# Research Papers — 2026-01 · bundle page 134 of 189

> Full-text markdown of papers #6651–6700 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/134
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/133.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/135.md)

### Unified Personalized Understanding, Generating and Editing

Authors: Yu Zhong, Tianwei Lin, Ruike Zhu, Yuqian Yuan, Haoyu Zheng, Liang Liang, Wenqiao Zhang, Feifei Shao, Haoyuan Li, Wanggui He, Hao Jiang, Yueting Zhuang
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06965v1

Unified large multimodal models (LMMs) have achieved remarkable progress in general-purpose multimodal understanding and generation. However, they still operate under a ``one-size-fits-all'' paradigm and struggle to model user-specific concepts (e.g., generate a photo of \texttt{<maeve>}) in a consistent and controllable manner. Existing personalization methods typically rely on external retrieval, which is inefficient and poorly integrated into unified multimodal pipelines. Recent personalized unified models introduce learnable soft prompts to encode concept information, yet they either couple understanding and generation or depend on complex multi-stage training, leading to cross-task interference and ultimately to fuzzy or misaligned personalized knowledge. We present \textbf{OmniPersona}, an end-to-end personalization framework for unified LMMs that, for the first time, integrates personalized understanding, generation, and image editing within a single architecture. OmniPersona introduces structurally decoupled concept tokens, allocating dedicated subspaces for different tasks to minimize interference, and incorporates an explicit knowledge replay mechanism that propagates personalized attribute knowledge across tasks, enabling consistent personalized behavior. To systematically evaluate unified personalization, we propose \textbf{\texttt{OmniPBench}}, extending the public UnifyBench concept set with personalized editing tasks and cross-task evaluation protocols integrating understanding, generation, and editing. Experimental results demonstrate that OmniPersona delivers competitive and robust performance across diverse personalization tasks. We hope OmniPersona will serve as a strong baseline and spur further research on controllable, unified personalization.

---

### The Impact of Anisotropic Covariance Structure on the Training Dynamics and Generalization Error of Linear Networks

Authors: Taishi Watanabe, Ryo Karakida, Jun-nosuke Teramae
Published: 2026-01-11
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.06961v1

The success of deep neural networks largely depends on the statistical structure of the training data. While learning dynamics and generalization on isotropic data are well-established, the impact of pronounced anisotropy on these crucial aspects is not yet fully understood. We examine the impact of data anisotropy, represented by a spiked covariance structure, a canonical yet tractable model, on the learning dynamics and generalization error of a two-layer linear network in a linear regression setting. Our analysis reveals that the learning dynamics proceed in two distinct phases, governed initially by the input-output correlation and subsequently by other principal directions of the data structure. Furthermore, we derive an analytical expression for the generalization error, quantifying how the alignment of the spike structure of the data with the learning task improves performance. Our findings offer deep theoretical insights into how data anisotropy shapes the learning trajectory and final performance, providing a foundation for understanding complex interactions in more advanced network architectures.

---

### HAS-VQ: Hessian-Adaptive Sparse Vector Quantization for High-Fidelity LLM Compression

Authors: Vladimer Khasia
Published: 2026-01-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06959v1

Post-training quantization is essential for deploying Large Language Models (LLMs) on resource-constrained devices. However, standard integer quantization (e.g., INT4) fundamentally degrades performance by imposing a uniform grid on the heavy-tailed distribution of weight parameters, particularly in smaller-scale models (e.g., <2B parameters). We introduce HAS-VQ (Hessian-Adaptive Sparse Vector Quantization), a compression framework that strictly decouples high-sensitivity outliers from the bulk weight distribution using second-order sensitivity analysis. HAS-VQ employs a Hessian-Masked Decoupling strategy to isolate sensitive parameters, followed by robust Vector Quantization (VQ) of the remaining dense body. Crucially, we introduce a residual sparse feedback mechanism that corrects quantization errors in the most sensitive dimensions, ensuring exact reconstruction of outliers. We evaluate HAS-VQ on SmolLM2-1.7B, demonstrating two distinct regimes of superiority: (1) Pareto Dominance over Integer Baselines: At 4.23 effective bits-per-parameter (BPP), we achieve a perplexity of 14.23, significantly outperforming the standard INT4 baseline (20.03 PPL at 4.71 BPP). (2) High-Fidelity Compression: Relative to the FP16 baseline, HAS-VQ achieves a 2.3x reduction in model size (7.03 BPP) while maintaining statistically indistinguishable perplexity (10.12 vs. 10.04), effectively offering a lossless compression alternative for bandwidth-constrained environments. The code is available at https://github.com/VladimerKhasia/HASVQ

---

### X-Coder: Advancing Competitive Programming with Synthetic Tasks, Solutions, and Tests

Authors: Jie Wu, Haoling Li, Xin Zhang, Jiani Guo, Jane Luo, Xuewei Yang, Steven Liu, Yangyu Huang, Ruihang Chu, Scarlett Li, Yujiu Yang
Published: 2026-01-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.06953v3

Competitive programming remains challenging for code LLMs. Despite recent progress, many training pipelines still depend on scarce real-world data, raising concerns about scalability and near-duplicate benchmark contamination. In this paper, we examine whether synthetic training artifacts can support the complete SFT-to-RL cycle for competitive programming: no real-world tasks, solutions, or test cases are directly used for post-training. To this end, we synthesize tasks, verified solutions, and reliable test cases that serve as reward signals for reinforcement learning. To improve reward reliability, we introduce a dual-verification strategy that reduces noise in both selected solutions and test outputs. Using this high-quality data, we train the X-Coder model series. X-Coder-14B achieves 67.5\% avg@8 on LiveCodeBench v5 and 63.4\% on v6, outperforming its base model by over 40 points. Further analysis provides practical insights into synthetic post-training, highlighting the value of diverse tasks, verified long-CoT supervision, and code-centric reinforcement. Our data and models are released at https://github.com/JieWu02/X-Coder

---

### SketchJudge: A Diagnostic Benchmark for Grading Hand-drawn Diagrams with Multimodal Large Language Models

Authors: Yuhang Su, Mei Wang, Yaoyao Zhong, Guozhang Li, Shixing Li, Yihan Feng, Hua Huang
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06944v1

While Multimodal Large Language Models (MLLMs) have achieved remarkable progress in visual understanding, they often struggle when faced with the unstructured and ambiguous nature of human-generated sketches. This limitation is particularly pronounced in the underexplored task of visual grading, where models should not only solve a problem but also diagnose errors in hand-drawn diagrams. Such diagnostic capabilities depend on complex structural, semantic, and metacognitive reasoning. To bridge this gap, we introduce SketchJudge, a novel benchmark tailored for evaluating MLLMs as graders of hand-drawn STEM diagrams. SketchJudge encompasses 1,015 hand-drawn student responses across four domains: geometry, physics, charts, and flowcharts, featuring diverse stylistic variations and distinct error types. Evaluations on SketchJudge demonstrate that even advanced MLLMs lag significantly behind humans, validating the benchmark's effectiveness in exposing the fragility of current vision-language alignment in symbolic and noisy contexts. All data, code, and evaluation scripts are publicly available at https://github.com/yuhangsu82/SketchJudge.

---

### Watching, Reasoning, and Searching: A Video Deep Research Benchmark on Open Web for Agentic Video Reasoning

Authors: Chengwen Liu, Xiaomin Yu, Zhuoyue Chang, Zhe Huang, Shuo Zhang, Heng Lian, Jisheng Dang, Rui Xu, Sen Hu, Jianheng Hou, Chengwei Qin, Xiaobin Hu et al.
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06943v2

In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed across the open web; models therefore need to jointly perform cross-frame clue extraction, iterative retrieval, and multi-hop reasoning-based verification. To bridge this gap, we construct the first video deep research benchmark, VideoDR. VideoDR centers on video-conditioned open-domain video question answering, requiring cross-frame visual anchor extraction, interactive web retrieval, and multi-hop reasoning over joint video-web evidence; through rigorous human annotation and quality control, we obtain high-quality video deep research samples spanning six semantic domains. We evaluate multiple closed-source and open-source multimodal large language models under both the Workflow and Agentic paradigms, and the results show that Agentic is not consistently superior to Workflow: its gains depend on a model's ability to maintain the initial video anchors over long retrieval chains. Further analysis indicates that goal drift and long-horizon consistency are the core bottlenecks. In sum, VideoDR provides a systematic benchmark for studying video agents in open-web settings and reveals the key challenges for next-generation video deep research agents.

---

### Towards Operational Streamflow Forecasting in the Limpopo River Basin using Long Short-Term Memory Networks

Authors: James Tlhomole, Edoardo Borgomeo, Karthikeyan Matheswaran, Mariangel Garcia Andarcia
Published: 2026-01-11
Categories: cs.LG, physics.geo-ph
arXiv: https://arxiv.org/abs/2601.06941v1

Robust hydrological simulation is key for sustainable development, water management strategies, and climate change adaptation. In recent years, deep learning methods have been demonstrated to outperform mechanistic models at the task of hydrological discharge simulation. Adoption of these methods has been catalysed by the proliferation of large sample hydrology datasets, consisting of the observed discharge and meteorological drivers, along with geological and topographical catchment descriptors. Deep learning methods infer rainfall-runoff characteristics that have been shown to generalise across catchments, benefitting from the data diversity in large datasets. Despite this, application to catchments in Africa has been limited. The lack of adoption of deep learning methodologies is primarily due to sparsity or lack of the spatiotemporal observational data required to enable downstream model training. We therefore investigate the application of deep learning models, including LSTMs, for hydrological discharge simulation in the transboundary Limpopo River basin, emphasising application to data scarce regions. We conduct a number of computational experiments primarily focused on assessing the impact of varying the LSTM model input data on performance. Results confirm that data constraints remain the largest obstacle to deep learning applications across African river basins. We further outline the impact of human influence on data-driven modelling which is a commonly overlooked aspect of data-driven large-sample hydrology approaches and investigate solutions for model adaptation under smaller datasets. Additionally, we include recommendations for future efforts towards seasonal hydrological discharge prediction and direct comparison or inclusion of SWAT model outputs, as well as architectural improvements.

---

### VISTA: Knowledge-Driven Vessel Trajectory Imputation with Repair Provenance

Authors: Hengyu Liu, Tianyi Li, Haoyu Wang, Kristian Torp, Tiancheng Zhang, Yushuai Li, Christian S. Jensen
Published: 2026-01-11
Categories: cs.DB, cs.AI
arXiv: https://arxiv.org/abs/2601.06940v2

Repairing incomplete trajectory data is essential for downstream spatio-temporal applications. Yet, existing repair methods focus solely on reconstruction without documenting the reasoning behind repair decisions, undermining trust in safety-critical applications where repaired trajectories affect operational decisions, such as in maritime anomaly detection and route planning. We introduce repair provenance - structured, queryable metadata that documents the full reasoning chain behind each repair - which transforms imputation from pure data recovery into a task that supports downstream decision-making. We propose VISTA (knowledge-driven interpretable vessel trajectory imputation), a framework that reliably equips repaired trajectories with repair provenance by grounding LLM reasoning in data-verified knowledge. Specifically, we formalize Structured Data-derived Knowledge (SDK), a knowledge model whose data-verifiable components can be validated against real data and used to anchor and constrain LLM-generated explanations. We organize SDK in a Structured Data-derived Knowledge Graph (SD-KG) and establish a data-knowledge-data loop for extraction, validation, and incremental maintenance over large-scale AIS data. A workflow management layer with parallel scheduling, fault tolerance, and redundancy control ensures consistent and efficient end-to-end processing. Experiments on two large-scale AIS datasets show that VISTA achieves state-of-the-art accuracy, improving over baselines by 5-91% and reducing inference time by 51-93%, while producing repair provenance, whose interpretability is further validated through a case study and an interactive demo system.

---

### Forgetting Similar Samples: Can Machine Unlearning Do it Better?

Authors: Heng Xu, Tianqing Zhu, Dayong Ye, Lefeng Zhang, Le Wang, Wanlei Zhou
Published: 2026-01-11
Categories: cs.LG, cs.CR
arXiv: https://arxiv.org/abs/2601.06938v1

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine unlearning strategies, we argue that these methods mainly aim at removing samples rather than removing samples' influence on the model, thus overlooking the fundamental definition of machine unlearning. In this paper, we first conduct a comprehensive study to evaluate the effectiveness of existing unlearning schemes when the training dataset includes many samples similar to those targeted for unlearning. Specifically, we evaluate: Do existing unlearning methods truly adhere to the original definition of machine unlearning and effectively eliminate all influence of target samples when similar samples are present in the training dataset? Our extensive experiments, conducted on four carefully constructed datasets with thorough analysis, reveal a notable gap between the expected and actual performance of most existing unlearning methods for image and language models, even for the retraining-from-scratch baseline. Additionally, we also explore potential solutions to enhance current unlearning approaches.

---

### mind_call: A Dataset for Mental Health Function Calling with Large Language Models

Authors: Fozle Rabbi Shafi, M. Anwar Hossain, Salimur Choudhury
Published: 2026-01-11
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06937v1

Large Language Model (LLM)-based systems increasingly rely on function calling to enable structured and controllable interaction with external data sources, yet existing datasets do not address mental health-oriented access to wearable sensor data. This paper presents a synthetic function-calling dataset designed for mental health assistance grounded in wearable health signals such as sleep, physical activity, cardiovascular measures, stress indicators, and metabolic data. The dataset maps diverse natural language queries to standardized API calls derived from a widely adopted health data schema. Each sample includes a user query, a query category, an explicit reasoning step, a normalized temporal parameter, and a target function. The dataset covers explicit, implicit, behavioral, symptom-based, and metaphorical expressions, which reflect realistic mental health-related user interactions. This resource supports research on intent grounding, temporal reasoning, and reliable function invocation in LLM-based mental health agents and is publicly released to promote reproducibility and future work.

---

### Symphonym: Universal Phonetic Embeddings for Cross-Script Name Matching

Authors: Stephen Gadd
Published: 2026-01-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06932v4

Matching place names across writing systems is a persistent obstacle to the integration of multilingual geographic sources, whether modern gazetteers, medieval itineraries, or colonial-era surveys. Existing approaches depend on language-specific phonetic algorithms or romanisation steps that discard phonetic information, and none generalises across script boundaries. This paper presents Symphonym, a neural embedding system which maps toponyms from twenty writing systems into a unified 128-dimensional phonetic space, enabling direct cross-script similarity comparison without language identification or phonetic resources at inference time. A Teacher-Student knowledge distillation architecture first learns from articulatory phonetic features derived from IPA transcriptions, then transfers this knowledge to a character-level Student model. Trained on 32.7 million triplet samples drawn from 67 million toponyms spanning GeoNames, Wikidata, and the Getty Thesaurus of Geographic Names, the Student achieves the highest Recall@1 (85.2%) and Mean Reciprocal Rank (90.8%) on the MEHDIE cross-script benchmark -- medieval Hebrew and Arabic toponym matches curated by domain experts and entirely independent of the training data -- demonstrating cross-temporal generalisation from modern training material to pre-modern sources. An ablation using raw articulatory features alone yields only 45.0% MRR, confirming the contribution of the neural training curriculum. The approach naturally handles pre-standardisation orthographic variation characteristic of historical documents, and transfers effectively to personal names in archival sources, suggesting broad applicability to name resolution tasks in digital humanities and linked open data contexts.

---

### Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos

Authors: Haodong Chen, Qiang Huang, Jiaqi Zhao, Qiuping Jiang, Xiaojun Chang, Jun Yu
Published: 2026-01-11
Categories: cs.CV, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06931v2

Vision-Language Models (VLMs) are increasingly deployed in socially consequential settings, raising concerns about social bias driven by demographic cues. A central challenge in measuring such social bias is attribution under visual confounding: real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution. We propose a \textbf{face-only counterfactual evaluation paradigm} that isolates demographic effects while preserving real-image realism. Starting from real photographs, we generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed. Based on this paradigm, we construct \textbf{FOCUS}, a dataset of 480 scene-matched counterfactual images across six occupations and ten demographic groups, and propose \textbf{REFLECT}, a benchmark comprising three decision-oriented tasks: two-alternative forced choice, multiple-choice socioeconomic inference, and numeric salary recommendation. Experiments on five state-of-the-art VLMs reveal that demographic disparities persist under strict visual control and vary substantially across task formulations. These findings underscore the necessity of controlled, counterfactual audits and highlight task design as a critical factor in evaluating social bias in multimodal models.

---

### RenderFlow: Single-Step Neural Rendering via Flow Matching

Authors: Shenghao Zhang, Runtao Liu, Christopher Schroers, Yang Zhang
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06928v2

Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry buffers (G-buffers) to produce visually compelling results without explicit scene geometry or light simulation, they remain constrained by two major limitations. First, the iterative nature of the diffusion process introduces substantial latency. Second, the inherent stochasticity of these generative models compromises physical accuracy and temporal consistency. In response to these challenges, we propose a novel, end-to-end, deterministic, single-step neural rendering framework, RenderFlow, built upon a flow matching paradigm. To further strengthen both rendering quality and generalization, we propose an efficient and effective module for sparse keyframe guidance. Our method significantly accelerates the rendering process and, by optionally incorporating sparsely rendered keyframes as guidance, enhances both the physical plausibility and overall visual quality of the output. The resulting pipeline achieves near real-time performance with photorealistic rendering quality, effectively bridging the gap between the efficiency of modern generative models and the precision of traditional physically based rendering. Furthermore, we demonstrate the versatility of our framework by introducing a lightweight, adapter-based module that efficiently repurposes the pretrained forward model for the inverse rendering task of intrinsic decomposition.

---

### TreePS-RAG: Tree-based Process Supervision for Reinforcement Learning in Agentic RAG

Authors: Tianhua Zhang, Kun Li, Junan Li, Yunxiang Li, Hongyin Luo, Xixin Wu, James Glass, Helen Meng
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06922v1

Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced by reinforcement learning (RL) with outcome-based supervision. While effective, relying solely on sparse final rewards limits step-wise credit assignment and provides weak guidance for intermediate reasoning and actions. Recent efforts explore process-level supervision, but typically depend on offline constructed training data, which risks distribution shift, or require costly intermediate annotations. We present TreePS-RAG, an online, tree-based RL framework for agentic RAG that enables step-wise credit assignment while retaining standard outcome-only rewards. Our key insight is to model agentic RAG reasoning as a rollout tree, where each reasoning step naturally maps to a node. This tree structure allows step utility to be estimated via Monte Carlo estimation over its descendant outcomes, yielding fine-grained process advantages without requiring intermediate labels. To make this paradigm practical, we introduce an efficient online tree construction strategy that preserves exploration diversity under a constrained computational budget. With a rollout cost comparable to strong baselines like Search-R1, experiments on seven multi-hop and general QA benchmarks across multiple model scales show that TreePS-RAG consistently and significantly outperforms both outcome-supervised and leading process-supervised RL methods.

---

### Calibrating Agent-Based Financial Markets Simulators with Pretrainable Automatic Posterior Transformation-Based Surrogates

Authors: Boquan Jiang, Zhenhua Yang, Chenkai Wang, Muyao Zhong, Heping Fang, Peng Yang
Published: 2026-01-11
Categories: cs.NE, cs.MA
arXiv: https://arxiv.org/abs/2601.06920v1

Calibrating Agent-Based Models (ABMs) is an important optimization problem for simulating the complex social systems, where the goal is to identify the optimal parameter of a given ABM by minimizing the discrepancy between the simulated data and the real-world observations. Unfortunately, it suffers from the extensive computational costs of iterative evaluations, which involves the expensive simulation with the candidate parameter. While Surrogate-Assisted Evolutionary Algorithms (SAEAs) have been widely adopted to alleviate the computational burden, existing methods face two key limitations: 1) surrogating the original evaluation function is hard due the nonlinear yet multi-modal nature of the ABMs, and 2) the commonly used surrogates cannot share the optimization experience among multiple calibration tasks, making the batched calibration less effective. To address these issues, this work proposes Automatic posterior transformation with Negatively Correlated Search and Adaptive Trust-Region (ANTR). ANTR first replaces the traditional surrogates with a pretrainable neural density estimator that directly models the posterior distribution of the parameters given observed data, thereby aligning the optimization objective with parameter-space accuracy. Furthermore, we incorporate a diversity-preserving search strategy to prevent premature convergence and an adaptive trust-region method to efficiently allocate computational resources. We take two representative ABM-based financial market simulators as the test bench as due to the high non-linearity. Experiments demonstrate that the proposed ANTR significantly outperforms conventional metaheuristics and state-of-the-art SAEAs in both calibration accuracy and computational efficiency, particularly in batch calibration scenarios across multiple market conditions.

---

### Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systems

Authors: Mohammed Azeez Khan, Aaron D'Souza, Vijay Choyal
Published: 2026-01-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06916v2

Efficient materials discovery requires reducing costly first-principles calculations for training machine-learned interatomic potentials (MLIPs). We develop an active learning (AL) framework that iteratively selects informative structures from the Materials Project and Open Quantum Materials Database (OQMD) using compositional and property-based descriptors with a neural network ensemble model. Query-by-Committee enables real-time uncertainty quantification. We compare four strategies: random sampling (baseline), uncertainty-based sampling, diversity-based sampling (k-means clustering with farthest-point refinement), and a hybrid approach. Experiments across four material systems (C, Si, Fe, and TiO2) with 5 random seeds demonstrate that diversity sampling achieves competitive or superior performance, with 10.9% improvement on TiO2. Our approach achieves equivalent accuracy with 5-13% fewer labeled samples than random baselines. The complete pipeline executes on Google Colab in under 4 hours per system using less than 8 GB RAM, democratizing MLIP development for resource-limited researchers. Open-source code and configurations are available on GitHub. This multi-system evaluation provides practical guidelines for data-efficient MLIP training and highlights integration with symmetry-aware architectures as a promising future direction.

---

### Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities

Authors: Ying Zhou, Jiacheng Wei, Yu Qi, Faguo Wu, Xiao Zhang
Published: 2026-01-11
Categories: cs.CR, cs.AI
arXiv: https://arxiv.org/abs/2601.06914v1

Large language models (LLMs) demonstrate remarkable capabilities in natural language understanding and generation. Despite being trained on large-scale, high-quality data, LLMs still fail to outperform traditional static analysis tools in specialized domains like smart contract vulnerability detection. To address this issue, this paper proposes a post-training algorithm based on atomic task decomposition and fusion. This algorithm aims to achieve combinatorial generalization under limited data by decomposing complex reasoning tasks. Specifically, we decompose the reentrancy vulnerability detection task into four linearly independent atomic tasks: identifying external calls, identifying state updates, identifying data dependencies between external calls and state updates, and determining their data flow order. These tasks form the core components of our approach. By training on synthetic datasets, we generate three compiler-verified datasets. We then employ the Slither tool to extract structural information from the control flow graph and data flow graph, which is used to fine-tune the LLM's adapter. Experimental results demonstrate that low-rank normalization fusion with the LoRA adapter improves the LLM's reentrancy vulnerability detection accuracy to 98.2%, surpassing state-of-the-art methods. On 31 real-world contracts, the algorithm achieves a 20% higher recall than traditional analysis tools.

---

### Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities

Authors: Taehyun Hwang, Dahngoon Kim, Min-hwan Oh
Published: 2026-01-11
Categories: cs.LG, stat.ML
arXiv: https://arxiv.org/abs/2601.06913v1

We study the multinomial logit (MNL) contextual bandit problem for sequential assortment selection. Although most existing research assumes utility functions to be linear in item features, this linearity assumption restricts the modeling of intricate interactions between items and user preferences. A recent work (Zhang & Luo, 2024) has investigated general utility function classes, yet its method faces fundamental trade-offs between computational tractability and statistical efficiency. To address this limitation, we propose a computationally efficient algorithm for MNL contextual bandits leveraging the upper confidence bound principle, specifically designed for non-linear parametric utility functions, including those modeled by neural networks. Under a realizability assumption and a mild geometric condition on the utility function class, our algorithm achieves a regret bound of $\tilde{O}(\sqrt{T})$, where $T$ denotes the total number of rounds. Our result establishes that sharp $\tilde{O}(\sqrt{T})$-regret is attainable even with neural network-based utilities, without relying on strong assumptions such as neural tangent kernel approximations. To the best of our knowledge, our proposed method is the first computationally tractable algorithm for MNL contextual bandits with non-linear utilities that provably attains $\tilde{O}(\sqrt{T})$ regret. Comprehensive numerical experiments validate the effectiveness of our approach, showing robust performance not only in realizable settings but also in scenarios with model misspecification.

---

### Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models

Authors: Shaoning Sun, Mingzhu Cai, Huang He, Bingjin Chen, Siqi Bao, Yujiu Yang, Hua Wu, Haifeng Wang
Published: 2026-01-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06911v1

Language model families exhibit striking disparity in their capacity to benefit from reinforcement learning: under identical training, models like Qwen achieve substantial gains, while others like Llama yield limited improvements. Complementing data-centric approaches, we reveal that this disparity reflects a hidden structural property: \textbf{distributional clarity} in probability space. Through a three-stage analysis-from phenomenon to mechanism to interpretation-we uncover that RL-friendly models exhibit intra-class compactness and inter-class separation in their probability assignments to correct vs. incorrect responses. We quantify this clarity using the \textbf{Silhouette Coefficient} ($S$) and demonstrate that (1) high $S$ correlates strongly with RL performance; (2) low $S$ is associated with severe logic errors and reasoning instability. To confirm this property, we introduce a Silhouette-Aware Reweighting strategy that prioritizes low-$S$ samples during training. Experiments across six mathematical benchmarks show consistent improvements across all model families, with gains up to 5.9 points on AIME24. Our work establishes distributional clarity as a fundamental, trainable property underlying RL-Friendliness.

---

### UDPNet: Unleashing Depth-based Priors for Robust Image Dehazing

Authors: Zengyuan Zuo, Junjun Jiang, Gang Wu, Xianming Liu
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06909v2

Image dehazing has witnessed significant advancements with the development of deep learning models. However, most existing methods focus solely on single-modal RGB features, neglecting the inherent correlation between scene depth and haze distribution. Even those that jointly optimize depth estimation and image dehazing often suffer from suboptimal performance due to inadequate utilization of accurate depth information. In this paper, we present UDPNet, a general framework that leverages depth-based priors from a large-scale pretrained depth estimation model DepthAnything V2 to boost existing image dehazing models. Specifically, our architecture comprises two key components: the Depth-Guided Attention Module (DGAM) adaptively modulates features via lightweight depth-guided channel attention, and the Depth Prior Fusion Module (DPFM) enables hierarchical fusion of multi-scale depth map features by dual sliding-window multi-head cross-attention mechanism. These modules ensure both computational efficiency and effective integration of depth priors. Moreover, the depth priors empower the network to dynamically adapt to varying haze densities, illumination conditions, and domain gaps across synthetic and real-world data. Extensive experimental results demonstrate the effectiveness of our UDPNet, outperforming the state-of-the-art methods on popular dehazing datasets, with PSNR improvements of 0.85 dB on SOTS-indoor, 1.19 dB on Haze4K, and 1.79 dB on NHR. Our proposed solution establishes a new benchmark for depth-aware dehazing across various scenarios. Pretrained models and codes are released at our project https://github.com/Harbinzzy/UDPNet.

---

### Fine-grained Verbal Attack Detection via a Hierarchical Divide-and-Conquer Framework

Authors: Quan Zheng, Yuanhe Tian, Ming Wang, Yan Song
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06907v1

In the digital era, effective identification and analysis of verbal attacks are essential for maintaining online civility and ensuring social security. However, existing research is limited by insufficient modeling of conversational structure and contextual dependency, particularly in Chinese social media where implicit attacks are prevalent. Current attack detection studies often emphasize general semantic understanding while overlooking user response relationships, hindering the identification of implicit and context-dependent attacks. To address these challenges, we present the novel "Hierarchical Attack Comment Detection" dataset and propose a divide-and-conquer, fine-grained framework for verbal attack recognition based on spatiotemporal information. The proposed dataset explicitly encodes hierarchical reply structures and chronological order, capturing complex interaction patterns in multi-turn discussions. Building on this dataset, the framework decomposes attack detection into hierarchical subtasks, where specialized lightweight models handle explicit detection, implicit intent inference, and target identification under constrained context. Extensive experiments on the proposed dataset and benchmark intention detection datasets show that smaller models using our framework significantly outperform larger monolithic models relying on parameter scaling, demonstrating the effectiveness of structured task decomposition.

---

### V2P: Visual Attention Calibration for GUI Grounding via Background Suppression and Center Peaking

Authors: Jikai Chen, Long Chen, Dong Wang, Qinglin Su, Zhixuan Chu, Bingguang Hao, Leilei Gan, Chenyi Zhuang, Jinjie Gu
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06899v2

Precise localization of GUI elements is crucial for the development of GUI agents. Traditional methods rely on bounding box or center-point regression, neglecting spatial interaction uncertainty and visual-semantic hierarchies. Recent methods incorporate attention mechanisms but still face two key issues: (1) ignoring processing background regions causes attention drift from the desired area, and (2) uniform modeling the target UI element fails to distinguish between its center and edges, leading to click imprecision. Inspired by how humans visually process and interact with GUI elements, we propose the Valley-to-Peak (V2P) method to address these issues. To mitigate background distractions, V2P introduces a suppression attention mechanism that minimizes the model's focus on irrelevant regions to highlight the intended region. For the issue of center-edge distinction, V2P applies a Fitts' Law-inspired approach by modeling GUI interactions as 2D Gaussian heatmaps where the weight gradually decreases from the center towards the edges. The weight distribution follows a Gaussian function, with the variance determined by the target's size. Consequently, V2P effectively isolates the target area and teaches the model to concentrate on the most essential point of the UI element. The model trained by V2P achieves the performance with 92.4\% and 52.5\% on two benchmarks ScreenSpot-v2 and ScreenSpot-Pro (see Fig.~\ref{fig:main_results_charts}). Ablations further confirm each component's contribution, underscoring V2P's generalizability in precise GUI grounding tasks and its potential for real-world deployment in future GUI agents.

---

### TagSpeech: End-to-End Multi-Speaker ASR and Diarization with Fine-Grained Temporal Grounding

Authors: Mingyue Huo, Yiwen Shao, Yuheng Zhang
Published: 2026-01-11
Categories: eess.AS, cs.CL
arXiv: https://arxiv.org/abs/2601.06896v2

We present TagSpeech, a unified LLM-based framework that utilizes Temporal Anchor Grounding for joint multi-speaker ASR and diarization. The framework is built on two key designs: (1) decoupled semantic and speaker streams fine-tuned via Serialized Output Training (SOT) to learn turn-taking dynamics; and (2) an interleaved time anchor mechanism that not only supports fine-grained timestamp prediction but also acts as a synchronization signal between semantic understanding and speaker tracking. Compared to previous works that primarily focus on speaker-attributed ASR or implicit diarization, TagSpeech addresses the challenge of fine-grained speaker-content alignment and explicitly models "who spoke what and when" in an end-to-end manner. Experiments on AMI and AliMeeting benchmarks demonstrate that our method achieves consistent improvements in Diarization Error Rate (DER) over strong end-to-end baselines, including Qwen-Omni and Gemini, particularly in handling complex speech overlaps. Moreover, TagSpeech employs a parameter-efficient training paradigm in which the LLM backbone is frozen and only lightweight projectors are trained, resulting in strong performance with low computational cost.

---

### CLIMP: Contrastive Language-Image Mamba Pretraining

Authors: Nimrod Shabtay, Itamar Zimerman, Eli Schwartz, Raja Giryes
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06891v2

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.The code and models are publicly available at https://github.com/NimrodShabtay/CLIMP}

---

### Paraphrasing Adversarial Attack on LLM-as-a-Reviewer

Authors: Masahiro Kaneko
Published: 2026-01-11
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.06884v1

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and conflates injection susceptibility with evaluation robustness. We propose the Paraphrasing Adversarial Attack (PAA), a black-box optimization method that searches for paraphrased sequences yielding higher review scores while preserving semantic equivalence and linguistic naturalness. PAA leverages in-context learning, using previous paraphrases and their scores to guide candidate generation. Experiments across five ML and NLP conferences with three LLM reviewers and five attacking models show that PAA consistently increases review scores without changing the paper's claims. Human evaluation confirms that generated paraphrases maintain meaning and naturalness. We also find that attacked papers exhibit increased perplexity in reviews, offering a potential detection signal, and that paraphrasing submissions can partially mitigate attacks.

---

### MixRI: Mixing Features of Reference Images for Novel Object Pose Estimation

Authors: Xinhang Liu, Jiawei Shi, Zheng Dang, Yuchao Dai
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06883v1

We present MixRI, a lightweight network that solves the CAD-based novel object pose estimation problem in RGB images. It can be instantly applied to a novel object at test time without finetuning. We design our network to meet the demands of real-world applications, emphasizing reduced memory requirements and fast inference time. Unlike existing works that utilize many reference images and have large network parameters, we directly match points based on the multi-view information between the query and reference images with a lightweight network. Thanks to our reference image fusion strategy, we significantly decrease the number of reference images, thus decreasing the time needed to process these images and the memory required to store them. Furthermore, with our lightweight network, our method requires less inference time. Though with fewer reference images, experiments on seven core datasets in the BOP challenge show that our method achieves comparable results with other methods that require more reference images and larger network parameters.

---

### Unsupervised Domain Adaptation with SAM-RefiSeR for Enhanced Brain Tumor Segmentation

Authors: Dillan Imans, Phuoc-Nguyen Bui, Duc-Tai Le, Hyunseung Choo
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06882v1

Unsupervised Domain Adaptation with SAM-RefiSeR for Enhanced Brain Tumor Segmentation

---

### Personality-Aware Reinforcement Learning for Persuasive Dialogue with LLM-Driven Simulation

Authors: Donghuo Zeng, Roberto Legaspi, Kazushi Ikeda
Published: 2026-01-11
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.06877v1

Effective persuasive dialogue agents adapt their strategies to individual users, accounting for the evolution of their psychological states and intentions throughout conversations. We present a personality-aware reinforcement learning approach comprising three main modules: (1) a Strategy-Oriented Interaction Framework, which serves as an agenda-based strategy controller that selects strategy-level actions and generate responses via Maximal Marginal Relevance (MMR) retrieval to ensure contextual relevance, diversity, and scalable data generation; (2) Personality-Aware User Representation Learning, which produces an 81-dimensional mixed-type embedding predicted at each turn from recent exchanges and appended to the reinforcement learning state; and (3) a Dueling Double DQN (D3QN) model and Reward Prediction, in which the policy is conditioned on dialogue history and turn-level personality estimates and trained using a composite reward incorporating agreement intent, donation amount, and changeof-mind penalties. We use an agenda-based LLM simulation pipeline to generate diverse interactions, from which personality estimation is inferred from the generated utterances. Experiments on the PersuasionForGood (P4G) dataset augmented with simulated dialogues reveal three main findings: (i) turn-level personality conditioning improves policy adaptability and cumulative persuasion rewards; (ii) LLM-driven simulation enhances generalization to unseen user behaviors; and (iii) incorporating a change-of-mind penalty reduces post-agreement retractions while slightly improving donation outcomes. These results demonstrate that structured interaction, dynamic personality estimation, and behaviorally informed rewards together yield more effective persuasive policies.

---

### An Ubuntu-Guided Large Language Model Framework for Cognitive Behavioral Mental Health Dialogue

Authors: Sontaga G. Forane, Absalom E. Ezugwu, Kevin Igwe, Karen van den Berg
Published: 2026-01-11
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.06875v1

South Africa's escalating mental health crisis, compounded by limited access to culturally responsive care, calls for innovative and contextually grounded interventions. While large language models show considerable promise for mental health support, their predominantly Western-centric training data limit cultural and linguistic applicability in African contexts. This study introduces a proof-of-concept framework that integrates cognitive behavioral therapy with the African philosophy of Ubuntu to create a culturally sensitive, emotionally intelligent, AI-driven mental health dialogue system. Guided by a design science research methodology, the framework applies both deep theoretical and therapeutic adaptations as well as surface-level linguistic and communicative cultural adaptations. Key CBT techniques, including behavioral activation and cognitive restructuring, were reinterpreted through Ubuntu principles that emphasize communal well-being, spiritual grounding, and interconnectedness. A culturally adapted dataset was developed through iterative processes of language simplification, spiritual contextualization, and Ubuntu-based reframing. The fine-tuned model was evaluated through expert-informed case studies, employing UniEval for conversational quality assessment alongside additional measures of CBT reliability and cultural linguistic alignment. Results demonstrate that the model effectively engages in empathetic, context-aware dialogue aligned with both therapeutic and cultural objectives. Although real-time end-user testing has not yet been conducted, the model underwent rigorous review and supervision by domain specialist clinical psychologists. The findings highlight the potential of culturally embedded emotional intelligence to enhance the contextual relevance, inclusivity, and effectiveness of AI-driven mental health interventions across African settings.

---

### MVGGT: Multimodal Visual Geometry Grounded Transformer for Multiview 3D Referring Expression Segmentation

Authors: Changli Wu, Haodong Wang, Jiayi Ji, Yutian Yao, Chunsai Du, Jihua Kang, Yanwei Fu, Liujuan Cao
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06874v3

Most existing 3D referring expression segmentation (3DRES) methods rely on dense, high-quality point clouds, while real-world agents such as robots and mobile phones operate with only a few sparse RGB views and strict latency constraints. We introduce Multi-view 3D Referring Expression Segmentation (MV-3DRES), where the model must recover scene structure and segment the referred object directly from sparse multi-view images. Traditional two-stage pipelines, which first reconstruct a point cloud and then perform segmentation, often yield low-quality geometry, produce coarse or degraded target regions, and run slowly. We propose the Multimodal Visual Geometry Grounded Transformer (MVGGT), an efficient end-to-end framework that integrates language information into sparse-view geometric reasoning through a dual-branch design. Training in this setting exposes a critical optimization barrier, termed Foreground Gradient Dilution (FGD), where sparse 3D signals lead to weak supervision. To resolve this, we introduce Per-view No-target Suppression Optimization (PVSO), which provides stronger and more balanced gradients across views, enabling stable and efficient learning. To support consistent evaluation, we build MVRefer, a benchmark that defines standardized settings and metrics for MV-3DRES. Experiments show that MVGGT establishes the first strong baseline and achieves both high accuracy and fast inference, outperforming existing alternatives. The code is available at https://mvggt.github.io/.

---

### Applying Embedding-Based Retrieval to Airbnb Search

Authors: Mustafa Abdool, Soumyadip Banerjee, Moutupsi Paul, Do-kyum Kim, Xioawei Liu, Bin Xu, Tracy Yu, Hui Gao, Karen Ouyang, Huiji Gao, Liwei He, Stephanie Moyerman et al.
Published: 2026-01-11
Categories: cs.IR, cs.LG
arXiv: https://arxiv.org/abs/2601.06873v1

The goal of Airbnb search is to match guests with the ideal accommodation that fits their travel needs. This is a challenging problem, as popular search locations can have around a hundred thousand available homes, and guests themselves have a wide variety of preferences. Furthermore, the launch of new product features, such as \textit{flexible date search,} significantly increased the number of eligible homes per search query. As such, there is a need for a sophisticated retrieval system which can provide high-quality candidates with low latency in a way that integrates with the overall ranking stack. This paper details our journey to build an efficient and high-quality retrieval system for Airbnb search. We describe the key unique challenges we encountered when implementing an Embedding-Based Retrieval (EBR) system for a two sided marketplace like Airbnb -- such as the dynamic nature of the inventory, a lengthy user funnel with multiple stages, and a variety of product surfaces. We cover unique insights when modeling the retrieval problem, how to build robust evaluation systems, and design choices for online serving. The EBR system was launched to production and powers several use-cases such as regular search, flexible date and promotional emails for marketing campaigns. The system demonstrated statistically-significant improvements in key metrics, such as booking conversion, via A/B testing.

---

### QASA: Quality-Aware Semantic Augmentation for Robust Multimodal Sentiment Analysis

Authors: Jiazhang Liang, Jianheng Dai, Miaosen Luo, Menghua Jiang, Sijie Mai
Published: 2026-01-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06870v2

Multimodal large language models have demonstrated strong ability in capturing semantic representations for multimodal sentiment analysis. Their capacity to learn stable and generalizable multimodal features is limited, however, by the scarcity of high-quality training data. To address this, we propose QASA (Quality-Aware Semantic Augmentation), which uses diffusion models to generate augmented visual and auditory samples, thereby enlarging the training dataset and supporting multimodal learning. The generated samples can vary in quality and may exhibit cross-modal inconsistencies. To manage this, we introduce a decoupled quality-aware scoring module that assigns training weights based on the reliability of each augmented sample. This approach reduces the influence of low-quality data and contributes to more stable and robust model training. The framework combines the generative capabilities of diffusion models with the semantic reasoning of multimodal large models, providing an automated data augmentation strategy that does not require human annotation while improving generalization and robustness under limited high-quality data. Experiments on the CH-SIMS dataset show that QASA yields a relative increase of 18.0\% and 5.9\% in five-class accuracy (Acc5) and binary accuracy (Acc2), respectively, and it also outperforms existing methods on the CMU-MOSI and MUStARD benchmarks.

---

### U-MASK: User-adaptive Spatio-Temporal Masking for Personalized Mobile AI Applications

Authors: Shiyuan Zhang, Yilai Liu, Yuwei Du, Ruoxuan Yang, Dong In Kim, Hongyang Du
Published: 2026-01-11
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.06867v1

Personalized mobile artificial intelligence applications are widely deployed, yet they are expected to infer user behavior from sparse and irregular histories under a continuously evolving spatio-temporal context. This setting induces a fundamental tension among three requirements, i.e., immediacy to adapt to recent behavior, stability to resist transient noise, and generalization to support long-horizon prediction and cold-start users. Most existing approaches satisfy at most two of these requirements, resulting in an inherent impossibility triangle in data-scarce, non-stationary personalization. To address this challenge, we model mobile behavior as a partially observed spatio-temporal tensor and unify short-term adaptation, long-horizon forecasting, and cold-start recommendation as a conditional completion problem, where a user- and task-specific mask specifies which coordinates are treated as evidence. We propose U-MASK, a user-adaptive spatio-temporal masking method that allocates evidence budgets based on user reliability and task sensitivity. To enable mask generation under sparse observations, U-MASK learns a compact, task-agnostic user representation from app and location histories via U-SCOPE, which serves as the sole semantic conditioning signal. A shared diffusion transformer then performs mask-guided generative completion while preserving observed evidence, so personalization and task differentiation are governed entirely by the mask and the user representation. Experiments on real-world mobile datasets demonstrate consistent improvements over state-of-the-art methods across short-term prediction, long-horizon forecasting, and cold-start settings, with the largest gains under severe data sparsity. The code and dataset will be available at https://github.com/NICE-HKU/U-MASK.

---

### Learning QoE from Packet-Level Measurements in Encrypted Video Conferencing Traffic

Authors: Michael Sidorov, Ofer Hadar
Published: 2026-01-11
Categories: cs.CR, cs.CV, cs.LG, cs.MM, eess.IV
arXiv: https://arxiv.org/abs/2601.06862v2

The quality of the user experience has become one of the most important aspects in todays world, as it directly influences individuals willingness to continue using or abandon a product or service. In this context, video conferencing applications (VCAs), which experienced widespread adoption following the COVID-19 pandemic, must deliver excellent performance to remain competitive in an increasingly crowded market. Although content providers (CPs) such as Zoom, WhatsApp, Telegram, and Google Meet can assess conversation quality by comparing transmitted and received data. The widespread use of end-to-end encryption in VCAs makes quality-of-experience (QoE) evaluation by internet service providers (ISPs) far more challenging. Since ISPs do not have access to the encrypted content, they must rely on passive measurements of unencrypted traffic characteristics on the data path. In this work, we present a simple yet effective QoE prediction framework based on an almost stock convolutional neural network (CNN) architecture that uses only the packet sizes extracted from the communication between two participants in a video conferencing (VC) call to predict two QoE metrics: BRISQUE and MOS. The proposed framework is simple, easy to implement, and does not require high-end computational resources, yet it provides superior prediction performance, as shown in our experiments on two custom datasets collected from WhatsApp and Zoom, which achieve substantial improvements over previous models for the QoE prediction task.

---

### BiasLab: A Multilingual Dual-Framing Framework for LLM Bias Measurement, Applied to Workplace and HR Contexts

Authors: William Guey, Wei Zhang, Pei-Luen Patrick Rau, Pierrick Bougault, Vitor D. de Moura, Bertan Ucar, Jose O. Gomes
Published: 2026-01-11
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.06861v2

Background: Large language models (LLMs) harbor systematic biases that are particularly consequential in workplace and HR contexts, where their outputs increasingly influence hiring, job design, and organizational decisions. Existing bias-evaluation approaches remain methodologically fragmented, limiting practitioners' ability to assess deployment risks. Objective: This study introduces BiasLab, a multilingual dual-framing framework to quantify and compare directional output-level bias in LLMs, demonstrated across six workplace and HR-relevant topics. Methods: BiasLab combines mirrored affirmative and reverse prompt pairs, randomized wrapper perturbations, fixed-choice response constraints, and polarity-aligned scoring. Ten LLMs were evaluated across six topics (gender in leadership, employment gap candidates, age in hiring, remote versus office work, four-day versus five-day work weeks, and AI-assisted versus human-only hiring), spanning 12 languages and 30 iterations per framing direction, yielding 43,200 responses. Results: All ten models showed consistent directional preferences across every topic. A recurring asymmetric pattern emerged in which models rejected disfavored claims more strongly than they endorsed their opposites, a distinction invisible to single-frame designs. Conclusions: BiasLab provides a standardized, reproducible instrument for measuring directional preferences across models. Whether a preference constitutes bias in a fairness sense is topic-dependent: for protected attributes such as gender and age it maps onto equal-employment standards, whereas elsewhere it is better described as systematic preference. The framework lets organizations compare and vet models before adopting them for hiring.

---

### ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration

Authors: Yifei Chen, Guanting Dong, Zhicheng Dou
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06860v2

Large Language Models (LLMs) can extend their parameter knowledge limits by adopting the Tool-Integrated Reasoning (TIR) paradigm. However, existing LLM-based agent training framework often focuses on answers' accuracy, overlooking specific alignment for behavior patterns. Consequently, agent often exhibits ineffective actions during TIR tasks, such as redundant and insufficient tool calls. How to calibrate erroneous behavioral patterns when executing TIR tasks, thereby exploring effective trajectories, remains an open-ended problem. In this paper, we propose ET-Agent, a training framework for calibrating agent's tool-use behavior through two synergistic perspectives: Self-evolving Data Flywheel and Behavior Calibration Training. Specifically, we introduce a self-evolutionary data flywheel to generate enhanced data, used to fine-tune LLM to improve its exploration ability. Based on this, we implement an two-phases behavior-calibration training framework. It is designed to progressively calibrate erroneous behavioral patterns to optimal behaviors. Further in-depth experiments confirm the superiority of \ourmodel{} across multiple dimensions, including correctness, efficiency, reasoning conciseness, and tool execution accuracy. Our ET-Agent framework provides practical insights for research in the TIR field. Codes can be found in https://github.com/asilverlight/ET-Agent

---

### Deep Learning-Based Channel Extrapolation for Dual-Band Massive MIMO Systems

Authors: Qikai Xiao, Kehui Li, Binggui Zhou, Shaodan Ma
Published: 2026-01-11
Categories: eess.SP, cs.LG
arXiv: https://arxiv.org/abs/2601.06858v2

Future wireless communication systems will increasingly rely on the integration of millimeter wave (mmWave) and sub-6 GHz bands to meet heterogeneous demands on high-speed data transmission and extensive coverage. To fully exploit the benefits of mmWave bands in massive multiple-input multiple-output (MIMO) systems, highly accurate channel state information (CSI) is required. However, directly estimating the mmWave channel demands substantial pilot overhead due to the large CSI dimension and low signal-to-noise ratio (SNR) led by severe path loss and blockage attenuation. In this paper, we propose an efficient \textbf{M}ulti-\textbf{D}omain \textbf{F}usion \textbf{C}hannel \textbf{E}xtrapolator (MDFCE) to extrapolate sub-6 GHz band CSI to mmWave band CSI, so as to reduce the pilot overhead for mmWave CSI acquisition in dual band massive MIMO systems. Unlike traditional channel extrapolation methods based on mathematical modeling, the proposed MDFCE combines the mixture-of-experts framework and the multi-head self-attention mechanism to fuse multi-domain features of sub-6 GHz CSI, aiming to characterize the mapping from sub-6 GHz CSI to mmWave CSI effectively and efficiently. The simulation results demonstrate that MDFCE can achieve superior performance with less training pilots compared with existing methods across various antenna array scales and signal-to-noise ratio levels while showing a much higher computational efficiency.

---

### MoE-DisCo:Low Economy Cost Training Mixture-of-Experts Models

Authors: Xin Ye, Daning Cheng, Boyang Zhang, Yunquan Zhang
Published: 2026-01-11
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.06857v1

Training large-scale Mixture-of-Experts (MoE) models typically requires high-memory, high-bandwidth GPUs (e.g., A100), and their high cost has become a major barrier to large-model training. In contrast, affordable hardware is low-cost but constrained by memory capacity and bandwidth, making it unsuitable for direct LLM training. To address this, we propose MoE-DisCo (Mixture-of-Experts with Disentangled Clustering and Coordination), a staged training framework. MoE-DisCo decomposes the MoE model into multiple dense submodels, each consisting of a shared backbone and a single expert, and partitions the training data into subsets using unsupervised clustering. Each submodel is trained independently and in parallel on its assigned data subset using low-cost devices, without any inter-device communication. Subsequently, all experts are integrated into a complete MoE model and fine-tuned globally for a short period on high-memory, high-bandwidth GPUs. Experiments show that our method matches or even surpasses full-parameter training in performance across multiple downstream tasks, loss function, and perplexity (PPL), while reducing training cost by 47.6 percent to 69.5 percent on Qwen1.5-MoE-2.7B and Llama-MoE-3.5B across different datasets.

---

### DAGGER: Distractor-Aware Graph Generation for Executable Reasoning in Math Problems

Authors: Zabir Al Nazi, Shubhashis Roy Dipta, Sudipta Kar
Published: 2026-01-11
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.06853v3

Chain-of-Thought (CoT) prompting is widely adopted for mathematical problem solving, including in low-resource languages, yet its behavior under irrelevant context remains underexplored. To systematically study this challenge, we introduce DISTRACTMATH-BN, a Bangla benchmark that augments MGSM and MSVAMP with semantically coherent but computationally irrelevant information. Evaluating seven models ranging from 3B to 12B parameters, we observe substantial performance degradation under distractors: standard models drop by up to 41 points, while reasoning-specialized models decline by 14 to 20 points despite consuming five times more tokens. We propose †DAGGER, which reformulates mathematical problem solving as executable computational graph generation with explicit modeling of distractor nodes. Fine-tuning Gemma-3 models using supervised fine-tuning followed by Group Relative Policy Optimization achieves comparable weighted accuracy on augmented benchmarks while using 89 percent fewer tokens than reasoning models. Importantly, this robustness emerges without explicit training on distractor-augmented examples. Our results suggest that enforcing structured intermediate representations improves robustness and inference efficiency in mathematical reasoning compared to free-form approaches, particularly in noisy, low-resource settings.

---

### A Brain-like Synergistic Core in LLMs Drives Behaviour and Learning

Authors: Pedro Urbina-Rodriguez, Zafeirios Fountas, Fernando E. Rosas, Jun Wang, Andrea I. Luppi, Haitham Bou-Ammar, Murray Shanahan, Pedro A. M. Mediano
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06851v1

The independent evolution of intelligence in biological and artificial systems offers a unique opportunity to identify its fundamental computational principles. Here we show that large language models spontaneously develop synergistic cores -- components where information integration exceeds individual parts -- remarkably similar to those in the human brain. Using principles of information decomposition across multiple LLM model families and architectures, we find that areas in middle layers exhibit synergistic processing while early and late layers rely on redundancy, mirroring the informational organisation in biological brains. This organisation emerges through learning and is absent in randomly initialised networks. Crucially, ablating synergistic components causes disproportionate behavioural changes and performance loss, aligning with theoretical predictions about the fragility of synergy. Moreover, fine-tuning synergistic regions through reinforcement learning yields significantly greater performance gains than training redundant components, yet supervised fine-tuning shows no such advantage. This convergence suggests that synergistic information processing is a fundamental property of intelligence, providing targets for principled model design and testable predictions for biological intelligence.

---

### Explainable Multimodal Aspect-Based Sentiment Analysis with Dependency-guided Large Language Model

Authors: Zhongzheng Wang, Yuanhe Tian, Hongzhi Wang, Yan Song
Published: 2026-01-11
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.06848v2

Multimodal aspect-based sentiment analysis (MABSA) aims to identify aspect-level sentiments by jointly modeling textual and visual information, which is essential for fine-grained opinion understanding in social media. Existing approaches mainly rely on discriminative classification with complex multimodal fusion, yet they lack explicit sentiment explainability. In this paper, we reformulate MABSA as a generative and explainable task, proposing a unified framework that simultaneously predicts aspect-level sentiment and generates natural language explanations. Based on multimodal large language models (MLLMs), our approach employs a prompt-based generative paradigm, jointly producing sentiment and explanation. To further enhance aspect-oriented reasoning capabilities, we propose a dependency-syntax-guided sentiment cue strategy. This strategy prunes and textualizes the aspect-centered dependency syntax tree, guiding the model to distinguish different sentiment aspects and enhancing its explainability. To enable explainability, we use MLLMs to construct explanation-augmented datasets for fine-tuning. Experiments show that our approach not only achieves overall gains in sentiment classification accuracy, but also produces coherent and aspect-grounded explanations.

---

### MedGround: Bridging the Evidence Gap in Medical Vision-Language Models with Verified Grounding Data

Authors: Mengmeng Zhang, Xiaoping Wu, Hao Luo, Fan Wang, Yisheng Lv
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06847v2

Vision-Language Models (VLMs) can generate convincing clinical narratives, yet frequently struggle to visually ground their statements. We posit that this limitation arises from the scarcity of high-quality, large-scale clinical referring-localization pairs. To address this, we introduce MedGround, an automated pipeline that transforms segmentation resources into high-quality medical referring grounding data. Leveraging expert masks as spatial anchors, MedGround precisely derives localization targets, extracts shape and spatial cues, and guides VLMs to synthesize natural, clinically grounded queries that reflect morphology and location. To ensure data rigor, a multi-stage verification system integrates strict formatting checks, geometry- and medical-prior rules, and image-based visual judging to filter out ambiguous or visually unsupported samples. Finally, we present MedGround-35K, a novel multimodal medical dataset. Extensive experiments demonstrate that VLMs trained with MedGround-35K consistently achieve improved referring grounding performance, enhance multi-object semantic disambiguation, and exhibit strong generalization to unseen grounding settings. This work highlights MedGround as a scalable, data-driven approach to anchor medical language to verifiable visual evidence.

---

### Code Evolution for Control: Synthesizing Policies via LLM-Driven Evolutionary Search

Authors: Ping Guo, Chao Li, Yinglan Feng, Chaoning Zhang
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06845v1

Designing effective control policies for autonomous systems remains a fundamental challenge, traditionally addressed through reinforcement learning or manual engineering. While reinforcement learning has achieved remarkable success, it often suffers from high sample complexity, reward shaping difficulties, and produces opaque neural network policies that are hard to interpret or verify. Manual design, on the other hand, requires substantial domain expertise and struggles to scale across diverse tasks. In this work, we demonstrate that LLM-driven evolutionary search can effectively synthesize interpretable control policies in the form of executable code. By treating policy synthesis as a code evolution problem, we harness the LLM's prior knowledge of programming patterns and control heuristics while employing evolutionary search to explore the solution space systematically. We implement our approach using EvoToolkit, a framework that seamlessly integrates LLM-driven evolution with customizable fitness evaluation. Our method iteratively evolves populations of candidate policy programs, evaluating them against task-specific objectives and selecting superior individuals for reproduction. This process yields compact, human-readable control policies that can be directly inspected, modified, and formally verified. This work highlights the potential of combining foundation models with evolutionary computation for synthesizing trustworthy control policies in autonomous systems. Code is available at https://github.com/pgg3/EvoControl.

---

### Variational decomposition autoencoding improves disentanglement of latent representations

Authors: Ioannis Ziogas, Aamna Al Shehhi, Ahsan H. Khandoker, Leontios J. Hadjileontiadis
Published: 2026-01-11
Categories: cs.LG, cs.AI, eess.AS, eess.SP, stat.ML
arXiv: https://arxiv.org/abs/2601.06844v1

Understanding the structure of complex, nonstationary, high-dimensional time-evolving signals is a central challenge in scientific data analysis. In many domains, such as speech and biomedical signal processing, the ability to learn disentangled and interpretable representations is critical for uncovering latent generative mechanisms. Traditional approaches to unsupervised representation learning, including variational autoencoders (VAEs), often struggle to capture the temporal and spectral diversity inherent in such data. Here we introduce variational decomposition autoencoding (VDA), a framework that extends VAEs by incorporating a strong structural bias toward signal decomposition. VDA is instantiated through variational decomposition autoencoders (DecVAEs), i.e., encoder-only neural networks that combine a signal decomposition model, a contrastive self-supervised task, and variational prior approximation to learn multiple latent subspaces aligned with time-frequency characteristics. We demonstrate the effectiveness of DecVAEs on simulated data and three publicly available scientific datasets, spanning speech recognition, dysarthria severity evaluation, and emotional speech classification. Our results demonstrate that DecVAEs surpass state-of-the-art VAE-based methods in terms of disentanglement quality, generalization across tasks, and the interpretability of latent encodings. These findings suggest that decomposition-aware architectures can serve as robust tools for extracting structured representations from dynamic signals, with potential applications in clinical diagnostics, human-computer interaction, and adaptive neurotechnologies.

---

### Speak While Watching: Unleashing TRUE Real-Time Video Understanding Capability of Multimodal Large Language Models

Authors: Junyan Lin, Junlong Tong, Hao Wu, Jialiang Zhang, Jinming Liu, Xin Jin, Xiaoyu Shen
Published: 2026-01-11
Categories: cs.CV, cs.CL
arXiv: https://arxiv.org/abs/2601.06843v1

Multimodal Large Language Models (MLLMs) have achieved strong performance across many tasks, yet most systems remain limited to offline inference, requiring complete inputs before generating outputs. Recent streaming methods reduce latency by interleaving perception and generation, but still enforce a sequential perception-generation cycle, limiting real-time interaction. In this work, we target a fundamental bottleneck that arises when extending MLLMs to real-time video understanding: the global positional continuity constraint imposed by standard positional encoding schemes. While natural in offline inference, this constraint tightly couples perception and generation, preventing effective input-output parallelism. To address this limitation, we propose a parallel streaming framework that relaxes positional continuity through three designs: Overlapped, Group-Decoupled, and Gap-Isolated. These designs enable simultaneous perception and generation, allowing the model to process incoming inputs while producing responses in real time. Extensive experiments reveal that Group-Decoupled achieves the best efficiency-performance balance, maintaining high fluency and accuracy while significantly reducing latency. We further show that the proposed framework yields up to 2x acceleration under balanced perception-generation workloads, establishing a principled pathway toward speak-while-watching real-time systems. We make all our code publicly available: https://github.com/EIT-NLP/Speak-While-Watching.

---

### Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation

Authors: Hua Ye, Siyuan Chen, Ziqi Zhong, Canran Xiao, Haoliang Zhang, Yuhan Wu, Fei Shen
Published: 2026-01-11
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.06842v1

Large language models (LLMs) equipped with retrieval--the Retrieval-Augmented Generation (RAG) paradigm--should combine their parametric knowledge with external evidence, yet in practice they often hallucinate, over-trust noisy snippets, or ignore vital context. We introduce TCR (Transparent Conflict Resolution), a plug-and-play framework that makes this decision process observable and controllable. TCR (i) disentangles semantic match and factual consistency via dual contrastive encoders, (ii) estimates self-answerability to gauge confidence in internal memory, and (iii) feeds the three scalar signals to the generator through a lightweight soft-prompt with SNR-based weighting. Across seven benchmarks TCR improves conflict detection (+5-18 F1), raises knowledge-gap recovery by +21.4 pp and cuts misleading-context overrides by -29.3 pp, while adding only 0.3% parameters. The signals align with human judgements and expose temporal decision patterns.

---

### PRISM: Color-Stratified Point Cloud Sampling

Authors: Hansol Lim, Minhyeok Im, Jongseong Brad Choi
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06839v2

We present PRISM, a novel color-guided stratified sampling method for RGB-LiDAR point clouds. Our approach is motivated by the observation that unique scene features often exhibit chromatic diversity while repetitive, redundant features are homogeneous in color. Conventional downsampling methods (Random Sampling, Voxel Grid, Normal Space Sampling) enforce spatial uniformity while ignoring this photometric content. In contrast, PRISM allocates sampling density proportional to chromatic diversity. By treating RGB color space as the stratification domain and imposing a maximum capacity k per color bin, the method preserves texture-rich regions with high color variation while substantially reducing visually homogeneous surfaces. This shifts the sampling space from spatial coverage to visual complexity to produce sparser point clouds that retain essential features for 3D reconstruction tasks.

---

### OSCAR: Optical-aware Semantic Control for Aleatoric Refinement in Sar-to-Optical Translation

Authors: Hyunseo Lee, Sang Min Kim, Ho Kyung Shin, Taeheon Kim, Woo-Jeoung Nam
Published: 2026-01-11
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.06835v1

Synthetic Aperture Radar (SAR) provides robust all-weather imaging capabilities; however, translating SAR observations into photo-realistic optical images remains a fundamentally ill-posed problem. Current approaches are often hindered by the inherent speckle noise and geometric distortions of SAR data, which frequently result in semantic misinterpretation, ambiguous texture synthesis, and structural hallucinations. To address these limitations, a novel SAR-to-Optical (S2O) translation framework is proposed, integrating three core technical contributions: (i) Cross-Modal Semantic Alignment, which establishes an Optical-Aware SAR Encoder by distilling robust semantic priors from an Optical Teacher into a SAR Student (ii) Semantically-Grounded Generative Guidance, realized by a Semantically-Grounded ControlNet that integrates class-aware text prompts for global context with hierarchical visual prompts for local spatial guidance; and (iii) an Uncertainty-Aware Objective, which explicitly models aleatoric uncertainty to dynamically modulate the reconstruction focus, effectively mitigating artifacts caused by speckle-induced ambiguity. Extensive experiments demonstrate that the proposed method achieves superior perceptual quality and semantic consistency compared to state-of-the-art approaches.

---

### Enhancing Low-resolution Image Representation Through Normalizing Flows

Authors: Chenglong Bao, Tongyao Pang, Zuowei Shen, Dihan Zheng, Yihang Zou
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06834v2

Low-resolution image representation can be regarded as a special form of sparse representation that retains only low-frequency information while discarding high-frequency components. This property reduces storage and transmission costs and benefits various image processing tasks. However, a key challenge is to preserve essential visual content while maintaining the ability to accurately reconstruct the original images. This work proposes LR2Flow, a nonlinear framework that learns low-resolution image representations by integrating wavelet tight frame blocks with normalizing flows. We conduct a reconstruction error analysis of the proposed network, which demonstrates the necessity of designing invertible neural networks in the wavelet tight frame domain. Experimental results on various tasks, including image rescaling, compression, and denoising, demonstrate the effectiveness of the learned representations and the robustness of the proposed framework. Code is available at https://github.com/Evanescentlove/LR2Flow-main.

---

### SARA: Scene-Aware Reconstruction Accelerator

Authors: Jee Won Lee, Hansol Lim, Minhyeok Im, Dohyeon Lee, Jongseong Brad Choi
Published: 2026-01-11
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.06831v1

We present SARA (Scene-Aware Reconstruction Accelerator), a geometry-driven pair selection module for Structure-from-Motion (SfM). Unlike conventional pipelines that select pairs based on visual similarity alone, SARA introduces geometry-first pair selection by scoring reconstruction informativeness - the product of overlap and parallax - before expensive matching. A lightweight pre-matching stage uses mutual nearest neighbors and RANSAC to estimate these cues, then constructs an Information-Weighted Spanning Tree (IWST) augmented with targeted edges for loop closure, long-baseline anchors, and weak-view reinforcement. Compared to exhaustive matching, SARA reduces rotation errors by 46.5+-5.5% and translation errors by 12.5+-6.5% across modern learned detectors, while achieving at most 50x speedup through 98% pair reduction (from 30,848 to 580 pairs). This reduces matching complexity from quadratic to quasi-linear, maintaining within +-3% of baseline reconstruction metrics for 3D Gaussian Splatting and SVRaster.

---