# Research Papers — 2026-01 · bundle page 144 of 189 > Full-text markdown of papers #7151–7200 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/144 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/143.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/145.md) ### A Causal Information-Flow Framework for Unbiased Learning-to-Rank Authors: Haoming Gong, Qingyao Ai, Zhihao Tao, Yongfeng Zhang Published: 2026-01-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.05590v1 In web search and recommendation systems, user clicks are widely used to train ranking models. However, click data is heavily biased, i.e., users tend to click higher-ranked items (position bias), choose only what was shown to them (selection bias), and trust top results more (trust bias). Without explicitly modeling these biases, the true relevance of ranked items cannot be correctly learned from clicks. Existing Unbiased Learning-to-Rank (ULTR) methods mainly correct position bias and rely on propensity estimation, but they cannot measure remaining bias, provide risk guarantees, or jointly handle multiple bias sources. To overcome these challenges, this paper introduces a novel causal learning-based ranking framework that extends ULTR by combining Structural Causal Models (SCMs) with information-theoretic tools. SCMs specify how clicks are generated and help identify the true relevance signal from click data, while conditional mutual information, measures how much bias leaks into the learned relevance estimates. We use this leakage measure to define a rigorous notion of disentanglement and include it as a regularizer during model training to reduce bias. In addition, we incorporate a causal inference estimator, i.e., doubly robust estimator, to ensure more reliable risk estimation. Experiments on standard Learning-to-Rank benchmarks show that our method consistently reduces measured bias leakage and improves ranking performance, especially in realistic scenarios where multiple biases-such as position and trust bias-interact strongly. --- ### ACR: Adaptive Context Refactoring via Context Refactoring Operators for Multi-Turn Dialogue Authors: Jiawei Shen, Jia Zhu, Hanghui Guo, Weijie Shi, Yue Cui, Qingyu Niu, Guoqing Ma, Yidan Liang, Jingjiang Liu, Yiling Wang, Shimin Di, Jiajie Xu Published: 2026-01-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.05589v1 Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and avoid drifting into incorrect facts as the interaction grows longer. Existing approaches primarily focus on extending the context window, introducing external memory, or applying context compression, yet these methods still face limitations such as \textbf{contextual inertia} and \textbf{state drift}. To address these challenges, we propose the \textbf{A}daptive \textbf{C}ontext \textbf{R}efactoring \textbf{(ACR)} Framework, which dynamically monitors and reshapes the interaction history to mitigate contextual inertia and state drift actively. ACR is built on a library of context refactoring operators and a teacher-guided self-evolving training paradigm that learns when to intervene and how to refactor, thereby decoupling context management from the reasoning process. Extensive experiments on multi-turn dialogue demonstrate that our method significantly outperforms existing baselines while reducing token consumption. --- ### Autoregressive Ranking: Bridging the Gap Between Dual and Cross Encoders Authors: Benjamin Rozonoyer, Chong You, Michael Boratko, Himanshu Jain, Nilesh Gupta, Srinadh Bhojanapalli, Andrew McCallum, Felix Yu Published: 2026-01-09 Categories: cs.IR, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.05588v4 The success of Large Language Models (LLMs) has motivated a shift toward generative approaches to retrieval and ranking, aiming to supersede classical Dual Encoders (DEs) and Cross Encoders (CEs). A prominent paradigm is pointwise Autoregressive Ranking (ARR), where an LLM generates document identifiers (docIDs) token-by-token to enable ranking via beam search. ARR offers the promise of superior expressivity compared to DEs while avoiding the prohibitive computational cost of CEs. However, a formal theoretical foundation for this expressive power has been missing. Moreover, the standard next-token prediction loss is rank-agnostic and inappropriate for finetuning an LLM for ranking tasks. In this paper, we first prove that the expressive capacity of ARR is strictly superior to DEs. While a DE requires an embedding dimension that grows linearly with corpus size to achieve arbitrary rankings, ARR can solve it with a constant hidden dimension. We then propose SToICaL (Simple Token-Item Calibrated Loss), a generalized rank-aware training loss for LLM finetuning. By using item-level reweighting and prefix-tree marginalization, we distribute probability mass over valid docID tokens based on their ground-truth relevance. Experiments on WordNet and ESCI datasets verify that our loss suppresses invalid docID generations and significantly improves ranking metrics beyond top-1 retrieval. --- ### HogVul: Black-box Adversarial Code Generation Framework Against LM-based Vulnerability Detectors Authors: Jingxiao Yang, Ping He, Tianyu Du, Sun Bing, Xuhong Zhang Published: 2026-01-09 Categories: cs.CR, cs.AI arXiv: https://arxiv.org/abs/2601.05587v1 Recent advances in software vulnerability detection have been driven by Language Model (LM)-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on LM-based vulnerability detectors primarily rely on isolated perturbation strategies, limiting their ability to efficiently explore the adversarial code space for optimal perturbations. To bridge this gap, we propose HogVul, a black-box adversarial code generation framework that integrates both lexical and syntax perturbations under a unified dual-channel optimization strategy driven by Particle Swarm Optimization (PSO). By systematically coordinating two-level perturbations, HogVul effectively expands the search space for adversarial examples, enhancing the attack efficacy. Extensive experiments on four benchmark datasets demonstrate that HogVul achieves an average attack success rate improvement of 26.05\% over state-of-the-art baseline methods. These findings highlight the potential of hybrid optimization strategies in exposing model vulnerabilities. --- ### Poisson Hyperplane Processes with Rectified Linear Units Authors: Shufei Ge, Shijia Wang, Lloyd Elliott Published: 2026-01-09 Categories: cs.LG, stat.ME, stat.ML arXiv: https://arxiv.org/abs/2601.05586v1 Neural networks have shown state-of-the-art performances in various classification and regression tasks. Rectified linear units (ReLU) are often used as activation functions for the hidden layers in a neural network model. In this article, we establish the connection between the Poisson hyperplane processes (PHP) and two-layer ReLU neural networks. We show that the PHP with a Gaussian prior is an alternative probabilistic representation to a two-layer ReLU neural network. In addition, we show that a two-layer neural network constructed by PHP is scalable to large-scale problems via the decomposition propositions. Finally, we propose an annealed sequential Monte Carlo algorithm for Bayesian inference. Our numerical experiments demonstrate that our proposed method outperforms the classic two-layer ReLU neural network. The implementation of our proposed model is available at https://github.com/ShufeiGe/Pois_Relu.git. --- ### GS-DMSR: Dynamic Sensitive Multi-scale Manifold Enhancement for Accelerated High-Quality 3D Gaussian Splatting Authors: Nengbo Lu, Minghua Pan, Shaohua Sun, Yizhou Liang Published: 2026-01-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.05584v1 In the field of 3D dynamic scene reconstruction, how to balance model convergence rate and rendering quality has long been a critical challenge that urgently needs to be addressed, particularly in high-precision modeling of scenes with complex dynamic motions. To tackle this issue, this study proposes the GS-DMSR method. By quantitatively analyzing the dynamic evolution process of Gaussian attributes, this mechanism achieves adaptive gradient focusing, enabling it to dynamically identify significant differences in the motion states of Gaussian models. It then applies differentiated optimization strategies to Gaussian models with varying degrees of significance, thereby significantly improving the model convergence rate. Additionally, this research integrates a multi-scale manifold enhancement module, which leverages the collaborative optimization of an implicit nonlinear decoder and an explicit deformation field to enhance the modeling efficiency for complex deformation scenes. Experimental results demonstrate that this method achieves a frame rate of up to 96 FPS on synthetic datasets, while effectively reducing both storage overhead and training time.Our code and data are available at https://anonymous.4open.science/r/GS-DMSR-2212. --- ### Learn to Evolve: Self-supervised Neural JKO Operator for Wasserstein Gradient Flow Authors: Xue Feng, Li Wang, Deanna Needell, Rongjie Lai Published: 2026-01-09 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2601.05583v1 The Jordan-Kinderlehrer-Otto (JKO) scheme provides a stable variational framework for computing Wasserstein gradient flows, but its practical use is often limited by the high computational cost of repeatedly solving the JKO subproblems. We propose a self-supervised approach for learning a JKO solution operator without requiring numerical solutions of any JKO trajectories. The learned operator maps an input density directly to the minimizer of the corresponding JKO subproblem, and can be iteratively applied to efficiently generate the gradient-flow evolution. A key challenge is that only a number of initial densities are typically available for training. To address this, we introduce a Learn-to-Evolve algorithm that jointly learns the JKO operator and its induced trajectories by alternating between trajectory generation and operator updates. As training progresses, the generated data increasingly approximates true JKO trajectories. Meanwhile, this Learn-to-Evolve strategy serves as a natural form of data augmentation, significantly enhancing the generalization ability of the learned operator. Numerical experiments demonstrate the accuracy, stability, and robustness of the proposed method across various choices of energies and initial conditions. --- ### Can large language models interpret unstructured chat data on dynamic group decision-making processes? Evidence on joint destination choice Authors: Sung-Yoo Lim, Koki Sato, Kiyoshi Takami, Giancarlos Parady, Eui-Jin Kim Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05582v1 Social activities result from complex joint activity-travel decisions between group members. While observing the decision-making process of these activities is difficult via traditional travel surveys, the advent of new types of data, such as unstructured chat data, can help shed some light on these complex processes. However, interpreting these decision-making processes requires inferring both explicit and implicit factors. This typically involves the labor-intensive task of manually annotating dialogues to capture context-dependent meanings shaped by the social and cultural norms. This study evaluates the potential of Large Language Models (LLMs) to automate and complement human annotation in interpreting decision-making processes from group chats, using data on joint eating-out activities in Japan as a case study. We designed a prompting framework inspired by the knowledge acquisition process, which sequentially extracts key decision-making factors, including the group-level restaurant choice set and outcome, individual preferences of each alternative, and the specific attributes driving those preferences. This structured process guides the LLM to interpret group chat data, converting unstructured dialogues into structured tabular data describing decision-making factors. To evaluate LLM-driven outputs, we conduct a quantitative analysis using a human-annotated ground truth dataset and a qualitative error analysis to examine model limitations. Results show that while the LLM reliably captures explicit decision-making factors, it struggles to identify nuanced implicit factors that human annotators readily identified. We pinpoint specific contexts when LLM-based extraction can be trusted versus when human oversight remains essential. These findings highlight both the potential and limitations of LLM-based analysis for incorporating non-traditional data sources on social activities. --- ### Generalizable and Adaptive Continual Learning Framework for AI-generated Image Detection Authors: Hanyi Wang, Jun Lan, Yaoyu Kang, Huijia Zhu, Weiqiang Wang, Zhuosheng Zhang, Shilin Wang Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05580v1 The malicious misuse and widespread dissemination of AI-generated images pose a significant threat to the authenticity of online information. Current detection methods often struggle to generalize to unseen generative models, and the rapid evolution of generative techniques continuously exacerbates this challenge. Without adaptability, detection models risk becoming ineffective in real-world applications. To address this critical issue, we propose a novel three-stage domain continual learning framework designed for continuous adaptation to evolving generative models. In the first stage, we employ a strategic parameter-efficient fine-tuning approach to develop a transferable offline detection model with strong generalization capabilities. Building upon this foundation, the second stage integrates unseen data streams into a continual learning process. To efficiently learn from limited samples of novel generated models and mitigate overfitting, we design a data augmentation chain with progressively increasing complexity. Furthermore, we leverage the Kronecker-Factored Approximate Curvature (K-FAC) method to approximate the Hessian and alleviate catastrophic forgetting. Finally, the third stage utilizes a linear interpolation strategy based on Linear Mode Connectivity, effectively capturing commonalities across diverse generative models and further enhancing overall performance. We establish a comprehensive benchmark of 27 generative models, including GANs, deepfakes, and diffusion models, chronologically structured up to August 2024 to simulate real-world scenarios. Extensive experiments demonstrate that our initial offline detectors surpass the leading baseline by +5.51% in terms of mean average precision. Our continual learning strategy achieves an average accuracy of 92.20%, outperforming state-of-the-art methods. --- ### RISE: Rule-Driven SQL Dialect Translation via Query Reduction Authors: Xudong Xie, Yuwei Zhang, Wensheng Dou, Yu Gao, Ziyu Cui, Jiansen Song, Rui Yang, Jun Wei Published: 2026-01-09 Categories: cs.DB, cs.AI, cs.CL, cs.SE arXiv: https://arxiv.org/abs/2601.05579v1 Translating SQL dialects across different relational database management systems (RDBMSs) is crucial for migrating RDBMS-based applications to the cloud. Traditional SQL dialect translation tools rely on manually-crafted rules, necessitating significant manual effort to support new RDBMSs and dialects. Although large language models (LLMs) can assist in translating SQL dialects, they often struggle with lengthy and complex SQL queries. In this paper, we propose RISE, a novel LLM-based SQL dialect translation approach that can accurately handle lengthy and complex SQL queries. Given a complex source query $Q_c$ that contains a SQL dialect $d$, we first employ a dialect-aware query reduction technique to derive a simplified query $Q_{s}$ by removing $d$-irrelevant SQL elements from $Q_c$. Subsequently, we utilize LLMs to translate $Q_{s}$ into $Q_{s^{'}}$, and automatically extract the translation rule $r_d$ for dialect $d$ based on the relationship between $Q_{s}$ and $Q_{s^{'}}$. By applying $r_d$ to $Q_c$, we can effectively translate the dialect $d$ within $Q_c$, thereby bypassing the complexity of the source query $Q_c$. We evaluate RISE on two real-world benchmarks, i.e., TPC-DS and SQLProcBench, comparing its performance against both the traditional rule-based tools and the LLM-based approaches with respect to translation accuracy. RISE achieves accuracies of 97.98% on TPC-DS and 100% on SQLProcBench, outperforming the baselines by an average improvement of 24.62% and 238.41%, respectively. --- ### Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection Authors: Cooper Lin, Yanting Zhang, Maohao Ran, Wei Xue, Hongwei Fan, Yibo Xu, Zhenglin Wan, Sirui Han, Yike Guo, Jun Song Published: 2026-01-09 Categories: cs.AI, cs.CE arXiv: https://arxiv.org/abs/2601.05578v1 E-commerce platforms and payment solution providers face increasingly sophisticated fraud schemes, ranging from identity theft and account takeovers to complex money laundering operations that exploit the speed and anonymity of digital transactions. However, despite their theoretical promise, the application of Large Language Models (LLMs) to fraud detection in real-world financial contexts remains largely unexploited, and their practical effectiveness in handling domain-specific e-commerce transaction data has yet to be empirically validated. To bridge this gap between conventional machine learning limitations and the untapped potential of LLMs in fraud detection, this paper proposes a novel approach that employs Reinforcement Learning (RL) to post-train lightweight language models specifically for fraud detection tasks using only raw transaction data. We utilize the Group Sequence Policy Optimization (GSPO) algorithm combined with a rule-based reward system to fine-tune language models of various sizes on a real-life transaction dataset provided by a Chinese global payment solution company. Through this reinforcement learning framework, the language models are encouraged to explore diverse trust and risk signals embedded within the textual transaction data, including patterns in customer information, shipping details, product descriptions, and order history. Our experimental results demonstrate the effectiveness of this approach, with post-trained language models achieving substantial F1-score improvements on held-out test data. Our findings demonstrate that the observed performance improvements are primarily attributable to the exploration mechanism inherent in reinforcement learning, which allows models to discover novel fraud indicators beyond those captured by traditional engineered features. --- ### Autonomous Discovery of the Ising Model's Critical Parameters with Reinforcement Learning Authors: Hai Man, Chaobo Wang, Jia-Rui Li, Yuping Tian, Shu-Gang Chen Published: 2026-01-09 Categories: cond-mat.stat-mech, cs.LG, physics.comp-ph arXiv: https://arxiv.org/abs/2601.05577v1 Traditional methods for determining critical parameters are often influenced by human factors. This research introduces a physics-inspired adaptive reinforcement learning framework that enables agents to autonomously interact with physical environments, simultaneously identifying both the critical temperature and various types of critical exponents in the Ising model with precision. Interestingly, our algorithm exhibits search behavior reminiscent of phase transitions, efficiently converging to target parameters regardless of initial conditions. Experimental results demonstrate that this method significantly outperforms traditional approaches, particularly in environments with strong perturbations. This study not only incorporates physical concepts into machine learning to enhance algorithm interpretability but also establishes a new paradigm for scientific exploration, transitioning from manual analysis to autonomous AI discovery. --- ### Orient Anything V2: Unifying Orientation and Rotation Understanding Authors: Zehan Wang, Ziang Zhang, Jiayang Xu, Jialei Wang, Tianyu Pang, Chao Du, HengShuang Zhao, Zhou Zhao Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05573v1 This work presents Orient Anything V2, an enhanced foundation model for unified understanding of object 3D orientation and rotation from single or paired images. Building upon Orient Anything V1, which defines orientation via a single unique front face, V2 extends this capability to handle objects with diverse rotational symmetries and directly estimate relative rotations. These improvements are enabled by four key innovations: 1) Scalable 3D assets synthesized by generative models, ensuring broad category coverage and balanced data distribution; 2) An efficient, model-in-the-loop annotation system that robustly identifies 0 to N valid front faces for each object; 3) A symmetry-aware, periodic distribution fitting objective that captures all plausible front-facing orientations, effectively modeling object rotational symmetry; 4) A multi-frame architecture that directly predicts relative object rotations. Extensive experiments show that Orient Anything V2 achieves state-of-the-art zero-shot performance on orientation estimation, 6DoF pose estimation, and object symmetry recognition across 11 widely used benchmarks. The model demonstrates strong generalization, significantly broadening the applicability of orientation estimation in diverse downstream tasks. --- ### Towards Generalized Multi-Image Editing for Unified Multimodal Models Authors: Pengcheng Xu, Peng Tang, Donghao Luo, Xiaobin Hu, Weichu Cui, Qingdong He, Zhennan Chen, Jiangning Zhang, Charles Ling, Boyu Wang Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05572v1 Unified Multimodal Models (UMMs) integrate multimodal understanding and generation, yet they are limited to maintaining visual consistency and disambiguating visual cues when referencing details across multiple input images. In this work, we propose a scalable multi-image editing framework for UMMs that explicitly distinguishes image identities and generalizes to variable input counts. Algorithmically, we introduce two innovations: 1) The learnable latent separators explicitly differentiate each reference image in the latent space, enabling accurate and disentangled conditioning. 2) The sinusoidal index encoding assigns visual tokens from the same image a continuous sinusoidal index embedding, which provides explicit image identity while allowing generalization and extrapolation on a variable number of inputs. To facilitate training and evaluation, we establish a high-fidelity benchmark using an inverse dataset construction methodology to guarantee artifact-free, achievable outputs. Experiments show clear improvements in semantic consistency, visual fidelity, and cross-image integration over prior baselines on diverse multi-image editing tasks, validating our advantages on consistency and generalization ability. --- ### Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models Authors: Cooper Lin, Maohao Ran, Yanting Zhang, Zhenglin Wan, Hongwei Fan, Yibo Xu, Yike Guo, Wei Xue, Jun Song Published: 2026-01-09 Categories: cs.AI, cs.MA arXiv: https://arxiv.org/abs/2601.05570v1 Standard safety alignment optimizes Large Language Models (LLMs) for universal helpfulness and honesty, effectively instilling a rigid "Boy Scout" morality. While robust for general-purpose assistants, this one-size-fits-all ethical framework imposes a "transparency tax" on professional domains requiring strategic ambiguity and information withholding, such as public relations, negotiation, and crisis management. To measure this gap between general safety and professional utility, we introduce Crisis-Bench, a multi-agent Partially Observable Markov Decision Process (POMDP) that evaluates LLMs in high-stakes corporate crises. Spanning 80 diverse storylines across 8 industries, Crisis-Bench tasks an LLM-based Public Relations (PR) Agent with navigating a dynamic 7-day corporate crisis simulation while managing strictly separated Private and Public narrative states to enforce rigorous information asymmetry. Unlike traditional benchmarks that rely on static ground truths, we introduce the Adjudicator-Market Loop: a novel evaluation metric where public sentiment is adjudicated and translated into a simulated stock price, creating a realistic economic incentive structure. Our results expose a critical dichotomy: while some models capitulate to ethical concerns, others demonstrate the capacity for Machiavellian, legitimate strategic withholding in order to stabilize the simulated stock price. Crisis-Bench provides the first quantitative framework for assessing "Reputation Management" capabilities, arguing for a shift from rigid moral absolutism to context-aware professional alignment. --- ### WildSci: Advancing Scientific Reasoning from In-the-Wild Literature Authors: Tengxiao Liu, Deepak Nathani, Zekun Li, Kevin Yang, William Yang Wang Published: 2026-01-09 Categories: cs.AI, cs.CL arXiv: https://arxiv.org/abs/2601.05567v1 Recent progress in large language model (LLM) reasoning has focused on domains like mathematics and coding, where abundant high-quality data and objective evaluation metrics are readily available. In contrast, progress in LLM reasoning models remains limited in scientific domains such as medicine and materials science due to limited dataset coverage and the inherent complexity of open-ended scientific questions. To address these challenges, we introduce WildSci, a new dataset of domain-specific science questions automatically synthesized from peer-reviewed literature, covering 9 scientific disciplines and 26 subdomains. By framing complex scientific reasoning tasks in a multiple-choice format, we enable scalable training with well-defined reward signals. We further apply reinforcement learning to finetune models on these data and analyze the resulting training dynamics, including domain-specific performance changes, response behaviors, and generalization trends. Experiments on a suite of scientific benchmarks demonstrate the effectiveness of our dataset and approach. We release WildSci to enable scalable and sustainable research in scientific reasoning, available at https://huggingface.co/datasets/JustinTX/WildSci. --- ### The ICASSP 2026 HumDial Challenge: Benchmarking Human-like Spoken Dialogue Systems in the LLM Era Authors: Zhixian Zhao, Shuiyuan Wang, Guojian Li, Hongfei Xue, Chengyou Wang, Shuai Wang, Longshuai Xiao, Zihan Zhang, Hui Bu, Xin Xu, Xinsheng Wang, Hexin Liu et al. Published: 2026-01-09 Categories: cs.SD, cs.CL, cs.HC, eess.AS arXiv: https://arxiv.org/abs/2601.05564v2 Driven by the rapid advancement of Large Language Models (LLMs), particularly Audio-LLMs and Omni-models, spoken dialogue systems have evolved significantly, progressively narrowing the gap between human-machine and human-human interactions. Achieving truly ``human-like'' communication necessitates a dual capability: emotional intelligence to perceive and resonate with users' emotional states, and robust interaction mechanisms to navigate the dynamic, natural flow of conversation, such as real-time turn-taking. Therefore, we launched the first Human-like Spoken Dialogue Systems Challenge (HumDial) at ICASSP 2026 to benchmark these dual capabilities. Anchored by a sizable dataset derived from authentic human conversations, this initiative establishes a fair evaluation platform across two tracks: (1) Emotional Intelligence, targeting long-term emotion understanding and empathetic generation; and (2) Full-Duplex Interaction, systematically evaluating real-time decision-making under `` listening-while-speaking'' conditions. This paper summarizes the dataset, track configurations, and the final results. --- ### What's Left Unsaid? Detecting and Correcting Misleading Omissions in Multimodal News Previews Authors: Fanxiao Li, Jiaying Wu, Tingchao Fu, Dayang Li, Herun Wan, Wei Zhou, Min-Yen Kan Published: 2026-01-09 Categories: cs.CV, cs.SI arXiv: https://arxiv.org/abs/2601.05563v3 Even when factually correct, social-media news previews (image-headline pairs) can induce interpretation drift: by selectively omitting crucial context, they lead readers to form judgments that diverge from what the full article supports. This covert harm is subtler than explicit misinformation, yet remains underexplored. To address this gap, we develop a multi-stage pipeline that simulates preview-based and context-based understanding, enabling construction of the MM-Misleading benchmark. Using MM-Misleading, we systematically evaluate open-source LVLMs and uncover pronounced blind spots in omission-based misleadingness detection. We further propose OMGuard, which combines (1) Interpretation-Aware Fine-Tuning for misleadingness detection and (2) Rationale-Guided Misleading Content Correction, where explicit rationales guide headline rewriting to reduce misleading impressions. Experiments show that OMGuard lifts an 8B model's detection accuracy to the level of a 235B LVLM while delivering markedly stronger end-to-end correction. Further analysis shows that misleadingness usually arises from local narrative shifts, such as missing background, instead of global frame changes, and identifies image-driven cases where text-only correction fails, underscoring the need for visual interventions. --- ### ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging Authors: Junyao Yang, Chen Qian, Dongrui Liu, Wen Shen, Yong Liu, Jing Shao Published: 2026-01-09 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.05560v1 Large Reasoning Models (LRMs) with long chain-of-thought reasoning have recently achieved remarkable success. Yet, equipping domain-specialized models with such reasoning capabilities, referred to as "Reasoning + X", remains a significant challenge. While model merging offers a promising training-free solution, existing methods often suffer from a destructive performance collapse: existing methods tend to both weaken reasoning depth and compromise domain-specific utility. Interestingly, we identify a counter-intuitive phenomenon underlying this failure: reasoning ability predominantly resides in parameter regions with low gradient sensitivity, contrary to the common assumption that domain capabilities correspond to high-magnitude parameters. Motivated by this insight, we propose ReasonAny, a novel merging framework that resolves the reasoning-domain performance collapse through Contrastive Gradient Identification. Experiments across safety, biomedicine, and finance domains show that ReasonAny effectively synthesizes "Reasoning + X" capabilities, significantly outperforming state-of-the-art baselines while retaining robust reasoning performance. --- ### Semi-Supervised Facial Expression Recognition based on Dynamic Threshold and Negative Learning Authors: Zhongpeng Cai, Jun Yu, Wei Xu, Tianyu Liu, Jianqing Sun, Jiaen Liang Published: 2026-01-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.05556v1 Facial expression recognition is a key task in human-computer interaction and affective computing. However, acquiring a large amount of labeled facial expression data is often costly. Therefore, it is particularly important to design a semi-supervised facial expression recognition algorithm that makes full use of both labeled and unlabeled data. In this paper, we propose a semi-supervised facial expression recognition algorithm based on Dynamic Threshold Adjustment (DTA) and Selective Negative Learning (SNL). Initially, we designed strategies for local attention enhancement and random dropout of feature maps during feature extraction, which strengthen the representation of local features while ensuring the model does not overfit to any specific local area. Furthermore, this study introduces a dynamic thresholding method to adapt to the requirements of the semi-supervised learning framework for facial expression recognition tasks, and through a selective negative learning strategy, it fully utilizes unlabeled samples with low confidence by mining useful expression information from complementary labels, achieving impressive results. We have achieved state-of-the-art performance on the RAF-DB and AffectNet datasets. Our method surpasses fully supervised methods even without using the entire dataset, which proves the effectiveness of our approach. --- ### One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection Authors: Bin-Bin Gao, Chengjie Wang Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05552v1 Universal visual anomaly detection (AD) aims to identify anomaly images and segment anomaly regions towards open and dynamic scenarios, following zero- and few-shot paradigms without any dataset-specific fine-tuning. We have witnessed significant progress in widely use of visual-language foundational models in recent approaches. However, current methods often struggle with complex prompt engineering, elaborate adaptation modules, and challenging training strategies, ultimately limiting their flexibility and generality. To address these issues, this paper rethinks the fundamental mechanism behind visual-language models for AD and presents an embarrassingly simple, general, and effective framework for Universal vision Anomaly Detection (UniADet). Specifically, we first find language encoder is used to derive decision weights for anomaly classification and segmentation, and then demonstrate that it is unnecessary for universal AD. Second, we propose an embarrassingly simple method to completely decouple classification and segmentation, and decouple cross-level features, i.e., learning independent weights for different tasks and hierarchical features. UniADet is highly simple (learning only decoupled weights), parameter-efficient (only 0.002M learnable parameters), general (adapting a variety of foundation models), and effective (surpassing state-of-the-art zero-/few-shot by a large margin and even full-shot AD methods for the first time) on 14 real-world AD benchmarks covering both industrial and medical domains. We will make the code and model of UniADet available at https://github.com/gaobb/UniADet. --- ### Generation-Based and Emotion-Reflected Memory Update: Creating the KEEM Dataset for Better Long-Term Conversation Authors: Jeonghyun Kang, Hongjin Kim, Harksoo Kim Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05548v1 In this work, we introduce the Keep Emotional and Essential Memory (KEEM) dataset, a novel generation-based dataset designed to enhance memory updates in long-term conversational systems. Unlike existing approaches that rely on simple accumulation or operation-based methods, which often result in information conflicts and difficulties in accurately tracking a user's current state, KEEM dynamically generates integrative memories. This process not only preserves essential factual information but also incorporates emotional context and causal relationships, enabling a more nuanced understanding of user interactions. By seamlessly updating a system's memory with both emotional and essential data, our approach promotes deeper empathy and enhances the system's ability to respond meaningfully in open-domain conversations. --- ### VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck Authors: Feiran Zhang, Yixin Wu, Zhenghua Wang, Xiaohua Wang, Changze Lv, Xuanjing Huang, Xiaoqing Zheng Published: 2026-01-09 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.05547v2 Vision-Language Models (VLMs) have demonstrated remarkable progress in multimodal tasks, but remain susceptible to hallucinations, where generated text deviates from the underlying visual content. Existing hallucination detection methods primarily rely on output logits or external verification tools, often overlooking their internal mechanisms. In this work, we investigate the outputs of internal attention heads, postulating that specific heads carry the primary signals for truthful generation.However, directly probing these high-dimensional states is challenging due to the entanglement of visual-linguistic syntax and noise. To address this, we propose VIB-Probe, a novel hallucination detection and mitigation framework leveraging the Variational Information Bottleneck (VIB) theory. Our method extracts discriminative patterns across layers and heads while filtering out semantic nuisances through the information bottleneck principle. Furthermore, by leveraging the gradients of our VIB probe, we identify attention heads with strong causal influence on hallucinations and introduce an inference-time intervention strategy for hallucination mitigation. Extensive experiments across diverse benchmarks demonstrate that VIB-Probe significantly outperforms existing baselines in both settings. Our code will be made publicly available. --- ### MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generation Authors: Yanfeng Li, Yue Sun, Keren Fu, Sio-Kei Im, Xiaoming Liu, Guangtao Zhai, Xiaohong Liu, Tao Tan Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05546v1 Existing multi-object image generation methods face difficulties in achieving precise alignment between localized image generation regions and their corresponding semantics based on language descriptions, frequently resulting in inconsistent object quantities and attribute aliasing. To mitigate this limitation, mainstream approaches typically rely on external control signals to explicitly constrain the spatial layout, local semantic and visual attributes of images. However, this strong dependency makes the input format rigid, rendering it incompatible with the heterogeneous resource conditions of users and diverse constraint requirements. To address these challenges, we propose MoGen, a user-friendly multi-object image generation method. First, we design a Regional Semantic Anchor (RSA) module that precisely anchors phrase units in language descriptions to their corresponding image regions during the generation process, enabling text-to-image generation that follows quantity specifications for multiple objects. Building upon this foundation, we further introduce an Adaptive Multi-modal Guidance (AMG) module, which adaptively parses and integrates various combinations of multi-source control signals to formulate corresponding structured intent. This intent subsequently guides selective constraints on scene layouts and object attributes, achieving dynamic fine-grained control. Experimental results demonstrate that MoGen significantly outperforms existing methods in generation quality, quantity consistency, and fine-grained control, while exhibiting superior accessibility and control flexibility. Code is available at: https://github.com/Tear-kitty/MoGen/tree/master. --- ### Can Large Language Models Differentiate Harmful from Argumentative Essays? Steps Toward Ethical Essay Scoring Authors: Hongjin Kim, Jeonghyun Kang, Harksoo Kim Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05545v1 This study addresses critical gaps in Automated Essay Scoring (AES) systems and Large Language Models (LLMs) with regard to their ability to effectively identify and score harmful essays. Despite advancements in AES technology, current models often overlook ethically and morally problematic elements within essays, erroneously assigning high scores to essays that may propagate harmful opinions. In this study, we introduce the Harmful Essay Detection (HED) benchmark, which includes essays integrating sensitive topics such as racism and gender bias, to test the efficacy of various LLMs in recognizing and scoring harmful content. Our findings reveal that: (1) LLMs require further enhancement to accurately distinguish between harmful and argumentative essays, and (2) both current AES models and LLMs fail to consider the ethical dimensions of content during scoring. The study underscores the need for developing more robust AES systems that are sensitive to the ethical implications of the content they are scoring. --- ### Buffered AUC maximization for scoring systems via mixed-integer optimization Authors: Moe Shiina, Shunnosuke Ikeda, Yuichi Takano Published: 2026-01-09 Categories: cs.LG, math.OC, stat.AP arXiv: https://arxiv.org/abs/2601.05544v2 A scoring system is a linear classifier composed of a small number of explanatory variables, each assigned a small integer coefficient. This system is highly interpretable and allows predictions to be made with simple manual calculations without the need for a calculator. Several previous studies have used mixed-integer optimization (MIO) techniques to develop scoring systems for binary classification; however, they have not focused on directly maximizing AUC (i.e., area under the receiver operating characteristic curve), even though AUC is recognized as an essential evaluation metric for scoring systems. Our goal herein is to establish an effective MIO framework for constructing scoring systems that directly maximize the buffered AUC (bAUC) as the tightest concave lower bound on AUC. Our optimization model is formulated as a mixed-integer linear optimization (MILO) problem that maximizes bAUC subject to a group sparsity constraint for limiting the number of questions in the scoring system. Computational experiments using publicly available real-world datasets demonstrate that our MILO method can build scoring systems with superior AUC values compared to the baseline methods based on regularization and stepwise regression. This research contributes to the advancement of MIO techniques for developing highly interpretable classification models. --- ### Closing the Modality Reasoning Gap for Speech Large Language Models Authors: Chaoren Wang, Heng Lu, Xueyao Zhang, Shujie Liu, Yan Lu, Jinyu Li, Zhizheng Wu Published: 2026-01-09 Categories: cs.CL, cs.SD, eess.AS arXiv: https://arxiv.org/abs/2601.05543v2 Although Speech Large Language Models have achieved notable progress, a substantial modality reasoning gap remains: their reasoning performance on speech inputs is markedly weaker than on text. This gap could be associated with representational drift across Transformer layers and behavior deviations in long-chain reasoning. To address this issue, we introduce TARS, a reinforcement-learning framework that aligns text-conditioned and speech-conditioned trajectories through an asymmetric reward design. The framework employs two dense and complementary signals: representation alignment, which measures layer-wise hidden-state similarity between speech- and text-conditioned trajectories, and behavior alignment, which evaluates semantic consistency between generated outputs and reference text completions. Experiments on challenging reasoning benchmarks, including MMSU and OBQA, show that our approach significantly narrows the modality reasoning gap and achieves state-of-the-art performance among 7B-scale Speech LLMs. --- ### Understanding LLM-Driven Test Oracle Generation Authors: Adam Bodicoat, Gunel Jahangirova, Valerio Terragni Published: 2026-01-09 Categories: cs.SE, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.05542v1 Automated unit test generation aims to improve software quality while reducing the time and effort required for creating tests manually. However, existing techniques primarily generate regression oracles that predicate on the implemented behavior of the class under test. They do not address the oracle problem: the challenge of distinguishing correct from incorrect program behavior. With the rise of Foundation Models (FMs), particularly Large Language Models (LLMs), there is a new opportunity to generate test oracles that reflect intended behavior. This positions LLMs as enablers of Promptware, where software creation and testing are driven by natural-language prompts. This paper presents an empirical study on the effectiveness of LLMs in generating test oracles that expose software failures. We investigate how different prompting strategies and levels of contextual input impact the quality of LLM-generated oracles. Our findings offer insights into the strengths and limitations of LLM-based oracle generation in the FM era, improving our understanding of their capabilities and fostering future research in this area. --- ### DIFF-MF: A Difference-Driven Channel-Spatial State Space Model for Multi-Modal Image Fusion Authors: Yiming Sun, Zifan Ye, Qinghua Hu, Pengfei Zhu Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05538v1 Multi-modal image fusion aims to integrate complementary information from multiple source images to produce high-quality fused images with enriched content. Although existing approaches based on state space model have achieved satisfied performance with high computational efficiency, they tend to either over-prioritize infrared intensity at the cost of visible details, or conversely, preserve visible structure while diminishing thermal target salience. To overcome these challenges, we propose DIFF-MF, a novel difference-driven channel-spatial state space model for multi-modal image fusion. Our approach leverages feature discrepancy maps between modalities to guide feature extraction, followed by a fusion process across both channel and spatial dimensions. In the channel dimension, a channel-exchange module enhances channel-wise interaction through cross-attention dual state space modeling, enabling adaptive feature reweighting. In the spatial dimension, a spatial-exchange module employs cross-modal state space scanning to achieve comprehensive spatial fusion. By efficiently capturing global dependencies while maintaining linear computational complexity, DIFF-MF effectively integrates complementary multi-modal features. Experimental results on the driving scenarios and low-altitude UAV datasets demonstrate that our method outperforms existing approaches in both visual quality and quantitative evaluation. --- ### Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Experts Authors: Wei Zhou, Hong Huang, Ruize Shi, Bang Liu Published: 2026-01-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.05537v1 Heterogeneous Graph Neural Networks(HGNNs) have advanced mainly through better encoders, yet their decoding/projection stage still relies on a single shared linear head, assuming it can map rich node embeddings to labels. We call this the Linear Projection Bottleneck: in heterogeneous graphs, contextual diversity and long-tail shifts make a global head miss fine semantics, overfit hub nodes, and underserve tail nodes. While Mixture-of-Experts(MoE) could help, naively applying it clashes with structural imbalance and risks expert collapse. We propose a Heterogeneous-aware Orthogonal Prototype Experts framework named HOPE, a plug-and-play replacement for the standard prediction head. HOPE uses learnable prototype-based routing to assign instances to experts by similarity, letting expert usage follow the natural long-tail distribution, and adds expert orthogonalization to encourage diversity and prevent collapse. Experiments on four real datasets show consistent gains across SOTA HGNN backbones with minimal overhead. --- ### SAS-VPReID: A Scale-Adaptive Framework with Shape Priors for Video-based Person Re-Identification at Extreme Far Distances Authors: Qiwei Yang, Pingping Zhang, Yuhao Wang, Zijing Gong Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05535v1 Video-based Person Re-IDentification (VPReID) aims to retrieve the same person from videos captured by non-overlapping cameras. At extreme far distances, VPReID is highly challenging due to severe resolution degradation, drastic viewpoint variation and inevitable appearance noise. To address these issues, we propose a Scale-Adaptive framework with Shape Priors for VPReID, named SAS-VPReID. The framework is built upon three complementary modules. First, we deploy a Memory-Enhanced Visual Backbone (MEVB) to extract discriminative feature representations, which leverages the CLIP vision encoder and multi-proxy memory. Second, we propose a Multi-Granularity Temporal Modeling (MGTM) to construct sequences at multiple temporal granularities and adaptively emphasize motion cues across scales. Third, we incorporate Prior-Regularized Shape Dynamics (PRSD) to capture body structure dynamics. With these modules, our framework can obtain more discriminative feature representations. Experiments on the VReID-XFD benchmark demonstrate the effectiveness of each module and our final framework ranks the first on the VReID-XFD challenge leaderboard. The source code is available at https://github.com/YangQiWei3/SAS-VPReID. --- ### DNATokenizer: A GPU-First Byte-to-Identifier Tokenizer for High-Throughput DNA Language Models Authors: Eliatan Niktab, Hardip Patel Published: 2026-01-09 Categories: q-bio.GN, cs.LG arXiv: https://arxiv.org/abs/2601.05531v1 Tokenization sits at the boundary between high-throughput genomic input and GPU compute, posing challenges in both algorithm design and system throughput. Overlapping k-mer tokenization can introduce information leakage under masked language modeling (MLM) and may degrade downstream accuracy. Single-nucleotide tokenization avoids leakage and preserves per-base fidelity, but it greatly increases sequence length for attention-based architectures. Non-overlapping k-mers and byte-pair encoding (BPE) provide compression and avoid leakage, at the cost of boundary sensitivity or reduced interpretability. Empirically, the choice of tokenization interacts strongly with model architecture and task requirements. At the system level, however, standard string tokenizers and host-bound vocabulary lookups dominate wall-clock time once inputs reach billions of bases, regardless of the tokenization algorithm. We present DNATok, a high-performance, GPU-first tokenization system that replaces general-purpose string processing with byte lookup table (LUT)-based identifier streaming and an overlapped host-to-device (H2D)/compute pipeline using pinned memory and architectural parallelism. DNATok is vocabulary-agnostic: it accelerates single-nucleotide, non-overlapping k-mer, and BPE tokenization, and integrates as a drop-in systems layer beneath genomic foundation models. DNATok achieves 84-95x higher encoding throughput than optimized Hugging Face baselines and up to 1.9x higher H2D throughput. End-to-end streaming reaches 1.27-1.84e8 tokens/s depending on configuration, effectively removing tokenization as a bottleneck for production-scale training and inference. --- ### Before We Trust Them: Decision-Making Failures in Navigation of Foundation Models Authors: Jua Han, Jaeyoon Seo, Jungbin Min, Sieun Choi, Huichan Seo, Jihie Kim, Jean Oh Published: 2026-01-09 Categories: cs.AI, cs.RO arXiv: https://arxiv.org/abs/2601.05529v5 High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on six diagnostic tasks spanning three settings: reasoning under complete spatial information, reasoning under incomplete spatial information, and reasoning under safety-relevant information. Our results show that the current metrics may not capture critical limitations of the models and indicate good performance, underscoring the need for failure-focused analysis to understand model limitations and guide future progress. In a path-planning setting with unknown cells, GPT-5 achieved a high success rate of 93%; Yet, the failed cases exhibit fundamental limitations of the models, e.g., the lack of structural spatial understanding essential for navigation. We also find that newer models are not always more reliable than their predecessors on this end. In reasoning under safety-relevant information, Gemini-2.5 Flash achieved only 67% on the challenging emergency-evacuation task, underperforming Gemini-2.0 Flash, which reached 100% under the same condition. Across all evaluations, models exhibited structural collapse, hallucinated reasoning, constraint violations, and unsafe decisions. These findings show that foundation models still exhibit substantial failures in navigation-related decision making and require fine-grained evaluation before they can be trusted. --- ### Autonomous Probe Microscopy with Robust Bag-of-Features Multi-Objective Bayesian Optimization: Pareto-Front Mapping of Nanoscale Structure-Property Trade-Offs Authors: Kamyar Barakati, Haochen Zhu, C Charlotte Buchanan, Dustin A Gilbert, Philip Rack, Sergei V. Kalinin Published: 2026-01-09 Categories: cond-mat.mtrl-sci, cs.LG, physics.data-an arXiv: https://arxiv.org/abs/2601.05528v1 Combinatorial materials libraries are an efficient route to generate large families of candidate compositions, but their impact is often limited by the speed and depth of characterization and by the difficulty of extracting actionable structure-property relations from complex characterization data. Here we develop an autonomous scanning probe microscopy (SPM) framework that integrates automated atomic force and magnetic force microscopy (AFM/MFM) to rapidly explore magnetic and structural properties across combinatorial spread libraries. To enable automated exploration of systems without a clear optimization target, we introduce a combination of a static physics-informed bag-of-features (BoF) representation of measured surface morphology and magnetic structure with multi-objective Bayesian optimization (MOBO) to discover the relative significance and robustness of features. The resulting closed-loop workflow selectively samples the compositional gradient and reconstructs feature landscapes consistent with dense grid "ground truth" measurements. The resulting Pareto structure reveals where multiple nanoscale objectives are simultaneously optimized, where trade-offs between roughness, coherence, and magnetic contrast are unavoidable, and how families of compositions cluster into distinct functional regimes, thereby turning multi-feature imaging data into interpretable maps of competing structure-property trends. While demonstrated for Au-Co-Ni and AFM/MFM, the approach is general and can be extended to other combinatorial systems, imaging modalities, and feature sets, illustrating how feature-based MOBO and autonomous SPM can transform microscopy images from static data products into active feedback for real-time, multi-objective materials discovery. --- ### DeMa: Dual-Path Delay-Aware Mamba for Efficient Multivariate Time Series Analysis Authors: Rui An, Haohao Qu, Wenqi Fan, Xuequn Shang, Qing Li Published: 2026-01-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.05527v2 Accurate and efficient multivariate time series (MTS) analysis is increasingly critical for a wide range of intelligent applications. Within this realm, Transformers have emerged as the predominant architecture due to their strong ability to capture pairwise dependencies. However, Transformer-based models suffer from quadratic computational complexity and high memory overhead, limiting their scalability and practical deployment in long-term and large-scale MTS modeling. Recently, Mamba has emerged as a promising linear-time alternative with high expressiveness. Nevertheless, directly applying vanilla Mamba to MTS remains suboptimal due to three key limitations: (i) the lack of explicit cross-variate modeling, (ii) difficulty in disentangling the entangled intra-series temporal dynamics and inter-series interactions, and (iii) insufficient modeling of latent time-lag interaction effects. These issues constrain its effectiveness across diverse MTS tasks. To address these challenges, we propose DeMa, a dual-path delay-aware Mamba backbone. DeMa preserves Mamba's linear-complexity advantage while substantially improving its suitability for MTS settings. Specifically, DeMa introduces three key innovations: (i) it decomposes the MTS into intra-series temporal dynamics and inter-series interactions; (ii) it develops a temporal path with a Mamba-SSD module to capture long-range dynamics within each individual series, enabling series-independent, parallel computation; and (iii) it designs a variate path with a Mamba-DALA module that integrates delay-aware linear attention to model cross-variate dependencies. Extensive experiments on five representative tasks, long- and short-term forecasting, data imputation, anomaly detection, and series classification, demonstrate that DeMa achieves state-of-the-art performance while delivering remarkable computational efficiency. --- ### Explainable AI: Learning from the Learners Authors: Ricardo Vinuesa, Steven L. Brunton, Gianmarco Mengaldo Published: 2026-01-09 Categories: cs.AI, cs.LG, physics.comp-ph, physics.soc-ph arXiv: https://arxiv.org/abs/2601.05525v2 Artificial intelligence now outperforms humans in several scientific and engineering tasks, yet its internal representations often remain opaque. In this Perspective, we argue that explainable artificial intelligence (XAI), combined with causal reasoning, enables {\it learning from the learners}. Focusing on discovery, optimization and certification, we show how the combination of foundation models and explainability methods allows the extraction of causal mechanisms, guides robust design and control, and supports trust and accountability in high-stakes applications. We discuss challenges in faithfulness, generalization and usability of explanations, and propose XAI as a unifying framework for human-AI collaboration in science and engineering. --- ### Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism Authors: Yuhao Shen, Tianyu Liu, Junyi Shen, Jinyang Wu, Quan Kong, Li Huan, Cong Wang Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05524v3 Parallel Speculative Decoding (PSD) accelerates traditional Speculative Decoding (SD) by overlapping draft generation with verification. However, it remains hampered by two fundamental challenges: (1) a theoretical speedup ceiling dictated by the speed ratio between the draft and target models, and (2) high computational waste and pipeline stall due to mid-sequence token rejections of early errors. To address these limitations, we introduce \textsc{Double} (Double Retrieval Speculative Parallelism). By bridging the gap between SD and PSD, our framework resolves the Retrieval \emph{Precision-Efficiency Dilemma} through a novel synchronous mechanism. Specifically, we enable the draft model to execute iterative retrieval speculations to break the theoretical speedup limits; to alleviate rejections without rollback, the target model performs authoritative retrieval to generate multi-token guidance. \textsc{Double} is entirely training-free and lossless. Extensive experiments demonstrate state-of-the-art speedup of $\textbf{5.3}\times$ on LLaMA3.3-70B and $\textbf{2.8}\times$ on Qwen3-32B, significantly outperforming the advanced method EAGLE-3 that requires extensive model training. --- ### Toward an Integrated Cross-Urban Accident Prevention System: A Multi-Task Spatial-Temporal Learning Framework for Urban Safety Management Authors: Jiayu Fang, Zhiqi Shao, Haoning Xi, Boris Choy, Junbin Gao Published: 2026-01-09 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.05521v1 The development of a cross-city accident prevention system is particularly challenging due to the heterogeneity, inconsistent reporting, and inherently clustered, sparse, cyclical, and noisy nature of urban accident data. These intrinsic data properties, combined with fragmented governance and incompatible reporting standards, have long hindered the creation of an integrated, cross-city accident prevention framework. To address this gap, we propose the Mamba Local-ttention Spatial-Temporal Network MLA-STNet, a unified system that formulates accident risk prediction as a multi-task learning problem across multiple cities. MLA-STNet integrates two complementary modules: (i)the Spatio-Temporal Geographical Mamba-Attention (STG-MA), which suppresses unstable spatio-temporal fluctuations and strengthens long-range temporal dependencies; and (ii) the Spatio-Temporal Semantic Mamba-Attention (STS-MA), which mitigates cross-city heterogeneity through a shared-parameter design that jointly trains all cities while preserving individual semantic representation spaces. We validate the proposed framework through 75 experiments under two forecasting scenarios, full-day and high-frequency accident periods, using real-world datasets from New York City and Chicago. Compared with the state-of-the-art baselines, MLA-STNet achieves up to 6% lower RMSE, 8% higher Recall, and 5% higher MAP, while maintaining less than 1% performance variation under 50% input noise. These results demonstrate that MLA-STNet effectively unifies heterogeneous urban datasets within a scalable, robust, and interpretable Cross-City Accident Prevention System, paving the way for coordinated and data-driven urban safety management. --- ### CHisAgent: A Multi-Agent Framework for Event Taxonomy Construction in Ancient Chinese Cultural Systems Authors: Xuemei Tang, Chengxi Yan, Jinghang Gu, Chu-Ren Huang Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05520v3 Despite strong performance on many tasks, large language models (LLMs) show limited ability in historical and cultural reasoning, particularly in non-English contexts such as Chinese history. Taxonomic structures offer an effective mechanism to organize historical knowledge and improve understanding. However, manual taxonomy construction is costly and difficult to scale. Therefore, we propose \textbf{CHisAgent}, a multi-agent LLM framework for historical taxonomy construction in ancient Chinese contexts. CHisAgent decomposes taxonomy construction into three role-specialized stages: a bottom-up \textit{Inducer} that derives an initial hierarchy from raw historical corpora, a top-down \textit{Expander} that introduces missing intermediate concepts using LLM world knowledge, and an evidence-guided \textit{Enricher} that integrates external structured historical resources to ensure faithfulness. Using the \textit{Twenty-Four Histories}, we construct a large-scale, domain-aware event taxonomy covering politics, military, diplomacy, and social life in ancient China. Extensive reference-free and reference-based evaluations demonstrate improved structural coherence and coverage, while further analysis shows that the resulting taxonomy supports cross-cultural alignment. --- ### GaussianSwap: Animatable Video Face Swapping with 3D Gaussian Splatting Authors: Xuan Cheng, Jiahao Rao, Chengyang Li, Wenhao Wang, Weilin Chen, Lvqing Yang Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05511v1 We introduce GaussianSwap, a novel video face swapping framework that constructs a 3D Gaussian Splatting based face avatar from a target video while transferring identity from a source image to the avatar. Conventional video swapping frameworks are limited to generating facial representations in pixel-based formats. The resulting swapped faces exist merely as a set of unstructured pixels without any capacity for animation or interactive manipulation. Our work introduces a paradigm shift from conventional pixel-based video generation to the creation of high-fidelity avatar with swapped faces. The framework first preprocesses target video to extract FLAME parameters, camera poses and segmentation masks, and then rigs 3D Gaussian splats to the FLAME model across frames, enabling dynamic facial control. To ensure identity preserving, we propose an compound identity embedding constructed from three state-of-the-art face recognition models for avatar finetuning. Finally, we render the face-swapped avatar on the background frames to obtain the face-swapped video. Experimental results demonstrate that GaussianSwap achieves superior identity preservation, visual clarity and temporal consistency, while enabling previously unattainable interactive applications. --- ### Enabling Stroke-Level Structural Analysis of Hieroglyphic Scripts without Language-Specific Priors Authors: Fuwen Luo, Zihao Wan, Ziyue Wang, Yaluo Liu, Pau Tong Lin Xu, Xuanjia Qiao, Xiaolong Wang, Peng Li, Yang Liu Published: 2026-01-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.05508v2 Hieroglyphs, as logographic writing systems, encode rich semantic and cultural information within their internal structural composition. Yet, current advanced Large Language Models (LLMs) and Multimodal LLMs (MLLMs) usually remain structurally blind to this information. LLMs process characters as textual tokens, while MLLMs additionally view them as raw pixel grids. Both fall short to model the underlying logic of character strokes. Furthermore, existing structural analysis methods are often script-specific and labor-intensive. In this paper, we propose Hieroglyphic Stroke Analyzer (HieroSA), a novel and generalizable framework that enables MLLMs to automatically derive stroke-level structures from character bitmaps without handcrafted data. It transforms modern logographic and ancient hieroglyphs character images into explicit, interpretable line-segment representations in a normalized coordinate space, allowing for cross-lingual generalization. Extensive experiments demonstrate that HieroSA effectively captures character-internal structures and semantics, bypassing the need for language-specific priors. Experimental results highlight the potential of our work as a graphematics analysis tool for a deeper understanding of hieroglyphic scripts. View our code at https://github.com/THUNLP-MT/HieroSA. --- ### FlashMem: Distilling Intrinsic Latent Memory via Computation Reuse Authors: Yubo Hou, Zhisheng Chen, Tao Wan, Zengchang Qin Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05505v2 The stateless architecture of Large Language Models inherently lacks the mechanism to preserve dynamic context, compelling agents to redundantly reprocess history to maintain long-horizon autonomy. While latent memory offers a solution, current approaches are hindered by architectural segregation, relying on auxiliary encoders that decouple memory from the reasoning backbone. We propose FlashMem, a framework that distills intrinsic memory directly from transient reasoning states via computation reuse. Leveraging the property that internal representations uniquely encode input trajectories, FlashMem identifies the last hidden state as a sufficient statistic for the interaction history. This enables a Shared-KV Consolidator to synthesize memory by attending directly to the backbone's frozen cache, eliminating redundant re-parameterization. Furthermore, a parameter-free Cognitive Monitor leverages attention entropy to adaptively trigger consolidation only when high epistemic uncertainty is detected. Experiments demonstrate that FlashMem matches the performance of heavy baselines while reducing inference latency by 5 times, effectively bridging the gap between efficiency and persistent cognition. --- ### Over-Searching in Search-Augmented Large Language Models Authors: Roy Xie, Deepak Gopinath, David Qiu, Dong Lin, Haitian Sun, Saloni Potdar, Bhuwan Dhingra Published: 2026-01-09 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.05503v2 Search-augmented large language models (LLMs) excel at knowledge-intensive tasks by integrating external retrieval. However, they often over-search -- unnecessarily invoking search tool even when it does not improve response quality, which leads to computational inefficiency and hallucinations by incorporating irrelevant context. In this work, we conduct a systematic evaluation of over-searching across multiple dimensions, including query types, model categories, retrieval conditions, and multi-turn conversations. Our finding shows: (i) search generally improves answer accuracy on answerable queries but harms abstention on unanswerable ones; (ii) over-searching is more pronounced in complex reasoning models and deep research systems, is exacerbated by noisy retrieval, and compounds across turns in multi-turn conversations; and (iii) the composition of retrieved evidence is crucial, as the presence of negative evidence improves abstention. To quantify over-searching, we introduce Tokens Per Correctness (TPC), an evaluation metric that captures the performance-cost trade-off for search-augmented LLMs. Lastly, we investigate mitigation approaches at both the query and retrieval levels and release the OverSearchQA to foster continued research into efficient search-augmented LLMs. --- ### Evaluating the Use of LLMs for Automated DOM-Level Resolution of Web Performance Issues Authors: Gideon Peters, SayedHassan Khatoonabadi, Emad Shihab Published: 2026-01-09 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.05502v1 Users demand fast, seamless webpage experiences, yet developers often struggle to meet these expectations within tight constraints. Performance optimization, while critical, is a time-consuming and often manual process. One of the most complex tasks in this domain is modifying the Document Object Model (DOM), which is why this study focuses on it. Recent advances in Large Language Models (LLMs) offer a promising avenue to automate this complex task, potentially transforming how developers address web performance issues. This study evaluates the effectiveness of nine state-of-the-art LLMs for automated web performance issue resolution. For this purpose, we first extracted the DOM trees of 15 popular webpages (e.g., Facebook), and then we used Lighthouse to retrieve their performance audit reports. Subsequently, we passed the extracted DOM trees and corresponding audits to each model for resolution. Our study considers 7 unique audit categories, revealing that LLMs universally excel at SEO & Accessibility issues. However, their efficacy in performance-critical DOM manipulations is mixed. While high-performing models like GPT-4.1 delivered significant reductions in areas like Initial Load, Interactivity, and Network Optimization (e.g., 46.52% to 48.68% audit incidence reductions), others, such as GPT-4o-mini, notably underperformed, consistently. A further analysis of these modifications showed a predominant additive strategy and frequent positional changes, alongside regressions particularly impacting Visual Stability. --- ### Hi-ZFO: Hierarchical Zeroth- and First-Order LLM Fine-Tuning via Importance-Guided Tensor Selection Authors: Feihu Jin, Ying Tan Published: 2026-01-09 Categories: cs.LG, cs.CL arXiv: https://arxiv.org/abs/2601.05501v1 Fine-tuning large language models (LLMs) using standard first-order (FO) optimization often drives training toward sharp, poorly generalizing minima. Conversely, zeroth-order (ZO) methods offer stronger exploratory behavior without relying on explicit gradients, yet suffer from slow convergence. More critically, our analysis reveals that in generative tasks, the vast output and search space significantly amplify estimation variance, rendering ZO methods both noisy and inefficient. To address these challenges, we propose \textbf{Hi-ZFO} (\textbf{Hi}erarchical \textbf{Z}eroth- and \textbf{F}irst-\textbf{O}rder optimization), a hybrid framework designed to synergize the precision of FO gradients with the exploratory capability of ZO estimation. Hi-ZFO adaptively partitions the model through layer-wise importance profiling, applying precise FO updates to critical layers while leveraging ZO optimization for less sensitive ones. Notably, ZO in Hi-ZFO is not merely a memory-saving surrogate; it is intentionally introduced as a source of "beneficial stochasticity" to help the model escape the local minima where pure FO optimization tends to stagnate. Validated across diverse generative, mathematical, and code reasoning tasks, Hi-ZFO consistently achieves superior performance while significantly reducing the training time. These results demonstrate the effectiveness of hierarchical hybrid optimization for LLM fine-tuning. --- ### The Illusion of AI Expertise Under Uncertainty: Navigating Elusive Ground Truth via a Probabilistic Paradigm Authors: Aparna Elangovan, Lei Xu, Mahsa Elyasi, Ismail Akdulum, Mehmet Aksakal, Enes Gurun, Brian Hur, Saab Mansour, Ravid Shwartz Ziv, Karin Verspoor, Dan Roth Published: 2026-01-09 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.05500v5 Benchmarking the capabilities of AI systems, including Large Language Models (LLMs) and Vision Models, typically ignores the impact of uncertainty in the underlying ground truth answers from experts. This ambiguity is not just limited to human preferences, but is also consequential even in safety critical domains such as medicine where uncertainty is pervasive. In this paper, we introduce a probabilistic paradigm to theoretically explain how high certainty in ground truth answers is almost always necessary for even an expert to achieve high scores, whereas in datasets with high variation in ground truth answers there may be little difference between a random labeller and an expert. This characteristic also manifests when comparing models, where uncertainty obfuscates differences between poor and high performing models. Therefore, ignoring uncertainty in ground truth evaluation data can result in the misleading conclusion that a non-expert has similar performance to that of an expert. Using the probabilistic paradigm, we thus bring forth the concepts of expected accuracy and expected F1 and compare the estimated score an expert human or system can achieve given ground truth answer variability across 6 datasets and 9 models. The results lead to the recommendation that stratification by the probability of the ground truth answer becomes critical when expert performance is relatively low. Under stratified evaluation, performance comparison becomes more reliable in high certainty bins, mitigating the effect of the key confounding factor -- uncertainty. --- ### Prompt-Free SAM-Based Multi-Task Framework for Breast Ultrasound Lesion Segmentation and Classification Authors: Samuel E. Johnny, Bernes L. Atabonfack, Israel Alagbe, Assane Gueye Published: 2026-01-09 Categories: cs.CV, cs.AI, cs.LG arXiv: https://arxiv.org/abs/2601.05498v1 Accurate tumor segmentation and classification in breast ultrasound (BUS) imaging remain challenging due to low contrast, speckle noise, and diverse lesion morphology. This study presents a multi-task deep learning framework that jointly performs lesion segmentation and diagnostic classification using embeddings from the Segment Anything Model (SAM) vision encoder. Unlike prompt-based SAM variants, our approach employs a prompt-free, fully supervised adaptation where high-dimensional SAM features are decoded through either a lightweight convolutional head or a UNet-inspired decoder for pixel-wise segmentation. The classification branch is enhanced via mask-guided attention, allowing the model to focus on lesion-relevant features while suppressing background artifacts. Experiments on the PRECISE 2025 breast ultrasound dataset, split per class into 80 percent training and 20 percent testing, show that the proposed method achieves a Dice Similarity Coefficient (DSC) of 0.887 and an accuracy of 92.3 percent, ranking among the top entries on the PRECISE challenge leaderboard. These results demonstrate that SAM-based representations, when coupled with segmentation-guided learning, significantly improve both lesion delineation and diagnostic prediction in breast ultrasound imaging. --- ### MMViR: A Multi-Modal and Multi-Granularity Representation for Long-range Video Understanding Authors: Zizhong Li, Haopeng Zhang, Jiawei Zhang Published: 2026-01-09 Categories: cs.CV, cs.CL arXiv: https://arxiv.org/abs/2601.05495v1 Long videos, ranging from minutes to hours, present significant challenges for current Multi-modal Large Language Models (MLLMs) due to their complex events, diverse scenes, and long-range dependencies. Direct encoding of such videos is computationally too expensive, while simple video-to-text conversion often results in redundant or fragmented content. To address these limitations, we introduce MMViR, a novel multi-modal, multi-grained structured representation for long video understanding. MMViR identifies key turning points to segment the video and constructs a three-level description that couples global narratives with fine-grained visual details. This design supports efficient query-based retrieval and generalizes well across various scenarios. Extensive evaluations across three tasks, including QA, summarization, and retrieval, show that MMViR outperforms the prior strongest method, achieving a 19.67% improvement in hour-long video understanding while reducing processing latency to 45.4% of the original. --- ### Hippocampal Atrophy Patterns Across the Alzheimer's Disease Spectrum: A Voxel-Based Morphometry Analysis Authors: Trishna Niraula Published: 2026-01-09 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.05494v1 Alzheimer's disease (AD) and mild cognitive impairment (MCI) are associated with progressive gray matter loss, particularly in medial temporal structures. In this study, CAT12/SPM12 voxel-based morphometry was applied to baseline T1-weighted MRI scans from 249 ADNI participants (CN = 90, MCI = 129, AD = 30). Gray matter volume was analyzed using a general linear model, with the diagnostic group as primary predictor and age and total intracranial volume as covariates. Statistical maps were thresholded at p < 0.001 (voxelwise) and corrected for multiple comparisons at the cluster level using family-wise error (FWE) correction (p < 0.05). Significant hippocampal atrophy was observed in AD relative to CN and MCI (Cohen's d = 2.03 and 1.61, respectively). Hippocampal volume demonstrated moderate predictive value for conversion from MCI to AD (AUC = 0.66). Stratification by APOE4 status did not reveal significant genetic effects on cross-sectional hippocampal volume. These results support medial temporal degeneration as a key feature of AD progression and provide insights into predictive biomarkers and genetic influences. --- ### MemBuilder: Reinforcing LLMs for Long-Term Memory Construction via Attributed Dense Rewards Authors: Zhiyu Shen, Ziming Wu, Fuming Lai, Shaobing Lian, Yanghui Rao Published: 2026-01-09 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.05488v4 Maintaining consistency in long-term dialogues remains a fundamental challenge for LLMs, as standard retrieval mechanisms often fail to capture the temporal evolution of historical states. While memory-augmented frameworks offer a structured alternative, current systems rely on static prompting of closed-source models or suffer from ineffective training paradigms with sparse rewards. We introduce MemBuilder, a reinforcement learning framework that trains models to orchestrate multi-dimensional memory construction with attributed dense rewards. MemBuilder addresses two key challenges: (1) Sparse Trajectory-Level Rewards: we employ synthetic session-level question generation to provide dense intermediate rewards across extended trajectories; and (2) Multi-Dimensional Memory Attribution: we introduce contribution-aware gradient weighting that scales policy updates based on each component's downstream impact. Experimental results show that MemBuilder enables a 4B-parameter model to outperform state-of-the-art closed-source baselines, exhibiting strong generalization across long-term dialogue benchmarks. ---