# Research Papers — 2026-01 · bundle page 52 of 189

> Full-text markdown of papers #2551–2600 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/52
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/51.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/53.md)

### Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning

Authors: Manjie Xu, Isabella Yin, Xinyi Tu, Chi Zhang, Yixin Zhu
Published: 2026-01-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.18352v2

LLMs struggle with Semantic Inertia: the inability to inhibit pre-trained priors (e.g., "Lava is Dangerous") when dynamic, in-context rules contradict them. We probe this phenomenon using Baba Is You, where physical laws are mutable text rules, enabling precise evaluation of models' ability to override learned priors when rules change. We quantatively observe that larger models can exhibit inverse scaling: they perform worse than smaller models when natural language reasoning requires suppressing pre-trained associations (e.g., accepting "Lava is Safe"). Our analysis attributes this to natural language encoding, which entangles descriptive semantics and logical rules, leading to persistent hallucinations of familiar physics despite explicit contradictory rules. Here we show that representing dynamics as executable code, rather than descriptive text, reverses this trend and enables effective prior inhibition. We introduce Code-Grounded Vistas (LCV), which fine-tunes models on counterfactual pairs and identifies states with contradictory rules, thereby forcing attention to logical constraints rather than visual semantics. This training-time approach outperforms expensive inference-time search methods in both efficiency and accuracy. Our results demonstrate that representation fundamentally determines whether scaling improves or impairs contextual reasoning. This challenges the assumption that larger models are universally better, with implications for domains that require dynamic overriding of learned priors.

---

### Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis

Authors: Junyi Zou
Published: 2026-01-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.18350v5

Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict decoding. We study this phenomenon in medical LLM settings using lightweight, reproducible measurements of trace leakage and instruction-following behavior. Beyond marker-based proxies, we introduce a marker-forbidden, answer-only evaluation and define a correctness-based direction that does not rely on surface markers; a rank-1 logit-space intervention along this direction modulates decision distributions and improves multiple-choice accuracy beyond random-direction controls at sufficiently large intervention strength. We further provide layer-wise geometric evidence that domain and instruction adapters induce partially misaligned update directions, and present a proof-of-concept geometry-aware merge that can reduce leakage and/or improve accuracy in a toy setting. Our results characterize boundary conditions of trace leakage and provide practical diagnostics and interventions for safer adapter merging.

---

### Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception

Authors: Sijing Wu, Yunhao Li, Zicheng Zhang, Qi Jia, Xinyue Li, Huiyu Duan, Xiongkuo Min, Guangtao Zhai
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18346v1

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive performance on existing low-level vision benchmarks, which primarily focus on generic images. However, their capabilities to perceive and assess portrait images, a domain characterized by distinct structural and perceptual properties, remain largely underexplored. To this end, we introduce Q-Bench-Portrait, the first holistic benchmark specifically designed for portrait image quality perception, comprising 2,765 image-question-answer triplets and featuring (1) diverse portrait image sources, including natural, synthetic distortion, AI-generated, artistic, and computer graphics images; (2) comprehensive quality dimensions, covering technical distortions, AIGC-specific distortions, and aesthetics; and (3) a range of question formats, including single-choice, multiple-choice, true/false, and open-ended questions, at both global and local levels. Based on Q-Bench-Portrait, we evaluate 20 open-source and 5 closed-source MLLMs, revealing that although current models demonstrate some competence in portrait image perception, their performance remains limited and imprecise, with a clear gap relative to human judgments. We hope that the proposed benchmark will foster further research into enhancing the portrait image perception capabilities of both general-purpose and domain-specific MLLMs.

---

### Structural Gender Bias in Credit Scoring: Proxy Leakage

Authors: Navya SD, Sreekanth D, SS Uma Sankari
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18342v1

As financial institutions increasingly adopt machine learning for credit risk assessment, the persistence of algorithmic bias remains a critical barrier to equitable financial inclusion. This study provides a comprehensive audit of structural gender bias within the Taiwan Credit Default dataset, specifically challenging the prevailing doctrine of "fairness through blindness." Despite the removal of explicit protected attributes and the application of industry standard fairness interventions, our results demonstrate that gendered predictive signals remain deeply embedded within non-sensitive features. Utilizing SHAP (SHapley Additive exPlanations), we identify that variables such as Marital Status, Age, and Credit Limit function as potent proxies for gender, allowing models to maintain discriminatory pathways while appearing statistically fair. To mathematically quantify this leakage, we employ an adversarial inverse modeling framework. Our findings reveal that the protected gender attribute can be reconstructed from purely non-sensitive financial features with an ROC AUC score of 0.65, demonstrating that traditional fairness audits are insufficient for detecting implicit structural bias. These results advocate for a shift from surface-level statistical parity toward causal-aware modeling and structural accountability in financial AI.

---

### Beyond Rigid: Benchmarking Non-Rigid Video Editing

Authors: Bingzheng Qu, Xuefeng Bai, Kehai Chen, Min Zhang
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18340v2

As video generation models are increasingly expected to manipulate physical dynamics, there is a growing need to move evaluation beyond appearance fidelity and semantic alignment. Non-rigid video editing offers a uniquely revealing testbed, where distinct materials impose distinct physical constraints. In this paper, we introduce NRVBench, a diagnostic benchmark for non-rigid video editing, where the task is to modify deformable motion while preserving irrelevant regions and maintaining material-specific plausibility. NRVBench contains 180 curated videos across six physics-grounded categories, 2,340 fine-grained editing instructions, 360 multiple-choice questions, and pixel-accurate masks. We further propose NRVE-Acc, a structured VLM-based protocol that decomposes editing success into instruction following, material-aware deformation plausibility, and temporal coherence with motion cues. Experiments on representative inference-time video editing methods reveal a clear mismatch between conventional metrics and physics-aware perceptual editing success: methods that preserve appearance or achieve strong global alignment may still fail under non-rigid dynamics. We additionally introduce VM-Edit, a simple region-conditioned editing baseline that frees the foreground while locking the background, exposing the stability--plasticity trade-off.

---

### A Dataset for Automatic Vocal Mode Classification

Authors: Reemt Hinrichs, Sonja Stephan, Alexander Lange, Jörn Ostermann
Published: 2026-01-26
Categories: cs.SD, cs.LG
arXiv: https://arxiv.org/abs/2601.18339v2

The Complete Vocal Technique (CVT) is a school of singing developed in the past decades by Cathrin Sadolin et al.. CVT groups the use of the voice into so called vocal modes, namely Neutral, Curbing, Overdrive and Edge. Knowledge of the desired vocal mode can be helpful for singing students. Automatic classification of vocal modes can thus be important for technology-assisted singing teaching. Previously, automatic classification of vocal modes has been attempted without major success, potentially due to a lack of data. Therefore, we recorded a novel vocal mode dataset consisting of sustained vowels recorded from four singers, three of which professional singers with more than five years of CVT-experience. The dataset covers the entire vocal range of the subjects, totaling 3,752 unique samples. By using four microphones, thereby offering a natural data augmentation, the dataset consists of more than 13,000 samples combined. An annotation was created using three CVT-experienced annotators, each providing an individual annotation. The merged annotation as well as the three individual annotations come with the published dataset. Additionally, we provide some baseline classification results. The best balanced accuracy across a 5-fold cross validation of 81.3\,\% was achieved with a ResNet18. The dataset can be downloaded under https://zenodo.org/records/14276415.

---

### PPISP: Physically-Plausible Compensation and Control of Photometric Variations in Radiance Field Reconstruction

Authors: Isaac Deutsch, Nicolas Moënne-Loccoz, Gavriel State, Zan Gojcic
Published: 2026-01-26
Categories: cs.CV, cs.GR
arXiv: https://arxiv.org/abs/2601.18336v2

Multi-view 3D reconstruction methods remain highly sensitive to photometric inconsistencies arising from camera optical characteristics and variations in image signal processing (ISP). Existing mitigation strategies such as per-frame latent variables or affine color corrections lack physical grounding and generalize poorly to novel views. We propose the Physically-Plausible ISP (PPISP) correction module, which disentangles camera-intrinsic and capture-dependent effects through physically based and interpretable transformations. A dedicated PPISP controller, trained on the input views, predicts ISP parameters for novel viewpoints, analogous to auto exposure and auto white balance in real cameras. This design enables realistic and fair evaluation on novel views without access to ground-truth images. PPISP achieves state-of-the-art performance on standard benchmarks, while providing intuitive control and supporting the integration of metadata when available. The source code is available at: https://github.com/nv-tlabs/ppisp

---

### Analytic Incremental Learning For Sound Source Localization With Imbalance Rectification

Authors: Zexia Fan, Yu Chen, Qiquan Zhang, Kainan Chen, Xinyuan Qian
Published: 2026-01-26
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.18335v1

Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance arising from long-tailed direction-of-arrival (DoA) distributions, and inter-task imbalance induced by cross-task skews and overlaps. These often lead to catastrophic forgetting, significantly degrading the localization accuracy. To mitigate these issues, we propose a unified framework with two key innovations. Specifically, we design a GCC-PHAT-based data augmentation (GDA) method that leverages peak characteristics to alleviate intra-task distribution skews. We also propose an Analytic dynamic imbalance rectifier (ADIR) with task-adaption regularization, which enables analytic updates that adapt to inter-task dynamics. On the SSLR benchmark, our proposal achieves state-of-the-art (SoTA) results of 89.0% accuracy, 5.3° mean absolute error, and 1.6 backward transfer, demonstrating robustness to evolving imbalances without exemplar storage.

---

### Overalignment in Frontier LLMs: An Empirical Study of Sycophantic Behaviour in Healthcare

Authors: Clément Christophe, Wadood Mohammed Abdul, Prateek Munjal, Tathagata Raha, Ronnie Rajan, Praveenkumar Kanithi
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18334v1

As LLMs are increasingly integrated into clinical workflows, their tendency for sycophancy, prioritizing user agreement over factual accuracy, poses significant risks to patient safety. While existing evaluations often rely on subjective datasets, we introduce a robust framework grounded in medical MCQA with verifiable ground truths. We propose the Adjusted Sycophancy Score, a novel metric that isolates alignment bias by accounting for stochastic model instability, or "confusability". Through an extensive scaling analysis of the Qwen-3 and Llama-3 families, we identify a clear scaling trajectory for resilience. Furthermore, we reveal a counter-intuitive vulnerability in reasoning-optimized "Thinking" models: while they demonstrate high vanilla accuracy, their internal reasoning traces frequently rationalize incorrect user suggestions under authoritative pressure. Our results across frontier models suggest that benchmark performance is not a proxy for clinical reliability, and that simplified reasoning structures may offer superior robustness against expert-driven sycophancy.

---

### A Tumor Aware DenseNet Swin Hybrid Learning with Boosted and Hierarchical Feature Spaces for Large-Scale Brain MRI Classification

Authors: Muhammad Ali Shah, Muhammad Mansoor Alam, Saddam Hussain Khan
Published: 2026-01-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18330v1

This study proposes an efficient Densely Swin Hybrid (EDSH) framework for brain tumor MRI analysis, designed to jointly capture fine grained texture patterns and long range contextual dependencies. Two tumor aware experimental setups are introduced to address class-specific diagnostic challenges. The first setup employs a Boosted Feature Space (BFS), where independently customized DenseNet and Swint branches learn complementary local and global representations that are dimension aligned, fused, and boosted, enabling highly sensitive detection of diffuse glioma patterns by successfully learning the features of irregular shape, poorly defined mass, and heterogeneous texture. The second setup adopts a hierarchical DenseNet Swint architecture with Deep Feature Extraction have Dual Residual connections (DFE and DR), in which DenseNet serves as a stem CNN for structured local feature learning, while Swin_t models global tumor morphology, effectively suppressing false negatives in meningioma and pituitary tumor classification by learning the features of well defined mass, location (outside brain) and enlargments in tumors (dural tail or upward extension). DenseNet is customized at the input level to match MRI spatial characteristics, leveraging dense residual connectivity to preserve texture information and mitigate vanishing-gradient effects. In parallel, Swint is tailored through task aligned patch embedding and shifted-window self attention to efficiently capture hierarchical global dependencies. Extensive evaluation on a large-scale MRI dataset (stringent 40,260 images across four tumor classes) demonstrates consistent superiority over standalone CNNs, Vision Transformers, and hybrids, achieving 98.50 accuracy and recall on the test unseen dataset.

---

### Discriminability-Driven Spatial-Channel Selection with Gradient Norm for Drone Signal OOD Detection

Authors: Chuhan Feng, Jing Li, Jie Li, Lu Lv, Fengkui Gong
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18329v1

We propose a drone signal out-of-distribution (OOD) detection algorithm based on discriminability-driven spatial-channel selection with a gradient norm. Time-frequency image features are adaptively weighted along both spatial and channel dimensions by quantifying inter-class similarity and variance based on protocol-specific time-frequency characteristics. Subsequently, a gradient-norm metric is introduced to measure perturbation sensitivity for capturing the inherent instability of OOD samples, which is then fused with energy-based scores for joint inference. Simulation results demonstrate that the proposed algorithm provides superior discriminative power and robust performance via SNR and various drone types.

---

### Cognitive Fusion of ZC Sequences and Time-Frequency Images for Out-of-Distribution Detection of Drone Signals

Authors: Jie Li, Jing Li, Lu Lv, Zhanyu Ju, Fengkui Gong
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18326v1

We propose a drone signal out-of-distribution detection (OODD) algorithm based on the cognitive fusion of Zadoff-Chu (ZC) sequences and time-frequency images (TFI). ZC sequences are identified by analyzing the communication protocols of DJI drones, while TFI capture the time-frequency characteristics of drone signals with unknown or non-standard communication protocols. Both modalities are used jointly to enable OODD in the drone remote identification (RID) task. Specifically, ZC sequence features and TFI features are generated from the received radio frequency signals, which are then processed through dedicated feature extraction module to enhance and align them. The resultant multi-modal features undergo multi-modal feature interaction, single-modal feature fusion, and multi-modal feature fusion to produce features that integrate and complement information across modalities. Discrimination scores are computed from the fused features along both spatial and channel dimensions to capture time-frequency characteristic differences dictated by the communication protocols, and these scores will be transformed into adaptive attention weights. The weighted features are then passed through a Softmax function to produce the signal classification results. Simulation results demonstrate that the proposed algorithm outperforms existing algorithms and achieves 1.7% and 7.5% improvements in RID and OODD metrics, respectively. The proposed algorithm also performs strong robustness under varying flight conditions and across different drone types.

---

### Integrating Fine-Grained Audio-Visual Evidence for Robust Multimodal Emotion Reasoning

Authors: Zhixian Zhao, Wenjie Tian, Lei Xie
Published: 2026-01-26
Categories: cs.MM, cs.CL, cs.CV
arXiv: https://arxiv.org/abs/2601.18321v2

Multimodal emotion analysis is shifting from static classification to generative reasoning. Beyond simple label prediction, robust affective reasoning must synthesize fine-grained signals such as facial micro-expressions and prosodic which shifts to decode the latent causality within complex social contexts. However, current Multimodal Large Language Models (MLLMs) face significant limitations in fine-grained perception, primarily due to data scarcity and insufficient cross-modal fusion. As a result, these models often exhibit unimodal dominance which leads to hallucinations in complex multimodal interactions, particularly when visual and acoustic cues are subtle, ambiguous, or even contradictory (e.g., in sarcastic scenery). To address this, we introduce SABER-LLM, a framework designed for robust multimodal reasoning. First, we construct SABER, a large-scale emotion reasoning dataset comprising 600K video clips, annotated with a novel six-dimensional schema that jointly captures audiovisual cues and causal logic. Second, we propose the structured evidence decomposition paradigm, which enforces a "perceive-then-reason" separation between evidence extraction and reasoning to alleviate unimodal dominance. The ability to perceive complex scenes is further reinforced by consistency-aware direct preference optimization, which explicitly encourages alignment among modalities under ambiguous or conflicting perceptual conditions. Experiments on EMER, EmoBench-M, and SABER-Test demonstrate that SABER-LLM significantly outperforms open-source baselines and achieves robustness competitive with closed-source models in decoding complex emotional dynamics. The dataset and model are available at https://github.com/zxzhao0/SABER-LLM.

---

### MultiVis-Agent: A Multi-Agent Framework with Logic Rules for Reliable and Comprehensive Cross-Modal Data Visualization

Authors: Jinwei Lu, Yuanfeng Song, Chen Zhang, Raymond Chi-Wing Wong
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2601.18320v1

Real-world visualization tasks involve complex, multi-modal requirements that extend beyond simple text-to-chart generation, requiring reference images, code examples, and iterative refinement. Current systems exhibit fundamental limitations: single-modality input, one-shot generation, and rigid workflows. While LLM-based approaches show potential for these complex requirements, they introduce reliability challenges including catastrophic failures and infinite loop susceptibility. To address this gap, we propose MultiVis-Agent, a logic rule-enhanced multi-agent framework for reliable multi-modal and multi-scenario visualization generation. Our approach introduces a four-layer logic rule framework that provides mathematical guarantees for system reliability while maintaining flexibility. Unlike traditional rule-based systems, our logic rules are mathematical constraints that guide LLM reasoning rather than replacing it. We formalize the MultiVis task spanning four scenarios from basic generation to iterative refinement, and develop MultiVis-Bench, a benchmark with over 1,000 cases for multi-modal visualization evaluation. Extensive experiments demonstrate that our approach achieves 75.63% visualization score on challenging tasks, significantly outperforming baselines (57.54-62.79%), with task completion rates of 99.58% and code execution success rates of 94.56% (vs. 74.48% and 65.10% without logic rules), successfully addressing both complexity and reliability challenges in automated visualization generation.

---

### A Master Class on Reproducibility: A Student Hackathon on Advanced MRI Reconstruction Methods

Authors: Lina Felsner, Sevgi G. Kafali, Hannah Eichhorn, Agnes A. J. Leth, Aidas Batvinskas, Andre Datchev, Fabian Klemm, Jan Aulich, Puntika Leepagorn, Ruben Klinger, Daniel Rueckert, Julia A. Schnabel
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18314v1

We report the design, protocol, and outcomes of a student reproducibility hackathon focused on replicating the results of three influential MRI reconstruction papers: (a) MoDL, an unrolled model-based network with learned denoising; (b) HUMUS-Net, a hybrid unrolled multiscale CNN+Transformer architecture; and (c) an untrained, physics-regularized dynamic MRI method that uses a quantitative MR model for early stopping. We describe the setup of the hackathon and present reproduction outcomes alongside additional experiments, and we detail fundamental practices for building reproducible codebases.

---

### Convex Chance-Constrained Stochastic Control under Uncertain Specifications with Application to Learning-Based Hybrid Powertrain Control

Authors: Teruki Kato, Ryotaro Shima, Kenji Kashima
Published: 2026-01-26
Categories: eess.SY, cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.18313v1

This paper presents a strictly convex chance-constrained stochastic control framework that accounts for uncertainty in control specifications such as reference trajectories and operational constraints. By jointly optimizing control inputs and risk allocation under general (possibly non-Gaussian) uncertainties, the proposed method guarantees probabilistic constraint satisfaction while ensuring strict convexity, leading to uniqueness and continuity of the optimal solution. The formulation is further extended to nonlinear model-based control using exactly linearizable models identified through machine learning. The effectiveness of the proposed approach is demonstrated through model predictive control applied to a hybrid powertrain system.

---

### A Generative AI-Driven Reliability Layer for Action-Oriented Disaster Resilience

Authors: Geunsik Lim
Published: 2026-01-26
Categories: cs.AI, cs.SI, eess.SY
arXiv: https://arxiv.org/abs/2601.18308v1

As climate-related hazards intensify, conventional early warning systems (EWS) disseminate alerts rapidly but often fail to trigger timely protective actions, leading to preventable losses and inequities. We introduce Climate RADAR (Risk-Aware, Dynamic, and Action Recommendation system), a generative AI-based reliability layer that reframes disaster communication from alerts delivered to actions executed. It integrates meteorological, hydrological, vulnerability, and social data into a composite risk index and employs guardrail-embedded large language models (LLMs) to deliver personalized recommendations across citizen, volunteer, and municipal interfaces. Evaluation through simulations, user studies, and a municipal pilot shows improved outcomes, including higher protective action execution, reduced response latency, and increased usability and trust. By combining predictive analytics, behavioral science, and responsible AI, Climate RADAR advances people-centered, transparent, and equitable early warning systems, offering practical pathways toward compliance-ready disaster resilience infrastructures.

---

### Calibrating Beyond English: Language Diversity for Better Quantized Multilingual LLM

Authors: Everlyn Asiko Chimoto, Mostafa Elhoushi, Bruce A. Bassett
Published: 2026-01-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.18306v1

Quantization is an effective technique for reducing the storage footprint and computational costs of Large Language Models (LLMs), but it often results in performance degradation. Existing post-training quantization methods typically use small, English-only calibration sets; however, their impact on multilingual models remains underexplored. We systematically evaluate eight calibration settings (five single-language and three multilingual mixes) on two quantizers (GPTQ, AWQ) on data from 10 languages. Our findings reveal a consistent trend: non-English and multilingual calibration sets significantly improve perplexity compared to English-only baselines. Specifically, we observe notable average perplexity gains across both quantizers on Llama3.1 8B and Qwen2.5 7B, with multilingual mixes achieving the largest overall reductions of up to 3.52 points in perplexity. Furthermore, our analysis indicates that tailoring calibration sets to the evaluation language yields the largest improvements for individual languages, underscoring the importance of linguistic alignment. We also identify specific failure cases where certain language-quantizer combinations degrade performance, which we trace to differences in activation range distributions across languages. These results highlight that static one-size-fits-all calibration is suboptimal and that tailoring calibration data, both in language and diversity, plays a crucial role in robustly quantizing multilingual LLMs.

---

### SwipeGen: Bridging the Execution Gap in GUI Agents via Human-like Swipe Synthesis

Authors: Xuan Wang, Siyuan Su, Quantong Fu, Yongxiang Hu, Yangfan Zhou
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18305v2

Despite numerous Graphical User Interface (GUI) agents claiming to automate user interaction tasks, to date, few achieve satisfactory interaction capability with human users in real-world scenarios. Through empirical analysis, this paper identifies the root cause of the limited interaction capability as the rigid swipe execution. In particular, unlike humans, who perform swipes with fine-grained control over trajectory, speed, and timing, existing agents can only conduct simplistic, deterministic swipe behaviors, leading to frequent failures on complicated user-like interaction tasks. Due to the lack of open-source human-like swipe training data, we propose SwipeGen, the first tool for synthesizing diverse and human-like swipe interactions, and SwipeBench, the first benchmark for evaluating agents' swipe interaction quality. Extensive experiments show that SwipeGen can improve the swipe execution success rate of existing agents by up to 2.46x. Our code, dataset, and model are available at https://github.com/TSKGHS17/SwipeGen.

---

### Suppressing Final Layer Hidden State Jumps in Transformer Pretraining

Authors: Keigo Shibata, Kazuki Yano, Ryosuke Takahashi, Jaesung Lee, Wataru Ikeda, Jun Suzuki
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18302v1

This paper discusses the internal behavior of Transformer language models. Many recent pre-trained models have been reported to exhibit only slight changes in the angular distance between the input and output hidden state vectors in the middle Transformer layers, despite a disproportionately large ``jump'' in the angular distance occurring in or around the final Transformer layer. To characterize this, we first introduce a quantitative metric for the jump strength around the final layer, and then demonstrate its prevalence across many open-weight models, as well as its amplification throughout pre-training. Assuming such jumps indicate an undesirable property, we propose the jump-suppressing regularizer (JREG) which penalizes this jump during pre-training, thereby encouraging more balanced capability usage across the middle layers. Empirical evaluations of three model sizes of Llama-based models, trained with the proposed JREG method, reveal improved task performance compared to the baseline without altering the model architecture.

---

### Contextual Range-View Projection for 3D LiDAR Point Clouds

Authors: Seyedali Mousavi, Seyedhamidreza Mousavi, Masoud Daneshtalab
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18301v2

Range-view projection provides an efficient method for transforming 3D LiDAR point clouds into 2D range image representations, enabling effective processing with 2D deep learning models. However, a major challenge in this projection is the many-to-one conflict, where multiple 3D points are mapped onto the same pixel in the range image, requiring a selection strategy. Existing approaches typically retain the point with the smallest depth (closest to the LiDAR), disregarding semantic relevance and object structure, which leads to the loss of important contextual information. In this paper, we extend the depth-based selection rule by incorporating contextual information from both instance centers and class labels, introducing two mechanisms: \textit{Centerness-Aware Projection (CAP)} and \textit{Class-Weighted-Aware Projection (CWAP)}. In CAP, point depths are adjusted according to their distance from the instance center, thereby prioritizing central instance points over noisy boundary and background points. In CWAP, object classes are prioritized through user-defined weights, offering flexibility in the projection strategy. Our evaluations on the SemanticKITTI dataset show that CAP preserves more instance points during projection, achieving up to a 3.1\% mIoU improvement compared to the baseline. Furthermore, CWAP enhances the performance of targeted classes while having a negligible impact on the performance of other classes

---

### Temp-R1: A Unified Autonomous Agent for Complex Temporal KGQA via Reverse Curriculum Reinforcement Learning

Authors: Zhaoyan Gong, Zhiqiang Liu, Songze Li, Xiaoke Guo, Yuanxiang Liu, Xinle Deng, Zhizhen Liu, Lei Liang, Huajun Chen, Wen Zhang
Published: 2026-01-26
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.18296v2

Temporal Knowledge Graph Question Answering (TKGQA) is inherently challenging, as it requires sophisticated reasoning over dynamic facts with multi-hop dependencies and complex temporal constraints. Existing methods rely on fixed workflows and expensive closed-source APIs, limiting flexibility and scalability. We propose Temp-R1, the first autonomous end-to-end agent for TKGQA trained through reinforcement learning. To address cognitive overload in single-action reasoning, we expand the action space with specialized internal actions alongside external action. To prevent shortcut learning on simple questions, we introduce reverse curriculum learning that trains on difficult questions first, forcing the development of sophisticated reasoning before transferring to easier cases. Our 8B-parameter Temp-R1 achieves state-of-the-art performance on MultiTQ and TimelineKGQA, improving 19.8% over strong baselines on complex questions. Our work establishes a new paradigm for autonomous temporal reasoning agents. The code is available at https://github.com/zjukg/Temp-R1.

---

### TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment

Authors: Zhewen Tan, Wenhan Yu, Jianfeng Si, Tongxin Liu, Kaiqi Guan, Huiyan Jin, Jiawen Tao, Xiaokun Yuan, Duohe Ma, Xiangzheng Zhang, Tong Yang, Lin Sun
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18292v2

In recent years, safety risks associated with large language models have become increasingly prominent, highlighting the urgent need to mitigate the generation of toxic and harmful content. The mainstream paradigm for LLM safety alignment typically adopts a collaborative framework involving three roles: an attacker for adversarial prompt generation, a defender for safety defense, and an evaluator for response assessment. In this paper, we propose a closed-loop reinforcement learning framework called TriPlay-RL that enables iterative and co-improving collaboration among three roles with near-zero manual annotation. Experimental results show that the attacker preserves high output diversity while achieving a 20%-50% improvement in adversarial effectiveness; the defender attains 10%-30% gains in safety performance without degrading general reasoning capability; and the evaluator continuously refines its fine-grained judgment ability through iterations, accurately distinguishing unsafe responses, simple refusals, and useful guidance. Overall, our framework establishes an efficient and scalable paradigm for LLM safety alignment, enabling continuous co-evolution within a unified learning loop.

---

### U-Fold: Dynamic Intent-Aware Context Folding for User-Centric Agents

Authors: Jin Su, Runnan Fang, Yeqiu Li, Xiaobin Wang, Shihao Cai, Pengjun Xie, Ningyu Zhang, Fajie Yuan
Published: 2026-01-26
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.18285v1

Large language model (LLM)-based agents have been successfully deployed in many tool-augmented settings, but their scalability is fundamentally constrained by context length. Existing context-folding methods mitigate this issue by summarizing past interactions, yet they are typically designed for single-query or single-intent scenarios. In more realistic user-centric dialogues, we identify two major failure modes: (i) they irreversibly discard fine-grained constraints and intermediate facts that are crucial for later decisions, and (ii) their summaries fail to track evolving user intent, leading to omissions and erroneous actions. To address these limitations, we propose U-Fold, a dynamic context-folding framework tailored to user-centric tasks. U-Fold retains the full user--agent dialogue and tool-call history but, at each turn, uses two core components to produce an intent-aware, evolving dialogue summary and a compact, task-relevant tool log. Extensive experiments on $τ$-bench, $τ^2$-bench, VitaBench, and harder context-inflated settings show that U-Fold consistently outperforms ReAct (achieving a 71.4% win rate in long-context settings) and prior folding baselines (with improvements of up to 27.0%), particularly on long, noisy, multi-turn tasks. Our study demonstrates that U-Fold is a promising step toward transferring context-management techniques from single-query benchmarks to realistic user-centric applications.

---

### Think-Augmented Function Calling: Improving LLM Parameter Accuracy Through Embedded Reasoning

Authors: Lei Wei, Xiao Peng, Jinpeng Ou, Bin Wang
Published: 2026-01-26
Categories: cs.AI, cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.18282v2

Large language models (LLMs) have demonstrated remarkable capabilities in function calling for autonomous agents, yet current mechanisms lack explicit reasoning transparency during parameter generation, particularly for complex functions with interdependent parameters. While existing approaches like chain-of-thought prompting operate at the agent level, they fail to provide fine-grained reasoning guidance for individual function parameters. To address these limitations, we propose Think-Augmented Function Calling (TAFC), a novel framework that enhances function calling accuracy through explicit reasoning at both function and parameter levels. Our method introduces a universal "think" parameter augmentation that enables models to articulate their decision-making process, with dynamic optimization for parameter descriptions to improve reasoning quality. For complex parameters, TAFC automatically triggers granular reasoning based on complexity scoring, ensuring appropriate justification for critical decisions. Additionally, we propose reasoning-guided optimization to align generated reasoning with human expectations. TAFC requires no architectural modifications to existing LLMs while maintaining full API compatibility. Evaluation on ToolBench across proprietary and open-source models demonstrates significant improvements in parameter generation accuracy and reasoning coherence for multi-parameter functions, while providing enhanced interpretability for debugging AI agent behaviors.

---

### Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue

Authors: Yuhang Jia, Pei Liu, Haoqin Sun, Jiaming Zhou, Xuxin Cheng, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin
Published: 2026-01-26
Categories: cs.CL, cs.SD
arXiv: https://arxiv.org/abs/2601.18281v1

End-to-end Spoken Language Models (SLMs) hold great potential for paralinguistic perception, and numerous studies have aimed to enhance their capabilities, particularly for empathetic dialogue. However, current approaches largely depend on rigid supervised signals, such as ground-truth response in supervised fine-tuning or preference scores in reinforcement learning. Such reliance is fundamentally limited for modeling complex empathy, as there is no single "correct" response and a simple numerical score cannot fully capture the nuances of emotional expression or the appropriateness of empathetic behavior. To address these limitations, we sequentially introduce EmpathyEval, a descriptive natural-language-based evaluation model for assessing empathetic quality in spoken dialogues. Building upon EmpathyEval, we propose ReEmpathy, an end-to-end SLM that enhances empathetic dialogue through a novel Empathetic Self-Reflective Alternating Inference mechanism, which interleaves spoken response generation with free-form, empathy-related reflective reasoning. Extensive experiments demonstrate that ReEmpathy substantially improves empathy-sensitive spoken dialogue by enabling reflective reasoning, offering a promising approach toward more emotionally intelligent and empathy-aware human-computer interactions.

---

### What Do Learned Models Measure?

Authors: Indrė Žliobaitė
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18278v1

In many scientific and data-driven applications, machine learning models are increasingly used as measurement instruments, rather than merely as predictors of predefined labels. When the measurement function is learned from data, the mapping from observations to quantities is determined implicitly by the training distribution and inductive biases, allowing multiple inequivalent mappings to satisfy standard predictive evaluation criteria. We formalize learned measurement functions as a distinct focus of evaluation and introduce measurement stability, a property capturing invariance of the measured quantity across admissible realizations of the learning process and across contexts. We show that standard evaluation criteria in machine learning, including generalization error, calibration, and robustness, do not guarantee measurement stability. Through a real-world case study, we show that models with comparable predictive performance can implement systematically inequivalent measurement functions, with distribution shift providing a concrete illustration of this failure. Taken together, our results highlight a limitation of existing evaluation frameworks in settings where learned model outputs are identified as measurements, motivating the need for an additional evaluative dimension.

---

### TEFormer: Structured Bidirectional Temporal Enhancement Modeling in Spiking Transformers

Authors: Sicheng Shen, Mingyang Lv, Bing Han, Dongcheng Zhao, Guobin Shen, Feifei Zhao, Yi Zeng
Published: 2026-01-26
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.18274v3

In recent years, Spiking Neural Networks (SNNs) have achieved remarkable progress, with Spiking Transformers emerging as a promising architecture for energy-efficient sequence modeling. However, existing Spiking Transformers still lack a principled mechanism for effective temporal fusion, limiting their ability to fully exploit spatiotemporal dependencies. Inspired by feedforward feedback modulation in the human visual pathway, we propose TEFormer, the first Spiking Transformer framework that achieves bidirectional temporal fusion by decoupling temporal modeling across its core components. Specifically, TEFormer employs a lightweight and hyperparameter-free forward temporal fusion mechanism in the attention module, enabling fully parallel computation, while incorporating a backward gated recurrent structure in the MLP to aggregate temporal information in reverse order and reinforce temporal consistency. Extensive experiments across a wide range of benchmarks demonstrate that TEFormer consistently and significantly outperforms strong SNN and Spiking Transformer baselines under diverse datasets. Moreover, through the first systematic evaluation of Spiking Transformers under different neural encoding schemes, we show that the performance gains of TEFormer remain stable across encoding choices, indicating that the improved temporal modeling directly translates into reliable accuracy improvements across varied spiking representations. These results collectively establish TEFormer as an effective and general framework for temporal modeling in Spiking Transformers. Code is available https://github.com/Fancyssc/TEFormer.

---

### Toward Scalable Normalizing Flows for the Hubbard Model

Authors: Janik Kreit, Andrea Bulgarelli, Lena Funcke, Thomas Luu, Dominic Schuh, Simran Singh, Lorenzo Verzichelli
Published: 2026-01-26
Categories: cond-mat.str-el, cs.LG, hep-lat
arXiv: https://arxiv.org/abs/2601.18273v1

Normalizing flows have recently demonstrated the ability to learn the Boltzmann distribution of the Hubbard model, opening new avenues for generative modeling in condensed matter physics. In this work, we investigate the steps required to extend such simulations to larger lattice sizes and lower temperatures, with a focus on enhancing stability and efficiency. Additionally, we present the scaling behavior of stochastic normalizing flows and non-equilibrium Markov chain Monte Carlo methods for this fermionic system.

---

### Designing large language model prompts to extract scores from messy text: A shared dataset and challenge

Authors: Mike Thelwall
Published: 2026-01-26
Categories: cs.DL, cs.CL
arXiv: https://arxiv.org/abs/2601.18271v1

In some areas of computing, natural language processing and information science, progress is made by sharing datasets and challenging the community to design the best algorithm for an associated task. This article introduces a shared dataset of 1446 short texts, each of which describes a research quality score on the UK scale of 1* to 4*. This is a messy collection, with some texts not containing scores and others including invalid scores or strange formats. With this dataset there is also a description of what constitutes a valid score and a "gold standard" of the correct scores for these texts (including missing values). The challenge is to design a prompt for Large Language Models (LLMs) to extract the scores from these texts as accurately as possible. The format for the response should be a number and no other text so there are two aspects to the challenge: ensuring that the LLM returns only a number, and instructing it to deduce the correct number for the text. As part of this, the LLM prompt needs to explain when to return the missing value code, -1, instead of a number when the text does not clearly contain one. The article also provides an example of a simple prompt. The purpose of the challenge is twofold: to get an effective solution to this problem, and to increase understanding of prompt design and LLM capabilities for complex numerical tasks. The initial solution suggested has an accuracy of 72.6%, so the challenge is to beat this.

---

### Neural Network Approximation: A View from Polytope Decomposition

Authors: ZeYu Li, ShiJun Zhang, TieYong Zeng, FengLei Fan
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18264v1

Universal approximation theory offers a foundational framework to verify neural network expressiveness, enabling principled utilization in real-world applications. However, most existing theoretical constructions are established by uniformly dividing the input space into tiny hypercubes without considering the local regularity of the target function. In this work, we investigate the universal approximation capabilities of ReLU networks from a view of polytope decomposition, which offers a more realistic and task-oriented approach compared to current methods. To achieve this, we develop an explicit kernel polynomial method to derive an universal approximation of continuous functions, which is characterized not only by the refined Totik-Ditzian-type modulus of continuity, but also by polytopical domain decomposition. Then, a ReLU network is constructed to approximate the kernel polynomial in each subdomain separately. Furthermore, we find that polytope decomposition makes our approximation more efficient and flexible than existing methods in many cases, especially near singular points of the objective function. Lastly, we extend our approach to analytic functions to reach a higher approximation rate.

---

### Revisiting Aerial Scene Classification on the AID Benchmark

Authors: Subhajeet Das, Susmita Ghosh, Abhiroop Chatterjee
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18263v1

Aerial images play a vital role in urban planning and environmental preservation, as they consist of various structures, representing different types of buildings, forests, mountains, and unoccupied lands. Due to its heterogeneous nature, developing robust models for scene classification remains a challenge. In this study, we conduct a literature review of various machine learning methods for aerial image classification. Our survey covers a range of approaches from handcrafted features (e.g., SIFT, LBP) to traditional CNNs (e.g., VGG, GoogLeNet), and advanced deep hybrid networks. In this connection, we have also designed Aerial-Y-Net, a spatial attention-enhanced CNN with multi-scale feature fusion mechanism, which acts as an attention-based model and helps us to better understand the complexities of aerial images. Evaluated on the AID dataset, our model achieves 91.72% accuracy, outperforming several baseline architectures.

---

### FGGM: Fisher-Guided Gradient Masking for Continual Learning

Authors: Chao-Hong Tan, Qian Chen, Wen Wang, Yukun Ma, Chong Zhang, Chong Deng, Qinglin Zhang, Xiangang Li, Jieping Ye
Published: 2026-01-26
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.18261v1

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher Information. FGGM dynamically generates binary masks with adaptive thresholds, preserving critical parameters to balance stability and plasticity without requiring historical data. Unlike magnitude-based methods such as MIGU, our approach offers a mathematically principled parameter importance estimation. On the TRACE benchmark, FGGM shows a 9.6% relative improvement in retaining general capabilities over supervised fine-tuning (SFT) and a 4.4% improvement over MIGU on TRACE tasks. Additional analysis on code generation tasks confirms FGGM's superior performance and reduced forgetting, establishing it as an effective solution.

---

### Depth to Anatomy: Organ Localization from Depth Images for Automated Patient Table Positioning in Radiology Workflow

Authors: Eytan Kats, Kai Geissler, Daniel Mensing, Julien Senegas, Jochen G. Hirsch, Stefan Heldman, Mattias P. Heinrich
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18260v3

In clinical radiology, accurate patient table positioning is essential to align specific internal organs of interest with the scanner imaging isocenter, ensuring image quality and diagnostic reliability. Automated patient positioning can streamline this process and improve radiology workflow efficiency by reducing the time required for manual table adjustments and scout-based scan planning. We propose a learning-based framework that predicts 3D organ locations and shapes for 41 anatomical structures, including both bones and soft tissues, directly from a single 2D depth image of the body surface. Leveraging $10,020$ whole-body MRI scans from the German National Cohort (NAKO) dataset, we synthetically generate depth images paired with anatomical segmentations to train a convolutional neural network for volumetric organ prediction. Our method achieves a mean dice similarity coefficient of $0.44\pm0.2$ and and a symmetric average surface distance of $7.69\pm5.68$ mm across all structures. Furthermore, the model derives organ bounding boxes with a mean absolute detection offset of $10.99\pm5.54$ mm. Qualitative results on real-world depth images indicate the ability of the model to generalize to practical clinical settings. These findings suggest that depth-only organ localization can support automated patient positioning reducing setup time, minimizing operator variability, and improving patient comfort.

---

### Beyond Retention: Orchestrating Structural Safety and Plasticity in Continual Learning for LLMs

Authors: Fei Meng
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18255v1

Continual learning in Large Language Models (LLMs) faces the critical challenge of balancing stability (retaining old knowledge) and plasticity (learning new tasks). While Experience Replay (ER) is a standard countermeasure against catastrophic forgetting, its impact across diverse capabilities remains underexplored. In this work, we uncover a critical dichotomy in ER's behavior: while it induces positive backward transfer on robust, unstructured tasks (e.g., boosting performance on previous NLP classification tasks through repeated rehearsal), it causes severe negative transfer on fragile, structured domains like code generation (e.g., a significant relative drop in coding accuracy). This reveals that ER trades structural integrity for broad consolidation. To address this dilemma, we propose \textbf{Orthogonal Subspace Wake-up (OSW)}. OSW identifies essential parameter subspaces of previous tasks via a brief "wake-up" phase and enforces orthogonal updates for new tasks, providing a mathematically grounded "safety guarantee" for established knowledge structures. Empirical results across a diverse four-task sequence demonstrate that OSW uniquely succeeds in preserving fragile coding abilities where Replay fails, while simultaneously maintaining high plasticity for novel tasks. Our findings emphasize the necessity of evaluating structural safety alongside average retention in LLM continual learning.

---

### BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation

Authors: Peng Sun, Xiangyu Zhang, Duan Wu, Lu Tan, Jian Lin, He Yang, Qi Qian, Yikai Wang
Published: 2026-01-26
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.18253v2

Accurate evaluation of user satisfaction is critical for iterative development of conversational AI. However, for open-ended assistants, traditional A/B testing lacks reliable metrics: explicit feedback is sparse, while implicit metrics are ambiguous. To bridge this gap, we introduce BoRP (Bootstrapped Regression Probing), a scalable framework for high-fidelity satisfaction evaluation. Unlike generative approaches, BoRP leverages the geometric properties of LLM latent space. It employs a polarization-index-based bootstrapping mechanism to automate rubric generation and utilizes Partial Least Squares (PLS) to map hidden states to continuous scores. Experiments on industrial datasets show that BoRP (Qwen3-8B/14B) significantly outperforms generative baselines (even Qwen3-Max) in alignment with human judgments. Furthermore, BoRP reduces inference costs by orders of magnitude, enabling full-scale monitoring and highly sensitive A/B testing via CUPED.

---

### Co-PLNet: A Collaborative Point-Line Network for Prompt-Guided Wireframe Parsing

Authors: Chao Wang, Xuanying Li, Cheng Dai, Jinglei Feng, Yuxiang Luo, Hao Qin, Yuqi Ouyang
Published: 2026-01-26
Categories: cs.CV, cs.AI, cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.18252v2

Wireframe parsing aims to recover line segments and their junctions to form a structured geometric representation useful for downstream tasks such as Simultaneous Localization and Mapping (SLAM). Existing methods predict lines and junctions separately and reconcile them post-hoc, causing mismatches and reduced robustness. We present Co-PLNet, a point-line collaborative framework that exchanges spatial cues between the two tasks, where early detections are converted into spatial prompts via a Point-Line Prompt Encoder (PLP-Encoder), which encodes geometric attributes into compact and spatially aligned maps. A Cross-Guidance Line Decoder (CGL-Decoder) then refines predictions with sparse attention conditioned on complementary prompts, enforcing point-line consistency and efficiency. Experiments on Wireframe and YorkUrban show consistent improvements in accuracy and robustness, together with favorable real-time efficiency, demonstrating our effectiveness for structured geometry perception. Our code is available at https://github.com/GalacticHogrider/Co-PLNet.

---

### A multimodal vision foundation model for generalizable knee pathology

Authors: Kang Yu, Dingyu Wang, Zimu Yuan, Nan Zhou, Jiajun Liu, Jiaxin Liu, Shanggui Liu, Yaoyan Zheng, Huishu Yuan, Di Huang, Dong Jiang
Published: 2026-01-26
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.18250v1

Musculoskeletal disorders represent a leading cause of global disability, creating an urgent demand for precise interpretation of medical imaging. Current artificial intelligence (AI) approaches in orthopedics predominantly rely on task-specific, supervised learning paradigms. These methods are inherently fragmented, require extensive annotated datasets, and often lack generalizability across different modalities and clinical scenarios. The development of foundation models in this field has been constrained by the scarcity of large-scale, curated, and open-source musculoskeletal datasets. To address these challenges, we introduce OrthoFoundation, a multimodal vision foundation model optimized for musculoskeletal pathology. We constructed a pre-training dataset of 1.2 million unlabeled knee X-ray and MRI images from internal and public databases. Utilizing a Dinov3 backbone, the model was trained via self-supervised contrastive learning to capture robust radiological representations. OrthoFoundation achieves state-of-the-art (SOTA) performance across 14 downstream tasks. It attained superior accuracy in X-ray osteoarthritis diagnosis and ranked first in MRI structural injury detection. The model demonstrated remarkable label efficiency, matching supervised baselines using only 50% of labeled data. Furthermore, despite being pre-trained on knee images, OrthoFoundation exhibited exceptional cross-anatomy generalization to the hip, shoulder, and ankle. OrthoFoundation represents a significant advancement toward general-purpose AI for musculoskeletal imaging. By learning fundamental, joint-agnostic radiological semantics from large-scale multimodal data, it overcomes the limitations of conventional models, which provides a robust framework for reducing annotation burdens and enhancing diagnostic accuracy in clinical practice.

---

### Tractable Gaussian Phase Retrieval with Heavy Tails and Adversarial Corruption with Near-Linear Sample Complexity

Authors: Santanu Das, Jatin Batra
Published: 2026-01-26
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.18245v2

Phase retrieval is the classical problem of recovering a signal $x^* \in \mathbb{R}^n$ from its noisy phaseless measurements $y_i = \langle a_i, x^* \rangle^2 + ζ_i$ (where $ζ_i$ denotes noise, and $a_i$ is the sensing vector) for $i \in (m)$. The problem of phase retrieval has a rich history, with a variety of applications such as optics, crystallography, heteroscedastic regression, astrophysics, etc. A major consideration in algorithms for phase retrieval is robustness against measurement errors. In recent breakthroughs in algorithmic robust statistics, efficient algorithms have been developed for several parameter estimation tasks such as mean estimation, covariance estimation, robust principal component analysis (PCA), etc. in the presence of heavy-tailed noise and adversarial corruptions. In this paper, we study efficient algorithms for robust phase retrieval with heavy-tailed noise when a constant fraction of both the measurements $y_i$ and the sensing vectors $a_i$ may be arbitrarily adversarially corrupted. For this problem, Buna and Rebeschini (AISTATS 2025) very recently gave an exponential time algorithm with sample complexity $O(n \log n)$. Their algorithm needs a robust spectral initialization, specifically, a robust estimate of the top eigenvector of a covariance matrix, which they deemed to be beyond known efficient algorithmic techniques (similar spectral initializations are a key ingredient of a large family of phase retrieval algorithms). In this work, we make a connection between robust spectral initialization and recent algorithmic advances in robust PCA, yielding the first polynomial-time algorithms for robust phase retrieval with both heavy-tailed noise and adversarial corruptions, in fact with near-linear (in $n$) sample complexity.

---

### Vision-Language-Model-Guided Differentiable Ray Tracing for Fast and Accurate Multi-Material RF Parameter Estimation

Authors: Zerui Kang, Yishen Lim, Zhouyou Gu, Seung-Woo Ko, Tony Q. S. Quek, Jihong Park
Published: 2026-01-26
Categories: cs.CV, cs.NI
arXiv: https://arxiv.org/abs/2601.18242v2

Accurate radio-frequency (RF) material parameters are essential for electromagnetic digital twins in 6G systems, yet gradient-based inverse ray tracing (RT) remains sensitive to initialization and costly under limited measurements. This paper proposes a vision-language-model (VLM) guided framework that accelerates and stabilizes multi-material parameter estimation in a differentiable RT (DRT) engine. A VLM parses scene images to infer material categories and maps them to quantitative priors via an ITU-R material table, yielding informed conductivity initializations. The VLM further selects informative transmitter/receiver placements that promote diverse, material-discriminative paths. Starting from these priors, the DRT performs gradient-based refinement using measured received signal strengths. Experiments in NVIDIA Sionna on indoor scenes show 2-4$\times$ faster convergence and 10-100$\times$ lower final parameter error compared with uniform or random initialization and random placement baselines, achieving sub-0.1\% mean relative error with only a few receivers. Complexity analyses indicate per-iteration time scales near-linearly with the number of materials and measurement setups, while VLM-guided placement reduces the measurements required for accurate recovery. Ablations over RT depth and ray counts confirm further accuracy gains without significant per-iteration overhead. Results demonstrate that semantic priors from VLMs effectively guide physics-based optimization for fast and reliable RF material estimation.

---

### TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance

Authors: Elena Bruches, Vadim Alperovich, Dari Baturova, Roman Derunets, Daniil Grebenkin, Georgy Mkrtchyan, Oleg Sedukhin, Mikhail Klementev, Ivan Bondarenko, Nikolay Bushkov, Stanislav Moiseev
Published: 2026-01-26
Categories: cs.SE, cs.AI
arXiv: https://arxiv.org/abs/2601.18241v1

While Large Language Models (LLMs) have shown promise in software engineering, their application to unit testing remains largely confined to isolated test generation or oracle prediction, neglecting the broader challenge of test suite maintenance. We introduce TAM-Eval (Test Automated Maintenance Evaluation), a framework and benchmark designed to evaluate model performance across three core test maintenance scenarios: creation, repair, and updating of test suites. Unlike prior work limited to function-level tasks, TAM-Eval operates at the test file level, while maintaining access to full repository context during isolated evaluation, better reflecting real-world maintenance workflows. Our benchmark comprises 1,539 automatically extracted and validated scenarios from Python, Java, and Go projects. TAM-Eval supports system-agnostic evaluation of both raw LLMs and agentic workflows, using a reference-free protocol based on test suite pass rate, code coverage, and mutation testing. Empirical results indicate that state-of-the-art LLMs have limited capabilities in realistic test maintenance processes and yield only marginal improvements in test effectiveness. We release TAM-Eval as an open-source framework to support future research in automated software testing. Our data and code are publicly available at https://github.com/trndcenter/TAM-Eval.

---

### V-Loop: Visual Logical Loop Verification for Hallucination Detection in Medical Visual Question Answering

Authors: Mengyuan Jin, Zehui Liao, Yong Xia
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18240v1

Multimodal Large Language Models (MLLMs) have shown remarkable capability in assisting disease diagnosis in medical visual question answering (VQA). However, their outputs remain vulnerable to hallucinations (i.e., responses that contradict visual facts), posing significant risks in high-stakes medical scenarios. Recent introspective detection methods, particularly uncertainty-based approaches, offer computational efficiency but are fundamentally indirect, as they estimate predictive uncertainty for an image-question pair rather than verifying the factual correctness of a specific answer. To address this limitation, we propose Visual Logical Loop Verification (V-Loop), a training-free and plug-and-play framework for hallucination detection in medical VQA. V-Loop introduces a bidirectional reasoning process that forms a visually grounded logical loop to verify factual correctness. Given an input, the MLLM produces an answer for the primary input pair. V-Loop extracts semantic units from the primary QA pair, generates a verification question by conditioning on the answer unit to re-query the question unit, and enforces visual attention consistency to ensure answering both primary question and verification question rely on the same image evidence. If the verification answer matches the expected semantic content, the logical loop closes, indicating factual grounding; otherwise, the primary answer is flagged as hallucinated. Extensive experiments on multiple medical VQA benchmarks and MLLMs show that V-Loop consistently outperforms existing introspective methods, remains highly efficient, and further boosts uncertainty-based approaches when used in combination.

---

### TechING: Towards Real World Technical Image Understanding via VLMs

Authors: Tafazzul Nadeem, Bhavik Shangari, Manish Rai, Gagan Raj Gupta, Ashutosh Modi
Published: 2026-01-26
Categories: cs.CL, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18238v1

Professionals working in technical domain typically hand-draw (on whiteboard, paper, etc.) technical diagrams (e.g., flowcharts, block diagrams, etc.) during discussions; however, if they want to edit these later, it needs to be drawn from scratch. Modern day VLMs have made tremendous progress in image understanding but they struggle when it comes to understanding technical diagrams. One way to overcome this problem is to fine-tune on real world hand-drawn images, but it is not practically possible to generate large number of such images. In this paper, we introduce a large synthetically generated corpus (reflective of real world images) for training VLMs and subsequently evaluate VLMs on a smaller corpus of hand-drawn images (with the help of humans). We introduce several new self-supervision tasks for training and perform extensive experiments with various baseline models and fine-tune Llama 3.2 11B-instruct model on synthetic images on these tasks to obtain LLama-VL-TUG, which significantly improves the ROUGE-L performance of Llama 3.2 11B-instruct by 2.14x and achieves the best all-round performance across all baseline models. On real-world images, human evaluation reveals that we achieve minimum compilation errors across all baselines in 7 out of 8 diagram types and improve the average F1 score of Llama 3.2 11B-instruct by 6.97x.

---

### Generative AI in Saudi Arabia: A National Survey of Adoption, Risks, and Public Perceptions

Authors: Abdulaziz AlDakheel, Ali Alshehre, Esraa Alamoudi, Moslim AlKhabbaz, Ahmed Aljohani, Raed Alharbi
Published: 2026-01-26
Categories: cs.CY, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.18234v1

Generative Artificial Intelligence (GenAI) is rapidly becoming embedded in Saudi Arabia's digital transformation under Vision 2030, yet public awareness, adoption, and concerns surrounding these tools remain underexplored. This study provides an early snapshot of GenAI engagement among Saudi nationals. Using a nationwide survey of 330 participants across regions, age groups, and employment sectors, we examine seven dimensions of GenAI use: awareness and understanding, adoption patterns, perceived impacts, training needs, risks and barriers, data-sharing behaviors, and future expectations. Findings show that 93% of respondents actively use GenAI primarily for text-based tasks, while more advanced uses such as programming or multimodal generation are less common. Despite the prevalence of use, overall awareness and conceptual understanding remain uneven, with many reporting limited technical knowledge. Participants recognize GenAI's benefits for productivity, work quality, and understanding complex information, yet caution that sustained reliance may undermine critical thinking and key professional skills. Trust in AI-generated outputs remains cautious, with widespread concerns about privacy, misinformation, and ethical misuse, including potential job displacement. Respondents show strong interest in structured GenAI training that combines foundational skills, domain-specific applications, and clear guidance on privacy, ethics, and responsible use. These results establish a baseline for GenAI engagement in Saudi Arabia and highlight priorities for policymakers and developers: expanding AI literacy, ensuring culturally and linguistically aligned GenAI solutions, and strengthening frameworks for privacy and responsible deployment.

---

### Rethinking Cross-Modal Fine-Tuning: Optimizing the Interaction Between Feature Alignment and Target Fitting

Authors: Trong Khiem Tran, Manh Cuong Dao, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang
Published: 2026-01-26
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.18231v4

Adapting pre-trained models to unseen feature modalities has become increasingly important due to the growing need for cross-disciplinary knowledge integration. A key challenge here is how to align the representation of new modalities with the most relevant parts of the pre-trained model's representation space to enable accurate knowledge transfer. This requires combining feature alignment with target fine-tuning, but uncalibrated combinations can exacerbate misalignment between the source and target feature-label structures and reduce target generalization. Existing work, however, lacks a theoretical understanding of this critical interaction between feature alignment and target fitting. To bridge this gap, we develop a principled framework that establishes a provable generalization bound on the target error, which explains the interaction between feature alignment and target fitting through a novel concept of feature-label distortion. This bound offers actionable insights into how this interaction should be optimized for practical algorithm design. The resulting approach achieves significantly improved performance over state-of-the-art methods across a wide range of benchmark datasets.

---

### Facial Emotion Recognition on FER-2013 using an EfficientNetB2-Based Approach

Authors: Sahil Naik, Soham Bagayatkar, Pavankumar Singh
Published: 2026-01-26
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18228v1

Detection of human emotions based on facial images in real-world scenarios is a difficult task due to low image quality, variations in lighting, pose changes, background distractions, small inter-class variations, noisy crowd-sourced labels, and severe class imbalance, as observed in the FER-2013 dataset of 48x48 grayscale images. Although recent approaches using large CNNs such as VGG and ResNet achieve reasonable accuracy, they are computationally expensive and memory-intensive, limiting their practicality for real-time applications. We address these challenges using a lightweight and efficient facial emotion recognition pipeline based on EfficientNetB2, trained using a two-stage warm-up and fine-tuning strategy. The model is enhanced with AdamW optimization, decoupled weight decay, label smoothing (epsilon = 0.06) to reduce annotation noise, and clipped class weights to mitigate class imbalance, along with dropout, mixed-precision training, and extensive real-time data augmentation. The model is trained using a stratified 87.5%/12.5% train-validation split while keeping the official test set intact, achieving a test accuracy of 68.78% with nearly ten times fewer parameters than VGG16-based baselines. Experimental results, including per-class metrics and learning dynamics, demonstrate stable training and strong generalization, making the proposed approach suitable for real-time and edge-based applications.

---

### Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Tasks

Authors: Haotian Li, Shijun Yang, Weizhen Qi, Silei Zhao, Rui Hua, Mingzhu Song, Xiaojian Yang, Chao Peng
Published: 2026-01-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.18226v2

Conventional agent systems often struggle in open-ended environments where task distributions continuously drift and external supervision is scarce. Their reliance on static toolsets or offline training lags behind these dynamics, leaving the system's capability boundaries rigid and unknown. To address this, we propose the In-Situ Self-Evolving paradigm. This approach treats sequential task interactions as a continuous stream of experience, enabling the system to distill short-term execution feedback into long-term, reusable capabilities without access to ground-truth labels. Within this framework, we identify tool evolution as the critical pathway for capability expansion, which provides verifiable, binary feedback signals. Within this framework, we develop Yunjue Agent, a system that iteratively synthesizes, optimizes, and reuses tools to navigate emerging challenges. To optimize evolutionary efficiency, we further introduce a Parallel Batch Evolution strategy. Empirical evaluations across five diverse benchmarks under a zero-start setting demonstrate significant performance gains over proprietary baselines. Additionally, complementary warm-start evaluations confirm that the accumulated general knowledge can be seamlessly transferred to novel domains. Finally, we propose a novel metric to monitor evolution convergence, serving as a function analogous to training loss in conventional optimization. We open-source our codebase, system traces, and evolved tools to facilitate future research in resilient, self-evolving intelligence.

---

### ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants

Authors: Pei Wang, Yanan Wu, Xiaoshuai Song, Weixun Wang, Gengru Chen, Zhongwen Li, Kezhong Yan, Ken Deng, Qi Liu, Shuaibing Zhao, Shaopan Xiong, Xuepeng Liu et al.
Published: 2026-01-26
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.18225v1

Large language model (LLM)-based agents are increasingly deployed in e-commerce shopping. To perform thorough, user-tailored product searches, agents should interpret personal preferences, engage in multi-turn dialogues, and ultimately retrieve and discriminate among highly similar products. However, existing research has yet to provide a unified simulation environment that consistently captures all of these aspects, and always focuses solely on evaluation benchmarks without training support. In this paper, we introduce ShopSimulator, a large-scale and challenging Chinese shopping environment. Leveraging ShopSimulator, we evaluate LLMs across diverse scenarios, finding that even the best-performing models achieve less than 40% full-success rate. Error analysis reveals that agents struggle with deep search and product selection in long trajectories, fail to balance the use of personalization cues, and to effectively engage with users. Further training exploration provides practical guidance for overcoming these weaknesses, with the combination of supervised fine-tuning (SFT) and reinforcement learning (RL) yielding significant performance improvements. Code and data will be released at https://github.com/ShopAgent-Team/ShopSimulator.

---

### HomoFM: Deep Homography Estimation with Flow Matching

Authors: Mengfan He, Liangzheng Sun, Chunyu Li, Ziyang Meng
Published: 2026-01-26
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.18222v1

Deep homography estimation has broad applications in computer vision and robotics. Remarkable progresses have been achieved while the existing methods typically treat it as a direct regression or iterative refinement problem and often struggling to capture complex geometric transformations or generalize across different domains. In this work, we propose HomoFM, a new framework that introduces the flow matching technique from generative modeling into the homography estimation task for the first time. Unlike the existing methods, we formulate homography estimation problem as a velocity field learning problem. By modeling a continuous and point-wise velocity field that transforms noisy distributions into registered coordinates, the proposed network recovers high-precision transformations through a conditional flow trajectory. Furthermore, to address the challenge of domain shifts issue, e.g., the cases of multimodal matching or varying illumination scenarios, we integrate a gradient reversal layer (GRL) into the feature extraction backbone. This domain adaptation strategy explicitly constrains the encoder to learn domain-invariant representations, significantly enhancing the network's robustness. Extensive experiments demonstrate the effectiveness of the proposed method, showing that HomoFM outperforms state-of-the-art methods in both estimation accuracy and robustness on standard benchmarks. Code and data resource are available at https://github.com/hmf21/HomoFM.

---

### Automated HER2 scoring with uncertainty quantification using lensfree holography and deep learning

Authors: Che-Yung Shen, Xilin Yang, Yuzhu Li, Leon Lenk, Aydogan Ozcan
Published: 2026-01-26
Categories: physics.med-ph, cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.18219v1

Accurate assessment of human epidermal growth factor receptor 2 (HER2) expression is critical for breast cancer diagnosis, prognosis, and therapy selection; yet, most existing digital HER2 scoring methods rely on bulky and expensive optical systems. Here, we present a compact and cost-effective lensfree holography platform integrated with deep learning for automated HER2 scoring of immunohistochemically stained breast tissue sections. The system captures lensfree diffraction patterns of stained HER2 tissue sections under RGB laser illumination and acquires complex field information over a sample area of ~1,250 mm^2 at an effective throughput of ~84 mm^2 per minute. To enhance diagnostic reliability, we incorporated an uncertainty quantification strategy based on Bayesian Monte Carlo dropout, which provides autonomous uncertainty estimates for each prediction and supports reliable, robust HER2 scoring, with an overall correction rate of 30.4%. Using a blinded test set of 412 unique tissue samples, our approach achieved a testing accuracy of 84.9% for 4-class (0, 1+, 2+, 3+) HER2 classification and 94.8% for binary (0/1+ vs. 2+/3+) HER2 scoring with uncertainty quantification. Overall, this lensfree holography approach provides a practical pathway toward portable, high-throughput, and cost-effective HER2 scoring, particularly suited for resource-limited settings, where traditional digital pathology infrastructure is unavailable.

---