# Research Papers — 2026-01 · bundle page 110 of 189

> Full-text markdown of papers #5451–5500 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/110
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/109.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/111.md)

### Difficulty-guided Sampling: Bridging the Target Gap between Dataset Distillation and Downstream Tasks

Authors: Mingzhuo Li, Guang Li, Linfeng Ye, Jiafeng Mao, Takahiro Ogawa, Konstantinos N. Plataniotis, Miki Haseyama
Published: 2026-01-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.10090v1

In this paper, we propose difficulty-guided sampling (DGS) to bridge the target gap between the distillation objective and the downstream task, therefore improving the performance of dataset distillation. Deep neural networks achieve remarkable performance but have time and storage-consuming training processes. Dataset distillation is proposed to generate compact, high-quality distilled datasets, enabling effective model training while maintaining downstream performance. Existing approaches typically focus on features extracted from the original dataset, overlooking task-specific information, which leads to a target gap between the distillation objective and the downstream task. We propose leveraging characteristics that benefit the downstream training into data distillation to bridge this gap. Focusing on the downstream task of image classification, we introduce the concept of difficulty and propose DGS as a plug-in post-stage sampling module. Following the specific target difficulty distribution, the final distilled dataset is sampled from image pools generated by existing methods. We also propose difficulty-aware guidance (DAG) to explore the effect of difficulty in the generation process. Extensive experiments across multiple settings demonstrate the effectiveness of the proposed methods. It also highlights the broader potential of difficulty for diverse downstream tasks.

---

### Bayesian Meta-Analyses Could Be More: A Case Study in Trial of Labor After a Cesarean-section Outcomes and Complications

Authors: Ashley Klein, Edward Raff, Marcia DesJardin
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10089v1

The meta-analysis's utility is dependent on previous studies having accurately captured the variables of interest, but in medical studies, a key decision variable that impacts a physician's decisions was not captured. This results in an unknown effect size and unreliable conclusions. A Bayesian approach may allow analysis to determine if the claim of a positive effect is still warranted, and we build a Bayesian approach to this common medical scenario. To demonstrate its utility, we assist professional OBGYNs in evaluating Trial of Labor After a Cesarean-section (TOLAC) situations where few interventions are available for patients and find the support needed for physicians to advance patient care.

---

### State of AI: An Empirical 100 Trillion Token Study with OpenRouter

Authors: Malika Aubakirova, Alex Atallah, Chris Clark, Justin Summerville, Anjney Midha
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10088v1

The past year has marked a turning point in the evolution and real-world use of large language models (LLMs). With the release of the first widely adopted reasoning model, o1, on December 5th, 2024, the field shifted from single-pass pattern generation to multi-step deliberation inference, accelerating deployment, experimentation, and new classes of applications. As this shift unfolded at a rapid pace, our empirical understanding of how these models have actually been used in practice has lagged behind. In this work, we leverage the OpenRouter platform, which is an AI inference provider across a wide variety of LLMs, to analyze over 100 trillion tokens of real-world LLM interactions across tasks, geographies, and time. In our empirical study, we observe substantial adoption of open-weight models, the outsized popularity of creative roleplay (beyond just the productivity tasks many assume dominate) and coding assistance categories, plus the rise of agentic inference. Furthermore, our retention analysis identifies foundational cohorts: early users whose engagement persists far longer than later cohorts. We term this phenomenon the Cinderella "Glass Slipper" effect. These findings underscore that the way developers and end-users engage with LLMs "in the wild" is complex and multifaceted. We discuss implications for model builders, AI developers, and infrastructure providers, and outline how a data-driven understanding of usage can inform better design and deployment of LLM systems.

---

### CALM-IT: Generating Realistic Long-Form Motivational Interviewing Dialogues with Dual-Actor Conversational Dynamics Tracking

Authors: Viet Cuong Nguyen, Nhi Yen Nguyen, Kristin A. Candan, Mary Conlon, Vanessa Rumie, Kristen Risola, Michael L. Birnbaum, Munmun De Choudhury
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10085v2

Therapeutic dialogue is not a sequence of isolated responses: client goals, motivation, resistance, and therapeutic alliance evolve over time. Yet current LLM-based mental health dialogue systems often lack explicit mechanisms for tracking these dynamics across extended interactions, which can lead to poorly timed interventions or premature goal resolution. We introduce CALM-IT, a framework for generating and evaluating long-form Motivational Interviewing dialogues through explicit modeling of evolving client and counselor states, guiding both counseling strategy selection and utterance generation. We evaluate CALM-IT on a large-scale corpus of 8,232 synthetic dialogues spanning multiple dialogue lengths and frameworks. Compared with all baselines, CALM-IT achieves the best performance on most MITI 4.2 global ratings, including Empathy, Partnership, and Softening Sustain Talk, as well as on other key performance metrics while exhibiting minimal performance degradation as dialogue length increases. Notably, although CALM-IT initiates fewer change-directed prompts, it produces the highest client acceptance rate (64.3%) on average across different length conditions. We release a reproducible generation framework, a MITI-grounded process-level evaluation protocol, and a large-scale synthetic corpus for studying therapeutic LLMs under realistic long-form interaction conditions.

---

### Adaptive Label Error Detection: A Bayesian Approach to Mislabeled Data Detection

Authors: Zan Chaudhry, Noam H. Rotenberg, Brian Caffo, Craig K. Jones, Haris I. Sair
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10084v1

Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is increasingly imperative to identify and correct mislabeling to develop more powerful models. In this work, we motivate and describe Adaptive Label Error Detection (ALED), a novel method of detecting mislabeling. ALED extracts an intermediate feature space from a deep convolutional neural network, denoises the features, models the reduced manifold of each class with a multidimensional Gaussian distribution, and performs a simple likelihood ratio test to identify mislabeled samples. We show that ALED has markedly increased sensitivity, without compromising precision, compared to established label error detection methods, on multiple medical imaging datasets. We demonstrate an example where fine-tuning a neural network on corrected data results in a 33.8% decrease in test set errors, providing strong benefits to end users. The ALED detector is deployed in the Python package statlab.

---

### Is MT Ready for the Next Crisis or Pandemic?

Authors: Vipasha Bansal, Elizabeth Brown, Chelsea Kendrick, Benjamin Pong, William D. Lewis
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10082v1

Communication in times of crisis is essential. However, there is often a mismatch between the language of governments, aid providers, doctors, and those to whom they are providing aid. Commercial MT systems are reasonable tools to turn to in these scenarios. But how effective are these tools for translating to and from low resource languages, particularly in the crisis or medical domain? In this study, we evaluate four commercial MT systems using the TICO-19 dataset, which is composed of pandemic-related sentences from a large set of high priority languages spoken by communities most likely to be affected adversely in the next pandemic. We then assess the current degree of ``readiness'' for another pandemic (or epidemic) based on the usability of the output translations.

---

### Deriving Character Logic from Storyline as Codified Decision Trees

Authors: Letian Peng, Kun Zhou, Longfei Yun, Yupeng Hou, Jingbo Shang
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10080v1

Role-playing (RP) agents rely on behavioral profiles to act consistently across diverse narrative contexts, yet existing profiles are largely unstructured, non-executable, and weakly validated, leading to brittle agent behavior. We propose Codified Decision Trees (CDT), a data-driven framework that induces an executable and interpretable decision structure from large-scale narrative data. CDT represents behavioral profiles as a tree of conditional rules, where internal nodes correspond to validated scene conditions and leaves encode grounded behavioral statements, enabling deterministic retrieval of context-appropriate rules at execution time. The tree is learned by iteratively inducing candidate scene-action rules, validating them against data, and refining them through hierarchical specialization, yielding profiles that support transparent inspection and principled updates. Across multiple benchmarks, CDT substantially outperforms human-written profiles and prior profile induction methods on $85$ characters across $16$ artifacts, indicating that codified and validated behavioral representations lead to more reliable agent grounding.

---

### Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts

Authors: Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang, Ke Wang, Jinbo Su, Mengshu Sun, Lei Liang, Jing Zhang
Published: 2026-01-15
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.10079v2

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon rollouts acts as a critical bottleneck, often prohibiting efficient training on limited hardware. While existing KV compression techniques offer a remedy for inference, directly applying them to RL training induces a severe policy mismatch, leading to catastrophic performance collapse. To address this, we introduce Sparse-RL empowers stable RL training under sparse rollouts. We show that instability arises from a fundamental policy mismatch among the dense old policy, the sparse sampler policy, and the learner policy. To mitigate this issue, Sparse-RL incorporates Sparsity-Aware Rejection Sampling and Importance-based Reweighting to correct the off-policy bias introduced by compression-induced information loss. Experimental results show that Sparse-RL reduces rollout overhead compared to dense baselines while preserving the performance. Furthermore, Sparse-RL inherently implements sparsity-aware training, significantly enhancing model robustness during sparse inference deployment. The corresponding training data and code are publicly available on the repository.

---

### Thinking Like Van Gogh: Structure-Aware Style Transfer via Flow-Guided 3D Gaussian Splatting

Authors: Lebin Zhou, Jingchuan Xiao, Zhendong Wang, Jinhao Wang, Rongduo Han, Nam Ling, Cihan Ruan
Published: 2026-01-15
Categories: cs.CV, cs.GR, cs.LG
arXiv: https://arxiv.org/abs/2601.10075v2

In 1888, Vincent van Gogh wrote, "I am seeking exaggeration in the essential." This principle, amplifying structural form while suppressing photographic detail, lies at the core of Post-Impressionist art. However, most existing 3D style transfer methods invert this philosophy, treating geometry as a rigid substrate for surface-level texture projection. To authentically reproduce Post-Impressionist stylization, geometric abstraction must be embraced as the primary vehicle of expression. We propose a flow-guided geometric advection framework for 3D Gaussian Splatting (3DGS) that operationalizes this principle in a mesh-free setting. Our method extracts directional flow fields from 2D paintings and back-propagates them into 3D space, rectifying Gaussian primitives to form flow-aligned brushstrokes that conform to scene topology without relying on explicit mesh priors. This enables expressive structural deformation driven directly by painterly motion rather than photometric constraints. Our contributions are threefold: (1) a projection-based, mesh-free flow guidance mechanism that transfers 2D artistic motion into 3D Gaussian geometry; (2) a luminance-structure decoupling strategy that isolates geometric deformation from color optimization, mitigating artifacts during aggressive structural abstraction; and (3) a VLM-as-a-Judge evaluation framework that assesses artistic authenticity through aesthetic judgment instead of conventional pixel-level metrics, explicitly addressing the subjective nature of artistic stylization.

---

### ReaMIL: Reasoning- and Evidence-Aware Multiple Instance Learning for Whole-Slide Histopathology

Authors: Hyun Do Jung, Jungwon Choi, Hwiyoung Kim
Published: 2026-01-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.10073v2

We introduce ReaMIL (Reasoning- and Evidence-Aware MIL), a multiple instance learning approach for whole-slide histopathology that adds a light selection head to a strong MIL backbone. The head produces soft per-tile gates and is trained with a budgeted-sufficiency objective: a hinge loss that enforces the true-class probability to be $\geq τ$ using only the kept evidence, under a sparsity budget on the number of selected tiles. The budgeted-sufficiency objective yields small, spatially compact evidence sets without sacrificing baseline performance. Across TCGA-NSCLC (LUAD vs. LUSC), TCGA-BRCA (IDC vs. Others), and PANDA, ReaMIL matches or slightly improves baseline AUC and provides quantitative evidence-efficiency diagnostics. On NSCLC, it attains AUC 0.983 with a mean minimal sufficient K (MSK) $\approx 8.2$ tiles at $τ= 0.90$ and AUKC $\approx 0.864$, showing that class confidence rises sharply and stabilizes once a small set of tiles is kept. The method requires no extra supervision, integrates seamlessly with standard MIL training, and naturally yields slide-level overlays. We report accuracy alongside MSK, AUKC, and contiguity for rigorous evaluation of model behavior on WSIs.

---

### Comparative Evaluation of Deep Learning-Based and WHO-Informed Approaches for Sperm Morphology Assessment

Authors: Mohammad Abbadi
Published: 2026-01-15
Categories: cs.LG, cs.CV, eess.IV, q-bio.QM
arXiv: https://arxiv.org/abs/2601.10070v1

Assessment of sperm morphological quality remains a critical yet subjective component of male fertility evaluation, often limited by inter-observer variability and resource constraints. This study presents a comparative biomedical artificial intelligence framework evaluating an image-based deep learning model (HuSHeM) alongside a clinically grounded baseline derived from World Health Organization criteria augmented with the Systemic Inflammation Response Index (WHO(+SIRI)). The HuSHeM model was trained on high-resolution sperm morphology images and evaluated using an independent clinical cohort. Model performance was assessed using discrimination, calibration, and clinical utility analyses. The HuSHeM model demonstrated higher discriminative performance, as reflected by an increased area under the receiver operating characteristic curve with relatively narrow confidence intervals compared to WHO(+SIRI). Precision-recall analysis further indicated improved performance under class imbalance, with higher precision-recall area values across evaluated thresholds. Calibration analysis indicated closer agreement between predicted probabilities and observed outcomes for HuSHeM, while decision curve analysis suggested greater net clinical benefit across clinically relevant threshold probabilities. These findings suggest that image-based deep learning may offer improved predictive reliability and clinical utility compared with traditional rule-based and inflammation-augmented criteria. The proposed framework supports objective and reproducible assessment of sperm morphology and may serve as a decision-support tool within fertility screening and referral workflows. The proposed models are intended as decision-support or referral tools and are not designed to replace clinical judgment or laboratory assessment.

---

### Efficient Content-based Recommendation Model Training via Noise-aware Coreset Selection

Authors: Hung Vinh Tran, Tong Chen, Hechuan Wen, Quoc Viet Hung Nguyen, Bin Cui, Hongzhi Yin
Published: 2026-01-15
Categories: cs.LG, cs.IR
arXiv: https://arxiv.org/abs/2601.10067v1

Content-based recommendation systems (CRSs) utilize content features to predict user-item interactions, serving as essential tools for helping users navigate information-rich web services. However, ensuring the effectiveness of CRSs requires large-scale and even continuous model training to accommodate diverse user preferences, resulting in significant computational costs and resource demands. A promising approach to this challenge is coreset selection, which identifies a small but representative subset of data samples that preserves model quality while reducing training overhead. Yet, the selected coreset is vulnerable to the pervasive noise in user-item interactions, particularly when it is minimally sized. To this end, we propose Noise-aware Coreset Selection (NaCS), a specialized framework for CRSs. NaCS constructs coresets through submodular optimization based on training gradients, while simultaneously correcting noisy labels using a progressively trained model. Meanwhile, we refine the selected coreset by filtering out low-confidence samples through uncertainty quantification, thereby avoid training with unreliable interactions. Through extensive experiments, we show that NaCS produces higher-quality coresets for CRSs while achieving better efficiency than existing coreset selection techniques. Notably, NaCS recovers 93-95\% of full-dataset training performance using merely 1\% of the training data. The source code is available at \href{https://github.com/chenxing1999/nacs}{https://github.com/chenxing1999/nacs}.

---

### Long-Chain Reasoning Distillation via Adaptive Prefix Alignment

Authors: Zhenghao Liu, Zhuoyang Wu, Xinze Li, Yukun Yan, Shuo Wang, Zulong Chen, Yu Gu, Ge Yu, Maosong Sun
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10064v1

Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities, particularly in solving complex mathematical problems. Recent studies show that distilling long reasoning trajectories can effectively enhance the reasoning performance of small-scale student models. However, teacher-generated reasoning trajectories are often excessively long and structurally complex, making them difficult for student models to learn. This mismatch leads to a gap between the provided supervision signal and the learning capacity of the student model. To address this challenge, we propose Prefix-ALIGNment distillation (P-ALIGN), a framework that fully exploits teacher CoTs for distillation through adaptive prefix alignment. Specifically, P-ALIGN adaptively truncates teacher-generated reasoning trajectories by determining whether the remaining suffix is concise and sufficient to guide the student model. Then, P-ALIGN leverages the teacher-generated prefix to supervise the student model, encouraging effective prefix alignment. Experiments on multiple mathematical reasoning benchmarks demonstrate that P-ALIGN outperforms all baselines by over 3%. Further analysis indicates that the prefixes constructed by P-ALIGN provide more effective supervision signals, while avoiding the negative impact of redundant and uncertain reasoning components. All code is available at https://github.com/NEUIR/P-ALIGN.

---

### CoF-T2I: Video Models as Pure Visual Reasoners for Text-to-Image Generation

Authors: Chengzhuo Tong, Mingkun Chang, Shenglong Zhang, Yuran Wang, Cheng Liang, Zhizheng Zhao, Ruichuan An, Bohan Zeng, Yang Shi, Yifan Dai, Ziming Zhao, Guanbin Li et al.
Published: 2026-01-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.10061v1

Recent video generation models have revealed the emergence of Chain-of-Frame (CoF) reasoning, enabling frame-by-frame visual inference. With this capability, video models have been successfully applied to various visual tasks (e.g., maze solving, visual puzzles). However, their potential to enhance text-to-image (T2I) generation remains largely unexplored due to the absence of a clearly defined visual reasoning starting point and interpretable intermediate states in the T2I generation process. To bridge this gap, we propose CoF-T2I, a model that integrates CoF reasoning into T2I generation via progressive visual refinement, where intermediate frames act as explicit reasoning steps and the final frame is taken as output. To establish such an explicit generation process, we curate CoF-Evol-Instruct, a dataset of CoF trajectories that model the generation process from semantics to aesthetics. To further improve quality and avoid motion artifacts, we enable independent encoding operation for each frame. Experiments show that CoF-T2I significantly outperforms the base video model and achieves competitive performance on challenging benchmarks, reaching 0.86 on GenEval and 7.468 on Imagine-Bench. These results indicate the substantial promise of video models for advancing high-quality text-to-image generation.

---

### Unlabeled Data Can Provably Enhance In-Context Learning of Transformers

Authors: Renpu Liu, Jing Yang
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10058v1

Large language models (LLMs) exhibit impressive in-context learning (ICL) capabilities, yet the quality of their predictions is fundamentally limited by the few costly labeled demonstrations that can fit into a prompt. Meanwhile, there exist vast and continuously growing amounts of unlabeled data that may be closely related to the ICL task. How to utilize such unlabeled data to provably enhance the performance of ICL thus becomes an emerging fundamental question. In this work, we propose a novel augmented ICL framework, in which the prompt includes a small set of labeled examples alongside a block of unlabeled inputs. We focus on the multi-class linear classification setting and demonstrate that, with chain-of-thought (CoT) prompting, a multi-layer transformer can effectively emulate an expectation-maximization (EM) algorithm. This enables the transformer to implicitly extract useful information from both labeled and unlabeled data, leading to provable improvements in ICL accuracy. Moreover, we show that such a transformer can be trained via teacher forcing, with its parameters converging to the desired solution at a linear rate. Experiments demonstrate that the augmented ICL framework consistently outperforms conventional few-shot ICL, providing empirical support for our theoretical findings. To the best of our knowledge, this is the first theoretical study on the impact of unlabeled data on the ICL performance of transformers.

---

### UEOF: A Benchmark Dataset for Underwater Event-Based Optical Flow

Authors: Nick Truong, Pritam P. Karmokar, William J. Beksi
Published: 2026-01-15
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2601.10054v1

Underwater imaging is fundamentally challenging due to wavelength-dependent light attenuation, strong scattering from suspended particles, turbidity-induced blur, and non-uniform illumination. These effects impair standard cameras and make ground-truth motion nearly impossible to obtain. On the other hand, event cameras offer microsecond resolution and high dynamic range. Nonetheless, progress on investigating event cameras for underwater environments has been limited due to the lack of datasets that pair realistic underwater optics with accurate optical flow. To address this problem, we introduce the first synthetic underwater benchmark dataset for event-based optical flow derived from physically-based ray-traced RGBD sequences. Using a modern video-to-event pipeline applied to rendered underwater videos, we produce realistic event data streams with dense ground-truth flow, depth, and camera motion. Moreover, we benchmark state-of-the-art learning-based and model-based optical flow prediction methods to understand how underwater light transport affects event formation and motion estimation accuracy. Our dataset establishes a new baseline for future development and evaluation of underwater event-based perception algorithms. The source code and dataset for this project are publicly available at https://robotic-vision-lab.github.io/ueof.

---

### DiCo: Disentangled Concept Representation for Text-to-image Person Re-identification

Authors: Giyeol Kim, Chanho Eom
Published: 2026-01-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.10053v2

Text-to-image person re-identification (TIReID) aims to retrieve person images from a large gallery given free-form textual descriptions. TIReID is challenging due to the substantial modality gap between visual appearances and textual expressions, as well as the need to model fine-grained correspondences that distinguish individuals with similar attributes such as clothing color, texture, or outfit style. To address these issues, we propose DiCo (Disentangled Concept Representation), a novel framework that achieves hierarchical and disentangled cross-modal alignment. DiCo introduces a shared slot-based representation, where each slot acts as a part-level anchor across modalities and is further decomposed into multiple concept blocks. This design enables the disentanglement of complementary attributes (\textit{e.g.}, color, texture, shape) while maintaining consistent part-level correspondence between image and text. Extensive experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate that our framework achieves competitive performance with state-of-the-art methods, while also enhancing interpretability through explicit slot- and block-level representations for more fine-grained retrieval results.

---

### Instruction Finetuning LLaMA-3-8B Model Using LoRA for Financial Named Entity Recognition

Authors: Zhiming Lian
Published: 2026-01-15
Categories: q-fin.CP, cs.LG
arXiv: https://arxiv.org/abs/2601.10043v1

Particularly, financial named-entity recognition (NER) is one of the many important approaches to translate unformatted reports and news into structured knowledge graphs. However, free, easy-to-use large language models (LLMs) often fail to differentiate organisations as people, or disregard an actual monetary amount entirely. This paper takes Meta's Llama 3 8B and applies it to financial NER by combining instruction fine-tuning and Low-Rank Adaptation (LoRA). Each annotated sentence is converted into an instruction-input-output triple, enabling the model to learn task descriptions while fine-tuning with small low-rank matrices instead of updating all weights. Using a corpus of 1,693 sentences, our method obtains a micro-F1 score of 0.894 compared with Qwen3-8B, Baichuan2-7B, T5, and BERT-Base. We present dataset statistics, describe training hyperparameters, and perform visualizations of entity density, learning curves, and evaluation metrics. Our results show that instruction tuning combined with parameter-efficient fine-tuning enables state-of-the-art performance on domain-sensitive NER.

---

### What Understanding Means in AI-Laden Astronomy

Authors: Yuan-Sen Ting, André Curtis-Trudel, Siyu Yao
Published: 2026-01-15
Categories: astro-ph.IM, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.10038v2

Artificial intelligence is rapidly transforming astronomical research, yet the scientific community has largely treated this transformation as an engineering challenge rather than an epistemological one. This perspective article argues that philosophy of science offers essential tools for navigating AI's integration into astronomy--conceptual clarity about what "understanding" means, critical examination of assumptions about data and discovery, and frameworks for evaluating AI's roles across different research contexts. Drawing on an interdisciplinary workshop convening astronomers, philosophers, and computer scientists, we identify several tensions. First, the narrative that AI will "derive fundamental physics" from data misconstrues contemporary astronomy as equation-derivation rather than the observation-driven enterprise it is. Second, scientific understanding involves more than prediction--it requires narrative construction, contextual judgment, and communicative achievement that current AI architectures struggle to provide. Third, because narrative and judgment matter, human peer review remains essential--yet AI-generated content flooding the literature threatens our capacity to identify genuine insight. Fourth, while AI excels at well-defined problem-solving, the ill-defined problem-finding that drives breakthroughs appears to require capacities beyond pattern recognition. Fifth, as AI accelerates what is feasible, pursuitworthiness criteria risk shifting toward what AI makes easy rather than what is genuinely important. We propose "pragmatic understanding" as a framework for integration--recognizing AI as a tool that extends human cognition while requiring new norms for validation and epistemic evaluation. Engaging with these questions now may help the community shape the transformation rather than merely react to it.

---

### A Compute and Communication Runtime Model for Loihi 2

Authors: Jonathan Timcheck, Alessandro Pierro, Sumit Bam Shrestha
Published: 2026-01-15
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.10035v2

Neuromorphic computers hold the potential to vastly improve the speed and efficiency of a wide range of computational kernels with their asynchronous, compute-memory co-located, spatially distributed, and scalable nature. However, performance models that are simple yet sufficiently expressive to predict runtime on actual neuromorphic hardware are lacking, posing a challenge for researchers and developers who strive to design fast algorithms and kernels. As breaking the memory bandwidth wall of conventional von-Neumann architectures is a primary neuromorphic advantage, modeling communication time is especially important. At the same time, modeling communication time is difficult, as complex congestion patterns arise in a heavily-loaded Network-on-Chip. In this work, we introduce the first max-affine lower-bound runtime model -- a multi-dimensional roofline model -- for Intel's Loihi 2 neuromorphic chip that quantitatively accounts for both compute and communication based on a suite of microbenchmarks. Despite being a lower-bound model, we observe a tight correspondence (Pearson correlation coefficient greater than or equal to 0.97) between our model's estimated runtime and the measured runtime on Loihi 2 for a neural network linear layer, i.e., matrix-vector multiplication, and for an example application, a Quadratic Unconstrained Binary Optimization solver. Furthermore, we derive analytical expressions for communication-bottlenecked runtime to study scalability of the linear layer, revealing an area-runtime tradeoff for different spatial workload configurations with linear to superlinear runtime scaling in layer size with a variety of constant factors. Our max-affine runtime model helps empower the design of high-speed algorithms and kernels for Loihi 2.

---

### Minimal Decision Dynamics and Contextual Probability: A Quantum Tug-of-War Model

Authors: Song-Ju Kim
Published: 2026-01-15
Categories: quant-ph, cs.AI, q-bio.NC
arXiv: https://arxiv.org/abs/2601.10034v3

Decision making often exhibits context dependence that is difficult to accommodate within a single non-invasive classical probability model. This paper develops a quantum-like extension of the Tug-of-War (QTOW) decision-making model to ask when such context dependence can be represented by a single constrained internal state. The QTOW construction uses a qutrit state, a state- disturbing generalized decision instrument, decision- and reward-conditioned norm-preserving feedback, and optional probing operations within one state space. The qutrit representation admits KCBS-type probe families and states that violate a non-contextuality bound, providing a witness that the specified operation family cannot be embedded in a single non-contextual classical prob- ability space. The claim is not that quantum theory is uniquely derived from decision making. Classical reconstructions can retain descriptive adequacy by introducing explicit context labels, stored history, or enlarged state descriptions; alternatively, the non-contextuality witness can be avoided by restricting the admissible probe set. Quantum probability instead supplies a compact single-state realization of the contextual operation family considered here. From the perspective of natural and artificial intelligence, the result identifies an architecture-level representational trade-off: contextual information may be carried intrinsically by transformations of a shared internal state or externalized into additional state and memory resources.

---

### EmplifAI: a Fine-grained Dataset for Japanese Empathetic Medical Dialogues in 28 Emotion Labels

Authors: Wan Jou She, Lis Kanashiro Pereira, Fei Cheng, Sakiko Yahata, Panote Siriaraya, Eiji Aramaki
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10033v1

This paper introduces EmplifAI, a Japanese empathetic dialogue dataset designed to support patients coping with chronic medical conditions. They often experience a wide range of positive and negative emotions (e.g., hope and despair) that shift across different stages of disease management. EmplifAI addresses this complexity by providing situation-based dialogues grounded in 28 fine-grained emotion categories, adapted and validated from the GoEmotions taxonomy. The dataset includes 280 medically contextualized situations and 4125 two-turn dialogues, collected through crowdsourcing and expert review. To evaluate emotional alignment in empathetic dialogues, we assessed model predictions on situation--dialogue pairs using BERTScore across multiple large language models (LLMs), achieving F1 scores of 0.83. Fine-tuning a baseline Japanese LLM (LLM-jp-3.1-13b-instruct4) with EmplifAI resulted in notable improvements in fluency, general empathy, and emotion-specific empathy. Furthermore, we compared the scores assigned by LLM-as-a-Judge and human raters on dialogues generated by multiple LLMs to validate our evaluation pipeline and discuss the insights and potential risks derived from the correlation analysis.

---

### FilDeep: Learning Large Deformations of Elastic-Plastic Solids with Multi-Fidelity Data

Authors: Jianheng Tang, Shilong Tao, Zhe Feng, Haonan Sun, Menglu Wang, Zhanxing Zhu, Yunhuai Liu
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10031v1

The scientific computation of large deformations in elastic-plastic solids is crucial in various manufacturing applications. Traditional numerical methods exhibit several inherent limitations, prompting Deep Learning (DL) as a promising alternative. The effectiveness of current DL techniques typically depends on the availability of high-quantity and high-accuracy datasets, which are yet difficult to obtain in large deformation problems. During the dataset construction process, a dilemma stands between data quantity and data accuracy, leading to suboptimal performance in the DL models. To address this challenge, we focus on a representative application of large deformations, the stretch bending problem, and propose FilDeep, a Fidelity-based Deep Learning framework for large Deformation of elastic-plastic solids. Our FilDeep aims to resolve the quantity-accuracy dilemma by simultaneously training with both low-fidelity and high-fidelity data, where the former provides greater quantity but lower accuracy, while the latter offers higher accuracy but in less quantity. In FilDeep, we provide meticulous designs for the practical large deformation problem. Particularly, we propose attention-enabled cross-fidelity modules to effectively capture long-range physical interactions across MF data. To the best of our knowledge, our FilDeep presents the first DL framework for large deformation problems using MF data. Extensive experiments demonstrate that our FilDeep consistently achieves state-of-the-art performance and can be efficiently deployed in manufacturing.

---

### PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization

Authors: Tingyue Pan, Jie Ouyang, Mingyue Cheng, Qingchuan Li, Zirui Liu, Daoyu Wang, Mingfan Pan, Shuo Yu, Qi Liu, Enhong Chen
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10029v3

Academic paper search is a fundamental task in scientific research, yet most existing approaches organize retrieval around predefined workflows or structured interaction protocols that struggle with complex, conditional queries. To address this limitation, we propose PaperScout, an autonomous agent that reformulates paper search as a sequential decision-making process. Unlike static workflows, PaperScout dynamically decides whether, when, and how to invoke search and expand tools based on accumulated retrieval context. However, training such agents presents a fundamental challenge: standard reinforcement learning methods, typically designed for single-turn tasks, suffer from a granularity mismatch when applied to multi-turn agentic tasks, where token-level optimization diverges from the granularity of sequence-level interactions, leading to noisy credit assignment and unstable training dynamics. We introduce Proximal Sequence Policy Optimization (PSPO), a process-aware, sequence-level policy optimization method that aligns optimization with agent--environment interaction. Comprehensive experiments on both synthetic and real-world benchmarks demonstrate that PaperScout significantly outperforms strong structured retrieval and RL baselines in both recall and relevance, validating the effectiveness of our adaptive agentic framework and optimization strategy.

---

### Structured Personality Control and Adaptation for LLM Agents

Authors: Jinpeng Wang, Xinyu Jia, Wei Wei Heng, Yuquan Li, Binbin Shi, Qianlei Chen, Guannan Chen, Junxia Zhang, Yuyu Yin
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10025v1

Large Language Models (LLMs) are increasingly shaping human-computer interaction (HCI), from personalized assistants to social simulations. Beyond language competence, researchers are exploring whether LLMs can exhibit human-like characteristics that influence engagement, decision-making, and perceived realism. Personality, in particular, is critical, yet existing approaches often struggle to achieve both nuanced and adaptable expression. We present a framework that models LLM personality via Jungian psychological types, integrating three mechanisms: a dominant-auxiliary coordination mechanism for coherent core expression, a reinforcement-compensation mechanism for temporary adaptation to context, and a reflection mechanism that drives long-term personality evolution. This design allows the agent to maintain nuanced traits while dynamically adjusting to interaction demands and gradually updating its underlying structure. Personality alignment is evaluated using Myers-Briggs Type Indicator questionnaires and tested under diverse challenge scenarios as a preliminary structured assessment. Findings suggest that evolving, personality-aware LLMs can support coherent, context-sensitive interactions, enabling naturalistic agent design in HCI.

---

### BPE: Behavioral Profiling Ensemble

Authors: Yanxin Liu, Yunqi Zhang
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10024v2

In the field of machine learning, ensemble learning is widely recognized as a pivotal strategy for pushing the boundaries of predictive performance. Traditional static ensemble methods typically assign weights by treating each base learner as a whole, thereby overlooking that individual models exhibit varying competence across different regions of the instance space. Dynamic Ensemble Selection (DES) was introduced to address this limitation. However, both static and dynamic approaches predominantly rely on inter-model differences as the basis for integration; this inter-model perspective neglects models' intrinsic characteristics and often requires heavy reliance on reference sets for competence estimation. We propose the Behavioral Profiling Ensemble (BPE) framework, which introduces a model-centric integration paradigm. Unlike traditional methods, BPE constructs an intrinsic behavioral profile $\mathcal{P}_k$ for each model and derives aggregation weights from the deviation between a model's response to a test instance and its established profile; in this work, we instantiate $\mathcal{P}_k$ with entropy-based summary statistics (e.g., mean and variance). Extensive experiments on 42 real-world datasets show that BPE-derived algorithms outperform state-of-the-art DES baselines, increasing predictive accuracy while reducing computational and storage overhead.

---

### EHRNavigator: A Multi-Agent System for Patient-Level Clinical Question Answering over Heterogeneous Electronic Health Records

Authors: Lingfei Qian, Mauro Giuffre, Yan Wang, Huan He, Qianqian Xie, Xuguang Ai, Xeuqing Peng, Fan Ma, Ruey-Ling Weng, Donald Wright, Adan Wang, Qingyu Chen et al.
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10020v1

Clinical decision-making increasingly relies on timely and context-aware access to patient information within Electronic Health Records (EHRs), yet most existing natural language question-answering (QA) systems are evaluated solely on benchmark datasets, limiting their practical relevance. To overcome this limitation, we introduce EHRNavigator, a multi-agent framework that harnesses AI agents to perform patient-level question answering across heterogeneous and multimodal EHR data. We assessed its performance using both public benchmark and institutional datasets under realistic hospital conditions characterized by diverse schemas, temporal reasoning demands, and multimodal evidence integration. Through quantitative evaluation and clinician-validated chart review, EHRNavigator demonstrated strong generalization, achieving 86% accuracy on real-world cases while maintaining clinically acceptable response times. Overall, these findings confirm that EHRNavigator effectively bridges the gap between benchmark evaluation and clinical deployment, offering a robust, adaptive, and efficient solution for real-world EHR question answering.

---

### Time Aggregation Features for XGBoost Models

Authors: Mykola Pinchuk
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10019v1

This paper studies time aggregation features for XGBoost models in click-through rate prediction. The setting is the Avazu click-through rate prediction dataset with strict out-of-time splits and a no-lookahead feature constraint. Features for hour H use only impressions from hours strictly before H. This paper compares a strong time-aware target encoding baseline to models augmented with entity history time aggregation under several window designs. Across two rolling-tail folds on a deterministic ten percent sample, a trailing window specification improves ROC AUC by about 0.0066 to 0.0082 and PR AUC by about 0.0084 to 0.0094 relative to target encoding alone. Within the time aggregation design grid, event count windows provide the only consistent improvement over trailing windows, and the gain is small. Gap windows and bucketized windows underperform simple trailing windows in this dataset and protocol. These results support a practical default of trailing windows, with an optional event count window when marginal ROC AUC gains matter.

---

### Helping the Helper: LLM-Assisted Problem Articulation for Older Adults Seeking Technology Support

Authors: Hasti Sharifi, Homaira Huda Shomee, Melissa Lamar, Sourav Medya, Debaleena Chattopadhyay
Published: 2026-01-15
Categories: cs.HC, cs.AI
arXiv: https://arxiv.org/abs/2601.10018v2

Older adults often struggle to articulate technology support needs due to unfamiliar technical terminology and age-related cognitive changes. We explore how large language models (LLMs) can facilitate this problem articulation process. Through a diary study (n = 27), we identified four communication barriers in older adults' queries: verbosity, incompleteness, over-specification, and under-specification. To mitigate these barriers, we developed an LLM pipeline that clarifies context and paraphrases unstructured queries. LLM-rephrased queries significantly improved automated solution accuracy (69% vs. 35%). Furthermore, younger adults (n = 48) acting as technology helpers understood LLM-rephrased queries better (93.7% vs. 65.8%) and reported greater ease in providing support. Older adults (n = 34) also found the resulting solutions highly actionable (94.7%). Finally, we contribute the first synthetic dataset of older adults' technology assistance queries (STAQ). This work demonstrates how LLMs can improve technology support seeking for older adults by addressing age-related communication barriers.

---

### Federated Personalization of Early-Exit Networks

Authors: Boyi Liu, Zimu Zhou, Cheng Fang, Yongxin Tong
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10015v2

Personalized Federated Learning (PFL) excels at tailoring client-specific models, which is particularly critical for decentralized and heterogeneous data environments, yet existing methods produce static models with a fixed tradeoff between accuracy and efficiency. This inherent static nature limits their ability to adapt to inference demands that vary with context and resource availability, posing a challenge for real-world deployment. Early-exit networks (EENs), which enable adaptive inference via intermediate classifiers, offer a promising solution. However, integrating EENs into PFL introduces two intertwined conflicts: client-wise heterogeneity across clients and depth-wise interference arising from conflicting exit objectives. Prior studies fail to resolve both conflicts simultaneously, leading to suboptimal performance. In this paper, we propose X-FED, a novel Conflict-Aware Cross-Client Federated Exit Distillation framework that jointly addresses both client- and depth-wise conflicts while extending PFL to early-exit networks. At its core, X-FED employs a progressive, depth-prioritized student coordination mechanism that mitigates interference among shallow and deep exits while enabling effective personalized knowledge transfer across clients. Furthermore, we introduce a client-decoupled formulation that reduces communication overhead with theoretical soundness. Extensive evaluations on various datasets show that compared to state-of-the-art PFL and PFL-EE methods, X-FED achieves higher accuracy while reducing inference costs by 30.79%-46.86%.

---

### PID-Guided Partial Alignment for Multimodal Decentralized Federated Learning

Authors: Yanhang Shi, Xiaoyu Wang, Houwei Cao, Jian Li, Yong Liu
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.10012v2

Multimodal decentralized federated learning (DFL) must support collaboration among agents that hold different modality subsets and often different model components, while operating over peer-to-peer (P2P) overlays without a coordinating server or a global network view. A key obstacle is that conventional multimodal training often relies on a single shared representation, which implicitly assumes that heterogeneous peers can exchange and aggregate the same model components over the same communication links. In multimodal DFL, this assumption breaks down: uni- and multimodal agents may push incompatible updates through shared overlays, weakening both inter-agent transfer and cross-modal interaction. We present PARSE, a server-free framework that brings partial information decomposition (PID) into multimodal DFL. Each agent splits its latent features into redundant, unique, and synergistic slices ("feature fission"), and performs slice-aware communication over modality-conditioned P2P overlays. During training, agents exchange only the slices that are semantically alignable with their neighbors, according to the modalities and model components they share ("partial alignment"). This design avoids centralized orchestration and gradient-surgery style conflict handling, while remaining compatible with standard DFL constraints and a range of P2P overlay topologies. Across multiple benchmarks and heterogeneous peer mixes, PARSE consistently outperforms task-, modality-, and hybrid-sharing multimodal DFL baselines while keeping per-link payloads bounded. Ablations on fusion choices and split ratios, together with qualitative feature analyses and overlay-topology studies, demonstrate the robustness and communication efficiency of the proposed slice-aware design.

---

### Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL

Authors: Zerui Yang, Weichuan Wang, Yanwei Xu, Linqi Song, Yudai Matsuda, Wei Han, Bo Bai
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.10011v1

Existing NL2SQL systems face two critical limitations: (1) they rely on in-context learning with only correct examples, overlooking the rich signal in historical error-fix pairs that could guide more robust self-correction; and (2) test-time scaling approaches often decompose questions arbitrarily, producing near-identical SQL candidates across runs and diminishing ensemble gains. Moreover, these methods suffer from a stark accuracy-efficiency trade-off: high performance demands excessive computation, while fast variants compromise quality. We present Memo-SQL, a training-free framework that addresses these issues through two simple ideas: structured decomposition and experience-aware self-correction. Instead of leaving decomposition to chance, we apply three clear strategies, entity-wise, hierarchical, and atomic sequential, to encourage diverse reasoning. For correction, we build a dynamic memory of both successful queries and historical error-fix pairs, and use retrieval-augmented prompting to bring relevant examples into context at inference time, no fine-tuning or external APIs required. On BIRD, Memo-SQL achieves 68.5% execution accuracy, setting a new state of the art among open, zero-fine-tuning methods, while using over 10 times fewer resources than prior TTS approaches.

---

### VERHallu: Evaluating and Mitigating Event Relation Hallucination in Video Large Language Models

Authors: Zefan Zhang, Kehua Zhu, Shijie Jiang, Hongyuan Lu, Shengkai Sun, Tian Bai
Published: 2026-01-15
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.10010v1

Video Large Language Models (VideoLLMs) exhibit various types of hallucinations. Existing research has primarily focused on hallucinations involving the presence of events, objects, and scenes in videos, while largely neglecting event relation hallucination. In this paper, we introduce a novel benchmark for evaluating the Video Event Relation Hallucination, named VERHallu. This benchmark focuses on causal, temporal, and subevent relations between events, encompassing three types of tasks: relation classification, question answering, and counterfactual question answering, for a comprehensive evaluation of event relation hallucination. Additionally, it features counterintuitive video scenarios that deviate from typical pretraining distributions, with each sample accompanied by human-annotated candidates covering both vision-language and pure language biases. Our analysis reveals that current state-of-the-art VideoLLMs struggle with dense-event relation reasoning, often relying on prior knowledge due to insufficient use of frame-level cues. Although these models demonstrate strong grounding capabilities for key events, they often overlook the surrounding subevents, leading to an incomplete and inaccurate understanding of event relations. To tackle this, we propose a Key-Frame Propagating (KFP) strategy, which reallocates frame-level attention within intermediate layers to enhance multi-event understanding. Experiments show it effectively mitigates the event relation hallucination without affecting inference speed.

---

### Continuous-Depth Transformers with Learned Control Dynamics

Authors: Peter Jemley
Published: 2026-01-15
Categories: cs.LG, cs.CL
arXiv: https://arxiv.org/abs/2601.10007v1

We present a hybrid transformer architecture that replaces discrete middle layers with a continuous-depth Neural Ordinary Differential Equation (ODE) block, enabling inference-time control over generation attributes via a learned steering signal. Unlike standard transformers that process representations through fixed discrete layers, our approach treats depth as a continuous variable governed by a learned vector field $F_θ(H, τ, u)$, where $u$ is a low-dimensional control signal injected via explicit concatenation. We validate the architecture through four experiments: (1) gradient flow stability with zero exploding/vanishing gradient events, (2) semantic steering achieving 98\%/88\% accuracy for positive/negative sentiment control, (3) continuous interpolation validated by a negligible 0.068\% trajectory divergence between fixed and adaptive solvers, and (4) efficiency benchmarking demonstrating latency parity with standard discrete baselines. Additionally, we show that adaptive ODE solvers reveal geometric structure in the learned dynamics: the control signal partitions the vector field into distinct dynamical regimes with different curvature characteristics. The adjoint method enables $O(1)$ memory training regardless of integration depth. Our results demonstrate that continuous-depth dynamics with learned control signals provide a viable, efficient mechanism for steerable language generation.

---

### SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations

Authors: Mohoshin Ara Tahera, Karamveer Singh Sidhu, Shuvalaxmi Dass, Sajal Saha
Published: 2026-01-15
Categories: cs.CR, cs.LG
arXiv: https://arxiv.org/abs/2601.10004v1

Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making, summarize electronic health records (EHRs), and enhance patient care. However, this integration introduces significant privacy and security challenges, driven by the sensitivity of clinical data and the high-stakes nature of medical workflows. These risks become even more pronounced across heterogeneous deployment environments, ranging from small on-premise hospital systems to regional health networks, each with unique resource limitations and regulatory demands. This Systematization of Knowledge (SoK) examines the evolving threat landscape across the three core LLM phases: Data preprocessing, Fine-tuning, and Inference within realistic healthcare settings. We present a detailed threat model that characterizes adversaries, capabilities, and attack surfaces at each phase, and we systematize how existing privacy-preserving techniques (PPTs) attempt to mitigate these vulnerabilities. While existing defenses show promise, our analysis identifies persistent limitations in securing sensitive clinical data across diverse operational tiers. We conclude with phase-aware recommendations and future research directions aimed at strengthening privacy guarantees for LLMs in regulated environments. This work provides a foundation for understanding the intersection of LLMs, threats, and privacy in healthcare, offering a roadmap toward more robust and clinically trustworthy AI systems.

---

### SocraticKG: Knowledge Graph Construction via QA-Driven Fact Extraction

Authors: Sanghyeok Choi, Woosang Jeon, Kyuseok Yang, Taehyeong Kim
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.10003v2

Constructing Knowledge Graphs (KGs) from unstructured text provides a structured framework for knowledge representation and reasoning, yet current LLM-based approaches struggle with a fundamental trade-off: factual coverage often leads to relational fragmentation, while premature consolidation causes information loss. To address this, we propose SocraticKG, an automated KG construction method that introduces question-answer pairs as a structured intermediate representation to systematically unfold document-level semantics prior to triple extraction. By employing 5W1H-guided QA expansion, SocraticKG captures contextual dependencies and implicit relational links typically lost in direct KG extraction pipelines, providing explicit grounding in the source document that helps mitigate implicit reasoning errors. Evaluation on the MINE benchmark and HotpotQA downstream task demonstrates that our approach effectively addresses the coverage-connectivity trade-off, achieving superior factual retention and structural cohesion while supporting complex multi-hop reasoning.

---

### DW-DGAT: Dynamically Weighted Dual Graph Attention Network for Neurodegenerative Disease Diagnosis

Authors: Chengjia Liang, Zhenjiong Wang, Chao Chen, Ruizhi Zhang, Songxi Liang, Hai Xie, Haijun Lei, Zhongwei Huang
Published: 2026-01-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.10001v3

Parkinson's disease (PD) and Alzheimer's disease (AD) are the two most prevalent and incurable neurodegenerative diseases (NDs) worldwide, for which early diagnosis is critical to delay their progression. However, the high dimensionality of multi-metric data with diverse structural forms, the heterogeneity of neuroimaging and phenotypic data, and class imbalance collectively pose significant challenges to early ND diagnosis. To address these challenges, we propose a dynamically weighted dual graph attention network (DW-DGAT) that integrates: (1) a general-purpose data fusion strategy to merge three structural forms of multi-metric data; (2) a dual graph attention architecture based on brain regions and inter-sample relationships to extract both micro- and macro-level features; and (3) a class weight generation mechanism combined with two stable and effective loss functions to mitigate class imbalance. Rigorous experiments, based on the Parkinson Progression Marker Initiative (PPMI) and Alzheimer's Disease Neuroimaging Initiative (ADNI) studies, demonstrate the state-of-the-art performance of our approach.

---

### EditEmoTalk: Controllable Speech-Driven 3D Facial Animation with Continuous Expression Editing

Authors: Diqiong Jiang, Kai Zhu, Dan Song, Jian Chang, Chenglizhao Chen, Zhenyu Wu
Published: 2026-01-15
Categories: cs.MM, cs.CV
arXiv: https://arxiv.org/abs/2601.10000v1

Speech-driven 3D facial animation aims to generate realistic and expressive facial motions directly from audio. While recent methods achieve high-quality lip synchronization, they often rely on discrete emotion categories, limiting continuous and fine-grained emotional control. We present EditEmoTalk, a controllable speech-driven 3D facial animation framework with continuous emotion editing. The key idea is a boundary-aware semantic embedding that learns the normal directions of inter-emotion decision boundaries, enabling a continuous expression manifold for smooth emotion manipulation. Moreover, we introduce an emotional consistency loss that enforces semantic alignment between the generated motion dynamics and the target emotion embedding through a mapping network, ensuring faithful emotional expression. Extensive experiments demonstrate that EditEmoTalk achieves superior controllability, expressiveness, and generalization while maintaining accurate lip synchronization. Code and pretrained models will be released.

---

### FaTRQ: Tiered Residual Quantization for LLM Vector Search in Far-Memory-Aware ANNS Systems

Authors: Tianqi Zhang, Flavio Ponzina, Tajana Rosing
Published: 2026-01-15
Categories: cs.LG, cs.AR, cs.IR
arXiv: https://arxiv.org/abs/2601.09985v1

Approximate Nearest-Neighbor Search (ANNS) is a key technique in retrieval-augmented generation (RAG), enabling rapid identification of the most relevant high-dimensional embeddings from massive vector databases. Modern ANNS engines accelerate this process using prebuilt indexes and store compressed vector-quantized representations in fast memory. However, they still rely on a costly second-pass refinement stage that reads full-precision vectors from slower storage like SSDs. For modern text and multimodal embeddings, these reads now dominate the latency of the entire query. We propose FaTRQ, a far-memory-aware refinement system using tiered memory that eliminates the need to fetch full vectors from storage. It introduces a progressive distance estimator that refines coarse scores using compact residuals streamed from far memory. Refinement stops early once a candidate is provably outside the top-k. To support this, we propose tiered residual quantization, which encodes residuals as ternary values stored efficiently in far memory. A custom accelerator is deployed in a CXL Type-2 device to perform low-latency refinement locally. Together, FaTRQ improves the storage efficiency by 2.4$\times$ and improves the throughput by up to 9$ \times$ than SOTA GPU ANNS system.

---

### Context Volume Drives Performance: Tackling Domain Shift in Extremely Low-Resource Translation via RAG

Authors: David Samuel Setiawan, Raphaël Merx, Jey Han Lau
Published: 2026-01-15
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09982v2

Neural Machine Translation (NMT) models for low-resource languages suffer significant performance degradation under domain shift. We quantify this challenge using Dhao, an indigenous language of Eastern Indonesia with no digital footprint beyond the New Testament (NT). When applied to the unseen Old Testament (OT), a standard NMT model fine-tuned on the NT drops from an in-domain score of 36.17 chrF++ to 27.11 chrF++. To recover this loss, we introduce a hybrid framework where a fine-tuned NMT model generates an initial draft, which is then refined by a Large Language Model (LLM) using Retrieval-Augmented Generation (RAG). The final system achieves 35.21 chrF++ (+8.10 recovery), effectively matching the original in-domain quality. Our analysis reveals that this performance is driven primarily by the number of retrieved examples rather than the choice of retrieval algorithm. Qualitative analysis confirms the LLM acts as a robust "safety net," repairing severe failures in zero-shot domains.

---

### DR$^2$Seg: Decomposed Two-Stage Rollouts for Efficient Reasoning Segmentation in Multimodal Large Language Models

Authors: Yulin He, Wei Chen, Zhikang Jian, Tianhang Guo, Wenjuan Zhou, Minglong Li, Shaowu Yang, Wenjing Yang
Published: 2026-01-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09981v2

Reasoning segmentation is an emerging vision-language task that requires reasoning over intricate text queries to precisely segment objects. However, existing methods typically suffer from overthinking, generating verbose reasoning chains that interfere with object localization in multimodal large language models (MLLMs). To address this issue, we propose DR$^2$Seg, a self-rewarding framework that improves both reasoning efficiency and segmentation accuracy without requiring extra thinking supervision. DR$^2$Seg employs a two-stage rollout strategy that decomposes reasoning segmentation into multimodal reasoning and referring segmentation. In the first stage, the model generates a self-contained description that explicitly specifies the target object. In the second stage, this description replaces the original complex query to verify its self-containment. Based on this design, two self-rewards are introduced to mitigate overthinking and the associated attention dispersion. Extensive experiments conducted on 3B and 7B variants of Qwen2.5-VL, as well as on both SAM2 and SAM3, demonstrate that DR$^2$Seg consistently improves reasoning efficiency and overall segmentation accuracy.

---

### Performance of AI agents based on reasoning language models on ALD process optimization tasks

Authors: Angel Yanguas-Gil
Published: 2026-01-15
Categories: cond-mat.mtrl-sci, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.09980v1

In this work we explore the performance and behavior of reasoning large language models to autonomously optimize atomic layer deposition (ALD) processes. In the ALD process optimization task, an agent built on top of a reasoning LLM has to find optimal dose times for an ALD precursor and a coreactant without any prior knowledge on the process, including whether it is actually self-limited. The agent is meant to interact iteratively with an ALD reactor in a fully unsupervised way. We evaluate this agent using a simple model of an ALD tool that incorporates ALD processes with different self-limited surface reaction pathways as well as a non self-limited component. Our results show that agents based on reasoning models like OpenAI's o3 and GPT5 consistently succeeded at completing this optimization task. However, we observed significant run-to-run variability due to the non deterministic nature of the model's response. In order to understand the logic followed by the reasoning model, the agent uses a two step process in which the model first generates an open response detailing the reasoning process. This response is then transformed into a structured output. An analysis of these reasoning traces showed that the logic of the model was sound and that its reasoning was based on the notions of self-limited process and saturation expected in the case of ALD. However, the agent can sometimes be misled by its own prior choices when exploring the optimization space.

---

### In-Context Operator Learning on the Space of Probability Measures

Authors: Frank Cole, Dixi Wang, Yineng Chen, Yulong Lu, Rongjie Lai
Published: 2026-01-15
Categories: cs.LG, math.NA
arXiv: https://arxiv.org/abs/2601.09979v1

We introduce \emph{in-context operator learning on probability measure spaces} for optimal transport (OT). The goal is to learn a single solution operator that maps a pair of distributions to the OT map, using only few-shot samples from each distribution as a prompt and \emph{without} gradient updates at inference. We parameterize the solution operator and develop scaling-law theory in two regimes. In the \emph{nonparametric} setting, when tasks concentrate on a low-intrinsic-dimension manifold of source--target pairs, we establish generalization bounds that quantify how in-context accuracy scales with prompt size, intrinsic task dimension, and model capacity. In the \emph{parametric} setting (e.g., Gaussian families), we give an explicit architecture that recovers the exact OT map in context and provide finite-sample excess-risk bounds. Our numerical experiments on synthetic transports and generative-modeling benchmarks validate the framework.

---

### SPRInG: Continual LLM Personalization via Selective Parametric Adaptation and Retrieval-Interpolated Generation

Authors: Seoyeon Kim, Jaehyung Kim
Published: 2026-01-15
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.09974v3

Personalizing Large Language Models typically relies on static retrieval or one-time adaptation, assuming user preferences remain invariant over time. However, real-world interactions are dynamic, where user interests continuously evolve, posing a challenge for models to adapt to preference drift without catastrophic forgetting. Standard continual learning approaches often struggle in this context, as they indiscriminately update on noisy interaction streams, failing to distinguish genuine preference shifts from transient contexts. To address this, we introduce SPRInG, a novel semi-parametric framework designed for effective continual personalization. During training, SPRInG employs drift-driven selective adaptation, which utilizes a likelihood-based scoring function to identify high-novelty interactions, selectively updating the user-specific adapter on drift signals while preserving hard-to-learn residuals in a replay buffer. During inference, we apply strict relevance gating and fuse parametric knowledge with retrieved history via probability interpolation. Experiments on the long-form personalized generation benchmark demonstrate that SPRInG significantly outperforms existing baselines, validating its robustness for real-world continual personalization.

---

### Chinese Labor Law Large Language Model Benchmark

Authors: Zixun Lan, Maochun Xu, Yifan Ren, Rui Wu, Jianghui Zhou, Xueyang Cheng, Jianan Ding Ding, Xinheng Wang, Mingmin Chi, Fei Ma
Published: 2026-01-15
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.09972v1

Recent advances in large language models (LLMs) have led to substantial progress in domain-specific applications, particularly within the legal domain. However, general-purpose models such as GPT-4 often struggle with specialized subdomains that require precise legal knowledge, complex reasoning, and contextual sensitivity. To address these limitations, we present LabourLawLLM, a legal large language model tailored to Chinese labor law. We also introduce LabourLawBench, a comprehensive benchmark covering diverse labor-law tasks, including legal provision citation, knowledge-based question answering, case classification, compensation computation, named entity recognition, and legal case analysis. Our evaluation framework combines objective metrics (e.g., ROUGE-L, accuracy, F1, and soft-F1) with subjective assessment based on GPT-4 scoring. Experiments show that LabourLawLLM consistently outperforms general-purpose and existing legal-specific LLMs across task categories. Beyond labor law, our methodology provides a scalable approach for building specialized LLMs in other legal subfields, improving accuracy, reliability, and societal value of legal AI applications.

---

### An Exploratory Study to Repurpose LLMs to a Unified Architecture for Time Series Classification

Authors: Hansen He, Shuheng Li
Published: 2026-01-15
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.09971v1

Time series classification (TSC) is a core machine learning problem with broad applications. Recently there has been growing interest in repurposing large language models (LLMs) for TSC, motivated by their strong reasoning and generalization ability. Prior work has primarily focused on alignment strategies that explicitly map time series data into the textual domain; however, the choice of time series encoder architecture remains underexplored. In this work, we conduct an exploratory study of hybrid architectures that combine specialized time series encoders with a frozen LLM backbone. We evaluate a diverse set of encoder families, including Inception, convolutional, residual, transformer-based, and multilayer perceptron architectures, among which the Inception model is the only encoder architecture that consistently yields positive performance gains when integrated with an LLM backbone. Overall, this study highlights the impact of time series encoder choice in hybrid LLM architectures and points to Inception-based models as a promising direction for future LLM-driven time series learning.

---

### A Sustainable AI Economy Needs Data Deals That Work for Generators

Authors: Ruoxi Jia, Luis Oala, Wenjie Xiong, Suqin Ge, Jiachen T. Wang, Feiyang Kang, Dawn Song
Published: 2026-01-15
Categories: cs.LG, cs.AI, cs.HC
arXiv: https://arxiv.org/abs/2601.09966v1

We argue that the machine learning value chain is structurally unsustainable due to an economic data processing inequality: each state in the data cycle from inputs to model weights to synthetic outputs refines technical signal but strips economic equity from data generators. We show, by analyzing seventy-three public data deals, that the majority of value accrues to aggregators, with documented creator royalties rounding to zero and widespread opacity of deal terms. This is not just an economic welfare concern: as data and its derivatives become economic assets, the feedback loop that sustains current learning algorithms is at risk. We identify three structural faults - missing provenance, asymmetric bargaining power, and non-dynamic pricing - as the operational machinery of this inequality. In our analysis, we trace these problems along the machine learning value chain and propose an Equitable Data-Value Exchange (EDVEX) Framework to enable a minimal market that benefits all participants. Finally, we outline research directions where our community can make concrete contributions to data deals and contextualize our position with related and orthogonal viewpoints.

---

### The Spatial Blindspot of Vision-Language Models

Authors: Nahid Alam, Leema Krishna Murali, Siddhant Bharadwaj, Patrick Liu, Timothy Chung, Drishti Sharma, Akshata A, Kranthi Kiran, Wesley Tam, Bala Krishna S Vegesna
Published: 2026-01-15
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09954v2

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The training recipe often flattens images into 1D patch sequences, discarding the 2D structure necessary for spatial reasoning. We argue that this lack of spatial awareness is a missing dimension in VLM design and a bottleneck for applications requiring spatial grounding, such as robotics and embodied AI. To address this, we investigate (i) image encoders trained with alternative objectives and (ii) 2D positional encodings. Our experiments show that these architectural choices can lead to improved spatial reasoning on several benchmarks.

---

### Take Out Your Calculators: Estimating the Real Difficulty of Question Items with LLM Student Simulations

Authors: Christabel Acquaye, Yi Ting Huang, Marine Carpuat, Rachel Rudinger
Published: 2026-01-15
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09953v2

Standardized math assessments require expensive human pilot studies to establish the difficulty of test items. We investigate the predictive value of open-source large language models (LLMs) for evaluating the difficulty of multiple-choice math questions for real-world students. We show that, while LLMs are poor direct judges of problem difficulty, simulation-based approaches with LLMs yield promising results under the right conditions. Under the proposed approach, we simulate a ``classroom'' of 4th, 8th, or 12th-grade students by prompting the LLM to role-play students of varying proficiency levels. We use the outcomes of these simulations to fit Item Response Theory (IRT) models, comparing learned difficulty parameters for items to their real-world difficulties, as determined by item-level statistics furnished by the National Assessment of Educational Progress (NAEP). We observe correlations as high as 0.75, 0.76, and 0.82 for grades 4, 8, and 12, respectively, on the item-level correctness rates. In our simulations, we experiment on math MCQs with different ``classroom sizes,'' showing tradeoffs between computation size and accuracy. We find that role-plays with diverse-named students improve predictions (compared to student IDs), and stratifying names across gender and race further improves predictions. Our results show that LLMs with relatively weaker mathematical abilities (Gemma) actually yield better real-world difficulty predictions than mathematically stronger models (Llama and Qwen), further underscoring the suitability of these models for the task.

---

### OT-Drive: Out-of-Distribution Off-Road Traversable Area Segmentation via Optimal Transport

Authors: Zhihua Zhao, Guoqiang Li, Chen Min, Kangping Lu
Published: 2026-01-15
Categories: cs.CV, cs.RO
arXiv: https://arxiv.org/abs/2601.09952v1

Reliable traversable area segmentation in unstructured environments is critical for planning and decision-making in autonomous driving. However, existing data-driven approaches often suffer from degraded segmentation performance in out-of-distribution (OOD) scenarios, consequently impairing downstream driving tasks. To address this issue, we propose OT-Drive, an Optimal Transport--driven multi-modal fusion framework. The proposed method formulates RGB and surface normal fusion as a distribution transport problem. Specifically, we design a novel Scene Anchor Generator (SAG) to decompose scene information into the joint distribution of weather, time-of-day, and road type, thereby constructing semantic anchors that can generalize to unseen scenarios. Subsequently, we design an innovative Optimal Transport-based multi-modal fusion module (OT Fusion) to transport RGB and surface normal features onto the manifold defined by the semantic anchors, enabling robust traversable area segmentation under OOD scenarios. Experimental results demonstrate that our method achieves 95.16% mIoU on ORFD OOD scenarios, outperforming prior methods by 6.35%, and 89.79% mIoU on cross-dataset transfer tasks, surpassing baselines by 13.99%.These results indicate that the proposed model can attain strong OOD generalization with only limited training data, substantially enhancing its practicality and efficiency for real-world deployment.

---