# Research Papers — 2026-01 · bundle page 115 of 189

> Full-text markdown of papers #5701–5750 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/115
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/114.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/116.md)

### Bridging Semantic Understanding and Popularity Bias with LLMs

Authors: Renqiang Luo, Dong Zhang, Yupeng Gao, Wen Shi, Mingliang Hou, Jiaying Liu, Zhe Wang, Shuo Yu
Published: 2026-01-14
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.09478v3

Semantic understanding of popularity bias is a crucial yet underexplored challenge in recommender systems, where popular items are often favored at the expense of niche content. Most existing debiasing methods treat the semantic understanding of popularity bias as a matter of diversity enhancement or long-tail coverage, neglecting the deeper semantic layer that embodies the causal origins of the bias itself. Consequently, such shallow interpretations limit both their debiasing effectiveness and recommendation accuracy. In this paper, we propose FairLRM, a novel framework that bridges the gap in the semantic understanding of popularity bias with Recommendation via Large Language Model (RecLLM). FairLRM decomposes popularity bias into item-side and user-side components, using structured instruction-based prompts to enhance the model's comprehension of both global item distributions and individual user preferences. Unlike traditional methods that rely on surface-level features such as "diversity" or "debiasing", FairLRM improves the model's ability to semantically interpret and address the underlying bias. Through empirical evaluation, we show that FairLRM significantly enhances both fairness and recommendation accuracy, providing a more semantically aware and trustworthy approach to enhance the semantic understanding of popularity bias. The implementation is available at https://github.com/LuoRenqiang/FairLRM.

---

### Bridging Semantic Understanding and Popularity Bias with LLMs

Authors: Renqiang Luo, Dong Zhang, Yupeng Gao, Wen Shi, Mingliang Hou, Jiaying Liu, Zhe Wang, Shuo Yu
Published: 2026-01-14
Categories: cs.IR, cs.AI
arXiv: https://arxiv.org/abs/2601.09478v1

Semantic understanding of popularity bias is a crucial yet underexplored challenge in recommender systems, where popular items are often favored at the expense of niche content. Most existing debiasing methods treat the semantic understanding of popularity bias as a matter of diversity enhancement or long-tail coverage, neglecting the deeper semantic layer that embodies the causal origins of the bias itself. Consequently, such shallow interpretations limit both their debiasing effectiveness and recommendation accuracy. In this paper, we propose FairLRM, a novel framework that bridges the gap in the semantic understanding of popularity bias with Recommendation via Large Language Model (RecLLM). FairLRM decomposes popularity bias into item-side and user-side components, using structured instruction-based prompts to enhance the model's comprehension of both global item distributions and individual user preferences. Unlike traditional methods that rely on surface-level features such as "diversity" or "debiasing", FairLRM improves the model's ability to semantically interpret and address the underlying bias. Through empirical evaluation, we show that FairLRM significantly enhances both fairness and recommendation accuracy, providing a more semantically aware and trustworthy approach to enhance the semantic understanding of popularity bias. The implementation is available at https://github.com/LuoRenqiang/FairLRM.

---

### Terminally constrained flow-based generative models from an optimal control perspective

Authors: Weiguo Gao, Ming Li, Qianxiao Li
Published: 2026-01-14
Categories: cs.LG, math.OC
arXiv: https://arxiv.org/abs/2601.09474v1

We address the problem of sampling from terminally constrained distributions with pre-trained flow-based generative models through an optimal control formulation. Theoretically, we characterize the value function by a Hamilton-Jacobi-Bellman equation and derive the optimal feedback control as the minimizer of the associated Hamiltonian. We show that as the control penalty increases, the controlled process recovers the reference distribution, while as the penalty vanishes, the terminal law converges to a generalized Wasserstein projection onto the constraint manifold. Algorithmically, we introduce Terminal Optimal Control with Flow-based models (TOCFlow), a geometry-aware sampling-time guidance method for pre-trained flows. Solving the control problem in a terminal co-moving frame that tracks reference trajectories yields a closed-form scalar damping factor along the Riemannian gradient, capturing second-order curvature effects without matrix inversions. TOCFlow therefore matches the geometric consistency of Gauss-Newton updates at the computational cost of standard gradient guidance. We evaluate TOCFlow on three high-dimensional scientific tasks spanning equality, inequality, and global statistical constraints, namely Darcy flow, constrained trajectory planning, and turbulence snapshot generation with Kolmogorov spectral scaling. Across all settings, TOCFlow improves constraint satisfaction over Euclidean guidance and projection baselines while preserving the reference model's generative quality.

---

### SimMerge: Learning to Select Merge Operators from Similarity Signals

Authors: Oliver Bolton, Aakanksha, Arash Ahmadian, Sara Hooker, Marzieh Fadaee, Beyza Ermis
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09473v2

Model merging combines multiple models into a single model with aggregated capabilities, making it a powerful tool for large language model (LLM) development. However, scaling model merging is challenging: performance depends on the choice of merge operator, model subset, and merge order, often requiring expensive merge-and-evaluate searches. In this work, we introduce SimMerge, a predictive merge-selection method that identifies high-performing merges using inexpensive, task-agnostic similarity signals between models. Given a small set of unlabeled probes, SimMerge extracts functional and structural features to predict the performance of candidate two-way merges, enabling merge operator, order and model subset selection without iterative evaluation. We show that SimMerge consistently outperforms the best fixed merge operator across 7B-parameter LLMs and generalizes to multi-way merges and 111B-parameter LLMs without retraining. We further introduce a bandit variant that supports adding new tasks and operators online. Our results suggest that learning how to merge enables scalable model composition when checkpoint catalogs are large and evaluation budgets are limited.

---

### SimMerge: Learning to Select Merge Operators from Similarity Signals

Authors: Oliver Bolton, Aakanksha, Arash Ahmadian, Sara Hooker, Marzieh Fadaee, Beyza Ermis
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09473v1

Model merging enables multiple large language models (LLMs) to be combined into a single model while preserving performance. This makes it a valuable tool in LLM development, offering a competitive alternative to multi-task training. However, merging can be difficult at scale, as successful merging requires choosing the right merge operator, selecting the right models, and merging them in the right order. This often leads researchers to run expensive merge-and-evaluate searches to select the best merge. In this work, we provide an alternative by introducing \simmerge{}, \emph{a predictive merge-selection method} that selects the best merge using inexpensive, task-agnostic similarity signals between models. From a small set of unlabeled probes, we compute functional and structural features and use them to predict the performance of a given 2-way merge. Using these predictions, \simmerge{} selects the best merge operator, the subset of models to merge, and the merge order, eliminating the expensive merge-and-evaluate loop. We demonstrate that we surpass standard merge-operator performance on 2-way merges of 7B-parameter LLMs, and that \simmerge{} generalizes to multi-way merges and 111B-parameter LLM merges without retraining. Additionally, we present a bandit variant that supports adding new tasks, models, and operators on the fly. Our results suggest that learning how to merge is a practical route to scalable model composition when checkpoint catalogs are large and evaluation budgets are tight.

---

### Personalized Multimodal Feedback Using Multiple External Representations: Strategy Profiles and Learning in High School Physics

Authors: Natalia Revenga-Lozano, Karina E. Avila, Steffen Steinert, Matthias Schweinberger, Clara E. Gómez-Pérez, Jochen Kuhn, Stefan Küchemann
Published: 2026-01-14
Categories: physics.ed-ph, cs.AI
arXiv: https://arxiv.org/abs/2601.09470v1

Multiple external representations (MERs) and personalized feedback support physics learning, yet evidence on how personalized feedback can effectively integrate MERs remains limited. This question is particularly timely given the emergence of multimodal large language models. We conducted a 16-24 week observational study in high school physics (N=661) using a computer-based platform that provided verification and optional elaborated feedback in verbal, graphical and mathematical forms. Linear mixed-effects models and strategy-cluster analyses (ANCOVA-adjusted comparisons) tested associations between feedback use and post-test performance and moderation by representational competence. Elaborated multirepresentational feedback showed a small but consistent positive association with post-test scores independent of prior knowledge and confidence. Learners adopted distinct representation-selection strategies; among students with lower representational competence, using a diverse set of representations related to higher learning, whereas this advantage diminished as competence increased. These findings motivate adaptive feedback designs and inform intelligent tutoring systems capable of tailoring feedback elaboration and representational format to learner profiles, advancing personalized instruction in physics education.

---

### FairGU: Fairness-aware Graph Unlearning in Social Networks

Authors: Renqiang Luo, Yongshuai Yang, Huafei Huang, Qing Qing, Mingliang Hou, Ziqi Xu, Yi Yu, Jingjing Zhou, Feng Xia
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09469v2

Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and thereby better safeguard user information. However, we observe that existing graph unlearning techniques insufficiently protect sensitive attributes, often leading to degraded algorithmic fairness compared with traditional graph learning methods. To address this gap, we introduce FairGU, a fairness-aware graph unlearning framework designed to preserve both utility and fairness during the unlearning process. FairGU integrates a dedicated fairness-aware module with effective data protection strategies, ensuring that sensitive attributes are neither inadvertently amplified nor structurally exposed when nodes are removed. Through extensive experiments on multiple real-world datasets, we demonstrate that FairGU consistently outperforms state-of-the-art graph unlearning methods and fairness-enhanced graph learning baselines in terms of both accuracy and fairness metrics. Our findings highlight a previously overlooked risk in current unlearning practices and establish FairGU as a robust and equitable solution for the next generation of socially sustainable networked systems. The codes are available at https://github.com/LuoRenqiang/FairGU.

---

### FairGU: Fairness-aware Graph Unlearning in Social Network

Authors: Renqiang Luo, Yongshuai Yang, Huafei Huang, Qing Qing, Mingliang Hou, Ziqi Xu, Yi Yu, Jingjing Zhou, Feng Xia
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09469v1

Graph unlearning has emerged as a critical mechanism for supporting sustainable and privacy-preserving social networks, enabling models to remove the influence of deleted nodes and thereby better safeguard user information. However, we observe that existing graph unlearning techniques insufficiently protect sensitive attributes, often leading to degraded algorithmic fairness compared with traditional graph learning methods. To address this gap, we introduce FairGU, a fairness-aware graph unlearning framework designed to preserve both utility and fairness during the unlearning process. FairGU integrates a dedicated fairness-aware module with effective data protection strategies, ensuring that sensitive attributes are neither inadvertently amplified nor structurally exposed when nodes are removed. Through extensive experiments on multiple real-world datasets, we demonstrate that FairGU consistently outperforms state-of-the-art graph unlearning methods and fairness-enhanced graph learning baselines in terms of both accuracy and fairness metrics. Our findings highlight a previously overlooked risk in current unlearning practices and establish FairGU as a robust and equitable solution for the next generation of socially sustainable networked systems. The codes are available at https://github.com/LuoRenqiang/FairGU.

---

### High-fidelity lunar topographic reconstruction across diverse terrain and illumination environments using deep learning

Authors: Hao Chen, Philipp Gläser, Konrad Willner, Jürgen Oberst
Published: 2026-01-14
Categories: astro-ph.EP, cs.LG
arXiv: https://arxiv.org/abs/2601.09468v1

Topographic models are essential for characterizing planetary surfaces and for inferring underlying geological processes. Nevertheless, meter-scale topographic data remain limited, which constrains detailed planetary investigations, even for the Moon, where extensive high-resolution orbital images are available. Recent advances in deep learning (DL) exploit single-view imagery, constrained by low-resolution topography, for fast and flexible reconstruction of fine-scale topography. However, their robustness and general applicability across diverse lunar landforms and illumination conditions remain insufficiently explored. In this study, we build upon our previously proposed DL framework by incorporating a more robust scale recovery scheme and extending the model to polar regions under low solar illumination conditions. We demonstrate that, compared with single-view shape-from-shading methods, the proposed DL approach exhibits greater robustness to varying illumination and achieves more consistent and accurate topographic reconstructions. Furthermore, it reliably reconstructs topography across lunar features of diverse scales, morphologies, and geological ages. High-quality topographic models are also produced for the lunar south polar areas, including permanently shadowed regions, demonstrating the method's capability in reconstructing complex and low-illumination terrain. These findings suggest that DL-based approaches have the potential to leverage extensive lunar datasets to support advanced exploration missions and enable investigations of the Moon at unprecedented topographic resolution.

---

### Searth Transformer: A Transformer Architecture Incorporating Earth's Geospheric Physical Priors for Global Mid-Range Weather Forecasting

Authors: Tianye Li, Qi Liu, Hao Li, Lei Chen, Wencong Cheng, Fei Zheng, Xiangao Xia, Ya Wang, Gang Huang, Weiwei Wang, Xuan Tong, Ziqing Zu et al.
Published: 2026-01-14
Categories: cs.LG, cs.AI, physics.ao-ph
arXiv: https://arxiv.org/abs/2601.09467v1

Accurate global medium-range weather forecasting is fundamental to Earth system science. Most existing Transformer-based forecasting models adopt vision-centric architectures that neglect the Earth's spherical geometry and zonal periodicity. In addition, conventional autoregressive training is computationally expensive and limits forecast horizons due to error accumulation. To address these challenges, we propose the Shifted Earth Transformer (Searth Transformer), a physics-informed architecture that incorporates zonal periodicity and meridional boundaries into window-based self-attention for physically consistent global information exchange. We further introduce a Relay Autoregressive (RAR) fine-tuning strategy that enables learning long-range atmospheric evolution under constrained memory and computational budgets. Based on these methods, we develop YanTian, a global medium-range weather forecasting model. YanTian achieves higher accuracy than the high-resolution forecast of the European Centre for Medium-Range Weather Forecasts and performs competitively with state-of-the-art AI models at one-degree resolution, while requiring roughly 200 times lower computational cost than standard autoregressive fine-tuning. Furthermore, YanTian attains a longer skillful forecast lead time for Z500 (10.3 days) than HRES (9 days). Beyond weather forecasting, this work establishes a robust algorithmic foundation for predictive modeling of complex global-scale geophysical circulation systems, offering new pathways for Earth system science.

---

### EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

Authors: Shuo Zhang, Chaofa Yuan, Ryan Guo, Xiaomin Yu, Rui Xu, Zhangquan Chen, Zinuo Li, Zhi Yang, Shuhao Guan, Zhenheng Tang, Sen Hu, Liwen Zhang et al.
Published: 2026-01-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.09465v2

While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.

---

### EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines

Authors: Shuo Zhang, Chaofa Yuan, Ryan Guo, Xiaomin Yu, Rui Xu, Zhangquan Chen, Zinuo Li, Zhi Yang, Shuhao Guan, Zhenheng Tang, Sen Hu, Liwen Zhang et al.
Published: 2026-01-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.09465v1

While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.

---

### SoK: Enhancing Cryptographic Collaborative Learning with Differential Privacy

Authors: Francesco Capano, Jonas Böhler, Benjamin Weggenmann
Published: 2026-01-14
Categories: cs.CR, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.09460v1

In collaborative learning (CL), multiple parties jointly train a machine learning model on their private datasets. However, data can not be shared directly due to privacy concerns. To ensure input confidentiality, cryptographic techniques, e.g., multi-party computation (MPC), enable training on encrypted data. Yet, even securely trained models are vulnerable to inference attacks aiming to extract memorized data from model outputs. To ensure output privacy and mitigate inference attacks, differential privacy (DP) injects calibrated noise during training. While cryptography and DP offer complementary guarantees, combining them efficiently for cryptographic and differentially private CL (CPCL) is challenging. Cryptography incurs performance overheads, while DP degrades accuracy, creating a privacy-accuracy-performance trade-off that needs careful design considerations. This work systematizes the CPCL landscape. We introduce a unified framework that generalizes common phases across CPCL paradigms, and identify secure noise sampling as the foundational phase to achieve CPCL. We analyze trade-offs of different secure noise sampling techniques, noise types, and DP mechanisms discussing their implementation challenges and evaluating their accuracy and cryptographic overhead across CPCL paradigms. Additionally, we implement identified secure noise sampling options in MPC and evaluate their computation and communication costs in WAN and LAN. Finally, we propose future research directions based on identified key observations, gaps and possible enhancements in the literature.

---

### Dissecting Judicial Reasoning in U.S. Copyright Damage Awards

Authors: Pei-Chi Lo, Thomas Y. Lu
Published: 2026-01-14
Categories: cs.IR, cs.CL
arXiv: https://arxiv.org/abs/2601.09459v1

Judicial reasoning in copyright damage awards poses a core challenge for computational legal analysis. Although federal courts follow the 1976 Copyright Act, their interpretations and factor weightings vary widely across jurisdictions. This inconsistency creates unpredictability for litigants and obscures the empirical basis of legal decisions. This research introduces a novel discourse-based Large Language Model (LLM) methodology that integrates Rhetorical Structure Theory (RST) with an agentic workflow to extract and quantify previously opaque reasoning patterns from judicial opinions. Our framework addresses a major gap in empirical legal scholarship by parsing opinions into hierarchical discourse structures and using a three-stage pipeline, i.e., Dataset Construction, Discourse Analysis, and Agentic Feature Extraction. This pipeline identifies reasoning components and extract feature labels with corresponding discourse subtrees. In analyzing copyright damage rulings, we show that discourse-augmented LLM analysis outperforms traditional methods while uncovering unquantified variations in factor weighting across circuits. These findings offer both methodological advances in computational legal analysis and practical insights into judicial reasoning, with implications for legal practitioners seeking predictive tools, scholars studying legal principle application, and policymakers confronting inconsistencies in copyright law.

---

### On the Hardness of Computing Counterfactual and Semifactual Explanations in XAI

Authors: André Artelt, Martin Olsen, Kevin Tierney
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09455v1

Providing clear explanations to the choices of machine learning models is essential for these models to be deployed in crucial applications. Counterfactual and semi-factual explanations have emerged as two mechanisms for providing users with insights into the outputs of their models. We provide an overview of the computational complexity results in the literature for generating these explanations, finding that in many cases, generating explanations is computationally hard. We strengthen the argument for this considerably by further contributing our own inapproximability results showing that not only are explanations often hard to generate, but under certain assumptions, they are also hard to approximate. We discuss the implications of these complexity results for the XAI community and for policymakers seeking to regulate explanations in AI.

---

### MAD: Motion Appearance Decoupling for efficient Driving World Models

Authors: Ahmad Rahimi, Valentin Gerard, Eloi Zablocki, Matthieu Cord, Alexandre Alahi
Published: 2026-01-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09452v1

Recent video diffusion models generate photorealistic, temporally coherent videos, yet they fall short as reliable world models for autonomous driving, where structured motion and physically consistent interactions are essential. Adapting these generalist video models to driving domains has shown promise but typically requires massive domain-specific data and costly fine-tuning. We propose an efficient adaptation framework that converts generalist video diffusion models into controllable driving world models with minimal supervision. The key idea is to decouple motion learning from appearance synthesis. First, the model is adapted to predict structured motion in a simplified form: videos of skeletonized agents and scene elements, focusing learning on physical and social plausibility. Then, the same backbone is reused to synthesize realistic RGB videos conditioned on these motion sequences, effectively "dressing" the motion with texture and lighting. This two-stage process mirrors a reasoning-rendering paradigm: first infer dynamics, then render appearance. Our experiments show this decoupled approach is exceptionally efficient: adapting SVD, we match prior SOTA models with less than 6% of their compute. Scaling to LTX, our MAD-LTX model outperforms all open-source competitors, and supports a comprehensive suite of text, ego, and object controls. Project page: https://vita-epfl.github.io/MAD-World-Model/

---

### Late Breaking Results: Quamba-SE: Soft-edge Quantizer for Activations in State Space Models

Authors: Yizhi Chen, Ahmed Hemani
Published: 2026-01-14
Categories: cs.LG, cs.AI, cs.AR
arXiv: https://arxiv.org/abs/2601.09451v1

We propose Quamba-SE, a soft-edge quantizer for State Space Model (SSM) activation quantization. Unlike existing methods, using standard INT8 operation, Quamba-SE employs three adaptive scales: high-precision for small values, standard scale for normal values, and low-precision for outliers. This preserves outlier information instead of hard clipping, while maintaining precision for other values. We evaluate on Mamba- 130M across 6 zero-shot benchmarks. Results show that Quamba- SE consistently outperforms Quamba, achieving up to +2.68% on individual benchmarks and up to +0.83% improvement in the average accuracy of 6 datasets.

---

### PrivLEX: Detecting legal concepts in images through Vision-Language Models

Authors: Darya Baranouskaya, Andrea Cavallaro
Published: 2026-01-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09449v1

We present PrivLEX, a novel image privacy classifier that grounds its decisions in legally defined personal data concepts. PrivLEX is the first interpretable privacy classifier aligned with legal concepts that leverages the recognition capabilities of Vision-Language Models (VLMs). PrivLEX relies on zero-shot VLM concept detection to provide interpretable classification through a label-free Concept Bottleneck Model, without requiring explicit concept labels during training. We demonstrate PrivLEX's ability to identify personal data concepts that are present in images. We further analyse the sensitivity of such concepts as perceived by human annotators of image privacy datasets.

---

### One Prompt, Many Sounds: Modeling Listener Variability in LLM-Based Equalization

Authors: Ioannis Stylianou, Jon Francombe, Pablo Martinez-Nuevo, Sven Ewan Shepstone, Zheng-Hua Tan
Published: 2026-01-14
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.09448v3

Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model (LLM)-based alternative that maps natural language text prompts to equalization settings. This enables a conversational approach to sound system control. By utilizing data collected from a controlled listening experiment, our models exploit in-context learning and parameter-efficient fine-tuning techniques to reliably align with population-preferred equalization settings. Our evaluation methods, which leverage distributional metrics that capture users' varied preferences, show statistically significant improvements in distributional alignment over random sampling and static preset baselines. These results indicate that LLMs could function as ``artificial equalizers," contributing to the development of more accessible, context-aware, and expert-level audio tuning methods.

---

### Population-Aligned Audio Reproduction With LLM-Based Equalizers

Authors: Ioannis Stylianou, Jon Francombe, Pablo Martinez-Nuevo, Sven Ewan Shepstone, Zheng-Hua Tan
Published: 2026-01-14
Categories: cs.SD, cs.AI
arXiv: https://arxiv.org/abs/2601.09448v1

Conventional audio equalization is a static process that requires manual and cumbersome adjustments to adapt to changing listening contexts (e.g., mood, location, or social setting). In this paper, we introduce a Large Language Model (LLM)-based alternative that maps natural language text prompts to equalization settings. This enables a conversational approach to sound system control. By utilizing data collected from a controlled listening experiment, our models exploit in-context learning and parameter-efficient fine-tuning techniques to reliably align with population-preferred equalization settings. Our evaluation methods, which leverage distributional metrics that capture users' varied preferences, show statistically significant improvements in distributional alignment over random sampling and static preset baselines. These results indicate that LLMs could function as "artificial equalizers," contributing to the development of more accessible, context-aware, and expert-level audio tuning methods.

---

### Improving Symbolic Translation of Language Models for Logical Reasoning

Authors: Ramya Keerthy Thatikonda, Jiuzhou Han, Wray Buntine, Ehsan Shareghi
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09446v1

The use of formal language for deductive logical reasoning aligns well with language models (LMs), where translating natural language (NL) into first-order logic (FOL) and employing an external solver results in a verifiable and therefore reliable reasoning system. However, smaller LMs often struggle with this translation task, frequently producing incorrect symbolic outputs due to formatting and translation errors. Existing approaches typically rely on self-iteration to correct these errors, but such methods depend heavily on the capabilities of the underlying model. To address this, we first categorize common errors and fine-tune smaller LMs using data synthesized by large language models. The evaluation is performed using the defined error categories. We introduce incremental inference, which divides inference into two stages, predicate generation and FOL translation, providing greater control over model behavior and enhancing generation quality as measured by predicate metrics. This decomposition framework also enables the use of a verification module that targets predicate-arity errors to further improve performance. Our study evaluates three families of models across four logical-reasoning datasets. The comprehensive fine-tuning, incremental inference, and verification modules reduce error rates, increase predicate coverage, and improve reasoning performance for smaller LMs, moving us closer to developing reliable and accessible symbolic-reasoning systems.

---

### Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models

Authors: Minh Vu Pham, Hsuvas Borkakoty, Yufang Hou
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09445v2

In language models (LMs), intra-memory knowledge conflict arises when inconsistent information about the same subject is encoded within the model's parametric knowledge. Prior work has primarily focused on resolving conflicts between a model's internal knowledge and external sources, which is known as context-memory knowledge conflict, through approaches such as fine-tuning or knowledge editing, while the understanding of conflicts that arise internally remains largely unexplored. In this work, we design a framework to identify where internal conflicting knowledge is encoded within LMs. We test our framework on four LMs using both synthetic and real-world knowledge conflicts. We find that internal conflicts often arise and are resolved in the final layers across all models, but that interventions are markedly less effective on real-world knowledge conflicts. Targeted attention-head interventions outperform layer-wise ones, and a filtering analysis shows that heads specialized for a single competing fact are far more common in synthetic conflicts, helping explain this gap. Finally, we find no evidence of a single universal circuit for handling knowledge conflict. Instead, our results suggest that distinct circuits may separately encode competing pieces of knowledge, giving rise to conflict. Our results offer a first mechanistic account of intra-memory conflict resolution and highlight a substantial gap between synthetic and real-world settings.

---

### Where Knowledge Collides: A Mechanistic Study of Intra-Memory Knowledge Conflict in Language Models

Authors: Minh Vu Pham, Hsuvas Borkakoty, Yufang Hou
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09445v1

In language models (LMs), intra-memory knowledge conflict largely arises when inconsistent information about the same event is encoded within the model's parametric knowledge. While prior work has primarily focused on resolving conflicts between a model's internal knowledge and external resources through approaches such as fine-tuning or knowledge editing, the problem of localizing conflicts that originate during pre-training within the model's internal representations remain unexplored. In this work, we design a framework based on mechanistic interpretability methods to identify where and how conflicting knowledge from the pre-training data is encoded within LMs. Our findings contribute to a growing body of evidence that specific internal components of a language model are responsible for encoding conflicting knowledge from pre-training, and we demonstrate how mechanistic interpretability methods can be leveraged to causally intervene in and control conflicting knowledge at inference time.

---

### DeepLight: A Sobolev-trained Image-to-Image Surrogate Model for Light Transport in Tissue

Authors: Philipp Haim, Vasilis Ntziachristos, Torsten Enßlin, Dominik Jüstel
Published: 2026-01-14
Categories: cs.LG, physics.med-ph
arXiv: https://arxiv.org/abs/2601.09439v1

In optoacoustic imaging, recovering the absorption coefficients of tissue by inverting the light transport remains a challenging problem. Improvements in solving this problem can greatly benefit the clinical value of optoacoustic imaging. Existing variational inversion methods require an accurate and differentiable model of this light transport. As neural surrogate models allow fast and differentiable simulations of complex physical processes, they are considered promising candidates to be used in solving such inverse problems. However, there are in general no guarantees that the derivatives of these surrogate models accurately match those of the underlying physical operator. As accurate derivatives are central to solving inverse problems, errors in the model derivative can considerably hinder high fidelity reconstructions. To overcome this limitation, we present a surrogate model for light transport in tissue that uses Sobolev training to improve the accuracy of the model derivatives. Additionally, the form of Sobolev training we used is suitable for high-dimensional models in general. Our results demonstrate that Sobolev training for a light transport surrogate model not only improves derivative accuracy but also reduces generalization error for in-distribution and out-of-distribution samples. These improvements promise to considerably enhance the utility of the surrogate model in downstream tasks, especially in solving inverse problems.

---

### Do Transformers Understand Ancient Roman Coin Motifs Better than CNNs?

Authors: David Reid, Ognjen Arandjelovic
Published: 2026-01-14
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.09433v1

Automated analysis of ancient coins has the potential to help researchers extract more historical insights from large collections of coins and to help collectors understand what they are buying or selling. Recent research in this area has shown promise in focusing on identification of semantic elements as they are commonly depicted on ancient coins, by using convolutional neural networks (CNNs). This paper is the first to apply the recently proposed Vision Transformer (ViT) deep learning architecture to the task of identification of semantic elements on coins, using fully automatic learning from multi-modal data (images and unstructured text). This article summarises previous research in the area, discusses the training and implementation of ViT and CNN models for ancient coins analysis and provides an evaluation of their performance. The ViT models were found to outperform the newly trained CNN models in accuracy.

---

### Video-MSR: Benchmarking Multi-hop Spatial Reasoning Capabilities of MLLMs

Authors: Rui Zhu, Xin Shen, Shuchen Wu, Chenxi Miao, Xin Yu, Yang Li, Weikang Li, Deguo Xia, Jizhou Huang
Published: 2026-01-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09430v1

Spatial reasoning has emerged as a critical capability for Multimodal Large Language Models (MLLMs), drawing increasing attention and rapid advancement. However, existing benchmarks primarily focus on single-step perception-to-judgment tasks, leaving scenarios requiring complex visual-spatial logical chains significantly underexplored. To bridge this gap, we introduce Video-MSR, the first benchmark specifically designed to evaluate Multi-hop Spatial Reasoning (MSR) in dynamic video scenarios. Video-MSR systematically probes MSR capabilities through four distinct tasks: Constrained Localization, Chain-based Reference Retrieval, Route Planning, and Counterfactual Physical Deduction. Our benchmark comprises 3,052 high-quality video instances with 4,993 question-answer pairs, constructed via a scalable, visually-grounded pipeline combining advanced model generation with rigorous human verification. Through a comprehensive evaluation of 20 state-of-the-art MLLMs, we uncover significant limitations, revealing that while models demonstrate proficiency in surface-level perception, they exhibit distinct performance drops in MSR tasks, frequently suffering from spatial disorientation and hallucination during multi-step deductions. To mitigate these shortcomings and empower models with stronger MSR capabilities, we further curate MSR-9K, a specialized instruction-tuning dataset, and fine-tune Qwen-VL, achieving a +7.82% absolute improvement on Video-MSR. Our results underscore the efficacy of multi-hop spatial instruction data and establish Video-MSR as a vital foundation for future research. The code and data will be available at https://github.com/ruiz-nju/Video-MSR.

---

### Draw it like Euclid: Teaching transformer models to generate CAD profiles using ruler and compass construction steps

Authors: Siyi Li, Joseph G. Lambourne, Longfei Zhang, Pradeep Kumar Jayaraman, Karl. D. D. Willis
Published: 2026-01-14
Categories: cs.LG, cs.GR
arXiv: https://arxiv.org/abs/2601.09428v1

We introduce a new method of generating Computer Aided Design (CAD) profiles via a sequence of simple geometric constructions including curve offsetting, rotations and intersections. These sequences start with geometry provided by a designer and build up the points and curves of the final profile step by step. We demonstrate that adding construction steps between the designer's input geometry and the final profile improves generation quality in a similar way to the introduction of a chain of thought in language models. Similar to the constraints in a parametric CAD model, the construction sequences reduce the degrees of freedom in the modeled shape to a small set of parameter values which can be adjusted by the designer, allowing parametric editing with the constructed geometry evaluated to floating point precision. In addition we show that applying reinforcement learning to the construction sequences gives further improvements over a wide range of metrics, including some which were not explicitly optimized.

---

### Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing

Authors: Filip Trhlik, Andrew Caines, Paula Buttery
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09421v2

Pre-trained language models (LMs) have, over the last few years, grown substantially in both societal adoption and training costs. This rapid growth in size has constrained progress in understanding and mitigating their biases. Since re-training LMs is prohibitively expensive, most debiasing work has focused on post-hoc or masking-based strategies, which often fail to address the underlying causes of bias. In this work, we seek to democratise pre-model debiasing research by using low-cost proxy models. Specifically, we investigate BabyLMs, compact BERT-like models trained on small and mutable corpora that can approximate bias acquisition and learning dynamics of larger models. We show that BabyLMs display closely aligned patterns of intrinsic bias formation and performance development compared to standard BERT models, despite their drastically reduced size. Furthermore, correlations between BabyLMs and BERT hold across multiple intra-model and post-model debiasing methods. Leveraging these similarities, we conduct pre-model debiasing experiments with BabyLMs, replicating prior findings and presenting new insights regarding the influence of gender imbalance and toxicity on bias formation. Our results demonstrate that BabyLMs can serve as an effective sandbox for large-scale LMs, reducing pre-training costs from over 500 GPU-hours to under 30 GPU-hours. This provides a way to democratise pre-model debiasing research and enables faster, more accessible exploration of methods for building fairer LMs.

---

### Bias Dynamics in BabyLMs: Towards a Compute-Efficient Sandbox for Democratising Pre-Training Debiasing

Authors: Filip Trhlik, Andrew Caines, Paula Buttery
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09421v1

Pre-trained language models (LMs) have, over the last few years, grown substantially in both societal adoption and training costs. This rapid growth in size has constrained progress in understanding and mitigating their biases. Since re-training LMs is prohibitively expensive, most debiasing work has focused on post-hoc or masking-based strategies, which often fail to address the underlying causes of bias. In this work, we seek to democratise pre-model debiasing research by using low-cost proxy models. Specifically, we investigate BabyLMs, compact BERT-like models trained on small and mutable corpora that can approximate bias acquisition and learning dynamics of larger models. We show that BabyLMs display closely aligned patterns of intrinsic bias formation and performance development compared to standard BERT models, despite their drastically reduced size. Furthermore, correlations between BabyLMs and BERT hold across multiple intra-model and post-model debiasing methods. Leveraging these similarities, we conduct pre-model debiasing experiments with BabyLMs, replicating prior findings and presenting new insights regarding the influence of gender imbalance and toxicity on bias formation. Our results demonstrate that BabyLMs can serve as an effective sandbox for large-scale LMs, reducing pre-training costs from over 500 GPU-hours to under 30 GPU-hours. This provides a way to democratise pre-model debiasing research and enables faster, more accessible exploration of methods for building fairer LMs.

---

### Radiomics-Integrated Deep Learning with Hierarchical Loss for Osteosarcoma Histology Classification

Authors: Yaxi Chen, Zi Ye, Shaheer U. Saeed, Oliver Yu, Simin Ni, Jie Huang, Yipeng Hu
Published: 2026-01-14
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.09416v1

Osteosarcoma (OS) is an aggressive primary bone malignancy. Accurate histopathological assessment of viable versus non-viable tumor regions after neoadjuvant chemotherapy is critical for prognosis and treatment planning, yet manual evaluation remains labor-intensive, subjective, and prone to inter-observer variability. Recent advances in digital pathology have enabled automated necrosis quantification. Evaluating on test data, independently sampled on patient-level, revealed that the deep learning model performance dropped significantly from the tile-level generalization ability reported in previous studies. First, this work proposes the use of radiomic features as additional input in model training. We show that, despite that they are derived from the images, such a multimodal input effectively improved the classification performance, in addition to its added benefits in interpretability. Second, this work proposes to optimize two binary classification tasks with hierarchical classes (i.e. tumor-vs-non-tumor and viable-vs-non-viable), as opposed to the alternative ``flat'' three-class classification task (i.e. non-tumor, non-viable tumor, viable tumor), thereby enabling a hierarchical loss. We show that such a hierarchical loss, with trainable weightings between the two tasks, the per-class performance can be improved significantly. Using the TCIA OS Tumor Assessment dataset, we experimentally demonstrate the benefits from each of the proposed new approaches and their combination, setting a what we consider new state-of-the-art performance on this open dataset for this application. Code and trained models: https://github.com/YaxiiC/RadiomicsOS.git.

---

### Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception

Authors: Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian, Hanrong Ye, Ankita Pasad, Szu-wei Fu, Arushi Goel, Ryo Hachiuma, Shizhe Diao, Kunal Dhawan, Sreyan Ghosh, Yusuke Hirota et al.
Published: 2026-01-14
Categories: cs.SD, cs.AI, cs.CL, cs.MA, eess.AS
arXiv: https://arxiv.org/abs/2601.09413v2

We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult external audio perception. Our work is motivated by a crucial yet counterintuitive finding: naively fine-tuning an omni-model on both speech recognition and external sound understanding tasks often degrades performance, as the model can be easily misled by noisy hypotheses. To address this, our framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. This learnable reflection primitive proves effective in preventing the model from being derailed by flawed external candidates. We show that this agentic action mechanism generalizes naturally from speech recognition to complex, multiple-choice audio reasoning. Across the OpenASR leaderboard, Speech-Hands consistently outperforms strong baselines by 12.1% WER on seven benchmarks. The model also achieves 77.37% accuracy and high F1 on audio QA decisions, showing robust generalization and reliability across diverse audio question answering datasets. By unifying perception and decision-making, our work offers a practical path toward more reliable and resilient audio intelligence.

---

### Speech-Hands: A Self-Reflection Voice Agentic Approach to Speech Recognition and Audio Reasoning with Omni Perception

Authors: Zhen Wan, Chao-Han Huck Yang, Jinchuan Tian, Hanrong Ye, Ankita Pasad, Szu-wei Fu, Arushi Goel, Ryo Hachiuma, Shizhe Diao, Kunal Dhawan, Sreyan Ghosh, Yusuke Hirota et al.
Published: 2026-01-14
Categories: cs.SD, cs.AI, cs.CL, cs.MA, eess.AS
arXiv: https://arxiv.org/abs/2601.09413v1

We introduce a voice-agentic framework that learns one critical omni-understanding skill: knowing when to trust itself versus when to consult external audio perception. Our work is motivated by a crucial yet counterintuitive finding: naively fine-tuning an omni-model on both speech recognition and external sound understanding tasks often degrades performance, as the model can be easily misled by noisy hypotheses. To address this, our framework, Speech-Hands, recasts the problem as an explicit self-reflection decision. This learnable reflection primitive proves effective in preventing the model from being derailed by flawed external candidates. We show that this agentic action mechanism generalizes naturally from speech recognition to complex, multiple-choice audio reasoning. Across the OpenASR leaderboard, Speech-Hands consistently outperforms strong baselines by 12.1% WER on seven benchmarks. The model also achieves 77.37% accuracy and high F1 on audio QA decisions, showing robust generalization and reliability across diverse audio question answering datasets. By unifying perception and decision-making, our work offers a practical path toward more reliable and resilient audio intelligence.

---

### Detail Loss in Super-Resolution Models Based on the Laplacian Pyramid and Repeated Upscaling and Downscaling Process

Authors: Sangjun Han, Youngmi Hur
Published: 2026-01-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09410v1

With advances in artificial intelligence, image processing has gained significant interest. Image super-resolution is a vital technology closely related to real-world applications, as it enhances the quality of existing images. Since enhancing fine details is crucial for the super-resolution task, pixels that contribute to high-frequency information should be emphasized. This paper proposes two methods to enhance high-frequency details in super-resolution images: a Laplacian pyramid-based detail loss and a repeated upscaling and downscaling process. Total loss with our detail loss guides a model by separately generating and controlling super-resolution and detail images. This approach allows the model to focus more effectively on high-frequency components, resulting in improved super-resolution images. Additionally, repeated upscaling and downscaling amplify the effectiveness of the detail loss by extracting diverse information from multiple low-resolution features. We conduct two types of experiments. First, we design a CNN-based model incorporating our methods. This model achieves state-of-the-art results, surpassing all currently available CNN-based and even some attention-based models. Second, we apply our methods to existing attention-based models on a small scale. In all our experiments, attention-based models adding our detail loss show improvements compared to the originals. These results demonstrate our approaches effectively enhance super-resolution images across different model structures.

---

### SEEK: Steering LLM Reasoning for RAG via Internal Reasoning Sketches

Authors: Xinze Li, Yuqing Lan, Zhenghao Liu, Haidong Xin, Yukun Yan, Shuo Wang, Zheni Zeng, Sen Mei, Ge Yu, Maosong Sun
Published: 2026-01-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09402v2

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge into the generation process. Benefiting from the reasoning capabilities of LLMs, existing methods have leveraged such capabilities to enable iterative knowledge acquisition and accumulation, thereby better supporting answer generation. However, as the reasoning trajectory grows, the accumulated knowledge and previously generated queries may interfere with subsequent retrieval decisions, resulting in sub-queries with repetitive intents and redundant knowledge acquisition. To address this issue, we propose SEEK, a sketch-guided knowledge acquisition framework for RAG. SEEK first prompts the LLM to construct a structured steering sketch for the given question. It consists of multiple groups of steering gists, with each gist followed by a slot for knowledge filling. Guided by these steering gists, SEEK iteratively retrieves and refines knowledge, and fills the corresponding slots to complete the sketch. The completed sketch is then used as contextual input for final answer generation. Experimental results show that SEEK achieves better performance than baseline models across multiple tasks. Further analyses demonstrate that SEEK can generate more diverse sub-queries, reduce redundant retrieval, and achieve a better balance between external knowledge utilization and internal knowledge conflict mitigation. All codes are available at https://github.com/OpenBMB/PAGER.

---

### Structured Knowledge Representation through Contextual Pages for Retrieval-Augmented Generation

Authors: Xinze Li, Zhenghao Liu, Haidong Xin, Yukun Yan, Shuo Wang, Zheni Zeng, Sen Mei, Ge Yu, Maosong Sun
Published: 2026-01-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09402v1

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by incorporating external knowledge. Recently, some works have incorporated iterative knowledge accumulation processes into RAG models to progressively accumulate and refine query-related knowledge, thereby constructing more comprehensive knowledge representations. However, these iterative processes often lack a coherent organizational structure, which limits the construction of more comprehensive and cohesive knowledge representations. To address this, we propose PAGER, a page-driven autonomous knowledge representation framework for RAG. PAGER first prompts an LLM to construct a structured cognitive outline for a given question, which consists of multiple slots representing a distinct knowledge aspect. Then, PAGER iteratively retrieves and refines relevant documents to populate each slot, ultimately constructing a coherent page that serves as contextual input for guiding answer generation. Experiments on multiple knowledge-intensive benchmarks and backbone models show that PAGER consistently outperforms all RAG baselines. Further analyses demonstrate that PAGER constructs higher-quality and information-dense knowledge representations, better mitigates knowledge conflicts, and enables LLMs to leverage external knowledge more effectively. All code is available at https://github.com/OpenBMB/PAGER.

---

### Preliminary Tests of the Anticipatory Classifier System with Hindsight Experience Replay

Authors: Olgierd Unold, Stanisław Franczyk
Published: 2026-01-14
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.09400v1

This paper introduces ACS2HER, a novel integration of the Anticipatory Classifier System (ACS2) with the Hindsight Experience Replay (HER) mechanism. While ACS2 is highly effective at building cognitive maps through latent learning, its performance often stagnates in environments characterized by sparse rewards. We propose a specific architectural variant that triggers hindsight learning when the agent fails to reach its primary goal, re-labeling visited states as virtual goals to densify the learning signal. The proposed model was evaluated on two benchmarks: the deterministic \texttt{Maze 6} and the stochastic \texttt{FrozenLake}. The results demonstrate that ACS2HER significantly accelerates knowledge acquisition and environmental mastery compared to the standard ACS2. However, this efficiency gain is accompanied by increased computational overhead and a substantial expansion in classifier numerosity. This work provides the first analysis of combining anticipatory mechanisms with retrospective goal-relabeling in Learning Classifier Systems.

---

### Ability Transfer and Recovery via Modularized Parameters Localization

Authors: Songyao Jin, Kun Zhou, Wenqi Li, Peng Wang, Biwei Huang
Published: 2026-01-14
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.09398v1

Large language models can be continually pre-trained or fine-tuned to improve performance in specific domains, languages, or skills, but this specialization often degrades other capabilities and may cause catastrophic forgetting. We investigate how abilities are distributed within LLM parameters by analyzing module activations under domain- and language-specific inputs for closely related models. Across layers and modules, we find that ability-related activations are highly concentrated in a small set of channels (typically <5\%), and these channels are largely disentangled with good sufficiency and stability. Building on these observations, we propose ACT (Activation-Guided Channel-wise Ability Transfer), which localizes ability-relevant channels via activation differences and selectively transfers only the corresponding parameters, followed by lightweight fine-tuning for compatibility. Experiments on multilingual mathematical and scientific reasoning show that ACT can recover forgotten abilities while preserving retained skills. It can also merge multiple specialized models to integrate several abilities into a single model with minimal interference. Our code and data will be publicly released.

---

### FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks

Authors: Renqiang Luo, Huafei Huang, Tao Tang, Jing Ren, Ziqi Xu, Mingliang Hou, Enyan Dai, Feng Xia
Published: 2026-01-14
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2601.09394v2

Graph Transformers (GTs) are increasingly applied to social network analysis, yet their deployment is often constrained by fairness concerns. This issue is particularly critical in incomplete social networks, where sensitive attributes are frequently missing due to privacy and ethical restrictions. Existing solutions commonly generate these incomplete attributes, which may introduce additional biases and further compromise user privacy. To address this challenge, FairGE (Fair Graph Encoding) is introduced as a fairness-aware framework for GTs in incomplete social networks. Instead of generating sensitive attributes, FairGE encodes fairness directly through spectral graph theory. By leveraging the principal eigenvector to represent structural information and padding incomplete sensitive attributes with zeros to maintain independence, FairGE ensures fairness without data reconstruction. Theoretical analysis demonstrates that the method suppresses the influence of non-principal spectral components, thereby enhancing fairness. Extensive experiments on seven real-world social network datasets confirm that FairGE achieves at least a 16% improvement in both statistical parity and equality of opportunity compared with state-of-the-art baselines. The source code is shown in https://github.com/LuoRenqiang/FairGE.

---

### FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks

Authors: Renqiang Luo, Huafei Huang, Tao Tang, Jing Ren, Ziqi Xu, Mingliang Hou, Enyan Dai, Feng Xia
Published: 2026-01-14
Categories: cs.SI, cs.AI
arXiv: https://arxiv.org/abs/2601.09394v1

Graph Transformers (GTs) are increasingly applied to social network analysis, yet their deployment is often constrained by fairness concerns. This issue is particularly critical in incomplete social networks, where sensitive attributes are frequently missing due to privacy and ethical restrictions. Existing solutions commonly generate these incomplete attributes, which may introduce additional biases and further compromise user privacy. To address this challenge, FairGE (Fair Graph Encoding) is introduced as a fairness-aware framework for GTs in incomplete social networks. Instead of generating sensitive attributes, FairGE encodes fairness directly through spectral graph theory. By leveraging the principal eigenvector to represent structural information and padding incomplete sensitive attributes with zeros to maintain independence, FairGE ensures fairness without data reconstruction. Theoretical analysis demonstrates that the method suppresses the influence of non-principal spectral components, thereby enhancing fairness. Extensive experiments on seven real-world social network datasets confirm that FairGE achieves at least a 16% improvement in both statistical parity and equality of opportunity compared with state-of-the-art baselines. The source code is shown in https://github.com/LuoRenqiang/FairGE.

---

### SLAM-LLM: A Modular, Open-Source Multimodal Large Language Model Framework and Best Practice for Speech, Language, Audio and Music Processing

Authors: Ziyang Ma, Guanrou Yang, Wenxi Chen, Zhifu Gao, Yexing Du, Xiquan Li, Zhisheng Zheng, Haina Zhu, Jianheng Zhuo, Zheshu Song, Ruiyang Xu, Tiranrui Wang et al.
Published: 2026-01-14
Categories: cs.SD, cs.CL, cs.MM
arXiv: https://arxiv.org/abs/2601.09385v1

The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and researchers. However, most of the MLLM frameworks take vision as the main input modality, and provide limited in-depth support for the modality of speech, audio, and music. This situation hinders the development of audio-language models, and forces researchers to spend a lot of effort on code writing and hyperparameter tuning. We present SLAM-LLM, an open-source deep learning framework designed to train customized MLLMs, focused on speech, language, audio, and music processing. SLAM-LLM provides a modular configuration of different encoders, projectors, LLMs, and parameter-efficient fine-tuning plugins. SLAM-LLM also includes detailed training and inference recipes for mainstream tasks, along with high-performance checkpoints like LLM-based Automatic Speech Recognition (ASR), Automated Audio Captioning (AAC), and Music Captioning (MC). Some of these recipes have already reached or are nearing state-of-the-art performance, and some relevant techniques have also been accepted by academic papers. We hope SLAM-LLM will accelerate iteration, development, data engineering, and model training for researchers. We are committed to continually pushing forward audio-based MLLMs through this open-source framework, and call on the community to contribute to the LLM-based speech, audio and music processing.

---

### Long-term Task-oriented Agent: Proactive Long-term Intent Maintenance in Dynamic Environments

Authors: Qinglong Shi, Donghai Wang, Hantao Zhou, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He
Published: 2026-01-14
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.09382v1

Current large language model agents predominantly operate under a reactive paradigm, responding only to immediate user queries within short-term sessions. This limitation hinders their ability to maintain long-term user's intents and dynamically adapt to evolving external environments. In this paper, we propose a novel interaction paradigm for proactive Task-oriented Agents capable of bridging the gap between relatively static user's needs and a dynamic environment. We formalize proactivity through two key capabilities, (i) Intent-Conditioned Monitoring: The agent autonomously formulates trigger conditions based on dialog history; (ii) Event-Triggered Follow-up: The agent actively engages the user upon detecting useful environmental updates. We introduce a high-quality data synthesis pipeline to construct complex, multi-turn dialog data in a dynamic environment. Furthermore, we attempt to address the lack of evaluation criteria of task-oriented interaction in a dynamic environment by proposing a new benchmark, namely ChronosBench. We evaluated some leading close-source and open-source models at present and revealed their flaws in long-term task-oriented interaction. Furthermore, our fine-tuned model trained using synthetic data for supervised learning achieves a task completion rate of 85.19% for complex tasks including shifts in user intent, outperforming other models under test. And the result validated the effectiveness of our data-driven strategy.

---

### Query Languages for Machine-Learning Models

Authors: Martin Grohe
Published: 2026-01-14
Categories: cs.LO, cs.AI, cs.DB
arXiv: https://arxiv.org/abs/2601.09381v1

In this paper, I discuss two logics for weighted finite structures: first-order logic with summation (FO(SUM)) and its recursive extension IFP(SUM). These logics originate from foundational work by Grädel, Gurevich, and Meer in the 1990s. In recent joint work with Standke, Steegmans, and Van den Bussche, we have investigated these logics as query languages for machine learning models, specifically neural networks, which are naturally represented as weighted graphs. I present illustrative examples of queries to neural networks that can be expressed in these logics and discuss fundamental results on their expressiveness and computational complexity.

---

### The Imperfective Paradox in Large Language Models

Authors: Bolei Ma, Yusuke Miyao
Published: 2026-01-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09373v2

Do Large Language Models (LLMs) genuinely grasp the compositional semantics of events, or do they rely on surface-level probabilistic heuristics? We investigate the Imperfective Paradox, a logical phenomenon where the past progressive aspect entails event realization for activities (e.g., running $\to$ ran) but not for accomplishments (e.g., building $\nrightarrow$ built). We introduce ImperfectiveNLI, a diagnostic dataset designed to probe this distinction across diverse semantic classes. Evaluating state-of-the-art open-weight models, we uncover a pervasive Teleological Bias: models systematically hallucinate completion for goal-oriented events, even overriding explicit textual cancellation. Prompting interventions partially reduce this bias but trigger a calibration crisis, causing models to incorrectly reject valid entailments for atelic verbs. Representational analyses further show that while internal embeddings often distinguish progressive from simple past forms, inference decisions are dominated by strong priors about goal attainment. Taken together, our findings indicate that these current open-weight LLMs operate as predictive narrative engines rather than faithful logical reasoners, and that resolving aspectual inference requires moving beyond prompting toward structurally grounded alignment.

---

### Relation Extraction Capabilities of LLMs on Clinical Text: A Bilingual Evaluation for English and Turkish

Authors: Aidana Aidynkyzy, Oğuz Dikenelli, Oylum Alatlı, Şebnem Bora
Published: 2026-01-14
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.09367v1

The scarcity of annotated datasets for clinical information extraction in non-English languages hinders the evaluation of large language model (LLM)-based methods developed primarily in English. In this study, we present the first comprehensive bilingual evaluation of LLMs for the clinical Relation Extraction (RE) task in both English and Turkish. To facilitate this evaluation, we introduce the first English-Turkish parallel clinical RE dataset, derived and carefully curated from the 2010 i2b2/VA relation classification corpus. We systematically assess a diverse set of prompting strategies, including multiple in-context learning (ICL) and Chain-of-Thought (CoT) approaches, and compare their performance to fine-tuned baselines such as PURE. Furthermore, we propose Relation-Aware Retrieval (RAR), a novel in-context example selection method based on contrastive learning, that is specifically designed to capture both sentence-level and relation-level semantics. Our results show that prompting-based LLM approaches consistently outperform traditional fine-tuned models. Moreover, evaluations for English performed better than their Turkish counterparts across all evaluated LLMs and prompting techniques. Among ICL methods, RAR achieves the highest performance, with Gemini 1.5 Flash reaching a micro-F1 score of 0.906 in English and 0.888 in Turkish. Performance further improves to 0.918 F1 in English when RAR is combined with a structured reasoning prompt using the DeepSeek-V3 model. These findings highlight the importance of high-quality demonstration retrieval and underscore the potential of advanced retrieval and prompting techniques to bridge resource gaps in clinical natural language processing.

---

### Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs

Authors: Biswesh Mohapatra, Théo Charlot, Giovanni Duca, Mayank Palan, Laurent Romary, Justine Cassell
Published: 2026-01-14
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.09365v2

Common ground plays a critical role in situated spoken dialogs, where interlocutors must establish and maintain shared references to entities, events, and relations to sustain coherent interaction in a shared space and over time. With the increasing presence of embodied conversational agents and social robots, the ability to correctly ground this kind of conversational content in order to refer back later also becomes important for dialog systems. Prior studies have demonstrated that LLMs are capable of performing certain grounding acts like acknowledgments. However, relatively little work has investigated their capacity to leverage the grounded information, like in complex scenarios involving space and time (e.g., "let's go to that café near the park we went to yesterday"). To that end, in this work, we evaluate a model's ability to establish common ground by utilizing these "relational references" in the dynamic and shared environments of situated dialogs. We then test multiple methods for representing common ground and further propose approaches to improve their performance by using reinforcement learning on our synthetically generated dialog data .

---

### GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR

Authors: Jiaying Zhang, Lei Shi, Jiguo Li, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He
Published: 2026-01-14
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.09361v4

Reinforcement Learning with Verifiable Rewards (RLVR) is a key paradigm for improving large-scale reasoning models. Unlike supervised fine-tuning (SFT), RLVR exhibits distinct optimization dynamics and is sensitive to the preservation of pre-trained geometric structures. However, existing parameter-efficient methods face key limitations in this regime. Low-rank adaptation methods, such as PiSSA, are primarily designed for Supervised Fine-Tuning (SFT) and do not account for the distinct optimization dynamics and geometric structures of RLVR. Conversely, directly fine-tuning the unstructured sparse parameter subspace favored by RLVR encounters efficiency bottlenecks on modern hardware. To address these challenges, we propose GeoRA (Geometry-Aware Low-Rank Adaptation), a low-rank adaptation method tailored for RLVR. Specifically, GeoRA exploits the anisotropic and compressible structure of RL update subspace, and extracts its principal directions via Singular Value Decomposition (SVD) to initialize low-rank adapters, while freezing residual components as a structural anchor during training. This design preserves the pre-trained structure and enables efficient dense computation. Experiments on Qwen and Llama models from 1.5B to 32B parameters show that GeoRA consistently outperforms strong low-rank baselines across RLVR settings in mathematics, medicine, and coding, while showing stronger generalization and less forgetting on out-of-domain tasks.

---

### Measuring the benefits of lying in MARA under egalitarian social welfare

Authors: Jonathan Carrero, Ismael Rodriguez, Fernando Rubio
Published: 2026-01-14
Categories: cs.GT, cs.NE
arXiv: https://arxiv.org/abs/2601.09354v1

When some resources are to be distributed among a set of agents following egalitarian social welfare, the goal is to maximize the utility of the agent whose utility turns out to be minimal. In this context, agents can have an incentive to lie about their actual preferences, so that more valuable resources are assigned to them. In this paper we analyze this situation, and we present a practical study where genetic algorithms are used to assess the benefits of lying under different situations.

---

### Monte-Carlo Tree Search with Neural Network Guidance for Lane-Free Autonomous Driving

Authors: Ioannis Peridis, Dimitrios Troullinos, Georgios Chalkiadakis, Pantelis Giankoulidis, Ioannis Papamichail, Markos Papageorgiou
Published: 2026-01-14
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.09353v1

Lane-free traffic environments allow vehicles to better harness the lateral capacity of the road without being restricted to lane-keeping, thereby increasing the traffic flow rates. As such, we have a distinct and more challenging setting for autonomous driving. In this work, we consider a Monte-Carlo Tree Search (MCTS) planning approach for single-agent autonomous driving in lane-free traffic, where the associated Markov Decision Process we formulate is influenced from existing approaches tied to reinforcement learning frameworks. In addition, MCTS is equipped with a pre-trained neural network (NN) that guides the selection phase. This procedure incorporates the predictive capabilities of NNs for a more informed tree search process under computational constraints. In our experimental evaluation, we consider metrics that address both safety (through collision rates) and efficacy (through measured speed). Then, we examine: (a) the influence of isotropic state information for vehicles in a lane-free environment, resulting in nudging behaviour--vehicles' policy reacts due to the presence of faster tailing ones, (b) the acceleration of performance for the NN-guided variant of MCTS, and (c) the trade-off between computational resources and solution quality.

---

### Spectral Complex Autoencoder Pruning: A Fidelity-Guided Criterion for Extreme Structured Channel Compression

Authors: Wei Liu, Xing Deng, Haijian Shao, Yingtao Jiang
Published: 2026-01-14
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.09352v1

We propose Spectral Complex Autoencoder Pruning (SCAP), a reconstruction-based criterion that measures functional redundancy at the level of individual output channels. For each convolutional layer, we construct a complex interaction field by pairing the full multi-channel input activation as the real part with a single output-channel activation (spatially aligned and broadcast across input channels) as the imaginary part. We transform this complex field to the frequency domain and train a low-capacity autoencoder to reconstruct normalized spectra. Channels whose spectra are reconstructed with high fidelity are interpreted as lying close to a low-dimensional manifold captured by the autoencoder and are therefore more compressible; conversely, channels with low fidelity are retained as they encode information that cannot be compactly represented by the learned manifold. This yields an importance score (optionally fused with the filter L1 norm) that supports simple threshold-based pruning and produces a structurally consistent pruned network. On VGG16 trained on CIFAR-10, at a fixed threshold of 0.6, we obtain 90.11% FLOP reduction and 96.30% parameter reduction with an absolute Top-1 accuracy drop of 1.67% from a 93.44% baseline after fine-tuning, demonstrating that spectral reconstruction fidelity of complex interaction fields is an effective proxy for channel-level redundancy under aggressive compression.

---

### Navigating Ethical AI Challenges in the Industrial Sector: Balancing Innovation and Responsibility

Authors: Ruomu Tan, Martin W Hoffmann
Published: 2026-01-14
Categories: cs.CY, cs.AI
arXiv: https://arxiv.org/abs/2601.09351v1

The integration of artificial intelligence (AI) into the industrial sector has not only driven innovation but also expanded the ethical landscape, necessitating a reevaluation of principles governing technology and its applications and awareness in research and development of industrial AI solutions. This chapter explores how AI-empowered industrial innovation inherently intersects with ethics, as advancements in AI introduce new challenges related to transparency, accountability, and fairness. In the chapter, we then examine the ethical aspects of several examples of AI manifestation in industrial use cases and associated factors such as ethical practices in the research and development process and data sharing. With the progress of ethical industrial AI solutions, we emphasize the importance of embedding ethical principles into industrial AI systems and its potential to inspire technological breakthroughs and foster trust among stakeholders. This chapter also offers actionable insights to guide industrial research and development toward a future where AI serves as an enabler for ethical and responsible industrial progress as well as a more inclusive industrial ecosystem.

---