# Research Papers — 2026-01 · bundle page 159 of 189 > Full-text markdown of papers #7901–7950 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/159 [← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/158.md) [Next bundle →](https://aipod.dev/papers/archive/2026-01/page/160.md) ### Prompt Tuning without Labeled Samples for Zero-Shot Node Classification in Text-Attributed Graphs Authors: Sethupathy Parameswaran, Suresh Sundaram, Yuan Fang Published: 2026-01-07 Categories: cs.LG, cs.IR arXiv: https://arxiv.org/abs/2601.03793v1 Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) presents a significant challenge, particularly due to the absence of labeled data. In this paper, we propose a novel Zero-shot Prompt Tuning (ZPT) framework to address this problem by leveraging a Universal Bimodal Conditional Generator (UBCG). Our approach begins with pre-training a graph-language model to capture both the graph structure and the associated textual descriptions of each node. Following this, a conditional generative model is trained to learn the joint distribution of nodes in both graph and text modalities, enabling the generation of synthetic samples for each class based solely on the class name. These synthetic node and text embeddings are subsequently used to perform continuous prompt tuning, facilitating effective node classification in a zero-shot setting. Furthermore, we conduct extensive experiments on multiple benchmark datasets, demonstrating that our framework performs better than existing state-of-the-art baselines. We also provide ablation studies to validate the contribution of the bimodal generator. The code is provided at: https://github.com/Sethup123/ZPT. --- ### VietMed-MCQ: A Consistency-Filtered Data Synthesis Framework for Vietnamese Traditional Medicine Evaluation Authors: Huynh Trung Kiet, Dao Sy Duy Minh, Nguyen Dinh Ha Duong, Le Hoang Minh Huy, Long Nguyen, Dien Dinh Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03792v2 Large Language Models (LLMs) have demonstrated remarkable proficiency in general medical domains. However, their performance significantly degrades in specialized, culturally specific domains such as Vietnamese Traditional Medicine (VTM), primarily due to the scarcity of high-quality, structured benchmarks. In this paper, we introduce VietMed-MCQ, a novel multiple-choice question dataset generated via a Retrieval-Augmented Generation (RAG) pipeline with an automated consistency check mechanism. Unlike previous synthetic datasets, our framework incorporates a dual-model validation approach to ensure reasoning consistency through independent answer verification, though the substring-based evidence checking has known limitations. The complete dataset of 3,190 questions spans three difficulty levels and underwent validation by one medical expert and four students, achieving 94.2 percent approval with substantial inter-rater agreement (Fleiss' kappa = 0.82). We benchmark seven open-source models on VietMed-MCQ. Results reveal that general-purpose models with strong Chinese priors outperform Vietnamese-centric models, highlighting cross-lingual conceptual transfer, while all models still struggle with complex diagnostic reasoning. Our code and dataset are publicly available to foster research in low-resource medical domains. --- ### Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework Authors: Xiaoyu Luo, Yiyi Chen, Qiongxiu Li, Johannes Bjerva Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03791v1 Large Language Models (LLMs) have been reported to "leak" Personally Identifiable Information (PII), with successful PII reconstruction often interpreted as evidence of memorization. We propose a principled revision of memorization evaluation for LLMs, arguing that PII leakage should be evaluated under low lexical cue conditions, where target PII cannot be reconstructed through prompt-induced generalization or pattern completion. We formalize Cue-Resistant Memorization (CRM) as a cue-controlled evaluation framework and a necessary condition for valid memorization evaluation, explicitly conditioning on prompt-target overlap cues. Using CRM, we conduct a large-scale multilingual re-evaluation of PII leakage across 32 languages and multiple memorization paradigms. Revisiting reconstruction-based settings, including verbatim prefix-suffix completion and associative reconstruction, we find that their apparent effectiveness is driven primarily by direct surface-form cues rather than by true memorization. When such cues are controlled for, reconstruction success diminishes substantially. We further examine cue-free generation and membership inference, both of which exhibit extremely low true positive rates. Overall, our results suggest that previously reported PII leakage is better explained by cue-driven behavior than by genuine memorization, highlighting the importance of cue-controlled evaluation for reliably quantifying privacy-relevant memorization in LLMs. --- ### NeoAMT: Neologism-Aware Agentic Machine Translation with Reinforcement Learning Authors: Zhongtao Miao, Kaiyan Zhao, Masaaki Nagata, Yoshimasa Tsuruoka Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03790v4 Neologism-aware machine translation aims to translate source sentences containing neologisms into target languages. This field remains underexplored compared with general machine translation (MT). In this paper, we propose an agentic framework, NeoAMT, for neologism-aware machine translation equipped with a Wiktionary-based search toolkit. Specifically, we first construct a dedicated dataset for neologism-aware machine translation and build a search toolkit grounded in Wiktionary. The dataset covers 16 languages and 75 translation directions in total, derived from approximately 10 million records of an English Wiktionary dump. The retrieval corpus of the search toolkit is also constructed from around 3 million cleaned records of the same dump. We then leverage the dataset and toolkit to train a translation agent via reinforcement learning (RL) and to evaluate the accuracy of neologism-aware machine translation. Furthermore, we propose an RL training framework featuring a novel reward design and an adaptive rollout generation strategy that exploits translation difficulty to further improve the translation quality of translation agents using our search toolkit. --- ### Criminal Liability of Generative Artificial Intelligence Providers for User-Generated Child Sexual Abuse Material Authors: Anamaria Mojica-Hanke, Thomas Goger, Svenja Wölfel, Brian Valerius, Steffen Herbold Published: 2026-01-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.03788v1 The development of more powerful Generative Artificial Intelligence (GenAI) has expanded its capabilities and the variety of outputs. This has introduced significant legal challenges, including gray areas in various legal systems, such as the assessment of criminal liability for those responsible for these models. Therefore, we conducted a multidisciplinary study utilizing the statutory interpretation of relevant German laws, which, in conjunction with scenarios, provides a perspective on the different properties of GenAI in the context of Child Sexual Abuse Material (CSAM) generation. We found that generating CSAM with GenAI may have criminal and legal consequences not only for the user committing the primary offense but also for individuals responsible for the models, such as independent software developers, researchers, and company representatives. Additionally, the assessment of criminal liability may be affected by contextual and technical factors, including the type of generated image, content moderation policies, and the model's intended purpose. Based on our findings, we discussed the implications for different roles, as well as the requirements when developing such systems. --- ### Compact Example-Based Explanations for Language Models Authors: Loris Schoenegger, Benjamin Roth Published: 2026-01-07 Categories: cs.CL, cs.LG arXiv: https://arxiv.org/abs/2601.03786v2 Training data influence estimation methods quantify the contribution of training documents to a model's output, making them a promising source of information for example-based explanations. As humans cannot interpret thousands of documents, only a small subset of the training data can be presented as an explanation. Although the choice of which documents to include directly affects explanation quality, previous evaluations of such systems have largely ignored any selection strategies. To address this, we propose a novel selection relevance score, a retraining-free metric that quantifies how useful a set of examples is for explaining a model's output. We validate this score through fine-tuning experiments, confirming that it can predict whether a set of examples supports or undermines the model's predictions. Using this metric, we further show that common selection strategies often underperform random selection. Motivated by this finding, we propose a strategy that balances influence and representativeness, enabling better use of selection budgets than naively selecting the highest-ranking examples. --- ### Membox: Weaving Topic Continuity into Long-Range Memory for LLM Agents Authors: Dehao Tao, Guoliang Ma, Yongfeng Huang, Minghu Jiang Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03785v3 Long-term human-agent dialogues are organized by topic continuity: adjacent turns often develop the same goal, plan, problem, or event, while related activities may recur across distant sessions. Yet many LLM agent memory systems first decompose histories into isolated turns or fixed-size chunks, then compensate through enrichment, consolidation, or retrieval mechanisms still tied to semantic proximity or fragment-level records. This weakens temporal and causal organization and biases memory access toward semantic proximity rather than task- or topic-level continuity. We introduce \emph{Membox}, a hierarchical memory architecture that instantiates topic continuity as an explicit organization layer for agent memory. Its \textbf{Topic Loom} incrementally organizes dialogue streams into boxes whose internal turns follow the same local topic, while its \textbf{Trace Weaver} links extracted events across boxes into macro-topic traces that recover recurring activities, goals, and factual developments across distant sessions. On LoCoMo, Topic-Loom-only retrieval improves over the best Mem0/A-MEM retrieval-depth setting by 13.00 F1 points (53.95 vs. 40.95), and trace-expanded retrieval further raises F1 to 55.28; with GPT-4o, trace-expanded retrieval reaches 59.71 F1. Additional DialSim results show the same gain from adding cross-box traces in multi-party dialogue. These results show that local topic-continuity organization and macro-topic trace expansion improve long-range memory beyond semantic retrieval over fragmented records. --- ### A Comparative Study of 3D Model Acquisition Methods for Synthetic Data Generation of Agricultural Products Authors: Steven Moonen, Rob Salaets, Kenneth Batstone, Abdellatif Bey-Temsamani, Nick Michiels Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03784v1 In the manufacturing industry, computer vision systems based on artificial intelligence (AI) are widely used to reduce costs and increase production. Training these AI models requires a large amount of training data that is costly to acquire and annotate, especially in high-variance, low-volume manufacturing environments. A popular approach to reduce the need for real data is the use of synthetic data that is generated by leveraging computer-aided design (CAD) models available in the industry. However, in the agricultural industry these models are not readily available, increasing the difficulty in leveraging synthetic data. In this paper, we present different techniques for substituting CAD files to create synthetic datasets. We measure their relative performance when used to train an AI object detection model to separate stones and potatoes in a bin picking environment. We demonstrate that using highly representative 3D models acquired by scanning or using image-to-3D approaches can be used to generate synthetic data for training object detection models. Finetuning on a small real dataset can significantly improve the performance of the models and even get similar performance when less representative models are used. --- ### HearSay Benchmark: Do Audio LLMs Leak What They Hear? Authors: Jin Wang, Liang Lin, Kaiwen Luo, Weiliu Wang, Yitian Chen, Moayad Aloqaily, Xuehai Tang, Zhenhong Zhou, Kun Wang, Li Sun, Qingsong Wen Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03783v1 While Audio Large Language Models (ALLMs) have achieved remarkable progress in understanding and generation, their potential privacy implications remain largely unexplored. This paper takes the first step to investigate whether ALLMs inadvertently leak user privacy solely through acoustic voiceprints and introduces $\textit{HearSay}$, a comprehensive benchmark constructed from over 22,000 real-world audio clips. To ensure data quality, the benchmark is meticulously curated through a rigorous pipeline involving automated profiling and human verification, guaranteeing that all privacy labels are grounded in factual records. Extensive experiments on $\textit{HearSay}$ yield three critical findings: $\textbf{Significant Privacy Leakage}$: ALLMs inherently extract private attributes from voiceprints, reaching 92.89% accuracy on gender and effectively profiling social attributes. $\textbf{Insufficient Safety Mechanisms}$: Alarmingly, existing safeguards are severely inadequate; most models fail to refuse privacy-intruding requests, exhibiting near-zero refusal rates for physiological traits. $\textbf{Reasoning Amplifies Risk}$: Chain-of-Thought (CoT) reasoning exacerbates privacy risks in capable models by uncovering deeper acoustic correlations. These findings expose critical vulnerabilities in ALLMs, underscoring the urgent need for targeted privacy alignment. The codes and dataset are available at https://github.com/JinWang79/HearSay_Benchmark --- ### PointWorld: Scaling 3D World Models for In-The-Wild Robotic Manipulation Authors: Wenlong Huang, Yu-Wei Chao, Arsalan Mousavian, Ming-Yu Liu, Dieter Fox, Kaichun Mo, Li Fei-Fei Published: 2026-01-07 Categories: cs.RO, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2601.03782v1 Humans anticipate, from a glance and a contemplated action of their bodies, how the 3D world will respond, a capability that is equally vital for robotic manipulation. We introduce PointWorld, a large pre-trained 3D world model that unifies state and action in a shared 3D space as 3D point flows: given one or few RGB-D images and a sequence of low-level robot action commands, PointWorld forecasts per-pixel displacements in 3D that respond to the given actions. By representing actions as 3D point flows instead of embodiment-specific action spaces (e.g., joint positions), this formulation directly conditions on physical geometries of robots while seamlessly integrating learning across embodiments. To train our 3D world model, we curate a large-scale dataset spanning real and simulated robotic manipulation in open-world environments, enabled by recent advances in 3D vision and simulated environments, totaling about 2M trajectories and 500 hours across a single-arm Franka and a bimanual humanoid. Through rigorous, large-scale empirical studies of backbones, action representations, learning objectives, partial observability, data mixtures, domain transfers, and scaling, we distill design principles for large-scale 3D world modeling. With a real-time (0.1s) inference speed, PointWorld can be efficiently integrated in the model-predictive control (MPC) framework for manipulation. We demonstrate that a single pre-trained checkpoint enables a real-world Franka robot to perform rigid-body pushing, deformable and articulated object manipulation, and tool use, without requiring any demonstrations or post-training and all from a single image captured in-the-wild. Project website at https://point-world.github.io/. --- ### MVP: Enhancing Video Large Language Models via Self-supervised Masked Video Prediction Authors: Xiaokun Sun, Zezhong Wu, Zewen Ding, Linli Xu Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03781v1 Reinforcement learning based post-training paradigms for Video Large Language Models (VideoLLMs) have achieved significant success by optimizing for visual-semantic tasks such as captioning or VideoQA. However, while these approaches effectively enhance perception abilities, they primarily target holistic content understanding, often lacking explicit supervision for intrinsic temporal coherence and inter-frame correlations. This tendency limits the models' ability to capture intricate dynamics and fine-grained visual causality. To explicitly bridge this gap, we propose a novel post-training objective: Masked Video Prediction (MVP). By requiring the model to reconstruct a masked continuous segment from a set of challenging distractors, MVP forces the model to attend to the sequential logic and temporal context of events. To support scalable training, we introduce a scalable data synthesis pipeline capable of transforming arbitrary video corpora into MVP training samples, and further employ Group Relative Policy Optimization (GRPO) with a fine-grained reward function to enhance the model's understanding of video context and temporal properties. Comprehensive evaluations demonstrate that MVP enhances video reasoning capabilities by directly reinforcing temporal reasoning and causal understanding. --- ### Tracing the complexity profiles of different linguistic phenomena through the intrinsic dimension of LLM representations Authors: Marco Baroni, Emily Cheng, Iria de-Dios-Flores, Francesca Franzon Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03779v3 We explore intrinsic dimension (ID) of LLM representations as a marker of linguistic complexity. Specifically, we test whether ID differences across model layers reflect well-known complexity contrasts established in (psycho)linguistics: coordination vs. subordination, right-branching vs. center-embedding, and unambiguous vs. ambiguous attachment. Our results on six different LLMs show that these contrasts are consistently reflected in ID differences, with more complex phenomena eliciting higher ID profiles. Notably, ID differences emerge at different points across layers for different contrasts, also reaching their peaks at different stages. Further experiments using representational similarity and layer pruning confirm the trends. We conclude that ID is a useful marker of linguistic complexity in LLMs, that it points to similar linguistic processing steps across disparate LLMs, and that it has the potential to differentiate between different types of complexity. --- ### Improving Compactness and Reducing Ambiguity of CFIRE Rule-Based Explanations Authors: Sebastian Müller, Tobias Schneider, Ruben Kemna, Vanessa Toborek Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.03776v1 Models trained on tabular data are widely used in sensitive domains, increasing the demand for explanation methods to meet transparency needs. CFIRE is a recent algorithm in this domain that constructs compact surrogate rule models from local explanations. While effective, CFIRE may assign rules associated with different classes to the same sample, introducing ambiguity. We investigate this ambiguity and propose a post-hoc pruning strategy that removes rules with low contribution or conflicting coverage, yielding smaller and less ambiguous models while preserving fidelity. Experiments across multiple datasets confirm these improvements with minimal impact on predictive performance. --- ### Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations Authors: Pingjun Hong, Benjamin Roth Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03775v1 Large Language Models (LLMs) can produce verbalized self-explanations, yet prior studies suggest that such rationales may not reliably reflect the model's true decision process. We ask whether these explanations nevertheless help users predict model behavior, operationalized as counterfactual simulatability. Using StrategyQA, we evaluate how well humans and LLM judges can predict a model's answers to counterfactual follow-up questions, with and without access to the model's chain-of-thought or post-hoc explanations. We compare LLM-generated counterfactuals with pragmatics-based perturbations as alternative ways to construct test cases for assessing the potential usefulness of explanations. Our results show that self-explanations consistently improve simulation accuracy for both LLM judges and humans, but the degree and stability of gains depend strongly on the perturbation strategy and judge strength. We also conduct a qualitative analysis of free-text justifications written by human users when predicting the model's behavior, which provides evidence that access to explanations helps humans form more accurate predictions on the perturbed questions. --- ### Scalable Machine Learning Force Fields for Macromolecular Systems Through Long-Range Aware Message Passing Authors: Chu Wang, Lin Huang, Xinran Wei, Tao Qin, Arthur Jiang, Lixue Cheng, Jia Zhang Published: 2026-01-07 Categories: physics.chem-ph, cs.AI, physics.bio-ph arXiv: https://arxiv.org/abs/2601.03774v1 Machine learning force fields (MLFFs) have revolutionized molecular simulations by providing quantum mechanical accuracy at the speed of molecular mechanical computations. However, a fundamental reliance of these models on fixed-cutoff architectures limits their applicability to macromolecular systems where long-range interactions dominate. We demonstrate that this locality constraint causes force prediction errors to scale monotonically with system size, revealing a critical architectural bottleneck. To overcome this, we establish the systematically designed MolLR25 ({Mol}ecules with {L}ong-{R}ange effect) benchmark up to 1200 atoms, generated using high-fidelity DFT, and introduce E2Former-LSR, an equivariant transformer that explicitly integrates long-range attention blocks. E2Former-LSR exhibits stable error scaling, achieves superior fidelity in capturing non-covalent decay, and maintains precision on complex protein conformations. Crucially, its efficient design provides up to 30% speedup compared to purely local models. This work validates the necessity of non-local architectures for generalizable MLFFs, enabling high-fidelity molecular dynamics for large-scale chemical and biological systems. --- ### EntroCoT: Enhancing Chain-of-Thought via Adaptive Entropy-Guided Segmentation Authors: Zihang Li, Yuhang Wang, Yikun Zong, Wenhan Yu, Xiaokun Yuan, Runhan Jiang, Zirui Liu, Tong Yang, Arthur Jiang Published: 2026-01-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.03769v3 Chain-of-Thought (CoT) prompting has significantly enhanced the mathematical reasoning capabilities of Large Language Models. We find existing fine-tuning datasets frequently suffer from the "answer right but reasoning wrong" probelm, where correct final answers are derived from hallucinated, redundant, or logically invalid intermediate steps. This paper proposes EntroCoT, a unified framework for automatically identifying and refining low-quality CoT supervision traces. EntroCoT first proposes an entropy-based mechanism to segment the reasoning trace into multiple steps at uncertain junctures, and then introduces a Monte Carlo rollout-based mechanism to evaluate the marginal contribution of each step. By accurately filtering deceptive reasoning samples, EntroCoT constructs a high-quality dataset where every intermediate step in each reasoning trace facilitates the final answer. Extensive experiments on mathematical benchmarks demonstrate that fine-tuning on the subset constructed by EntroCoT consistently outperforms the baseslines of full-dataset supervision. --- ### Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model Authors: Noam Levi Published: 2026-01-07 Categories: cs.LG, cond-mat.dis-nn, cs.AI, stat.ML arXiv: https://arxiv.org/abs/2601.03764v1 We analyze neural scaling laws in a solvable model of last-layer fine-tuning where targets have intrinsic, instance-heterogeneous difficulty. In our Latent Instance Difficulty (LID) model, each input's target variance is governed by a latent ``precision'' drawn from a heavy-tailed distribution. While generalization loss recovers standard scaling laws, our main contribution connects this to inference. The pass@$k$ failure rate exhibits a power-law decay, $k^{-β_\text{eff}}$, but the observed exponent $β_\text{eff}$ is training-dependent. It grows with sample size $N$ before saturating at an intrinsic limit $β$ set by the difficulty distribution's tail. This coupling reveals that learning shrinks the ``hard tail'' of the error distribution: improvements in the model's generalization error steepen the pass@$k$ curve until irreducible target variance dominates. The LID model yields testable, closed-form predictions for this behavior, including a compute-allocation rule that favors training before saturation and inference attempts after. We validate these predictions in simulations and in two real-data proxies: CIFAR-10H (human-label variance) and a maths teacher-student distillation task. --- ### Probabilistic Transformers for Joint Modeling of Global Weather Dynamics and Decision-Centric Variables Authors: Paulius Rauba, Viktor Cikojevic, Fran Bartolic, Sam Levang, Ty Dickinson, Chase Dwelle Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.03753v1 Weather forecasts sit upstream of high-stakes decisions in domains such as grid operations, aviation, agriculture, and emergency response. Yet forecast users often face a difficult trade-off. Many decision-relevant targets are functionals of the atmospheric state variables, such as extrema, accumulations, and threshold exceedances, rather than state variables themselves. As a result, users must estimate these targets via post-processing, which can be suboptimal and can introduce structural bias. The core issue is that decisions depend on distributions over these functionals that the model is not trained to learn directly. In this work, we introduce GEM-2, a probabilistic transformer that jointly learns global atmospheric dynamics alongside a suite of variables that users directly act upon. Using this training recipe, we show that a lightweight (~275M params) and computationally efficient (~20-100x training speedup relative to state-of-the-art) transformer trained on the CRPS objective can directly outperform operational numerical weather prediction (NWP) models and be competitive with ML models that rely on expensive multi-step diffusion processes or require bespoke multi-stage fine-tuning strategies. We further demonstrate state-of-the-art economic value metrics under decision-theoretic evaluation, stable convergence to climatology at S2S and seasonal timescales, and a surprising insensitivity to many commonly assumed architectural and training design choices. --- ### Evaluation of Multilingual LLMs Personalized Text Generation Capabilities Targeting Groups and Social-Media Platforms Authors: Dominik Macko Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03752v1 Capabilities of large language models to generate multilingual coherent text have continuously enhanced in recent years, which opens concerns about their potential misuse. Previous research has shown that they can be misused for generation of personalized disinformation in multiple languages. It has also been observed that personalization negatively affects detectability of machine-generated texts; however, this has been studied in the English language only. In this work, we examine this phenomenon across 10 languages, while we focus not only on potential misuse of personalization capabilities, but also on potential benefits they offer. Overall, we cover 1080 combinations of various personalization aspects in the prompts, for which the texts are generated by 16 distinct language models (17,280 texts in total). Our results indicate that there are differences in personalization quality of the generated texts when targeting demographic groups and when targeting social-media platforms across languages. Personalization towards platforms affects detectability of the generated texts in a higher scale, especially in English, where the personalization quality is the highest. --- ### Bridging OLAP and RAG: A Multidimensional Approach to the Design of Corpus Partitioning Authors: Dario Maio, Stefano Rizzi Published: 2026-01-07 Categories: cs.IR, cs.AI arXiv: https://arxiv.org/abs/2601.03748v1 Retrieval-Augmented Generation (RAG) systems are increasingly deployed on large-scale document collections, often comprising millions of documents and tens of millions of text chunks. In industrial-scale retrieval platforms, scalability is typically addressed through horizontal sharding and a combination of Approximate Nearest-Neighbor search, hybrid indexing, and optimized metadata filtering. Although effective from an efficiency perspective, these mechanisms rely on bottom-up, similarity-driven organization and lack a conceptual rationale for corpus partitioning. In this paper, we claim that the design of large-scale RAG systems may benefit from the combination of two orthogonal strategies: semantic clustering, which optimizes locality in embedding space, and multidimensional partitioning, which governs where retrieval should occur based on conceptual dimensions such as time and organizational context. Although such dimensions are already implicitly present in current systems, they are used in an ad hoc and poorly structured manner. We propose the Dimensional Fact Model (DFM) as a conceptual framework to guide the design of multidimensional partitions for RAG corpora. The DFM provides a principled way to reason about facts, dimensions, hierarchies, and granularity in retrieval-oriented settings. This framework naturally supports hierarchical routing and controlled fallback strategies, ensuring that retrieval remains robust even in the presence of incomplete metadata, while transforming the search process from a 'black-box' similarity matching into a governable and deterministic workflow. This work is intended as a position paper; its goal is to bridge the gap between OLAP-style multidimensional modeling and modern RAG architectures, and to stimulate further research on principled, explainable, and governable retrieval strategies at scale. --- ### Whose Facts Win? LLM Source Preferences under Knowledge Conflicts Authors: Jakob Schuster, Vagrant Gautam, Katja Markert Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03746v3 As large language models (LLMs) are more frequently used in retrieval-augmented generation pipelines, it is increasingly relevant to study their behavior under knowledge conflicts. Thus far, the role of the source of the retrieved information has gone unexamined. We address this gap with a novel framework to investigate how source preferences affect LLM resolution of inter-context knowledge conflicts in English, motivated by interdisciplinary research on credibility. By using synthetic sources, we study preferences for different types of sources without inheriting the biases of specific real-world sources. With a comprehensive, tightly-controlled evaluation of 13 open-weight LLMs, we find that LLMs prefer institutionally-corroborated information (e.g., government or newspaper sources) over information from people and social media. However, these source preferences can be reversed by simply repeating information from less credible sources. To mitigate repetition effects and maintain consistent preferences, we propose a novel method that reduces repetition bias by up to 79.2%, while also maintaining at least 72.5% of original preferences. We release all data and code to encourage future work on credibility and source preferences in knowledge-intensive NLP. --- ### O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL Authors: Yi Yao, He Zhu, Piaohong Wang, Jincheng Ren, Xinlong Yang, Qianben Chen, Xiaowan Li, Dingfeng Shi, Jiaxian Li, Qiexiang Wang, Sinuo Wang, Xinpeng Liu et al. Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03743v1 The performance gap between closed-source and open-source large language models (LLMs) is largely attributed to disparities in access to high-quality training data. To bridge this gap, we introduce a novel framework for the automated synthesis of sophisticated, research-grade instructional data. Our approach centers on a multi-agent workflow where collaborative AI agents simulate complex tool-integrated reasoning to generate diverse and high-fidelity data end-to-end. Leveraging this synthesized data, we develop a two-stage training strategy that integrates supervised fine-tuning with a novel reinforcement learning method, designed to maximize model alignment and capability. Extensive experiments demonstrate that our framework empowers open-source models across multiple scales, enabling them to achieve new state-of-the-art performance on the major deep research benchmark. This work provides a scalable and effective pathway for advancing open-source LLMs without relying on proprietary data or models. --- ### I2E: From Image Pixels to Actionable Interactive Environments for Text-Guided Image Editing Authors: Jinghan Yu, Junhao Xiao, Chenyu Zhu, Jiaming Li, Jia Li, HanMing Deng, Xirui Wang, Guoli Jia, Jianjun Li, Xiang Bai, Bowen Zhou, Zhiyuan Ma Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03741v2 Existing text-guided image editing methods primarily rely on end-to-end pixel-level inpainting paradigm. Despite its success in simple scenarios, this paradigm still significantly struggles with compositional editing tasks that require precise local control and complex multi-object spatial reasoning. This paradigm is severely limited by 1) the implicit coupling of planning and execution, 2) the lack of object-level control granularity, and 3) the reliance on unstructured, pixel-centric modeling. To address these limitations, we propose I2E, a novel "Decompose-then-Action" paradigm that revisits image editing as an actionable interaction process within a structured environment. I2E utilizes a Decomposer to transform unstructured images into discrete, manipulable object layers and then introduces a physics-aware Vision-Language-Action Agent to parse complex instructions into a series of atomic actions via Chain-of-Thought reasoning. Further, we also construct I2E-Bench, a benchmark designed for multi-instance spatial reasoning and high-precision editing. Experimental results on I2E-Bench and multiple public benchmarks demonstrate that I2E significantly outperforms state-of-the-art methods in handling complex compositional instructions, maintaining physical plausibility, and ensuring multi-turn editing stability. --- ### HyperCOD: The First Challenging Benchmark and Baseline for Hyperspectral Camouflaged Object Detection Authors: Shuyan Bai, Tingfa Xu, Peifu Liu, Yuhao Qiu, Huiyan Bai, Huan Chen, Yanyan Peng, Jianan Li Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03736v1 RGB-based camouflaged object detection struggles in real-world scenarios where color and texture cues are ambiguous. While hyperspectral image offers a powerful alternative by capturing fine-grained spectral signatures, progress in hyperspectral camouflaged object detection (HCOD) has been critically hampered by the absence of a dedicated, large-scale benchmark. To spur innovation, we introduce HyperCOD, the first challenging benchmark for HCOD. Comprising 350 high-resolution hyperspectral images, It features complex real-world scenarios with minimal objects, intricate shapes, severe occlusions, and dynamic lighting to challenge current models. The advent of foundation models like the Segment Anything Model (SAM) presents a compelling opportunity. To adapt the Segment Anything Model (SAM) for HCOD, we propose HyperSpectral Camouflage-aware SAM (HSC-SAM). HSC-SAM ingeniously reformulates the hyperspectral image by decoupling it into a spatial map fed to SAM's image encoder and a spectral saliency map that serves as an adaptive prompt. This translation effectively bridges the modality gap. Extensive experiments show that HSC-SAM sets a new state-of-the-art on HyperCOD and generalizes robustly to other public HSI datasets. The HyperCOD dataset and our HSC-SAM baseline provide a robust foundation to foster future research in this emerging area. --- ### RadDiff: Describing Differences in Radiology Image Sets with Natural Language Authors: Xiaoxian Shen, Yuhui Zhang, Sahithi Ankireddy, Xiaohan Wang, Maya Varma, Henry Guo, Curtis Langlotz, Serena Yeung-Levy Published: 2026-01-07 Categories: cs.CV, cs.AI, cs.CL, cs.CY, cs.LG arXiv: https://arxiv.org/abs/2601.03733v1 Understanding how two radiology image sets differ is critical for generating clinical insights and for interpreting medical AI systems. We introduce RadDiff, a multimodal agentic system that performs radiologist-style comparative reasoning to describe clinically meaningful differences between paired radiology studies. RadDiff builds on a proposer-ranker framework from VisDiff, and incorporates four innovations inspired by real diagnostic workflows: (1) medical knowledge injection through domain-adapted vision-language models; (2) multimodal reasoning that integrates images with their clinical reports; (3) iterative hypothesis refinement across multiple reasoning rounds; and (4) targeted visual search that localizes and zooms in on salient regions to capture subtle findings. To evaluate RadDiff, we construct RadDiffBench, a challenging benchmark comprising 57 expert-validated radiology study pairs with ground-truth difference descriptions. On RadDiffBench, RadDiff achieves 47% accuracy, and 50% accuracy when guided by ground-truth reports, significantly outperforming the general-domain VisDiff baseline. We further demonstrate RadDiff's versatility across diverse clinical tasks, including COVID-19 phenotype comparison, racial subgroup analysis, and discovery of survival-related imaging features. Together, RadDiff and RadDiffBench provide the first method-and-benchmark foundation for systematically uncovering meaningful differences in radiological data. --- ### From Laboratory to Real-World Applications: Benchmarking Agentic Code Reasoning at the Repository Level Authors: Jia Li, Yuxin Su, Michael R. Lyu Published: 2026-01-07 Categories: cs.SE, cs.AI arXiv: https://arxiv.org/abs/2601.03731v3 As large language models (LLMs) evolve into autonomous agents, evaluating repository-level reasoning, the ability to maintain logical consistency across massive, real-world, interdependent file systems, has become critical. Current benchmarks typically fluctuate between isolated code snippets and black-box evaluations. We present RepoReason, a white-box diagnostic benchmark centered on abductive assertion verification. To eliminate memorization while preserving authentic logical depth, we implement an execution-driven mutation framework that utilizes the environment as a semantic oracle to regenerate ground-truth states. Furthermore, we establish a fine-grained diagnostic system using dynamic program slicing, quantifying reasoning via three orthogonal metrics: $ESV$ (reading load), $MCL$ (simulation depth), and $DFI$ (integration width). Comprehensive evaluations of frontier models (e.g., Claude-4.5-Sonnet, DeepSeek-v3.1-Terminus) reveal a prevalent aggregation deficit, where integration width serves as the primary cognitive bottleneck. Our findings provide granular white-box insights for optimizing the next generation of agentic software engineering. --- ### MATANet: A Multi-context Attention and Taxonomy-Aware Network for Fine-Grained Underwater Recognition of Marine Species Authors: Donghwan Lee, Byeongjin Kim, Geunhee Kim, Hyukjin Kwon, Nahyeon Maeng, Wooju Kim Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03729v4 Accurate fine-grained recognition of marine organisms is important for scalable biodiversity monitoring and ecological assessment using underwater imagery. However, existing methods mainly focus on target appearance and make limited use of surrounding environmental cues and biological taxonomy. We propose the Multi-Context Attention and Taxonomy-Aware Network (MATANet) for region-of-interest (ROI)-guided marine organism recognition. MATANet contains two complementary components. The Multi-Context Environmental Attention Module uses the ROI representation as a query to aggregate spatial patch features from ROI-centered contextual views at multiple scales, enabling target-conditioned modeling of the surrounding environment. Level-wise auxiliary classifiers further incorporate higher taxonomic ranks during training, encouraging hierarchically consistent representations without changing the finest-label prediction space or inference procedure. On the official FathomNet 2025 Private test split, MATANet achieves a hierarchical distance of 1.570 with the base backbone and 1.423 with the large backbone, substantially outperforming the strongest benchmark value of 2.603. On FishCLEF2015, MATANet achieves an accuracy of 0.793 and a hierarchical distance of 1.120, outperforming the strongest benchmark values of 0.766 and 1.327, respectively. Ablation studies show that surrounding scene information provides complementary evidence beyond repeated multi-scale observations of the target and that target-conditioned aggregation outperforms direct multi-view concatenation. Additional experiments on FAIR1M v2.0 examine the applicability of the proposed design beyond underwater imagery. In post-detection evaluation, MATANet improves fine-grained classification accuracy on matched detector-generated ROIs from 0.828 to 0.959 supporting its engineering applicability to automated marine monitoring. --- ### CSMCIR: CoT-Enhanced Symmetric Alignment with Memory Bank for Composed Image Retrieval Authors: Zhipeng Qian, Zihan Liang, Yufei Ma, Ben Chen, Huangyu Dai, Yiwei Ma, Jiayi Ji, Chenyi Lei, Han Li, Xiaoshuai Sun Published: 2026-01-07 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2601.03728v3 Composed Image Retrieval (CIR) enables users to search for target images using both a reference image and manipulation text, offering substantial advantages over single-modality retrieval systems. However, existing CIR methods suffer from representation space fragmentation: queries and targets comprise heterogeneous modalities and are processed by distinct encoders, forcing models to bridge misaligned representation spaces only through post-hoc alignment, which fundamentally limits retrieval performance. This architectural asymmetry manifests as three distinct, well-separated clusters in the feature space, directly demonstrating how heterogeneous modalities create fundamentally misaligned representation spaces from initialization. In this work, we propose CSMCIR, a unified representation framework that achieves efficient query-target alignment through three synergistic components. First, we introduce a Multi-level Chain-of-Thought (MCoT) prompting strategy that guides Multimodal Large Language Models to generate discriminative, semantically compatible captions for target images, establishing modal symmetry. Building upon this, we design a symmetric dual-tower architecture where both query and target sides utilize the identical shared-parameter Q-Former for cross-modal encoding, ensuring consistent feature representations and further reducing the alignment gap. Finally, this architectural symmetry enables an entropy-based, temporally dynamic Memory Bank strategy that provides high-quality negative samples while maintaining consistency with the evolving model state. Extensive experiments on four benchmark datasets demonstrate that our CSMCIR achieves state-of-the-art performance with superior training efficiency. Comprehensive ablation studies further validate the effectiveness of each proposed component. --- ### Stuttering-Aware Automatic Speech Recognition for Indonesian Language Authors: Fadhil Muhammad, Alwin Djuliansah, Adrian Aryaputra Hamzah, Kurniawati Azizah Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03727v2 Automatic speech recognition systems have achieved remarkable performance on fluent speech but continue to degrade significantly when processing stuttered speech, a limitation that is particularly acute for low-resource languages like Indonesian where specialized datasets are virtually non-existent. To overcome this scarcity, we propose a data augmentation framework that generates synthetic stuttered audio by injecting repetitions and prolongations into fluent text through a combination of rule-based transformations and large language models followed by text-to-speech synthesis. We apply this synthetic data to fine-tune a pre-trained Indonesian Whisper model using transfer learning, enabling the architecture to adapt to dysfluent acoustic patterns without requiring large-scale real-world recordings. Our experiments demonstrate that this targeted synthetic exposure consistently reduces recognition errors on stuttered speech while maintaining performance on fluent segments, validating the utility of synthetic data pipelines for developing more inclusive speech technologies in under-represented languages. --- ### EDCO: Dynamic Curriculum Orchestration for Domain-specific Large Language Model Fine-tuning Authors: Jing-Cheng Pang, Liu Sun, Chang Zhou, Xian Tang, Haichuan Ma, Kun Jiang, Jianlong Wang, Kai Zhang, Sijie Wu, Haoran Cai, Chenwei Wu, Xubin Li et al. Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.03725v1 Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is curriculum learning, which pre-orders training samples based on metrics like difficulty to improve learning efficiency compared to a random sampling strategy. However, most existing methods for LLM fine-tuning rely on a static curriculum, designed prior to training, which lacks adaptability to the model's evolving needs during fine-tuning. To address this, we propose EDCO, a novel framework based on two key concepts: inference entropy and dynamic curriculum orchestration. Inspired by recent findings that maintaining high answer entropy benefits long-term reasoning gains, EDCO prioritizes samples with high inference entropy in a continuously adapted curriculum. EDCO integrates three core components: an efficient entropy estimator that uses prefix tokens to approximate full-sequence entropy, an entropy-based curriculum generator that selects data points with the highest inference entropy, and an LLM trainer that optimizes the model on the selected curriculum. Comprehensive experiments in communication, medicine and law domains, EDCO outperforms traditional curriculum strategies for fine-tuning Qwen3-4B and Llama3.2-3B models under supervised and reinforcement learning settings. Furthermore, the proposed efficient entropy estimation reduces computational time by 83.5% while maintaining high accuracy. --- ### ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization Authors: Shijie Zhang, Kevin Zhang, Zheyuan Gu, Xiang Guo, Rujun Guo, Shaoyu Liu, Guanjun Jiang, Xiaozhao Wang Published: 2026-01-07 Categories: cs.LG arXiv: https://arxiv.org/abs/2601.03723v1 Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an important paradigm for unlocking reasoning capabilities in large language models, exemplified by the success of OpenAI o1 and DeepSeek-R1. Currently, Group Relative Policy Optimization (GRPO) stands as the dominant algorithm in this domain due to its stable training and critic-free efficiency. However, we argue that GRPO suffers from a structural limitation: it imposes a uniform, static trust region constraint across all samples. This design implicitly assumes signal homogeneity, a premise misaligned with the heterogeneous nature of outcome-driven learning, where advantage magnitudes and variances fluctuate significantly. Consequently, static constraints fail to fully exploit high-quality signals while insufficiently suppressing noise, often precipitating rapid entropy collapse. To address this, we propose \textbf{E}lastic \textbf{T}rust \textbf{R}egions (\textbf{ETR}), a dynamic mechanism that aligns optimization constraints with signal quality. ETR constructs a signal-aware landscape through dual-level elasticity: at the micro level, it scales clipping boundaries based on advantage magnitude to accelerate learning from high-confidence paths; at the macro level, it leverages group variance to implicitly allocate larger update budgets to tasks in the optimal learning zone. Extensive experiments on AIME and MATH benchmarks demonstrate that ETR consistently outperforms GRPO, achieving superior accuracy while effectively mitigating policy entropy degradation to ensure sustained exploration. --- ### Towards Real-world Lens Active Alignment with Unlabeled Data via Domain Adaptation Authors: Wenyong Li, Qi Jiang, Weijian Hu, Kailun Yang, Zhanjun Zhang, Wenjun Tian, Kaiwei Wang, Jian Bai Published: 2026-01-07 Categories: cs.CV, eess.IV, physics.optics arXiv: https://arxiv.org/abs/2601.03718v2 Active Alignment (AA) is a key technology for the large-scale automated assembly of high-precision optical systems. Compared with labor-intensive per-model on-device calibration, a digital-twin pipeline built on optical simulation offers a substantial advantage in generating large-scale labeled data. However, complex imaging conditions induce a domain gap between simulation and real-world images, limiting the generalization of simulation-trained models. To address this, we propose augmenting a simulation baseline with minimal unlabeled real-world images captured at random misalignment positions, mitigating the gap from a domain adaptation perspective. We introduce Domain Adaptive Active Alignment (DA3), which utilizes an autoregressive domain transformation generator and an adversarial-based feature alignment strategy to distill real-world domain information via self-supervised learning. This enables the extraction of domain-invariant image degradation features to facilitate robust misalignment prediction. Experiments on two lens types reveal that DA3 improves accuracy by 46% over a purely simulation pipeline. Notably, it approaches the performance achieved with precisely labeled real-world data collected on 3 lens samples, while reducing on-device data collection time by 98.7%. The results demonstrate that domain adaptation effectively endows simulation-trained models with robust real-world performance, validating the digital-twin pipeline as a practical solution to significantly enhance the efficiency of large-scale optical assembly. --- ### MIND: From Passive Mimicry to Active Reasoning through Capability-Aware Multi-Perspective CoT Distillation Authors: Jin Cui, Jiaqi Guo, Jiepeng Zhou, Ruixuan Yang, Jiayi Lu, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03717v1 While Large Language Models (LLMs) have emerged with remarkable capabilities in complex tasks through Chain-of-Thought reasoning, practical resource constraints have sparked interest in transferring these abilities to smaller models. However, achieving both domain performance and cross-domain generalization remains challenging. Existing approaches typically restrict students to following a single golden rationale and treat different reasoning paths independently. Due to distinct inductive biases and intrinsic preferences, alongside the student's evolving capacity and reasoning preferences during training, a teacher's "optimal" rationale could act as out-of-distribution noise. This misalignment leads to a degeneration of the student's latent reasoning distribution, causing suboptimal performance. To bridge this gap, we propose MIND, a capability-adaptive framework that transitions distillation from passive mimicry to active cognitive construction. We synthesize diverse teacher perspectives through a novel "Teaching Assistant" network. By employing a Feedback-Driven Inertia Calibration mechanism, this network utilizes inertia-filtered training loss to align supervision with the student's current adaptability, effectively enhancing performance while mitigating catastrophic forgetting. Extensive experiments demonstrate that MIND achieves state-of-the-art performance on both in-distribution and out-of-distribution benchmarks, and our sophisticated latent space analysis further confirms the mechanism of reasoning ability internalization. --- ### R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification Authors: Weijie Shi, Yanxi Chen, Zexi Li, Xuchen Pan, Yuchang Sun, Jiajie Xu, Xiaofang Zhou, Yaliang Li Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.03715v2 Reinforcement learning drives recent advances in LLM reasoning and agentic capabilities, yet current approaches struggle with both exploration and exploitation. Exploration suffers from low success rates on difficult tasks and high costs of repeated rollouts from scratch. Exploitation suffers from coarse credit assignment and training instability: Trajectory-level rewards penalize valid prefixes for later errors, and failure-dominated groups overwhelm the few positive signals, leaving optimization without constructive direction. To this end, we propose R$^3$L, Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification. To synthesize high-quality trajectories, R$^3$L shifts from stochastic sampling to active synthesis via reflect-then-retry, leveraging language feedback to diagnose errors, transform failed attempts into successful ones, and reduce rollout costs by restarting from identified failure points. With errors diagnosed and localized, Pivotal Credit Assignment updates only the diverging suffix where contrastive signals exist, excluding the shared prefix from gradient update. Since failures dominate on difficult tasks and reflect-then-retry produces off-policy data, risking training instability, Positive Amplification upweights successful trajectories to ensure positive signals guide the optimization process. Experiments on agentic and reasoning tasks demonstrate 5\% to 52\% relative improvements over baselines while maintaining training stability. Our code is released at https://github.com/shiweijiezero/R3L. --- ### Visual Merit or Linguistic Crutch? A Close Look at DeepSeek-OCR Authors: Yunhao Liang, Ruixuan Ying, Bo Li, Hong Li, Kai Yan, Qingwen Li, Min Yang, Okamoto Satoshi, Zhe Cui, Shiwen Ni Published: 2026-01-07 Categories: cs.CL, cs.CV arXiv: https://arxiv.org/abs/2601.03714v2 DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM long-context bottleneck, we investigate a critical question: "Visual merit or linguistic crutch - which drives DeepSeek-OCR's performance?" By employing sentence-level and word-level semantic corruption, we isolate the model's intrinsic OCR capabilities from its language priors. Results demonstrate that without linguistic support, DeepSeek-OCR's performance plummets from approximately 90% to 20%. Comparative benchmarking against 13 baseline models reveals that traditional pipeline OCR methods exhibit significantly higher robustness to such semantic perturbations than end-to-end methods. Furthermore, we find that lower visual token counts correlate with increased reliance on priors, exacerbating hallucination risks. Context stress testing also reveals a total model collapse around 10,000 text tokens, suggesting that current optical compression techniques may paradoxically aggravate the long-context bottleneck. This study empirically defines DeepSeek-OCR's capability boundaries and offers essential insights for future optimizations of the vision-text compression paradigm. We release all data, results and scripts used in this study at https://github.com/dududuck00/DeepSeekOCR. --- ### BREATH-VL: Vision-Language-Guided 6-DoF Bronchoscopy Localization via Semantic-Geometric Fusion Authors: Qingyao Tian, Bingyu Yang, Huai Liao, Xinyan Huang, Junyong Li, Dong Yi, Hongbin Liu Published: 2026-01-07 Categories: cs.CV arXiv: https://arxiv.org/abs/2601.03713v1 Vision-language models (VLMs) have recently shown remarkable performance in navigation and localization tasks by leveraging large-scale pretraining for semantic understanding. However, applying VLMs to 6-DoF endoscopic camera localization presents several challenges: 1) the lack of large-scale, high-quality, densely annotated, and localization-oriented vision-language datasets in real-world medical settings; 2) limited capability for fine-grained pose regression; and 3) high computational latency when extracting temporal features from past frames. To address these issues, we first construct BREATH dataset, the largest in-vivo endoscopic localization dataset to date, collected in the complex human airway. Building on this dataset, we propose BREATH-VL, a hybrid framework that integrates semantic cues from VLMs with geometric information from vision-based registration methods for accurate 6-DoF pose estimation. Our motivation lies in the complementary strengths of both approaches: VLMs offer generalizable semantic understanding, while registration methods provide precise geometric alignment. To further enhance the VLM's ability to capture temporal context, we introduce a lightweight context-learning mechanism that encodes motion history as linguistic prompts, enabling efficient temporal reasoning without expensive video-level computation. Extensive experiments demonstrate that the vision-language module delivers robust semantic localization in challenging surgical scenes. Building on this, our BREATH-VL outperforms state-of-the-art vision-only localization methods in both accuracy and generalization, reducing translational error by 25.5% compared with the best-performing baseline, while achieving competitive computational latency. --- ### The Power of 10: New Rules for the Digital World Authors: Sarah Spiekermann-Hoff, Marc Langheinrich, Johannes Hoff, Christiane Wendehorst, Jürgen Pfeffer, Thomas Fuchs, Armin Grunwald Published: 2026-01-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.03709v1 As artificial intelligence rapidly advances, society is increasingly captivated by promises of superhuman machines and seamless digital futures. Yet these visions often obscure mounting social, ethical, and psychological concerns tied to pervasive digital technologies - from surveillance to mental health crises. This article argues that a guiding ethos is urgently needed to navigate these transformations. Inspired by the lasting influence of the biblical Ten Commandments, a European interdisciplinary group has proposed "Ten Rules for the Digital World" - a novel ethical framework to help individuals and societies make prudent, human-centered decisions in the age of "supercharged" technology. --- ### MHRC-Bench: A Multilingual Hardware Repository-Level Code Completion benchmark Authors: Qingyun Zou, Jiahao Cui, Nuo Chen, Bingsheng He, Weng-Fai Wong Published: 2026-01-07 Categories: cs.PL, cs.AI arXiv: https://arxiv.org/abs/2601.03708v2 Large language models (LLMs) have achieved strong performance on code completion tasks in general-purpose programming languages. However, existing repository-level code completion benchmarks focus almost exclusively on software code and largely overlook hardware description languages. In this work, we present \textbf{MHRC-Bench}, consisting of \textbf{MHRC-Bench-Train} and \textbf{MHRC-Bench-Eval}, the first benchmark designed for multilingual hardware code completion at the repository level. Our benchmark targets completion tasks and covers three major hardware design coding styles. Each completion target is annotated with code-structure-level and hardware-oriented semantic labels derived from concrete syntax tree analysis. We conduct a comprehensive evaluation of models on MHRC-Bench-Eval. Comprehensive evaluation results and analysis demonstrate the effectiveness of MHRC-Bench. --- ### AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions Authors: Hengxing Cai, Yijie Rao, Ligang Huang, Zanyang Zhong, Jinhan Dong, Jingjun Tan, Changhao Nai, Jue Hou, Wenhao Lu, Renxin Zhong Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03707v2 Existing UAV vision-and-language navigation (VLN) benchmarks rarely provide realistic aerial scenes, natural process-level instructions, and sufficient scale simultaneously, making it difficult to systematically train and evaluate UAV VLN agents under realistic settings. To address this, we propose \textbf{AirNav}, a large-scale benchmark built on real urban aerial data, comprising 137K navigation samples with natural and diverse instructions generated via a human--LLM collaborative pipeline with 10 user personas. We conduct a systematic evaluation of representative approaches on AirNav, ranging from traditional models to multimodal large language models (MLLMs), under unified metrics with open-source implementations. We further propose \textbf{AirVLN-R1}, trained via supervised fine-tuning (SFT) and reinforcement fine-tuning (RFT), achieving state-of-the-art performance with a 51.82\% success rate on the test-unseen split. Real-world experiments on a physical UAV platform provide preliminary evidence of sim-to-real transferability, and our dataset and code are publicly available. --- ### The Geometry of the Pivot: A Note on Lazy Pivoted Cholesky and Farthest Point Sampling Authors: Gil Shabat Published: 2026-01-07 Categories: cs.LG, math.NA arXiv: https://arxiv.org/abs/2601.03706v3 Low-rank approximations of large kernel matrices are ubiquitous in machine learning, particularly for scaling Gaussian Processes to massive datasets. The Pivoted Cholesky decomposition is a standard tool for this task, offering a computationally efficient, greedy low-rank approximation. While its algebraic properties are well-documented in numerical linear algebra, its geometric intuition within the context of kernel methods often remains obscure. In this note, we elucidate the geometric interpretation of the algorithm within the Reproducing Kernel Hilbert Space (RKHS). We demonstrate that the pivotal selection step is mathematically equivalent to Farthest Point Sampling (FPS) using the kernel metric, and that the Cholesky factor construction is an implicit Gram-Schmidt orthogonalization. We provide a concise derivation and a minimalist Python implementation to bridge the gap between theory and practice. --- ### Investigating Knowledge Distillation Through Neural Networks for Protein Binding Affinity Prediction Authors: Wajid Arshad Abbasi, Syed Ali Abbas, Maryum Bibi, Saiqa Andleeb, Muhammad Naveed Akhtar Published: 2026-01-07 Categories: cs.LG, cs.AI, q-bio.BM, q-bio.MN, q-bio.QM arXiv: https://arxiv.org/abs/2601.03704v1 The trade-off between predictive accuracy and data availability makes it difficult to predict protein--protein binding affinity accurately. The lack of experimentally resolved protein structures limits the performance of structure-based machine learning models, which generally outperform sequence-based methods. In order to overcome this constraint, we suggest a regression framework based on knowledge distillation that uses protein structural data during training and only needs sequence data during inference. The suggested method uses binding affinity labels and intermediate feature representations to jointly supervise the training of a sequence-based student network under the guidance of a structure-informed teacher network. Leave-One-Complex-Out (LOCO) cross-validation was used to assess the framework on a non-redundant protein--protein binding affinity benchmark dataset. A maximum Pearson correlation coefficient (P_r) of 0.375 and an RMSE of 2.712 kcal/mol were obtained by sequence-only baseline models, whereas a P_r of 0.512 and an RMSE of 2.445 kcal/mol were obtained by structure-based models. With a P_r of 0.481 and an RMSE of 2.488 kcal/mol, the distillation-based student model greatly enhanced sequence-only performance. Improved agreement and decreased bias were further confirmed by thorough error analyses. With the potential to close the performance gap between sequence-based and structure-based models as larger datasets become available, these findings show that knowledge distillation is an efficient method for transferring structural knowledge to sequence-based predictors. The source code for running inference with the proposed distillation-based binding affinity predictor can be accessed at https://github.com/wajidarshad/ProteinAffinityKD. --- ### TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL Authors: Lang Cao, Hui Ruan, Yongqian Li, Peng Chao, Wu Ning, Haonan Song, Renhong Chen, Yitong Li Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.03703v2 Reinforcement learning with group-based objectives, such as Group Relative Policy Optimization (GRPO), is a common framework for aligning large language models on complex reasoning tasks. However, standard GRPO treats each rollout trajectory as an independent flat sequence and assigns a single sequence-level advantage to all tokens, which leads to sample inefficiency and a length bias toward verbose, redundant chains of thought without improving logical depth. We introduce TreeAdv (Tree-Structured Advantage Redistribution for Group-Based RL), which makes the tree structure of group rollouts explicit for both exploration and advantage assignment. Specifically, TreeAdv builds a group of trees (a forest) based on an entropy-driven sampling method where each tree branches at high-uncertainty decisions while sharing low-uncertainty tokens across rollouts. Then, TreeAdv aggregates token-level advantages for internal tree segments by redistributing the advantages of complete rollouts (all leaf nodes), and TreeAdv can easily apply to group-based objectives such as GRPO or GSPO. Across 10 math reasoning benchmarks, TreeAdv consistently outperforms GRPO and GSPO, while using substantially fewer generated tokens under identical supervision, data, and decoding budgets. --- ### Inference Attacks Against Graph Generative Diffusion Models Authors: Xiuling Wang, Xin Huang, Guibo Luo, Jianliang Xu Published: 2026-01-07 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2601.03701v1 Graph generative diffusion models have recently emerged as a powerful paradigm for generating complex graph structures, effectively capturing intricate dependencies and relationships within graph data. However, the privacy risks associated with these models remain largely unexplored. In this paper, we investigate information leakage in such models through three types of black-box inference attacks. First, we design a graph reconstruction attack, which can reconstruct graphs structurally similar to those training graphs from the generated graphs. Second, we propose a property inference attack to infer the properties of the training graphs, such as the average graph density and the distribution of densities, from the generated graphs. Third, we develop two membership inference attacks to determine whether a given graph is present in the training set. Extensive experiments on three different types of graph generative diffusion models and six real-world graphs demonstrate the effectiveness of these attacks, significantly outperforming the baseline approaches. Finally, we propose two defense mechanisms that mitigate these inference attacks and achieve a better trade-off between defense strength and target model utility than existing methods. Our code is available at https://zenodo.org/records/17946102. --- ### ADEPT: Adaptive Dynamic Early-Exit Process for Transformers Authors: Sangmin Yoo, Srikanth Malla, Chiho Choi, Wei D. Lu, Joon Hee Choi Published: 2026-01-07 Categories: cs.CL, cs.AI arXiv: https://arxiv.org/abs/2601.03700v1 The inference of large language models imposes significant computational workloads, often requiring the processing of billions of parameters. Although early-exit strategies have proven effective in reducing computational demands by halting inference earlier, they apply either to only the first token in the generation phase or at the prompt level in the prefill phase. Thus, the Key-Value (KV) cache for skipped layers remains a bottleneck for subsequent token generation, limiting the benefits of early exit. We introduce ADEPT (Adaptive Dynamic Early-exit Process for Transformers), a novel approach designed to overcome this issue and enable dynamic early exit in both the prefill and generation phases. The proposed adaptive token-level early-exit mechanism adjusts computation dynamically based on token complexity, optimizing efficiency without compromising performance. ADEPT further enhances KV generation procedure by decoupling sequential dependencies in skipped layers, making token-level early exit more practical. Experimental results demonstrate that ADEPT improves efficiency by up to 25% in language generation tasks and achieves a 4x speed-up in downstream classification tasks, with up to a 45% improvement in performance. --- ### RedBench: A Universal Dataset for Comprehensive Red Teaming of Large Language Models Authors: Quy-Anh Dang, Chris Ngo, Truong-Son Hy Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03699v2 As large language models (LLMs) become integral to safety-critical applications, ensuring their robustness against adversarial prompts is paramount. However, existing red teaming datasets suffer from inconsistent risk categorizations, limited domain coverage, and outdated evaluations, hindering systematic vulnerability assessments. To address these challenges, we introduce RedBench, a universal dataset aggregating 37 benchmark datasets from leading conferences and repositories, comprising 29,362 samples across attack and refusal prompts. RedBench employs a standardized taxonomy with 22 risk categories and 19 domains, enabling consistent and comprehensive evaluations of LLM vulnerabilities. We provide a detailed analysis of existing datasets, establish baselines for modern LLMs, and open-source the dataset and evaluation code. Our contributions facilitate robust comparisons, foster future research, and promote the development of secure and reliable LLMs for real-world deployment. Code: https://github.com/knoveleng/redeval --- ### Evaluation Framework for AI Creativity: A Case Study Based on Story Generation Authors: Pharath Sathya, Yin Jou Huang, Fei Cheng Published: 2026-01-07 Categories: cs.CL arXiv: https://arxiv.org/abs/2601.03698v1 Evaluating creative text generation remains a challenge because existing reference-based metrics fail to capture the subjective nature of creativity. We propose a structured evaluation framework for AI story generation comprising four components (Novelty, Value, Adherence, and Resonance) and eleven sub-components. Using controlled story generation via ``Spike Prompting'' and a crowdsourced study of 115 readers, we examine how different creative components shape both immediate and reflective human creativity judgments. Our findings show that creativity is evaluated hierarchically rather than cumulatively, with different dimensions becoming salient at different stages of judgment, and that reflective evaluation substantially alters both ratings and inter-rater agreement. Together, these results support the effectiveness of our framework in revealing dimensions of creativity that are obscured by reference-based evaluation. --- ### Can AI Chatbots Provide Coaching in Engineering? Beyond Information Processing Toward Mastery Authors: Junaid Qadir, Muhammad Adil Attique, Saleha Shoaib, Syed Ibrahim Ghaznavi Published: 2026-01-07 Categories: cs.CY, cs.AI arXiv: https://arxiv.org/abs/2601.03693v1 Engineering education faces a double disruption: traditional apprenticeship models that cultivated judgment and tacit skill are eroding, just as generative AI emerges as an informal coaching partner. This convergence rekindles long-standing questions in the philosophy of AI and cognition about the limits of computation, the nature of embodied rationality, and the distinction between information processing and wisdom. Building on this rich intellectual tradition, this paper examines whether AI chatbots can provide coaching that fosters mastery rather than merely delivering information. We synthesize critical perspectives from decades of scholarship on expertise, tacit knowledge, and human-machine interaction, situating them within the context of contemporary AI-driven education. Empirically, we report findings from a mixed-methods study (N = 75 students, N = 7 faculty) exploring the use of a coaching chatbot in engineering education. Results reveal a consistent boundary: participants accept AI for technical problem solving (convergent tasks; M = 3.84 on a 1-5 Likert scale) but remain skeptical of its capacity for moral, emotional, and contextual judgment (divergent tasks). Faculty express stronger concerns over risk (M = 4.71 vs. M = 4.14, p = 0.003), and privacy emerges as a key requirement, with 64-71 percent of participants demanding strict confidentiality. Our findings suggest that while generative AI can democratize access to cognitive and procedural support, it cannot replicate the embodied, value-laden dimensions of human mentorship. We propose a multiplex coaching framework that integrates human wisdom within expert-in-the-loop models, preserving the depth of apprenticeship while leveraging AI scalability to enrich the next generation of engineering education. --- ### A Pre-trained Reaction Embedding Descriptor Capturing Bond Transformation Patterns Authors: Weiqi Liu, Fenglei Cao, Yuan Qi, Li-Cheng Xu Published: 2026-01-07 Categories: cs.LG, cs.AI, physics.chem-ph arXiv: https://arxiv.org/abs/2601.03689v1 With the rise of data-driven reaction prediction models, effective reaction descriptors are crucial for bridging the gap between real-world chemistry and digital representations. However, general-purpose, reaction-wise descriptors remain scarce. This study introduces RXNEmb, a novel reaction-level descriptor derived from RXNGraphormer, a model pre-trained to distinguish real reactions from fictitious ones with erroneous bond changes, thereby learning intrinsic bond formation and cleavage patterns. We demonstrate its utility by data-driven re-clustering of the USPTO-50k dataset, yielding a classification that more directly reflects bond-change similarities than rule-based categories. Combined with dimensionality reduction, RXNEmb enables visualization of reaction space diversity. Furthermore, attention weight analysis reveals the model's focus on chemically critical sites, providing mechanistic insight. RXNEmb serves as a powerful, interpretable tool for reaction fingerprinting and analysis, paving the way for more data-centric approaches in reaction analysis and discovery. --- ### Personalized Medication Planning via Direct Domain Modeling and LLM-Generated Heuristics Authors: Yonatan Vernik, Alexander Tuisov, David Izhaki, Hana Weitman, Gal A. Kaminka, Alexander Shleyfman Published: 2026-01-07 Categories: cs.AI arXiv: https://arxiv.org/abs/2601.03687v1 Personalized medication planning involves selecting medications and determining a dosing schedule to achieve medical goals specific to each individual patient. Previous work successfully demonstrated that automated planners, using general domain-independent heuristics, are able to generate personalized treatments, when the domain and problems are modeled using a general domain description language (\pddlp). Unfortunately, this process was limited in practice to consider no more than seven medications. In clinical terms, this is a non-starter. In this paper, we explore the use of automatically-generated domain- and problem-specific heuristics to be used with general search, as a method of scaling up medication planning to levels allowing closer work with clinicians. Specifically, we specify the domain programmatically (specifying an initial state and a successor generation procedure), and use an LLM to generate a problem specific heuristic that can be used by a fixed search algorithm (GBFS). The results indicate dramatic improvements in coverage and planning time, scaling up the number of medications to at least 28, and bringing medication planning one step closer to practical applications. --- ### Rethinking Recurrent Neural Networks for Time Series Forecasting: A Reinforced Recurrent Encoder with Prediction-Oriented Proximal Policy Optimization Authors: Xin Lai, Shiming Deng, Lu Yu, Yumin Lai, Shenghao Qiao, Xinze Zhang Published: 2026-01-07 Categories: cs.LG, cs.NE arXiv: https://arxiv.org/abs/2601.03683v2 Time series forecasting plays a crucial role in contemporary engineering information systems for supporting decision-making across various industries, where Recurrent Neural Networks (RNNs) have been widely adopted due to their capability in modeling sequential data. Conventional RNN-based predictors adopt an encoder-only strategy with sliding historical windows as inputs to forecast future values. However, this approach treats all time steps and hidden states equally without considering their distinct contributions to forecasting, leading to suboptimal performance. To address this limitation, we propose a novel Reinforced Recurrent Encoder with Prediction-oriented Proximal Policy Optimization, RRE-PPO4Pred, which significantly improves time series modeling capacity and forecasting accuracy of the RNN models. The core innovations of this method are: (1) A novel Reinforced Recurrent Encoder (RRE) framework that enhances RNNs by formulating their internal adaptation as a Markov Decision Process, creating a unified decision environment capable of learning input feature selection, hidden skip connection, and output target selection; (2) An improved Prediction-oriented Proximal Policy Optimization algorithm, termed PPO4Pred, which is equipped with a Transformer-based agent for temporal reasoning and develops a dynamic transition sampling strategy to enhance sampling efficiency; (3) A co-evolutionary optimization paradigm to facilitate the learning of the RNN predictor and the policy agent, providing adaptive and interactive time series modeling. Comprehensive evaluations on five real-world datasets indicate that our method consistently outperforms existing baselines, and attains accuracy better than state-of-the-art Transformer models, thus providing an advanced time series predictor in engineering informatics. ---