# Research Papers — 2026-01 · bundle page 160 of 189

> Full-text markdown of papers #7951–8000 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/160
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/159.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/161.md)

### From Implicit to Explicit: Token-Efficient Logical Supervision for Mathematical Reasoning in LLMs

Authors: Shaojie Wang, Liang Zhang
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03682v2

Recent studies reveal that large language models (LLMs) exhibit limited logical reasoning abilities in mathematical problem-solving, instead often relying on pattern-matching and memorization. We systematically analyze this limitation, focusing on logical relationship understanding, which is a core capability underlying genuine logical reasoning, and reveal that errors related to this capability account for over 90\% of incorrect predictions, with Chain-of-Thought Supervised Fine-Tuning (CoT-SFT) failing to substantially reduce these errors. To address this bottleneck, we propose First-Step Logical Reasoning (FSLR), a lightweight training framework targeting logical relationship understanding. Our key insight is that the first planning step-identifying which variables to use and which operation to apply-encourages the model to derive logical relationships directly from the problem statement. By training models on this isolated step, FSLR provides explicit supervision for logical relationship understanding, unlike CoT-SFT which implicitly embeds such relationships within complete solution trajectories. Extensive experiments across multiple models and datasets demonstrate that FSLR consistently outperforms CoT-SFT under both in-distribution and out-of-distribution settings, with average improvements of 3.2\% and 4.6\%, respectively. Moreover, FSLR achieves 4-6x faster training and reduces training token consumption by over 80\%.

---

### Accounting for Optimal Control in the Sizing of Isolated Hybrid Renewable Energy Systems Using Imitation Learning

Authors: Simon Halvdansson, Lucas Ferreira Bernardino, Brage Rugstad Knudsen
Published: 2026-01-07
Categories: eess.SY, cs.LG
arXiv: https://arxiv.org/abs/2601.03679v2

Decarbonization of isolated or off-grid energy systems through phase-in of large shares of intermittent solar or wind generation requires co-installation of energy storage or continued use of existing fossil dispatchable power sources to balance supply and demand. The effective CO2 emission reduction depends on the relative capacity of the energy storage and renewable sources, the stochasticity of the renewable generation, and the control of the isolated energy system. While the operation of the energy storage and dispatchable sources impacts the optimal sizing of the system, it is challenging to account for the effect of finite-horizon optimal control at the stage of system sizing. In this work, we present a flexible and computationally efficient sizing framework for energy storage and renewable capacity in isolated energy systems, accounting for uncertainty in the renewable generation and the optimal control. We implement an imitation learning approach to stochastic neural model predictive control (MPC) which allows us to relate the battery storage and wind peak capacities to the emissions reduction and investment costs while accounting for finite horizon, optimal control without solving an infeasible number of optimization problems. We evaluate the proposed sizing framework on a case study of an offshore energy system with a gas turbine, a wind farm and a battery energy storage system (BESS). In this case, we find a nonlinear, nontrivial relationship between the investment costs and the reduction in gas usage for different wind and BESS capacities.

---

### Towards Compositional Generalization of LLMs via Skill Taxonomy Guided Data Synthesis

Authors: Yifan Wei, Li Du, Xiaoyan Yu, Yang Feng, Angsheng Li
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03676v1

Large Language Models (LLMs) and agent-based systems often struggle with compositional generalization due to a data bottleneck in which complex skill combinations follow a long-tailed, power-law distribution, limiting both instruction-following performance and generalization in agent-centric tasks. To address this challenge, we propose STEPS, a Skill Taxonomy guided Entropy-based Post-training data Synthesis framework for generating compositionally challenging data. STEPS explicitly targets compositional generalization by uncovering latent relationships among skills and organizing them into an interpretable, hierarchical skill taxonomy using structural information theory. Building on this taxonomy, we formulate data synthesis as a constrained information maximization problem, selecting skill combinations that maximize marginal structural information within the hierarchy while preserving semantic coherence. Experiments on challenging instruction-following benchmarks show that STEPS outperforms existing data synthesis baselines, while also yielding improved compositional generalization in downstream agent-based evaluations.

---

### Disentangling Aleatoric and Epistemic Uncertainty in Physics-Informed Neural Networks. Application to Insulation Material Degradation Prognostics

Authors: Ibai Ramirez, Jokin Alcibar, Joel Pino, Mikel Sanz, Jose I. Aizpurua
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03673v2

Physics-Informed Neural Networks (PINNs) provide a framework for integrating physical laws with data. However, their application to Prognostics and Health Management (PHM) remains constrained by the limited uncertainty quantification (UQ) capabilities. Most existing PINN-based prognostics approaches are deterministic or account only for epistemic uncertainty, limiting their suitability for risk-aware decision-making. This work introduces a heteroscedastic Bayesian Physics-Informed Neural Network (B-PINN) framework that jointly models epistemic and aleatoric uncertainty, yielding full predictive posteriors for spatiotemporal insulation material ageing estimation. The approach integrates Bayesian Neural Networks (BNNs) with physics-based residual enforcement and prior distributions, enabling probabilistic inference within a physics-informed learning architecture. The framework is evaluated on transformer insulation ageing application, validated with a finite-element thermal model and field measurements from a solar power plant, and benchmarked against deterministic PINNs, dropout-based PINNs (d-PINNs), and alternative B-PINN variants. Results show that the proposed B-PINN provides improved predictive accuracy and better-calibrated uncertainty estimates than competing approaches. A systematic sensitivity study further analyzes the impact of boundary-condition, initial-condition, and residual sampling strategies on accuracy, calibration, and generalization, and the influence of measurement noise on aleatoric uncertainty. Overall, the findings highlight the capability of Bayesian physics-informed learning to support uncertainty-aware prognostics and informed decision-making in transformer asset management by tracking aleatoric and epistemic sources of uncertainty.

---

### Sandwich Reasoning: An Answer-Reasoning-Answer Approach for Low-Latency Query Correction

Authors: Chen Zhang, Kepu Zhang, Jiatong Zhang, Xiao Zhang, Jun Xu
Published: 2026-01-07
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.03672v1

Query correction is a critical entry point in modern search pipelines, demanding high accuracy strictly within real-time latency constraints. Chain-of-Thought (CoT) reasoning improves accuracy but incurs prohibitive latency for real-time query correction. A potential solution is to output an answer before reasoning to reduce latency; however, under autoregressive decoding, the early answer is independent of subsequent reasoning, preventing the model from leveraging its reasoning capability to improve accuracy. To address this issue, we propose Sandwich Reasoning (SandwichR), a novel approach that explicitly aligns a fast initial answer with post-hoc reasoning, enabling low-latency query correction without sacrificing reasoning-aware accuracy. SandwichR follows an Answer-Reasoning-Answer paradigm, producing an initial correction, an explicit reasoning process, and a final refined correction. To align the initial answer with post-reasoning insights, we design a consistency-aware reinforcement learning (RL) strategy: a dedicated consistency reward enforces alignment between the initial and final corrections, while margin-based rejection sampling prioritizes borderline samples where reasoning drives the most impactful corrective gains. Additionally, we construct a high-quality query correction dataset, addressing the lack of specialized benchmarks for complex query correction. Experimental results demonstrate that SandwichR achieves SOTA accuracy comparable to standard CoT while delivering a 40-70% latency reduction, resolving the latency-accuracy trade-off in online search.

---

### NeuronScope: A Multi-Agent Framework for Explaining Polysemantic Neurons in Language Models

Authors: Weiqi Liu, Yongliang Miao, Haiyan Zhao, Yanguang Liu, Mengnan Du
Published: 2026-01-07
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.03671v1

Neuron-level interpretation in large language models (LLMs) is fundamentally challenged by widespread polysemanticity, where individual neurons respond to multiple distinct semantic concepts. Existing single-pass interpretation methods struggle to faithfully capture such multi-concept behavior. In this work, we propose NeuronScope, a multi-agent framework that reformulates neuron interpretation as an iterative, activation-guided process. NeuronScope explicitly deconstructs neuron activations into atomic semantic components, clusters them into distinct semantic modes, and iteratively refines each explanation using neuron activation feedback. Experiments demonstrate that NeuronScope uncovers hidden polysemanticity and produces explanations with significantly higher activation correlation compared to single-pass baselines.

---

### DisastQA: A Comprehensive Benchmark for Evaluating Question Answering in Disaster Management

Authors: Zhitong Chen, Kai Yin, Xiangjue Dong, Chengkai Liu, Xiangpeng Li, Yiming Xiao, Bo Li, Junwei Ma, Ali Mostafavi, James Caverlee
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03670v1

Accurate question answering (QA) in disaster management requires reasoning over uncertain and conflicting information, a setting poorly captured by existing benchmarks built on clean evidence. We introduce DisastQA, a large-scale benchmark of 3,000 rigorously verified questions (2,000 multiple-choice and 1,000 open-ended) spanning eight disaster types. The benchmark is constructed via a human-LLM collaboration pipeline with stratified sampling to ensure balanced coverage. Models are evaluated under varying evidence conditions, from closed-book to noisy evidence integration, enabling separation of internal knowledge from reasoning under imperfect information. For open-ended QA, we propose a human-verified keypoint-based evaluation protocol emphasizing factual completeness over verbosity. Experiments with 20 models reveal substantial divergences from general-purpose leaderboards such as MMLU-Pro. While recent open-weight models approach proprietary systems in clean settings, performance degrades sharply under realistic noise, exposing critical reliability gaps for disaster response. All code, data, and evaluation resources are available at https://github.com/TamuChen18/DisastQA_open.

---

### eTracer: Polarity-Aware Evidence Grounding

Authors: Bohao Chu, Qianli Wang, Hendrik Damm, Shuning Zhang, Hui Wang, Andrea Papenmeier, Georg Lodde, Elisabeth Livingstone, Christoph M. Friedrich, Norbert Fuhr
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03669v2

Evidence grounding makes generated content verifiable by linking statements to their sources. However, effective verifiability requires two properties that existing methods fail to jointly provide: verification granularity, the ability to localize fine-grained evidence for each statement, and verification completeness, the ability to capture both support and contradiction. Existing methods either operate at granularities too coarse for rapid inspection or are support-only. We formalize polarity-aware evidence grounding: linking each response sentence to its contextual evidence with a supporting, contradicting, or irrelevant label. We construct eTracer-Bench, a human-annotated benchmark with 7,905 supporting and contradicting sentence pairs across seven domains, covering both explicit and implicit contradictions. We further propose eTracer, a post-hoc framework whose context-aware signed scorer recovers the full evidence map in a single forward pass per response, with localization and polarity emerging jointly from one mechanism. eTracer achieves the best overall Citation F1 of 82.39, driven by a Contradict F1 of 89.20. A pre-registered within-subjects user study (n = 30) shows that polarity-aware grounding nearly doubles contradiction detection over the document-level baseline (27.9% to 51.9%, Cohen's d = 0.82, p = 0.0003), and suggests a false-completeness bias under which support-only grounding fails to improve over this baseline (23.4% vs. 27.9%). Dataset and code: https://github.com/chubohao/eTracer.

---

### Discontinuous Galerkin finite element operator network for solving non-smooth PDEs

Authors: Kapil Chawla, Youngjoon Hong, Jae Yong Lee, Sanghyun Lee
Published: 2026-01-07
Categories: math.NA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.03668v1

We introduce Discontinuous Galerkin Finite Element Operator Network (DG--FEONet), a data-free operator learning framework that combines the strengths of the discontinuous Galerkin (DG) method with neural networks to solve parametric partial differential equations (PDEs) with discontinuous coefficients and non-smooth solutions. Unlike traditional operator learning models such as DeepONet and Fourier Neural Operator, which require large paired datasets and often struggle near sharp features, our approach minimizes the residual of a DG-based weak formulation using the Symmetric Interior Penalty Galerkin (SIPG) scheme. DG-FEONet predicts element-wise solution coefficients via a neural network, enabling data-free training without the need for precomputed input-output pairs. We provide theoretical justification through convergence analysis and validate the model's performance on a series of one- and two-dimensional PDE problems, demonstrating accurate recovery of discontinuities, strong generalization across parameter space, and reliable convergence rates. Our results highlight the potential of combining local discretization schemes with machine learning to achieve robust, singularity-aware operator approximation in challenging PDE settings.

---

### TRec: Learning Hand-Object Interactions through 2D Point Track Motion

Authors: Dennis Holzmann, Sven Wachsmuth
Published: 2026-01-07
Categories: cs.CV, cs.LG
arXiv: https://arxiv.org/abs/2601.03667v3

We present a novel approach for hand-object action recognition that leverages 2D point tracks as an additional motion cue. While most existing methods rely on RGB appearance, human pose estimation, or their combination, our work demonstrates that tracking randomly sampled image points across video frames can substantially improve recognition accuracy. Unlike prior approaches, we do not detect hands, objects, or interaction regions. Instead, we employ CoTracker to follow a set of randomly initialized points through each video and use the resulting trajectories, together with the corresponding image frames, as input to a Transformer-based recognition model. Surprisingly, our method achieves notable gains even when only the initial frame and the point tracks are provided, without incorporating the full video sequence. Experimental results confirm that integrating 2D point tracks consistently enhances performance compared to the same model trained without motion information, highlighting their potential as a lightweight yet effective representation for hand-object action understanding.

---

### e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings

Authors: Haonan Chen, Sicheng Gao, Radu Timofte, Tetsuya Sakai, Zhicheng Dou
Published: 2026-01-07
Categories: cs.CL, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.03666v2

Modern information systems often involve different types of items, e.g., a text query, an image, a video clip, or an audio segment. This motivates omni-modal embedding models that map heterogeneous modalities into a shared space for direct comparison. However, most recent omni-modal embeddings still rely heavily on implicit alignment inherited from pretrained vision-language model (VLM) backbones. In practice, this causes three common issues: (i) similarity logits have modality-dependent sharpness, so scores are not on a consistent scale; (ii) in-batch negatives become less effective over time because mixed-modality batches create an imbalanced hardness distribution; as a result, many negatives quickly become trivial and contribute little gradient; and (iii) embeddings across modalities show mismatched first- and second-order statistics, which makes rankings less stable. To tackle these problems, we propose e5-omni, a lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. e5-omni combines three simple components: (1) modality-aware temperature calibration to align similarity scales, (2) a controllable negative curriculum with debiasing to focus on confusing negatives while reducing the impact of false negatives, and (3) batch whitening with covariance regularization to better match cross-modal geometry in the shared embedding space. Experiments on MMEB-V2 and AudioCaps show consistent gains over strong bi-modal and omni-modal baselines, and the same recipe also transfers well to other VLM backbones. We release our model checkpoint at https://huggingface.co/Haon-Chen/e5-omni-7B.

---

### PhysVideoGenerator: Towards Physically Aware Video Generation via Latent Physics Guidance

Authors: Siddarth Nilol Kundur Satish, Devesh Jaiswal, Hongyu Chen, Abhishek Bakshi
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03665v1

Current video generation models produce high-quality aesthetic videos but often struggle to learn representations of real-world physics dynamics, resulting in artifacts such as unnatural object collisions, inconsistent gravity, and temporal flickering. In this work, we propose PhysVideoGenerator, a proof-of-concept framework that explicitly embeds a learnable physics prior into the video generation process. We introduce a lightweight predictor network, PredictorP, which regresses high-level physical features extracted from a pre-trained Video Joint Embedding Predictive Architecture (V-JEPA 2) directly from noisy diffusion latents. These predicted physics tokens are injected into the temporal attention layers of a DiT-based generator (Latte) via a dedicated cross-attention mechanism. Our primary contribution is demonstrating the technical feasibility of this joint training paradigm: we show that diffusion latents contain sufficient information to recover V-JEPA 2 physical representations, and that multi-task optimization remains stable over training. This report documents the architectural design, technical challenges, and validation of training stability, establishing a foundation for future large-scale evaluation of physics-aware generative models.

---

### Stochastic Voronoi Ensembles for Anomaly Detection

Authors: Yang Cao, Sikun Yang, Xuyun Zhang, Yujiu Yang
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03664v2

Anomaly detection aims to identify data instances that deviate significantly from majority of data, which has been widely used in fraud detection, network security, and industrial quality control. Existing methods struggle with datasets exhibiting varying local densities: distance-based methods miss local anomalies, while density-based approaches require careful parameter selection and incur quadratic time complexity. We observe that local anomalies, though indistinguishable under global analysis, become conspicuous when the data space is decomposed into restricted regions and each region is examined independently. Leveraging this geometric insight, we propose SVEAD (Stochastic Voronoi Ensembles Anomaly Detector), which constructs ensemble random Voronoi diagrams and scores points by normalized cell-relative distances weighted by local scale. The proposed method achieves linear time complexity and constant space complexity. Experiments on 45 datasets demonstrate that SVEAD outperforms 12 state-of-the-art approaches.

---

### How Does the Thinking Step Influence Model Safety? An Entropy-based Safety Reminder for LRMs

Authors: Su-Hyeon Kim, Hyundong Jin, Yejin Lee, Yo-Sub Han
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03662v1

Large Reasoning Models (LRMs) achieve remarkable success through explicit thinking steps, yet the thinking steps introduce a novel risk by potentially amplifying unsafe behaviors. Despite this vulnerability, conventional defense mechanisms remain ineffective as they overlook the unique reasoning dynamics of LRMs. In this work, we find that the emergence of safe-reminding phrases within thinking steps plays a pivotal role in ensuring LRM safety. Motivated by this finding, we propose SafeRemind, a decoding-time defense method that dynamically injects safe-reminding phrases into thinking steps. By leveraging entropy triggers to intervene at decision-locking points, SafeRemind redirects potentially harmful trajectories toward safer outcomes without requiring any parameter updates. Extensive evaluations across five LRMs and six benchmarks demonstrate that SafeRemind substantially enhances safety, achieving improvements of up to 45.5%p while preserving core reasoning utility.

---

### AMIR-GRPO: Inducing Implicit Preference Signals into GRPO

Authors: Amir Hossein Yari, Fajri Koto
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03661v1

Reinforcement learning has become the primary paradigm for aligning large language models (LLMs) on complex reasoning tasks, with group relative policy optimization (GRPO) widely used in large-scale post-training. However, GRPO faces structural limitations in reasoning-heavy settings: sequence-level advantage normalization introduces systematic length bias, penalties for low-quality trajectories are diluted, and the scalar objective discards rich pairwise preference information embedded in within-group reward rankings. As a result, valuable supervision from costly rollouts remains underutilized. We propose AMIR-GRPO, which augments GRPO with an implicit DPO-style contrastive regularizer constructed directly from intra-group reward rankings, requiring no additional annotations. This mechanism amplifies suppression of low-reward trajectories, attenuates response-level length bias, and transforms each rollout group into a denser set of supervision constraints. Across multiple mathematical reasoning benchmarks, AMIR-GRPO consistently outperforms strong GRPO baselines, yields clearer separation between correct and incorrect reasoning chains, and delivers broader coverage gains beyond the subset of instances solved by standard GRPO.

---

### MGPC: Multimodal Network for Generalizable Point Cloud Completion With Modality Dropout and Progressive Decoding

Authors: Jiangyuan Liu, Yuhao Zhao, Hongxuan Ma, Zhe Liu, Jian Wang, Wei Zou
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03660v2

Point cloud completion aims to recover complete 3D geometry from partial observations caused by limited viewpoints and occlusions. Existing learning-based works, including 3D Convolutional Neural Network (CNN)-based, point-based, and Transformer-based methods, have achieved strong performance on synthetic benchmarks. However, due to the limitations of modality, scalability, and generative capacity, their generalization to novel objects and real-world scenarios remains challenging. In this paper, we propose MGPC, a generalizable multimodal point cloud completion framework that integrates point clouds, RGB images, and text within a unified architecture. MGPC introduces an innovative modality dropout strategy, a Transformer-based fusion module, and a novel progressive generator to improve robustness, scalability, and geometric modeling capability. We further develop an automatic data generation pipeline and construct MGPC-1M, a large-scale benchmark with over 1,000 categories and one million training pairs. Extensive experiments on MGPC-1M and in-the-wild data demonstrate that the proposed method consistently outperforms prior baselines and exhibits strong generalization under real-world conditions.

---

### Group and Exclusive Sparse Regularization-based Continual Learning of CNNs

Authors: Basile Tousside, Janis Mohr, Jörg Frochte
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03658v1

We present a regularization-based approach for continual learning (CL) of fixed capacity convolutional neural networks (CNN) that does not suffer from the problem of catastrophic forgetting when learning multiple tasks sequentially. This method referred to as Group and Exclusive Sparsity based Continual Learning (GESCL) avoids forgetting of previous tasks by ensuring the stability of the CNN via a stability regularization term, which prevents filters detected as important for past tasks to deviate too much when learning a new task. On top of that, GESCL makes the network plastic via a plasticity regularization term that leverage the over-parameterization of CNNs to efficiently sparsify the network and tunes unimportant filters making them relevant for future tasks. Doing so, GESCL deals with significantly less parameters and computation compared to CL approaches that either dynamically expand the network or memorize past tasks' data. Experiments on popular CL vision benchmarks show that GESCL leads to significant improvements over state-of-the-art method in terms of overall CL performance, as measured by classification accuracy as well as in terms of avoiding catastrophic forgetting.

---

### In Search of Grandmother Cells: Tracing Interpretable Neurons in Tabular Representations

Authors: Ricardo Knauer, Erik Rodner
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03657v1

Foundation models are powerful yet often opaque in their decision-making. A topic of continued interest in both neuroscience and artificial intelligence is whether some neurons behave like grandmother cells, i.e., neurons that are inherently interpretable because they exclusively respond to single concepts. In this work, we propose two information-theoretic measures that quantify the neuronal saliency and selectivity for single concepts. We apply these metrics to the representations of TabPFN, a tabular foundation model, and perform a simple search across neuron-concept pairs to find the most salient and selective pair. Our analysis provides the first evidence that some neurons in such models show moderate, statistically significant saliency and selectivity for high-level concepts. These findings suggest that interpretable neurons can emerge naturally and that they can, in some cases, be identified without resorting to more complex interpretability techniques.

---

### VideoMemory: Toward Consistent Video Generation via Memory Integration

Authors: Jinsong Zhou, Yihua Du, Xinli Xu, Luozhou Wang, Zijie Zhuang, Yehang Zhang, Shuaibo Li, Xiaojun Hu, Bolan Su, Ying-cong Chen
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03655v1

Maintaining consistent characters, props, and environments across multiple shots is a central challenge in narrative video generation. Existing models can produce high-quality short clips but often fail to preserve entity identity and appearance when scenes change or when entities reappear after long temporal gaps. We present VideoMemory, an entity-centric framework that integrates narrative planning with visual generation through a Dynamic Memory Bank. Given a structured script, a multi-agent system decomposes the narrative into shots, retrieves entity representations from memory, and synthesizes keyframes and videos conditioned on these retrieved states. The Dynamic Memory Bank stores explicit visual and semantic descriptors for characters, props, and backgrounds, and is updated after each shot to reflect story-driven changes while preserving identity. This retrieval-update mechanism enables consistent portrayal of entities across distant shots and supports coherent long-form generation. To evaluate this setting, we construct a 54-case multi-shot consistency benchmark covering character-, prop-, and background-persistent scenarios. Extensive experiments show that VideoMemory achieves strong entity-level coherence and high perceptual quality across diverse narrative sequences.

---

### Hybrid Quantum-Classical Ridgelet Neural Networks for Portfolio Optimization

Authors: Bahadur Yadav, Sanjay Kumar Mohanty
Published: 2026-01-07
Categories: cs.LG, math.OC, math.QA
arXiv: https://arxiv.org/abs/2601.03654v2

In this study, we introduce a quantum computing method that incorporates Ridglet transforms into quantum processing pipelines for financial time-series forecasting with Quantum Approximate Optimization Algorithm (QAOA)-based portfolio optimization. We propose a Quantum Ridgelet Neural Network (QRNN) model for forecasting time-series data that integrates Parametrized Quantum Circuits (PQCs) with ridgelet-based feature transformations and QAOA-based portfolio optimization for asset selection. By breaking down financial time-series data into multi-resolution components, the ridgelet transform enables the identification of both local and global trends. Ridgelet-based features improve the scalability and accuracy of quantum computing by significantly reducing the number of qubits needed. However, the predicted results are turned into a QUBO-based mean-variance optimization problem and solved with QAOA to select the best stocks. Our study begins with a theoretical formulation of the single-qubit system for our proposed model. This formulation is further extended to a multi-qubit system, and we show that it captures a significant fraction of the predictive signal.

---

### SyncThink: A Training-Free Strategy to Align Inference Termination with Reasoning Saturation

Authors: Gengyang Li, Wang Cai, Yifeng Gao, Yunfang Wu
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03649v1

Chain-of-Thought (CoT) prompting improves reasoning but often produces long and redundant traces that substantially increase inference cost. We present SyncThink, a training-free and plug-and-play decoding method that reduces CoT overhead without modifying model weights. We find that answer tokens attend weakly to early reasoning and instead focus on the special token "/think", indicating an information bottleneck. Building on this observation, SyncThink monitors the model's own reasoning-transition signal and terminates reasoning. Experiments on GSM8K, MMLU, GPQA, and BBH across three DeepSeek-R1 distilled models show that SyncThink achieves 62.00 percent average Top-1 accuracy using 656 generated tokens and 28.68 s latency, compared to 61.22 percent, 2141 tokens, and 92.01 s for full CoT decoding. On long-horizon tasks such as GPQA, SyncThink can further yield up to +8.1 absolute accuracy by preventing over-thinking.

---

### ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs

Authors: HanGyeol Yoo, ChangSu Choi, Minjun Kim, Seohyun Song, SeungWoo Song, Inho Won, Jongyoul Park, Cheoneum Park, KyungTae Lim
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03648v2

We propose an efficient layer-specific optimization (ELO) method designed to enhance continual pretraining (CP) for specific languages in multilingual large language models (MLLMs). This approach addresses the common challenges of high computational cost and degradation of source language performance associated with traditional CP. The ELO method consists of two main stages: (1) ELO Pretraining, where a small subset of specific layers, identified in our experiments as the critically important first and last layers, are detached from the original MLLM and trained with the target language. This significantly reduces not only the number of trainable parameters but also the total parameters computed during the forward pass, minimizing GPU memory consumption and accelerating the training process. (2) Layer Alignment, where the newly trained layers are reintegrated into the original model, followed by a brief full fine-tuning step on a small dataset to align the parameters. Experimental results demonstrate that the ELO method achieves a training speedup of up to 6.46 times compared to existing methods, while improving target language performance by up to 6.2\% on qualitative benchmarks and effectively preserving source language (English) capabilities.

---

### ReLA: Representation Learning and Aggregation for Job Scheduling with Reinforcement Learning

Authors: Zhengyi Kwan, Wei Zhang, Aik Beng Ng, Zhengkui Wang, Simon See
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03646v2

Job scheduling is widely used in real-world manufacturing systems to assign ordered job operations to machines under various constraints. Existing solutions remain limited by long running time or insufficient schedule quality, especially when problem scale increases. In this paper, we propose ReLA, a reinforcement-learning (RL) scheduler built on structured representation learning and aggregation. ReLA first learns diverse representations from scheduling entities, including job operations and machines, using two intra-entity learning modules with self-attention and convolution and one inter-entity learning module with cross-attention. These modules are applied in a multi-scale architecture, and their outputs are aggregated to support RL decision-making. Across experiments on small, medium, and large job instances, ReLA achieves the best makespan in most tested settings over the latest solutions. On non-large instances, ReLA reduces the optimality gap of the SOTA baseline by 13.0%, while on large-scale instances it reduces the gap by 78.6%, with the average optimality gaps lowered to 7.3% and 2.1%, respectively. These results confirm that ReLA's learned representations and aggregation provide strong decision support for RL scheduling, and enable fast job completion and decision-making for real-world applications.

---

### LLM-MC-Affect: LLM-Based Monte Carlo Modeling of Affective Trajectories and Latent Ambiguity for Interpersonal Dynamic Insight

Authors: Yu-Zheng Lin, Bono Po-Jen Shih, John Paul Martin Encinas, Elizabeth Victoria Abraham Achom, Karan Himanshu Patel, Jesus Horacio Pacheco, Sicong Shao, Jyotikrishna Dass, Soheil Salehi, Pratik Satam
Published: 2026-01-07
Categories: cs.CL, cs.CY
arXiv: https://arxiv.org/abs/2601.03645v2

Emotional coordination is a core property of human interaction that shapes how relational meaning is constructed in real time. While text-based affect inference has become increasingly feasible, prior approaches often treat sentiment as a deterministic point estimate for individual speakers, failing to capture the inherent subjectivity, latent ambiguity, and sequential coupling found in mutual exchanges. We introduce LLM-MC-Affect, a probabilistic framework that characterizes emotion not as a static label, but as a continuous latent probability distribution defined over an affective space. By leveraging stochastic LLM decoding and Monte Carlo estimation, the methodology approximates these distributions to derive high-fidelity sentiment trajectories that explicitly quantify both central affective tendencies and perceptual ambiguity. These trajectories enable a structured analysis of interpersonal coupling through sequential cross-correlation and slope-based indicators, identifying leading or lagging influences between interlocutors. To validate the interpretive capacity of this approach, we utilize teacher-student instructional dialogues as a representative case study, where our quantitative indicators successfully distill high-level interaction insights such as effective scaffolding. This work establishes a scalable and deployable pathway for understanding interpersonal dynamics, offering a generalizable solution that extends beyond education to broader social and behavioral research.

---

### Agent-Dice: Disentangling Knowledge Updates via Geometric Consensus for Agent Continual Learning

Authors: Zheng Wu, Xingyu Lou, Xinbei Ma, Yansi Li, Weiwen Liu, Weinan Zhang, Jun Wang, Zhuosheng Zhang
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03641v4

Large Language Model (LLM)-based agents significantly extend the utility of LLMs by interacting with dynamic environments. However, enabling agents to continually learn new tasks without catastrophic forgetting remains a critical challenge, known as the stability-plasticity dilemma. In this work, we argue that this dilemma fundamentally arises from the failure to explicitly distinguish between common knowledge shared across tasks and conflicting knowledge introduced by task-specific interference. To address this, we propose Agent-Dice, a parameter fusion framework based on directional consensus evaluation. Concretely, Agent-Dice disentangles knowledge updates through a two-stage process: geometric consensus filtering to prune conflicting gradients, and curvature-based importance weighting to amplify shared semantics. We provide a rigorous theoretical analysis that establishes the validity of the proposed fusion scheme and offers insight into the origins of the stability-plasticity dilemma. Extensive experiments on GUI agents and tool-use agent domains demonstrate that Agent-Dice exhibits outstanding continual learning performance with minimal computational overhead and parameter updates. The codes are available at https://github.com/Wuzheng02/Agent-Dice.

---

### CrackSegFlow: Controllable Flow Matching Synthesis for Generalizable Crack Segmentation with a 50K Image-Mask Benchmark

Authors: Babak Asadi, Peiyang Wu, Mani Golparvar-Fard, Ramez Hajj
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03637v3

Defect segmentation is central to computer vision based inspection of infrastructure assets during both construction and operation. However, deployment remains limited due to scarce pixel-level labels and domain shift across environments. We introduce CrackSegFlow, a controllable Flow Matching synthesis method that renders synthetic images of cracks from masks with pixel-level alignment. Our renderer combines topology-preserving mask injection with edge gating to maintain thin-structure continuity. Class-conditional FM samples masks for topology diversity, and CrackSegFlow renders aligned ground truth images from them. We further inject cracks onto crack-free backgrounds to diversify confounders and reduce false positives. Across five datasets and using a CNN-Transformer backbone, our results demonstrate that adding synthesized pairs improves in-domain performance by +5.37 mIoU and +5.13 F1, while target-guided cross-domain synthesis driven by target mask statistics adds +13.12 mIoU and +14.82 F1. We also release CSF-50K, a benchmark dataset comprising 50,000 image-mask pairs.

---

### Kantorovich-Type Stochastic Neural Network Operators for the Mean-Square Approximation of Certain Second-Order Stochastic Processes

Authors: Sachin Saini, Uaday Singh
Published: 2026-01-07
Categories: cs.LG, math.PR
arXiv: https://arxiv.org/abs/2601.03634v1

Artificial neural network operators (ANNOs) have been widely used for approximating deterministic input-output functions; however, their extension to random dynamics remains comparatively unexplored. In this paper, we construct a new class of \textbf{Kantorovich-type Stochastic Neural Network Operators (K-SNNOs)} in which randomness is incorporated not at the coefficient level, but through \textbf{stochastic neurons} driven by stochastic integrators. This framework enables the operator to inherit the probabilistic structure of the underlying process, making it suitable for modeling and approximating stochastic signals. We establish mean-square convergence of K-SNNOs to the target stochastic process and derive quantitative error estimates expressing the rate of approximation in terms of the modulus of continuity. Numerical simulations further validate the theoretical results by demonstrating accurate reconstruction of sample paths and rapid decay of the mean square error (MSE). Graphical results, including sample-wise approximations and empirical MSE behaviour, illustrate the robustness and effectiveness of the proposed stochastic-neuron-based operator.

---

### MFC-RFNet: A Multi-scale Guided Rectified Flow Network for Radar Sequence Prediction

Authors: Wenjie Luo, Chuanhu Deng, Chaorong Li, Rongyao Deng, Qiang Yang
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03633v2

Accurate and high-resolution precipitation nowcasting from radar echo sequences is crucial for disaster mitigation and economic planning, yet it remains a significant challenge. Key difficulties include modeling complex multi-scale evolution, correcting inter-frame feature misalignment caused by displacement, and efficiently capturing long-range spatiotemporal context without sacrificing spatial fidelity. To address these issues, we present the Multi-scale Feature Communication Rectified Flow (RF) Network (MFC-RFNet), a generative framework that integrates multi-scale communication with guided feature fusion. To enhance multi-scale fusion while retaining fine detail, a Wavelet-Guided Skip Connection (WGSC) preserves high-frequency components, and a Feature Communication Module (FCM) promotes bidirectional cross-scale interaction. To correct inter-frame displacement, a Condition-Guided Spatial Transform Fusion (CGSTF) learns spatial transforms from conditioning echoes to align shallow features. The backbone adopts rectified flow training to learn near-linear probability-flow trajectories, enabling few-step sampling with stable fidelity. Additionally, lightweight Vision-RWKV (RWKV) blocks are placed at the encoder tail, the bottleneck, and the first decoder layer to capture long-range spatiotemporal dependencies at low spatial resolutions with moderate compute. Evaluations on four public datasets (SEVIR, MeteoNet, Shanghai, and CIKM) demonstrate consistent improvements over strong baselines, yielding clearer echo morphology at higher rain-rate thresholds and sustained skill at longer lead times. These results suggest that the proposed synergy of RF training with scale-aware communication, spatial alignment, and frequency-aware fusion presents an effective and robust approach for radar-based nowcasting.

---

### ReStyle-TTS: Relative and Continuous Style Control for Zero-Shot Speech Synthesis

Authors: Haitao Li, Chunxiang Jin, Chenglin Li, Wenhao Guan, Zhengxing Huang, Xie Chen
Published: 2026-01-07
Categories: eess.AS, cs.AI, cs.SD
arXiv: https://arxiv.org/abs/2601.03632v2

Zero-shot text-to-speech models can clone a speaker's timbre from a short reference audio, but they also strongly inherit the speaking style present in the reference. As a result, synthesizing speech with a desired style often requires carefully selecting reference audio, which is impractical when only limited or mismatched references are available. While recent controllable TTS methods attempt to address this issue, they typically rely on absolute style targets and discrete textual prompts, and therefore do not support continuous and reference-relative style control. We propose ReStyle-TTS, a framework that enables continuous and reference-relative style control in zero-shot TTS. Our key insight is that effective style control requires first reducing the model's implicit dependence on reference style before introducing explicit control mechanisms. To this end, we introduce Decoupled Classifier-Free Guidance (DCFG), which independently controls text and reference guidance, reducing reliance on reference style while preserving text fidelity. On top of this, we apply style-specific LoRAs together with Orthogonal LoRA Fusion to enable continuous and disentangled multi-attribute control, and introduce a Timbre Consistency Optimization module to mitigate timbre drift caused by weakened reference guidance. Experiments show that ReStyle-TTS enables user-friendly, continuous, and relative control over pitch, energy, and multiple emotions while maintaining intelligibility and speaker timbre, and performs robustly in challenging mismatched reference-target style scenarios.

---

### Reasoning Model Is Superior LLM-Judge, Yet Suffers from Biases

Authors: Hui Huang, Xuanxin Wu, Muyun Yang, Yuki Arase
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03630v2

This paper presents the first systematic comparison investigating whether Large Reasoning Models (LRMs) are superior judges to non-reasoning LLMs. Our empirical analysis yields four key findings: 1) LRMs outperform non-reasoning LLMs in terms of judgment accuracy, particularly on reasoning-intensive tasks; 2) LRMs demonstrate superior evaluation instruction-following capabilities; 3) LRMs exhibit enhanced robustness against adversarial attacks targeting judgment tasks; 4) However, LRMs still exhibit strong evaluation biases. To mitigate this bias vulnerability, we propose PlanJudge, a lightweight evaluation strategy that prompts the model to generate an explicit evaluation plan before executing the judgment. Despite its simplicity, our experiments demonstrate that PlanJudge significantly mitigates biases in LLM-as-a-Judge while preserving overall judgment accuracy.

---

### Learning Shortest Paths When Data is Scarce

Authors: Dmytro Matsypura, Yu Pan, Hanzhao Wang
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03629v1

Digital twins and other simulators are increasingly used to support routing decisions in large-scale networks. However, simulator outputs often exhibit systematic bias, while ground-truth measurements are costly and scarce. We study a stochastic shortest-path problem in which a planner has access to abundant synthetic samples, limited real-world observations, and an edge-similarity structure capturing expected behavioral similarity across links. We model the simulator-to-reality discrepancy as an unknown, edge-specific bias that varies smoothly over the similarity graph, and estimate it using Laplacian-regularized least squares. This approach yields calibrated edge cost estimates even in data-scarce regimes. We establish finite-sample error bounds, translate estimation error into path-level suboptimality guarantees, and propose a computable, data-driven certificate that verifies near-optimality of a candidate route. For cold-start settings without initial real data, we develop a bias-aware active learning algorithm that leverages the simulator and adaptively selects edges to measure until a prescribed accuracy is met. Numerical experiments on multiple road networks and traffic graphs further demonstrate the effectiveness of our methods.

---

### Evaluating the Pre-Consultation Ability of LLMs using Diagnostic Guidelines

Authors: Jean Seo, Gibaeg Kim, Kihun Shin, Seungseop Lim, Hyunkyung Lee, Wooseok Han, Jongwon Lee, Eunho Yang
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03627v3

We introduce EPAG, a benchmark dataset and framework designed for Evaluating the Pre-consultation Ability of LLMs using diagnostic Guidelines. LLMs are evaluated directly through HPI-diagnostic guideline comparison and indirectly through disease diagnosis. In our experiments, we observe that small open-source models fine-tuned with a well-curated, task-specific dataset can outperform frontier LLMs in pre-consultation. Additionally, we find that increased amount of HPI (History of Present Illness) does not necessarily lead to improved diagnostic performance. Further experiments reveal that the language of pre-consultation influences the characteristics of the dialogue. By open-sourcing our dataset and evaluation pipeline on https://github.com/seemdog/EPAG, we aim to contribute to the evaluation and further development of LLM applications in real-world clinical settings.

---

### Learning from Limited Labels: Transductive Graph Label Propagation for Indian Music Analysis

Authors: Parampreet Singh, Akshay Raina, Sayeedul Islam Sheikh, Vipul Arora
Published: 2026-01-07
Categories: eess.AS, cs.LG
arXiv: https://arxiv.org/abs/2601.03626v1

Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is resource-intensive, laborious, and often require expert domain knowledge. In this work, we explore the use of label propagation (LP), a graph-based semi-supervised learning technique, for automatically labeling the unlabeled set in an unsupervised manner. By constructing a similarity graph over audio embeddings, we propagate limited label information from a small annotated subset to a larger unlabeled corpus in a transductive, semi-supervised setting. We apply this method to two tasks in Indian Art Music (IAM): Raga identification and Instrument classification. For both these tasks, we integrate multiple public datasets along with additional recordings we acquire from Prasar Bharati Archives to perform LP. Our experiments demonstrate that LP significantly reduces labeling overhead and produces higher-quality annotations compared to conventional baseline methods, including those based on pretrained inductive models. These results highlight the potential of graph-based semi-supervised learning to democratize data annotation and accelerate progress in music information retrieval.

---

### Shape Classification using Approximately Convex Segment Features

Authors: Bimal Kumar Ray
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03625v1

The existing object classification techniques based on descriptive features rely on object alignment to compute the similarity of objects for classification. This paper replaces the necessity of object alignment through sorting of feature. The object boundary is normalized and segmented into approximately convex segments and the segments are then sorted in descending order of their length. The segment length, number of extreme points in segments, area of segments, the base and the width of the segments - a bag of features - is used to measure the similarity between image boundaries. The proposed method is tested on datasets and acceptable results are observed.

---

### Architecting Agentic Communities using Design Patterns

Authors: Zoran Milosevic, Fethi Rabhi
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03624v3

The rapid evolution of Large Language Models (LLM) and subsequent Agentic AI technologies requires systematic architectural guidance for building sophisticated, production-grade systems. This paper presents an approach for architecting such systems using design patterns derived from enterprise distributed systems standards, formal methods, and industry practice. We classify these patterns into three tiers: LLM Agents (task-specific automation), Agentic AI (adaptive goal-seekers), and Agentic Communities (organizational frameworks where AI agents and human participants coordinate through formal roles, protocols, and governance structures). We focus on Agentic Communities - coordination frameworks encompassing LLM Agents, Agentic AI entities, and humans - most relevant for enterprise and industrial applications. Drawing on established coordination principles from distributed systems, we ground these patterns in a formal framework that specifies collaboration agreements where AI agents and humans fill roles within governed ecosystems. This approach provides both practical guidance and formal verification capabilities, enabling expression of organizational, legal, and ethical rules through accountability mechanisms that ensure operational and verifiable governance of inter-agent communication, negotiation, and intent modeling. We validate this framework through a clinical trial matching case study. Our goal is to provide actionable guidance to practitioners while maintaining the formal rigor essential for enterprise deployment in dynamic, multi-agent ecosystems.

---

### Systematic Evaluation of Depth Backbones and Semantic Cues for Monocular Pseudo-LiDAR 3D Detection

Authors: Samson Oseiwe Ajadalu
Published: 2026-01-07
Categories: cs.CV, cs.LG, cs.RO
arXiv: https://arxiv.org/abs/2601.03617v1

Monocular 3D object detection offers a low-cost alternative to LiDAR, yet remains less accurate due to the difficulty of estimating metric depth from a single image. We systematically evaluate how depth backbones and feature engineering affect a monocular Pseudo-LiDAR pipeline on the KITTI validation split. Specifically, we compare NeWCRFs (supervised metric depth) against Depth Anything V2 Metric-Outdoor (Base) under an identical pseudo-LiDAR generation and PointRCNN detection protocol. NeWCRFs yields stronger downstream 3D detection, achieving 10.50\% AP$_{3D}$ at IoU$=0.7$ on the Moderate split using grayscale intensity (Exp~2). We further test point-cloud augmentations using appearance cues (grayscale intensity) and semantic cues (instance segmentation confidence). Contrary to the expectation that semantics would substantially close the gap, these features provide only marginal gains, and mask-based sampling can degrade performance by removing contextual geometry. Finally, we report a depth-accuracy-versus-distance diagnostic using ground-truth 2D boxes (including Ped/Cyc), highlighting that coarse depth correctness does not fully predict strict 3D IoU. Overall, under an off-the-shelf LiDAR detector, depth-backbone choice and geometric fidelity dominate performance, outweighing secondary feature injection.

---

### SARA: Stress Test Reasoning in Audio Deepfake Detection

Authors: Binh Nguyen, Charles Fleming, Thai Le
Published: 2026-01-07
Categories: cs.CL, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.03615v2

Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADD), moving beyond \textit{black-box} classifiers by providing transparency to their predictions via reasoning traces. However, such reasoning may not support the model predictions, reflecting poor coherence, or, worse, may rationalize incorrect predictions with plausible but misleading explanation. Moreover, the behavior of ALM reasoning under adversarial attacks remains under-explored, raising questions about the practical reliability of such explanation capabilities. To address this gap, this study introduces \textbf{SARA} (\textbf{S}hift \textbf{A}nalysis of \textbf{R}easoning in \textbf{A}udio), a diagnostic framework that evaluates ALM reasoning across three dimensions: acoustic perception, reasoning-verdict coherence and dissonance. We test five open-source ALMs against both acoustic and linguistic adversarial attacks. We show that acoustic attacks significantly degrade reasoning-verdict coherence (average decrease of 14.20\%), frequently inducing internal logical conflicts. Conversely, linguistic attacks achieve higher attack success rates while maintaining reasoning coherence. We further demonstrate that the textual coherence of generated reasoning traces also serves as a latent indicator of adversarial inputs, enabling effective detection of perturbed audio (0.78 in F1) \textit{without accessing the raw acoustic signal}. These findings suggest that reasoning traces provide diagnostic utility that persists even when final classification outputs are compromised.

---

### Mathematical Foundations of Polyphonic Music Generation via Structural Inductive Bias

Authors: Joonwon Seo
Published: 2026-01-07
Categories: cs.LG, cs.SD, eess.AS
arXiv: https://arxiv.org/abs/2601.03612v8

This monograph addresses the "Missing Middle" problem in AI music generation - the challenge of producing coherent, phrase-level musical structure. Using Beethoven's piano sonatas as a case study, I introduce the Smart Embedding architecture, a factorized representation grounded in the empirically verified independence of pitch and hand attributes (NMI=0.167). The architecture achieves a 48.3% reduction in embedding parameters while improving validation loss by 9.47%. Theoretically, I establish formal guarantees through information theory, Rademacher complexity analysis (yielding a 28.09% tighter generalization bound), and category-theoretic interpretation. These results are further supported by Singular Value Decomposition analysis and a blind expert listening study (N=53). Collectively, this work presents a dual contribution that combines architectural innovation with mathematical rigor, offering a principled framework for building more efficient, stable, and interpretable generative models for complex sequential data.

---

### Investigation into respiratory sound classification for an imbalanced data set using hybrid LSTM-KAN architectures

Authors: Nithinkumar K., Anand R
Published: 2026-01-07
Categories: cs.SD, cs.AI, eess.AS
arXiv: https://arxiv.org/abs/2601.03610v1

Respiratory sounds captured via auscultation contain critical clues for diagnosing pulmonary conditions. Automated classification of these sounds faces challenges due to subtle acoustic differences and severe class imbalance in clinical datasets. This study investigates respiratory sound classification with a focus on mitigating pronounced class imbalance. We propose a hybrid deep learning model that combines a Long Short-Term Memory (LSTM) network for sequential feature encoding with a Kolmogorov-Arnold Network (KAN) for classification. The model is integrated with a comprehensive feature extraction pipeline and targeted imbalance mitigation strategies. Experiments were conducted on a public respiratory sound database comprising six classes with a highly skewed distribution. Techniques such as focal loss, class-specific data augmentation, and Synthetic Minority Over-sampling Technique (SMOTE) were employed to enhance minority class recognition. The proposed Hybrid LSTM-KAN model achieves an overall accuracy of 94.6 percent and a macro-averaged F1 score of 0.703, despite the dominant COPD class accounting for over 86 percent of the data. Improved detection performance is observed for minority classes compared to baseline approaches, demonstrating the effectiveness of the proposed architecture for imbalanced respiratory sound classification.

---

### Unveiling Text in Challenging Stone Inscriptions: A Character-Context-Aware Patching Strategy for Binarization

Authors: Pratyush Jena, Amal Joseph, Arnav Sharma, Ravi Kiran Sarvadevabhatla
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03609v1

Binarization is a popular first step towards text extraction in historical artifacts. Stone inscription images pose severe challenges for binarization due to poor contrast between etched characters and the stone background, non-uniform surface degradation, distracting artifacts, and highly variable text density and layouts. These conditions frequently cause existing binarization techniques to fail and struggle to isolate coherent character regions. Many approaches sub-divide the image into patches to improve text fragment resolution and improve binarization performance. With this in mind, we present a robust and adaptive patching strategy to binarize challenging Indic inscriptions. The patches from our approach are used to train an Attention U-Net for binarization. The attention mechanism allows the model to focus on subtle structural cues, while our dynamic sampling and patch selection method ensures that the model learns to overcome surface noise and layout irregularities. We also introduce a carefully annotated, pixel-precise dataset of Indic stone inscriptions at the character-fragment level. We demonstrate that our novel patching mechanism significantly boosts binarization performance across classical and deep learning baselines. Despite training only on single script Indic dataset, our model exhibits strong zero-shot generalization to other Indic and non-indic scripts, highlighting its robustness and script-agnostic generalization capabilities. By producing clean, structured representations of inscription content, our method lays the foundation for downstream tasks such as script identification, OCR, and historical text analysis. Project page: https://ihdia.iiit.ac.in/shilalekhya-binarization/

---

### Policy-Guided Search on Tree-of-Thoughts for Efficient Problem Solving with Bounded Language Model Queries

Authors: Sumedh Pendurkar, Guni Sharon
Published: 2026-01-07
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.03606v1

Recent studies explored integrating state-space search algorithms with Language Models (LM) to perform look-ahead on the token generation process, the ''Tree-of-Thoughts'' (ToT), generated by LMs, thereby improving performance on problem-solving tasks. However, the affiliated search algorithms often overlook the significant computational costs associated with LM inference, particularly in scenarios with constrained computational budgets. Consequently, we address the problem of improving LM performance on problem-solving tasks under limited computational budgets. We demonstrate how the probabilities assigned to thoughts by LMs can serve as a heuristic to guide search within the ToT framework, thereby reducing the number of thought evaluations. Building on this insight, we adapt a heuristic search algorithm, Levin Tree Search (LTS), to the ToT framework, which leverages LMs as policies to guide the tree exploration efficiently. We extend the theoretical results of LTS by showing that, for ToT (a pruned tree), LTS guarantees a bound on the number of states expanded, and consequently, on the number of thoughts generated. Additionally, we analyze the sensitivity of this bound to the temperature values commonly used in the final softmax layer of the LM. Empirical evaluation under a fixed LM query budget demonstrates that LTS consistently achieves comparable or higher accuracy than baseline search algorithms within the ToT framework, across three domains (Blocksworld, PrOntoQA, Array Sorting) and four distinct LMs. These findings highlight the efficacy of LTS on ToT, particularly in enabling cost-effective and time-efficient problem-solving, making it well-suited for latency-critical and resource-constrained applications.

---

### AEScorer: An Agentic Evidence-Grounded Framework for Graded Factuality Verification

Authors: Hui Huang, Muyun Yang, Yuki Arase
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03605v2

Despite the significant advancements of Large Language Models (LLMs), their factuality remains a critical challenge, creating a growing need for more nuanced factuality verification. Existing factuality verification methods do not capture graded judgments, even though factuality is better understood as a spectrum rather than a binary of right and wrong. To bridge this gap, we focus on graded factuality verification and propose AEScorer, an agentic evidence-grounded framework with two stages: agentic evidence acquisition and graded scoring. AEScorer first gathers and refines external evidence through agentic search, and then predicts a scalar factuality score to distinguish nuanced differences in factual correctness. We further construct GradedVeriBench, a benchmark for graded factuality verification spanning both general and multi-hop question answering. Experimental results on GradedVeriBench show that AEScorer substantially outperforms existing methods across both settings, demonstrating the value of coupling targeted evidence acquisition with graded scoring.

---

### Interleaved Tool-Call Reasoning for Protein Function Understanding

Authors: Chuanliu Fan, Zicheng Ma, Huanran Meng, Aijia Zhang, Wenjie Du, Jun Zhang, Yi Qin Gao, Ziqiang Cao, Guohong Fu
Published: 2026-01-07
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.03604v2

Recent advances in large language models (LLMs) have highlighted the effectiveness of chain-of-thought reasoning in symbolic domains such as mathematics and programming. However, our study shows that directly transferring such text-based reasoning paradigms to protein function understanding is ineffective: reinforcement learning mainly amplifies superficial keyword patterns while failing to introduce new biological knowledge, resulting in limited generalization. We argue that protein function prediction is a knowledge-intensive scientific task that fundamentally relies on external biological priors and computational tools rather than purely internal reasoning. To address this gap, we propose PFUA, a tool-augmented protein reasoning agent that unifies problem decomposition, tool invocation, and grounded answer generation. Instead of relying on long unconstrained reasoning traces, PFUA integrates domain-specific tools to produce verifiable intermediate evidence. Experiments on four benchmarks demonstrate that PFUA consistently outperforms text-only reasoning models with an average performance improvement of 103%.

---

### A Comparative Study of Traditional Machine Learning, Deep Learning, and Large Language Models for Mental Health Forecasting using Smartphone Sensing Data

Authors: Kaidong Feng, Zhu Sun, Roy Ka-Wei Lee, Xun Jiang, Yin-Leng Theng, Yi Ding
Published: 2026-01-07
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.03603v2

Smartphone sensing offers an unobtrusive and scalable way to track daily behaviors linked to mental health, capturing changes in sleep, mobility, and phone use that often precede symptoms of stress, anxiety, or depression. While most prior studies focus on detection that responds to existing conditions, forecasting mental health enables proactive support through Just-in-Time Adaptive Interventions. In this paper, we present the first comprehensive benchmarking study comparing traditional machine learning (ML), deep learning (DL), and large language model (LLM) approaches for mental health forecasting using the College Experience Sensing (CES) dataset, the most extensive longitudinal dataset of college student mental health to date. We systematically evaluate models across temporal windows, feature granularities, personalization strategies, and class imbalance handling. Our results show that DL models, particularly Transformer (Macro-F1 = 0.58), achieve the best overall performance, while LLMs show strength in contextual reasoning but weaker temporal modeling. Personalization substantially improves forecasts of severe mental health states. By revealing how different modeling approaches interpret phone sensing behavioral data over time, this work lays the groundwork for next-generation, adaptive, and human-centered mental health technologies that can advance both research and real-world well-being.

---

### ALERT: Zero-shot LLM Jailbreak Detection via Internal Discrepancy Amplification

Authors: Xiao Lin, Philip Li, Zhichen Zeng, Tingwei Li, Tianxin Wei, Xuying Ning, Gaotang Li, Yuzhong Chen, Hanghang Tong
Published: 2026-01-07
Categories: cs.LG, cs.AI, cs.IR
arXiv: https://arxiv.org/abs/2601.03600v1

Despite rich safety alignment strategies, large language models (LLMs) remain highly susceptible to jailbreak attacks, which compromise safety guardrails and pose serious security risks. Existing detection methods mainly detect jailbreak status relying on jailbreak templates present in the training data. However, few studies address the more realistic and challenging zero-shot jailbreak detection setting, where no jailbreak templates are available during training. This setting better reflects real-world scenarios where new attacks continually emerge and evolve. To address this challenge, we propose a layer-wise, module-wise, and token-wise amplification framework that progressively magnifies internal feature discrepancies between benign and jailbreak prompts. We uncover safety-relevant layers, identify specific modules that inherently encode zero-shot discriminative signals, and localize informative safety tokens. Building upon these insights, we introduce ALERT (Amplification-based Jailbreak Detector), an efficient and effective zero-shot jailbreak detector that introduces two independent yet complementary classifiers on amplified representations. Extensive experiments on three safety benchmarks demonstrate that ALERT achieves consistently strong zero-shot detection performance. Specifically, (i) across all datasets and attack strategies, ALERT reliably ranks among the top two methods, and (ii) it outperforms the second-best baseline by at least 10% in average Accuracy and F1-score, and sometimes by up to 40%.

---

### From Chains to Graphs: Self-Structured Reasoning for General-Domain LLMs

Authors: Yingjian Chen, Haoran Liu, Yinhong Liu, Sherry T. Tong, Aosong Feng, Jinghui Lu, Juntao Zhang, Yusuke Iwasawa, Yutaka Matsuo, Irene Li
Published: 2026-01-07
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.03597v2

Large Language Models (LLMs) show strong reasoning ability in open-domain question answering, yet their reasoning processes are typically linear and often logically inconsistent. In contrast, real-world reasoning requires integrating multiple premises and solving subproblems in parallel. Existing methods, such as Chain-of-Thought (CoT), express reasoning in a linear textual form, which may appear coherent but frequently leads to inconsistent conclusions. Recent approaches rely on externally provided graphs and do not explore how LLMs can construct and use their own graph-structured reasoning, particularly in open-domain QA. To fill this gap, we novelly explore graph-structured reasoning of LLMs in general-domain question answering. We propose Self-Graph Reasoning (SGR), a framework that enables LLMs to explicitly represent their reasoning process as a structured graph before producing the final answer. We further construct a graph-structured reasoning dataset that merges multiple candidate reasoning graphs into refined graph structures for model training. Experiments on five QA benchmarks across both general and specialized domains show that SGR consistently improves reasoning consistency and yields a 17.74% gain over the base model. The LLaMA-3.3-70B model fine-tuned with SGR performs comparably to GPT-4o and surpasses Claude-3.5-Haiku, demonstrating the effectiveness of graph-structured reasoning.

---

### Adaptive Attention Distillation for Robust Few-Shot Segmentation under Environmental Perturbations

Authors: Qianyu Guo, Jingrong Wu, Jieji Ren, Weifeng Ge, Wenqiang Zhang
Published: 2026-01-07
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.03596v3

Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However, existing studies largely overlook the complex environmental factors encountered in real world scenarios-such as illumination, background, and camera viewpoint-which can substantially increase the difficulty of test images. As a result, models trained under laboratory conditions often fall short of practical deployment requirements. To bridge this gap, in this paper, an environment-robust FSS setting is introduced that explicitly incorporates challenging test cases arising from complex environments-such as motion blur, small objects, and camouflaged targets-to enhance model's robustness under realistic, dynamic conditions. An environment robust FSS benchmark (ER-FSS) is established, covering eight datasets across multiple real world scenarios. In addition, an Adaptive Attention Distillation (AAD) method is proposed, which repeatedly contrasts and distills key shared semantics between known (support) and unknown (query) images to derive class-specific attention for novel categories. This strengthens the model's ability to focus on the correct targets in complex environments, thereby improving environmental robustness. Comparative experiments show that AAD improves mIoU by 3.3% - 8.5% across all datasets and settings, demonstrating superior performance and strong generalization. The source code and dataset are available at: https://github.com/guoqianyu-alberta/Adaptive-Attention-Distillation-for-FSS.

---

### Controllable LLM Reasoning via Sparse Autoencoder-Based Steering

Authors: Yi Fang, Wenjie Wang, Mingfeng Xue, Boyi Deng, Fengli Xu, Dayiheng Liu, Fuli Feng
Published: 2026-01-07
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.03595v2

Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (\eg backtracking, cross-verification) during the reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are autonomously selected by LRMs themselves. However, such autonomous selection often produces inefficient or even erroneous reasoning paths. To make reasoning more reliable and flexible, it is important to develop methods for controlling reasoning strategies. Existing methods struggle to control fine-grained reasoning strategies due to conceptual entanglement in LRMs' hidden states. To address this, we leverage Sparse Autoencoders (SAEs) to decompose strategy-entangled hidden states into a disentangled feature space. To identify the few strategy-specific features from the vast pool of SAE features, we propose SAE-Steering, an efficient two-stage feature identification pipeline. SAE-Steering first recalls features that amplify the logits of strategy-specific keywords, filtering out over 99\% of features, and then ranks the remaining features by their control effectiveness. Using the identified strategy-specific features as control vectors, SAE-Steering outperforms existing methods by over 15\% in control effectiveness. Furthermore, controlling reasoning strategies can redirect LRMs from erroneous paths to correct ones, achieving a 7\% absolute accuracy improvement. Our code and data are available at https://github.com/Peter-Fy/SAE-Steering.

---

### Can LLMs See Without Pixels? Benchmarking Spatial Intelligence from Textual Descriptions

Authors: Zhongbin Guo, Zhen Yang, Yushan Li, Xinyue Zhang, Wenyu Gao, Jiacheng Wang, Chengzhi Li, Xiangrui Liu, Ping Jian
Published: 2026-01-07
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.03590v1

Recent advancements in Spatial Intelligence (SI) have predominantly relied on Vision-Language Models (VLMs), yet a critical question remains: does spatial understanding originate from visual encoders or the fundamental reasoning backbone? Inspired by this question, we introduce SiT-Bench, a novel benchmark designed to evaluate the SI performance of Large Language Models (LLMs) without pixel-level input, comprises over 3,800 expert-annotated items across five primary categories and 17 subtasks, ranging from egocentric navigation and perspective transformation to fine-grained robotic manipulation. By converting single/multi-view scenes into high-fidelity, coordinate-aware textual descriptions, we challenge LLMs to perform symbolic textual reasoning rather than visual pattern matching. Evaluation results of state-of-the-art (SOTA) LLMs reveals that while models achieve proficiency in localized semantic tasks, a significant "spatial gap" remains in global consistency. Notably, we find that explicit spatial reasoning significantly boosts performance, suggesting that LLMs possess latent world-modeling potential. Our proposed dataset SiT-Bench serves as a foundational resource to foster the development of spatially-grounded LLM backbones for future VLMs and embodied agents. Our code and benchmark will be released at https://github.com/binisalegend/SiT-Bench .

---

### OLA: Output Language Alignment in Code-Switched LLM Interactions

Authors: Juhyun Oh, Haneul Yoo, Faiz Ghifari Haznitrama, Alice Oh
Published: 2026-01-07
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.03589v1

Code-switching, alternating between languages within a conversation, is natural for multilingual users, yet poses fundamental challenges for large language models (LLMs). When a user code-switches in their prompt to an LLM, they typically do not specify the expected language of the LLM response, and thus LLMs must infer the output language from contextual and pragmatic cues. We find that current LLMs systematically fail to align with this expectation, responding in undesired languages even when cues are clear to humans. We introduce OLA, a benchmark to evaluate LLMs' Output Language Alignment in code-switched interactions. OLA focuses on Korean--English code-switching and spans simple intra-sentential mixing to instruction-content mismatches. Even frontier models frequently misinterpret implicit language expectation, exhibiting a bias toward non-English responses. We further show this bias generalizes beyond Korean to Chinese and Indonesian pairs. Models also show instability through mid-response switching and language intrusions. Chain-of-Thought prompting fails to resolve these errors, indicating weak pragmatic reasoning about output language. However, Code-Switching Aware DPO with minimal data (about 1K examples) substantially reduces misalignment, suggesting these failures stem from insufficient alignment rather than fundamental limitations. Our results highlight the need to align multilingual LLMs with users' implicit expectations in real-world code-switched interactions.

---