 1) merge outcomes across task types, 2) code changes, 3) CI build results, and 4) review dynamics. We observe that tasks related to documentation, CI, and build update achieve the highest merge success, whereas performance and bug-fix tasks perform the worst. Not-merged PRs tend to involve larger code changes, touch more files, and often do not pass the project's CI/CD pipeline validation. (RQ2) To further investigate why some agentic PRs are not merged, we qualitatively analyze 600 PRs to derive a hierarchical taxonomy of rejection patterns. This analysis complements the quantitative findings in RQ1 by uncovering rejection reasons not captured by quantitative metrics, including lack of meaningful reviewer engagement, duplicate PRs, unwanted feature implementations, and agent misalignment. Together, our findings highlight key socio-technical and human-AI collaboration factors that are critical to improving the success of future agentic workflows. --- ### Benchmarking Large Language Models for ABAP Code Generation: An Empirical Study on Iterative Improvement by Compiler Feedback Authors: Stephan Wallraven, Tim Köhne, Hartmut Westenberger, Andreas Moser Published: 2026-01-21 Categories: cs.SE, cs.AI, cs.PL arXiv: https://arxiv.org/abs/2601.15188v1 This work investigates the performance of Large Language Models (LLMs) in generating ABAP code. Despite successful applications of generative AI in many programming languages, there are hardly any systematic analyses of ABAP code generation to date. The aim of the study is to empirically analyze to what extent various LLMs can generate syntactically correct and functional ABAP code, how effectively they use compiler feedback for iterative improvement, and which task types pose special challenges. For this purpose, a benchmark with 180 tasks is conducted, consisting of adapted HumanEval tasks and practical SAP scenarios. The results show significant performance differences between the models: more powerful LLMs achieve success rates of around 75% after several iterations and benefit greatly from compiler feedback, while smaller models perform significantly weaker. Overall, the study highlights the high potential of powerful LLMs for ABAP development processes, especially in iterative error correction. --- ### Supporting Humans in Evaluating AI Summaries of Legal Depositions Authors: Naghmeh Farzi, Laura Dietz, Dave D. Lewis Published: 2026-01-21 Categories: cs.CL, cs.IR arXiv: https://arxiv.org/abs/2601.15182v1 While large language models (LLMs) are increasingly used to summarize long documents, this trend poses significant challenges in the legal domain, where the factual accuracy of deposition summaries is crucial. Nugget-based methods have been shown to be extremely helpful for the automated evaluation of summarization approaches. In this work, we translate these methods to the user side and explore how nuggets could directly assist end users. Although prior systems have demonstrated the promise of nugget-based evaluation, its potential to support end users remains underexplored. Focusing on the legal domain, we present a prototype that leverages a factual nugget-based approach to support legal professionals in two concrete scenarios: (1) determining which of two summaries is better, and (2) manually improving an automatically generated summary. --- ### Dynamic Management of a Deep Learning-Based Anomaly Detection System for 5G Networks Authors: Lorenzo Fernández Maimó, Alberto Huertas Celdrán, Manuel Gil Pérez, Félix J. García Clemente, Gregorio Martínez Pérez Published: 2026-01-21 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.15177v1 Fog and mobile edge computing (MEC) will play a key role in the upcoming fifth generation (5G) mobile networks to support decentralized applications, data analytics and management into the network itself by using a highly distributed compute model. Furthermore, increasing attention is paid to providing user-centric cybersecurity solutions, which particularly require collecting, processing and analyzing significantly large amount of data traffic and huge number of network connections in 5G networks. In this regard, this paper proposes a MEC-oriented solution in 5G mobile networks to detect network anomalies in real-time and in autonomic way. Our proposal uses deep learning techniques to analyze network flows and to detect network anomalies. Moreover, it uses policies in order to provide an efficient and dynamic management system of the computing resources used in the anomaly detection process. The paper presents relevant aspects of the deployment of the proposal and experimental results to show its performance. --- ### Is Peer Review Really in Decline? Analyzing Review Quality across Venues and Time Authors: Ilia Kuznetsov, Rohan Nayak, Alla Rozovskaya, Iryna Gurevych Published: 2026-01-21 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.15172v1 Peer review is at the heart of modern science. As submission numbers rise and research communities grow, the decline in review quality is a popular narrative and a common concern. Yet, is it true? Review quality is difficult to measure, and the ongoing evolution of reviewing practices makes it hard to compare reviews across venues and time. To address this, we introduce a new framework for evidence-based comparative study of review quality and apply it to major AI and machine learning conferences: ICLR, NeurIPS and *ACL. We document the diversity of review formats and introduce a new approach to review standardization. We propose a multi-dimensional schema for quantifying review quality as utility to editors and authors, coupled with both LLM-based and lightweight measurements. We study the relationships between measurements of review quality, and its evolution over time. Contradicting the popular narrative, our cross-temporal analysis reveals no consistent decline in median review quality across venues and years. We propose alternative explanations, and outline recommendations to facilitate future empirical studies of review quality. --- ### Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval Authors: Zhucun Xue, Jiangning Zhang, Juntao Jiang, Jinzhuo Liu, Haoyang He, Teng Hu, Xiaobin Hu, Yong Liu, Shuicheng Yan Published: 2026-01-21 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.15170v2 The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult to synthesize. Traditional bibliometric tools rely mainly on metadata and offer limited visibility into the semantic content of papers, making it hard to track how research themes evolve over time or how different areas influence one another.To obtain a clearer picture of recent developments, we compile a unified corpus of more than 100,000 papers from 22 major conferences between 2020 and 2025 and construct a multidimensional profiling pipeline to organize and analyze their textual content. By combining topic clustering, LLM-assisted parsing, and structured retrieval, we derive a comprehensive representation of research activity that supports the study of topic lifecycles, methodological transitions, dataset and model usage patterns, and institutional research directions.Our analysis highlights several notable shifts, including the growth of safety, multimodal reasoning, and agent-oriented studies, as well as the gradual stabilization of areas such as neural machine translation and graph-based methods. These findings provide an evidence-based view of how AI research is evolving and offer a resource for understanding broader trends and identifying emerging directions. --- ### The Flexibility Trap: Rethinking the Value of Arbitrary Order in Diffusion Language Models Authors: Zanlin Ni, Shenzhi Wang, Yang Yue, Tianyu Yu, Weilin Zhao, Yeguo Hua, Tianyi Chen, Jun Song, Cheng Yu, Bo Zheng, Gao Huang Published: 2026-01-21 Categories: cs.CL, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.15165v4 Diffusion Large Language Models (dLLMs) break the rigid left-to-right constraint of traditional LLMs, enabling token generation in arbitrary orders. Intuitively, this flexibility implies a solution space that strictly supersets the fixed autoregressive trajectory, theoretically unlocking superior reasoning potential. However, in this paper, we find that for general reasoning tasks (e.g., mathematics and coding), arbitrary order generation may in fact limit the reasoning potential of dLLMs. We observe that dLLMs tend to exploit this order flexibility to bypass high-uncertainty tokens that are crucial for exploration, which can lead to a premature collapse of solution coverage. This observation motivates a rethink of RL approaches for dLLMs, where considerable complexities, such as handling combinatorial trajectories and intractable likelihoods, are often devoted to preserving this flexibility. We show that effective reasoning can be elicited by simply forgoing arbitrary order and applying standard Group Relative Policy Optimization (GRPO) instead. Our approach, JustGRPO, is minimalist yet surprisingly effective (e.g., 89.1% accuracy on GSM8K) while fully retaining the parallel decoding ability of dLLMs. Project page: https://nzl-thu.github.io/the-flexibility-trap --- ### V-CAGE: Context-Aware Generation and Verification for Scalable Long-Horizon Embodied Tasks Authors: Yaru Liu, Ao-bo Wang, Nanyang Ye Published: 2026-01-21 Categories: cs.RO, cs.AI arXiv: https://arxiv.org/abs/2601.15164v1 Learning long-horizon embodied behaviors from synthetic data remains challenging because generated scenes are often physically implausible, language-driven programs frequently "succeed" without satisfying task semantics, and high-level instructions require grounding into executable action sequences. To address these limitations, we introduce V-CAGE, a closed-loop framework for generating robust, semantically aligned manipulation datasets at scale. First, we propose a context-aware instantiation mechanism that enforces geometric consistency during scene synthesis. By dynamically maintaining a map of prohibited spatial areas as objects are placed, our system prevents interpenetration and ensures reachable, conflict-free configurations in cluttered environments. Second, to bridge the gap between abstract intent and low-level control, we employ a hierarchical instruction decomposition module. This decomposes high-level goals (e.g., "get ready for work") into compositional action primitives, facilitating coherent long-horizon planning. Crucially, we enforce semantic correctness through a VLM-based verification loop. Acting as a visual critic, the VLM performs rigorous rejection sampling after each subtask, filtering out "silent failures" where code executes but fails to achieve the visual goal. Experiments demonstrate that V-CAGE yields datasets with superior physical and semantic fidelity, significantly boosting the success rate and generalization of downstream policies compared to non-verified baselines. --- ### Retrieval-Augmented Agentic Rubric Generation for Reliable Medical Response Evaluation Authors: Yinzhu Chen, Abdine Maiga, Hossein A. Rahmani, Emine Yilmaz Published: 2026-01-21 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.15161v3 Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed by generic metrics and LLM judges using general criteria, while expert-authored fine-grained rubrics are expensive and difficult to scale. In this paper, we propose a retrieval-augmented multi-agent framework for automatically generating instance-specific evaluation rubrics. Our approach grounds evaluation in authoritative medical evidence by decomposing retrieved content into atomic facts and synthesizing them with user interaction constraints to form fine-grained evaluation criteria. Evaluated on HealthBench and LLMEval-Med, our framework achieves Clinical Intent Alignment (CIA) scores of 50.20% and 31.90%, significantly outperforming the GPT-4o baseline and showing consistent improvements across English and Chinese medical benchmarks. In discriminative tests on HealthBench, our rubrics achieve a 7.8% point higher win rate than GPT-4o and increase the mean score difference from 4.972 to 8.658. Ablation studies further show that individual components contribute differently across datasets, with interaction-intent modeling providing the most consistent contribution to clinical-criterion coverage. Beyond evaluation, our rubrics guide response refinement, improving response quality by 9.2%. These results suggest that automated, knowledge-grounded rubric generation provides a scalable foundation for evaluating and improving medical LLMs. The code is available at https://anonymous.4open.science/r/Automated-Rubric-Generation-E716/. --- ### Knowledge Graphs are Implicit Reward Models: Path-Derived Signals Enable Compositional Reasoning Authors: Yuval Kansal, Niraj K. Jha Published: 2026-01-21 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.15160v3 Large language models have achieved near-expert performance in structured reasoning domains like mathematics and programming, yet their ability to perform compositional multi-hop reasoning in specialized scientific fields remains limited. We propose a bottom-up learning paradigm in which models are grounded in axiomatic domain facts and compose them to solve complex, unseen tasks. To this end, we present a post-training pipeline, based on a combination of supervised fine-tuning and reinforcement learning (RL), in which knowledge graphs act as implicit reward models. By deriving novel reward signals from knowledge graph paths, we provide verifiable, scalable, and grounded supervision that encourages models to compose intermediate axioms rather than optimize only final answers during RL. We validate this approach in the medical domain, training a 14B model on short-hop reasoning paths (1-3 hops) and evaluating its zero-shot generalization to complex multi-hop queries (4-5 hops). Our experiments show that path-derived rewards act as a "compositional bridge", enabling our model to significantly outperform much larger models and frontier systems like GPT-5.2 and Gemini 3 Pro, on the most difficult reasoning tasks. Furthermore, we demonstrate the robustness of our approach to adversarial perturbations against option-shuffling stress tests. This work suggests that grounding the reasoning process in structured knowledge is a scalable and efficient path toward intelligent reasoning. Our code is publicly available at: https://github.com/jha-lab/kg-implicit-reward-compositional-rl/. --- ### Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data Authors: Yuval Ran-Milo, Yotam Alexander, Shahar Mendel, Nadav Cohen Published: 2026-01-21 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.15158v4 Transformers trained via Reinforcement Learning (RL) with outcome-based supervision can spontaneously develop the ability to generate intermediate reasoning steps (Chain-of-Thought). Yet the mechanism by which sparse rewards drive policy gradient to discover such systematic reasoning remains poorly understood. We address this by analyzing the policy gradient dynamics of single-layer Transformers on a synthetic graph traversal task that cannot be solved without Chain-of-Thought but admits a simple iterative solution. We prove that despite training solely on final-answer correctness, policy gradient drives the Transformer to converge to a structured, interpretable algorithm that iteratively traverses the graph vertex-by-vertex. We characterize the distributional properties required for this emergence, identifying the critical role of "simple examples": instances requiring fewer reasoning steps. When the training distribution places sufficient mass on these simpler examples, the Transformer learns a generalizable traversal strategy that extrapolates to longer chains; when this mass vanishes, policy gradient learning becomes infeasible. We corroborate our theoretical results through experiments on synthetic data and with real-world language models on mathematical reasoning tasks, validating that our theoretical findings carry over to practical settings. --- ### How to Build AI Agents by Augmenting LLMs with Codified Human Expert Domain Knowledge? A Software Engineering Framework Authors: Choro Ulan uulu, Mikhail Kulyabin, Iris Fuhrmann, Jan Joosten, Nuno Miguel Martins Pacheco, Filippos Petridis, Rebecca Johnson, Jan Bosch, Helena Holmström Olsson Published: 2026-01-21 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.15153v1 Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting expert time. This paper investigates how to capture and embed human domain knowledge into AI agent systems through an industrial case study. We propose a software engineering framework to capture human domain knowledge for engineering AI agents in simulation data visualization by augmenting a Large Language Model (LLM) with a request classifier, Retrieval-Augmented Generation (RAG) system for code generation, codified expert rules, and visualization design principles unified in an agent demonstrating autonomous, reactive, proactive, and social behavior. Evaluation across five scenarios spanning multiple engineering domains with 12 evaluators demonstrates 206% improvement in output quality, with our agent achieving expert-level ratings in all cases versus baseline's poor performance, while maintaining superior code quality with lower variance. Our contributions are: an automated agent-based system for visualization generation and a validated framework for systematically capturing human domain knowledge and codifying tacit expert knowledge into AI agents, demonstrating that non-experts can achieve expert-level outcomes in specialized domains. ---