# Research Papers — 2026-01 · bundle page 16 of 189

> Full-text markdown of papers #751–800 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/16
[← Previous bundle](https://aipod.dev/papers/archive/2026-01/page/15.md)
[Next bundle →](https://aipod.dev/papers/archive/2026-01/page/17.md)

### Real-Time Aligned Reward Model beyond Semantics

Authors: Zixuan Huang, Xin Xia, Yuxi Ren, Jianbin Zheng, Xuefeng Xiao, Hongyan Xie, Li Huaqiu, Songshi Liang, Zhongxiang Dai, Fuzhen Zhuang, Jianxin Li, Yikun Ban et al.
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22664v4

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capturing human intent. Prior mitigations primarily relies on surface semantic information and fails to efficiently address the misalignment between the reward model (RM) and the policy model caused by continuous policy distribution shifts. This inevitably leads to an increasing reward discrepancy, exacerbating reward overoptimization. To address these limitations, we introduce R2M (Real-Time Aligned Reward Model), a novel lightweight RLHF framework. R2M goes beyond vanilla reward models that solely depend on the semantic representations of a pretrained LLM. Instead, it leverages the evolving hidden states of the policy (namely policy feedback) to align with the real-time distribution shift of the policy during the RL process. This work points to a promising new direction for improving the performance of reward models through real-time utilization of feedback from policy models.

---

### Unsupervised Synthetic Image Attribution: Alignment and Disentanglement

Authors: Zongfang Liu, Guangyi Chen, Boyang Sun, Tongliang Liu, Kun Zhang
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22663v1

As the quality of synthetic images improves, identifying the underlying concepts of model-generated images is becoming increasingly crucial for copyright protection and ensuring model transparency. Existing methods achieve this attribution goal by training models using annotated pairs of synthetic images and their original training sources. However, obtaining such paired supervision is challenging, as it requires either well-designed synthetic concepts or precise annotations from millions of training sources. To eliminate the need for costly paired annotations, in this paper, we explore the possibility of unsupervised synthetic image attribution. We propose a simple yet effective unsupervised method called Alignment and Disentanglement. Specifically, we begin by performing basic concept alignment using contrastive self-supervised learning. Next, we enhance the model's attribution ability by promoting representation disentanglement with the Infomax loss. This approach is motivated by an interesting observation: contrastive self-supervised models, such as MoCo and DINO, inherently exhibit the ability to perform simple cross-domain alignment. By formulating this observation as a theoretical assumption on cross-covariance, we provide a theoretical explanation of how alignment and disentanglement can approximate the concept-matching process through a decomposition of the canonical correlation analysis objective. On the real-world benchmarks, AbC, we show that our unsupervised method surprisingly outperforms the supervised methods. As a starting point, we expect our intuitive insights and experimental findings to provide a fresh perspective on this challenging task.

---

### Task-Aware LLM Council with Adaptive Decision Pathways for Decision Support

Authors: Wei Zhu, Lixing Yu, Hao-Ren Yao, Zhiwen Tang, Kun Yue
Published: 2026-01-30
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.22662v1

Large language models (LLMs) have shown strong capabilities across diverse decision-making tasks. However, existing approaches often overlook the specialization differences among available models, treating all LLMs as uniformly applicable regardless of task characteristics. This limits their ability to adapt to varying reasoning demands and task complexities. In this work, we propose Task-Aware LLM Council (TALC), a task-adaptive decision framework that integrates a council of LLMs with Monte Carlo Tree Search (MCTS) to enable dynamic expert selection and efficient multi-step planning. Each LLM is equipped with a structured success memory profile derived from prior task trajectories, enabling semantic matching between current reasoning context and past successes. At each decision point, TALC routes control to the most contextually appropriate model and estimates node value using a dual-signal mechanism that fuses model-based evaluations with historical utility scores. These signals are adaptively weighted based on intra-node variance and used to guide MCTS selection, allowing the system to balance exploration depth with planning confidence. Experiments on WebShop, HumanEval, and the Game of 24 demonstrate that TALC achieves superior task success rates and improved search efficiency compared to strong baselines, validating the benefits of specialization-aware routing and adaptive planning.

---

### Layerwise Progressive Freezing Enables STE-Free Training of Deep Binary Neural Networks

Authors: Evan Gibson Smith, Bashima Islam
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22660v1

We investigate progressive freezing as an alternative to straight-through estimators (STE) for training binary networks from scratch. Under controlled training conditions, we find that while global progressive freezing works for binary-weight networks, it fails for full binary neural networks due to activation-induced gradient blockades. We introduce StoMPP (Stochastic Masked Partial Progressive Binarization), which uses layerwise stochastic masking to progressively replace differentiable clipped weights/activations with hard binary step functions, while only backpropagating through the unfrozen (clipped) subset (i.e., no straight-through estimator). Under a matched minimal training recipe, StoMPP improves accuracy over a BinaryConnect-style STE baseline, with gains that increase with depth (e.g., for ResNet-50 BNN: +18.0 on CIFAR-10, +13.5 on CIFAR-100, and +3.8 on ImageNet; for ResNet-18: +3.1, +4.7, and +1.3). For binary-weight networks, StoMPP achieves 91.2\% accuracy on CIFAR-10 and 69.5\% on CIFAR-100 with ResNet-50. We analyze training dynamics under progressive freezing, revealing non-monotonic convergence and improved depth scaling under binarization constraints.

---

### NAG: A Unified Native Architecture for Encoder-free Text-Graph Modeling in Language Models

Authors: Haisong Gong, Zhibo Liu, Qiang Liu, Shu Wu, Liang Wang
Published: 2026-01-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.22657v1

Prevailing methods for integrating graphs into Language Models (LMs) typically rely on a segregated architecture: external Graph Neural Networks (GNNs) encode structural topology, while LMs process textual semantics. We argue this approach is suboptimal for text-graphs: it creates a conceptually disjointed interaction paradigm. By segregating structural encoding from semantic processing, these systems must perform a complex implicit alignment between abstract graph tokens and concrete textual elements. Challenging the necessity of external encoders, we propose NAG (Native Architecture for Graphs), a unified framework that internalizes graph processing within the LM's native manifold. Instead of bridging disparate embedding spaces, NAG repurposes the self-attention mechanism to enforce topological dependencies and recalibrates positional IDs to ensure structural equivalence. This allows the model to harness its intrinsic linguistic capability to simultaneously comprehend node and edge content alongside structural topology. We introduce two efficient implementations: NAG-Zero for absolute preservation of the base model's linguistic capabilities, and NAG-LoRA for enhanced structural adaptation. Experiments across diverse graph tasks validate that NAG achieves robust graph comprehension without the overhead of external encoders, offering a simpler, more coherent paradigm for text-graph modeling.

---

### Human-Centered Explainability in AI-Enhanced UI Security Interfaces: Designing Trustworthy Copilots for Cybersecurity Analysts

Authors: Mona Rajhans
Published: 2026-01-30
Categories: cs.HC, cs.AI, cs.CR
arXiv: https://arxiv.org/abs/2601.22653v1

Artificial intelligence (AI) copilots are increasingly integrated into enterprise cybersecurity platforms to assist analysts in threat detection, triage, and remediation. However, the effectiveness of these systems depends not only on the accuracy of underlying models but also on the degree to which users can understand and trust their outputs. Existing research on algorithmic explainability has largely focused on model internals, while little attention has been given to how explanations should be surfaced in user interfaces for high-stakes decision-making contexts (8), (5), (6). We present a mixed-methods study of explanation design strategies in AI-driven security dashboards. Through a taxonomy of explanation styles and a controlled user study with security practitioners, we compare natural language rationales, confidence visualizations, counterfactual explanations, and hybrid approaches. Our findings show that explanation style significantly affects user trust calibration, decision accuracy, and cognitive load. We contribute (1) empirical evidence on the usability of explanation interfaces for security copilots, (2) design guidelines for integrating explainability into enterprise UIs, and (3) a framework for aligning explanation strategies with analyst needs in security operations centers (SOCs). This work advances the design of human-centered AI tools in cybersecurity and provides broader implications for explainability in other high-stakes domains.

---

### Spectral Gradient Descent Mitigates Anisotropy-Driven Misalignment: A Case Study in Phase Retrieval

Authors: Guillaume Braun, Han Bao, Wei Huang, Masaaki Imaizumi
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22652v2

Spectral gradient methods, such as the Muon optimizer, modify gradient updates by preserving directional information while discarding scale, and have shown strong empirical performance in deep learning. We investigate the mechanisms underlying these gains through a dynamical analysis of a nonlinear phase retrieval model with anisotropic Gaussian inputs, equivalent to training a two-layer neural network with the quadratic activation and fixed second-layer weights. Focusing on a spiked covariance setting where the dominant variance direction is orthogonal to the signal, we show that gradient descent (GD) suffers from a variance-induced misalignment: during the early escaping stage, the high-variance but uninformative spike direction is multiplicatively amplified, degrading alignment with the true signal under strong anisotropy. In contrast, spectral gradient descent (SpecGD) removes this spike amplification effect, leading to stable alignment and accelerated noise contraction. Numerical experiments confirm the theory and show that these phenomena persist under broader anisotropic covariances.

---

### GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

Authors: Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22651v2

Training-data attribution for vision generative models aims to identify which training data influenced a given output. While most methods score individual examples, practitioners often need group-level answers (e.g., artistic styles or object classes). Group-wise attribution is counterfactual: how would a model's behavior on a generated sample change if a group were absent from training? A natural realization of this counterfactual is Leave-One-Group-Out (LOGO) retraining, which retrains the model with each group removed; however, it becomes computationally prohibitive as the number of groups grows. We propose GUDA (Group Unlearning-based Data Attribution) for diffusion models, which approximates each counterfactual model by applying machine unlearning to a shared full-data model instead of training from scratch. GUDA quantifies group influence using differences in a likelihood-based scoring rule (ELBO) between the full model and each unlearned counterfactual. Experiments on CIFAR-10 and artistic style attribution with Stable Diffusion show that GUDA identifies primary contributing groups more reliably than semantic similarity, gradient-based attribution, and instance-level unlearning approaches, while achieving ~100x speedup on CIFAR-10 over LOGO retraining.

---

### Generative and Nonparametric Approaches for Conditional Distribution Estimation: Methods, Perspectives, and Comparative Evaluations

Authors: Yen-Shiu Chin, Zhi-Yu Jou, Toshinari Morimoto, Chia-Tse Wang, Ming-Chung Chang, Tso-Jung Yen, Su-Yun Huang, Tailen Hsing
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22650v1

The inference of conditional distributions is a fundamental problem in statistics, essential for prediction, uncertainty quantification, and probabilistic modeling. A wide range of methodologies have been developed for this task. This article reviews and compares several representative approaches spanning classical nonparametric methods and modern generative models. We begin with the single-index method of Hall and Yao (2005), which estimates the conditional distribution through a dimension-reducing index and nonparametric smoothing of the resulting one-dimensional cumulative conditional distribution function. We then examine the basis-expansion approaches, including FlexCode (Izbicki and Lee, 2017) and DeepCDE (Dalmasso et al., 2020), which convert conditional density estimation into a set of nonparametric regression problems. In addition, we discuss two recent generative simulation-based methods that leverage modern deep generative architectures: the generative conditional distribution sampler (Zhou et al., 2023) and the conditional denoising diffusion probabilistic model (Fu et al., 2024; Yang et al., 2025). A systematic numerical comparison of these approaches is provided using a unified evaluation framework that ensures fairness and reproducibility. The performance metrics used for the estimated conditional distribution include the mean-squared errors of conditional mean and standard deviation, as well as the Wasserstein distance. We also discuss their flexibility and computational costs, highlighting the distinct advantages and limitations of each approach.

---

### UCPO: Uncertainty-Aware Policy Optimization

Authors: Xianzhou Zeng, Jing Huang, Chunmei Xie, Gongrui Nan, Siye Chen, Mengyu Lu, Weiqi Xiong, Qixuan Zhou, Junhao Zhang, Qiang Zhu, Yadong Li, Xingzhong Xu
Published: 2026-01-30
Categories: cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22648v2

The key to building trustworthy large language models (LLMs) lies in endowing them with inherent uncertainty expression capabilities, thereby mitigating overconfident errors in high-stakes applications. However, existing RL paradigms such as GRPO often suffer from Advantage Bias due to binary decision spaces and static uncertainty rewards, inducing either excessive conservatism or overconfidence. To tackle this challenge, this paper unveils the root causes of reward hacking and overconfidence in current RL paradigms incorporating uncertainty-based rewards, based on which we propose the UnCertainty-Aware Policy Optimization (UCPO) framework. UCPO employs Ternary Advantage Decoupling to separate and independently normalize deterministic and uncertain rollouts, thereby eliminating advantage bias. Furthermore, a Dynamic Uncertainty Reward Adjustment mechanism adapts uncertainty weights in real-time according to model evolution and instance difficulty. Experimental results in mathematical reasoning and general tasks demonstrate that UCPO effectively resolves the reward imbalance, significantly improving the reliability of the model beyond their knowledge boundaries.

---

### Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments

Authors: Jinwoo Jang, Minjong Yoo, Sihyung Yoon, Honguk Woo
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22647v1

Language model (LM)-based embodied agents are increasingly deployed in real-world settings. Yet, their adaptability remains limited in dynamic environments, where constructing accurate and flexible world models is crucial for effective reasoning and decision-making. To address this challenge, we extend the Mixture-of-Experts (MoE) paradigm to embodied agents. While conventional MoE architectures modularize knowledge into expert components with pre-trained routing, they remain rigid once deployed, making them less effective for adapting to unseen domains in dynamic environments. We therefore propose Test-time Mixture of World Models (TMoW), a framework that enhances adaptability to unseen and evolving domains. TMoW updates its routing function over world models at test time, unlike conventional MoE where the function remains fixed, enabling agents to recombine existing models and integrate new ones for continual adaptation. It achieves this through (i) multi-granular prototype-based routing, which adapts mixtures across object- to scene-level similarities, (ii) test-time refinement that aligns unseen domain features with prototypes during inference, and (iii) distilled mixture-based augmentation, which efficiently constructs new models from few-shot data and existing prototypes. We evaluate TMoW on VirtualHome, ALFWorld, and RLBench benchmarks, demonstrating strong performance in both zero-shot adaptation and few-shot expansion scenarios, and showing that it enables embodied agents to operate effectively in dynamic environments.

---

### Beyond Medical Chatbots: Meddollina and the Rise of Continuous Clinical Intelligence

Authors: Vaibhav Ram S. V. N. S, Swetanshu Agrawal, Samudra Banerjee, Abdul Muhsin
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22645v1

Generative medical AI now appears fluent and knowledgeable enough to resemble clinical intelligence, encouraging the belief that scaling will make it safe. But clinical reasoning is not text generation. It is a responsibility-bound process under ambiguity, incomplete evidence, and longitudinal context. Even as benchmark scores rise, generation-centric systems still show behaviours incompatible with clinical deployment: premature closure, unjustified certainty, intent drift, and instability across multi-step decisions. We argue these are structural consequences of treating medicine as next-token prediction. We formalise Clinical Contextual Intelligence (CCI) as a distinct capability class required for real-world clinical use, defined by persistent context awareness, intent preservation, bounded inference, and principled deferral when evidence is insufficient. We introduce Meddollina, a governance-first clinical intelligence system designed to constrain inference before language realisation, prioritising clinical appropriateness over generative completeness. Meddollina acts as a continuous intelligence layer supporting clinical workflows while preserving clinician authority. We evaluate Meddollina using a behaviour-first regime across 16,412+ heterogeneous medical queries, benchmarking against general-purpose models, medical-tuned models, and retrieval-augmented systems. Meddollina exhibits a distinct behavioural profile: calibrated uncertainty, conservative reasoning under underspecification, stable longitudinal constraint adherence, and reduced speculative completion relative to generation-centric baselines. These results suggest deployable medical AI will not emerge from scaling alone, motivating a shift toward Continuous Clinical Intelligence, where progress is measured by clinician-aligned behaviour under uncertainty rather than fluency-driven completion.

---

### Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification

Authors: Chuxue Cao, Jinluan Yang, Haoran Li, Kunhao Pan, Zijian Zhao, Zhengyu Chen, Yuchen Tian, Lijun Wu, Conghui He, Sirui Han, Yike Guo
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22642v2

Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic systems avoid. To bridge this gap, we introduce a formal logic verification-guided framework that dynamically interleaves formal symbolic verification with the natural language generation process, providing real-time feedback to detect and rectify errors as they occur. Distinguished from previous neuro-symbolic methods limited by passive post-hoc validation, our approach actively penalizes intermediate fallacies during the reasoning chain. We operationalize this framework via a novel two-stage training pipeline that synergizes formal logic verification-guided supervised fine-tuning and policy optimization. Extensive evaluation on six benchmarks spanning mathematical, logical, and general reasoning demonstrates that our 7B and 14B models outperform state-of-the-art baselines by average margins of 10.4% and 14.2%, respectively. These results validate that formal verification can serve as a scalable mechanism to significantly push the performance boundaries of advanced LLM reasoning.

---

### ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review

Authors: Palash Goyal, Mihir Parmar, Yiwen Song, Hamid Palangi, Tomas Pfister, Jinsung Yoon
Published: 2026-01-30
Categories: cs.MA, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22638v2

The exponential growth of machine learning submissions has strained the traditional peer review process, resulting in slow feedback loops for authors and an immense burden on reviewers to rigorously audit technical soundness and verify literature. To address this, we introduce ScholarPeer, a multi-agent framework designed to operationalize the rigorous auditing workflow of a senior researcher. Rather than attempting to replace human judgment, ScholarPeer serves as a co-scientist: acting as a mentor for rapid author iteration prior to submission, and as an active verification assistant that augments human reviewers. The framework structurally decouples contextualization from critique by deploying a sub-domain historian to synthesize the field's trajectory, a baseline scout to proactively hunt for omitted state-of-the-art comparisons, and a multi-aspect Q&A engine that deeply audits technical soundness-scrutinizing internal logical consistency, experimental validity, and mathematical rigor-while cross-referencing claims against top-tier academic venues. We comprehensively evaluate ScholarPeer on ~1,800 ICLR submissions spanning 2020 through 2025. Our results show that ScholarPeer achieves significant win-rates against state-of-the-art fine-tuned models and search-augmented agentic baselines.

---

### Training Beyond Convergence: Grokking nnU-Net for Glioma Segmentation in Sub-Saharan MRI

Authors: Mohtady Barakat, Omar Salah, Ahmed Yasser, Mostafa Ahmed, Zahirul Arief, Waleed Khan, Dong Zhang, Aondona Iorumbur, Confidence Raymond, Mohannad Barakat, Noha Magdy
Published: 2026-01-30
Categories: eess.IV, cs.AI, cs.CV
arXiv: https://arxiv.org/abs/2601.22637v1

Gliomas are placing an increasingly clinical burden on Sub-Saharan Africa (SSA). In the region, the median survival for patients remains under two years, and access to diagnostic imaging is extremely limited. These constraints highlight an urgent need for automated tools that can extract the maximum possible information from each available scan, tools that are specifically trained on local data, rather than adapted from high-income settings where conditions are vastly different. We utilize the Brain Tumor Segmentation (BraTS) Africa 2025 Challenge dataset, an expert annotated collection of glioma MRIs. Our objectives are: (i) establish a strong baseline with nnUNet on this dataset, and (ii) explore whether the celebrated "grokking" phenomenon an abrupt, late training jump from memorization to superior generalization can be triggered to push performance without extra labels. We evaluate two training regimes. The first is a fast, budget-conscious approach that limits optimization to just a few epochs, reflecting the constrained GPU resources typically available in African institutions. Despite this limitation, nnUNet achieves strong Dice scores: 92.3% for whole tumor (WH), 86.6% for tumor core (TC), and 86.3% for enhancing tumor (ET). The second regime extends training well beyond the point of convergence, aiming to trigger a grokking-driven performance leap. With this approach, we were able to achieve grokking and enhanced our results to higher Dice scores: 92.2% for whole tumor (WH), 90.1% for tumor core (TC), and 90.2% for enhancing tumor (ET).

---

### Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N Sampling

Authors: Mingqian Feng, Xiaodong Liu, Weiwei Yang, Chenliang Xu, Christopher White, Jianfeng Gao
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22636v2

Large Language Models (LLMs) are typically evaluated for safety under single-shot or low-budget adversarial prompting, which underestimates real-world risk. In practice, attackers can exploit large-scale parallel sampling to repeatedly probe a model until a harmful response is produced. While recent work shows that attack success increases with repeated sampling, principled methods for predicting large-scale adversarial risk remain limited. We propose a scaling-aware Best-of-N estimation of risk, SABER, for modeling jailbreak vulnerability under Best-of-N sampling. We model sample-level success probabilities using a Beta distribution, the conjugate prior of the Bernoulli distribution, and derive an analytic scaling law that enables reliable extrapolation of large-N attack success rates from small-budget measurements. Using only n=100 samples, our anchored estimator predicts ASR@1000 with a mean absolute error of 1.66, compared to 12.04 for the baseline, which is an 86.2% reduction in estimation error. Our results reveal heterogeneous risk scaling profiles and show that models appearing robust under standard evaluation can experience rapid nonlinear risk amplification under parallel adversarial pressure. This work provides a low-cost, scalable methodology for realistic LLM safety assessment. We will release our code and evaluation scripts upon publication to future research.

---

### What can Computer Vision learn from Ranganathan?

Authors: Mayukh Bagchi, Fausto Giunchiglia
Published: 2026-01-30
Categories: cs.CV, cs.AI
arXiv: https://arxiv.org/abs/2601.22634v1

The Semantic Gap Problem (SGP) in Computer Vision (CV) arises from the misalignment between visual and lexical semantics leading to flawed CV dataset design and CV benchmarks. This paper proposes that classification principles of S.R. Ranganathan can offer a principled starting point to address SGP and design high-quality CV datasets. We elucidate how these principles, suitably adapted, underpin the vTelos CV annotation methodology. The paper also briefly presents experimental evidence showing improvements in CV annotation and accuracy, thereby, validating vTelos.

---

### MCP-Diag: A Deterministic, Protocol-Driven Architecture for AI-Native Network Diagnostics

Authors: Devansh Lodha, Mohit Panchal, Sameer G. Kulkarni
Published: 2026-01-30
Categories: cs.NI, cs.AI
arXiv: https://arxiv.org/abs/2601.22633v1

The integration of Large Language Models (LLMs) into network operations (AIOps) is hindered by two fundamental challenges: the stochastic grounding problem, where LLMs struggle to reliably parse unstructured, vendor-specific CLI output, and the security gap of granting autonomous agents shell access. This paper introduces MCP-Diag, a hybrid neuro-symbolic architecture built upon the Model Context Protocol (MCP). We propose a deterministic translation layer that converts raw stdout from canonical utilities (dig, ping, traceroute) into rigorous JSON schemas before AI ingestion. We further introduce a mandatory "Elicitation Loop" that enforces Human-in-the-Loop (HITL) authorization at the protocol level. Our preliminary evaluation demonstrates that MCP-Diag achieving 100% entity extraction accuracy with less than 0.9% execution latency overhead and 3.7x increase in context token usage.

---

### DART-ing Through the Drift: Dynamic Tracing of Knowledge Neurons for Adaptive Inference-Time Pruning

Authors: Abhishek Tyagi, Yunuo Cen, Shrey Dhorajiya, Bharadwaj Veeravalli, Xuanyao Fong
Published: 2026-01-30
Categories: cs.CL, cs.LG
arXiv: https://arxiv.org/abs/2601.22632v1

Large Language Models (LLMs) exhibit substantial parameter redundancy, particularly in Feed-Forward Networks (FFNs). Existing pruning methods suffer from two primary limitations. First, reliance on dataset-specific calibration introduces significant data dependency and computational overhead. Second, being predominantly static, they fail to account for the evolving subset of knowledge neurons in LLMs during autoregressive generation as the context evolves. To address this, we introduce DART, i.e., Dynamic Attention-Guided Runtime Tracing), a lightweight, training-free method that performs on-the-fly context-based pruning. DART monitors shifts in attention score distributions to infer context changes, dynamically updating neuron-level masks to retain salient parameters. Across ten benchmarks, DART outperforms prior dynamic baseline, achieving accuracy gains of up to 14.5% on LLAMA-3.1-8B at 70% FFN sparsity. Furthermore, DART achieves up to 3x better ROUGE-L scores with respect to static-masked pruning on summarization tasks, with its performance comparable to the original dense models. We conclusively demonstrate that the proposed framework effectively adapts to diverse semantic contexts, preserves model capabilities across both general and domain-specific tasks while running at less than 10MBs of memory for LLAMA-3.1-8B(16GBs) with 0.1% FLOPs overhead. The code is available at https://github.com/seeder-research/DART.

---

### PEFT-MuTS: A Multivariate Parameter-Efficient Fine-Tuning Framework for Remaining Useful Life Prediction based on Cross-domain Time Series Representation Model

Authors: En Fu, Yanyan Hu, Zengwang Jin, Kaixiang Peng
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22631v2

The application of data-driven remaining useful life (RUL) prediction has long been constrained by the availability of large amount of degradation data. Mainstream solutions such as domain adaptation and meta-learning still rely on large amounts of historical degradation data from equipment that is identical or similar to the target, which imposes significant limitations in practical applications. This study investigates PEFT-MuTS, a Parameter-Efficient Fine-Tuning framework for few-shot RUL prediction, built on cross-domain pre-trained time-series representation models. Contrary to the widely held view that knowledge transfer in RUL prediction can only occur within similar devices, we demonstrate that substantial benefits can be achieved through pre-training process with large-scale cross-domain time series datasets. A independent feature tuning network and a meta-variable-based low rank multivariate fusion mechanism are developed to enable the pre-trained univariate time-series representation backbone model to fully exploit the multivariate relationships in degradation data for downstream RUL prediction task. Additionally, we introduce a zero-initialized regressor that stabilizes the fine-tuning process under few-shot conditions. Experiments on aero-engine and industrial bearing datasets demonstrate that our method can achieve effective RUL prediction even when less than 1\% of samples of target equipment are used. Meanwhile, it substantially outperforms conventional supervised and few-shot approaches while markedly reducing the data required to achieve high predictive accuracy. Our code is available at https://github.com/fuen1590/PEFT-MuTS.

---

### LINA: Linear Autoregressive Image Generative Models with Continuous Tokens

Authors: Jiahao Wang, Ting Pan, Haoge Deng, Dongchen Han, Taiqiang Wu, Xinlong Wang, Ping Luo
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22630v1

Autoregressive models with continuous tokens form a promising paradigm for visual generation, especially for text-to-image (T2I) synthesis, but they suffer from high computational cost. We study how to design compute-efficient linear attention within this framework. Specifically, we conduct a systematic empirical analysis of scaling behavior with respect to parameter counts under different design choices, focusing on (1) normalization paradigms in linear attention (division-based vs. subtraction-based) and (2) depthwise convolution for locality augmentation. Our results show that although subtraction-based normalization is effective for image classification, division-based normalization scales better for linear generative transformers. In addition, incorporating convolution for locality modeling plays a crucial role in autoregressive generation, consistent with findings in diffusion models. We further extend gating mechanisms, commonly used in causal linear attention, to the bidirectional setting and propose a KV gate. By introducing data-independent learnable parameters to the key and value states, the KV gate assigns token-wise memory weights, enabling flexible memory management similar to forget gates in language models. Based on these findings, we present LINA, a simple and compute-efficient T2I model built entirely on linear attention, capable of generating high-fidelity 1024x1024 images from user instructions. LINA achieves competitive performance on both class-conditional and T2I benchmarks, obtaining 2.18 FID on ImageNet (about 1.4B parameters) and 0.74 on GenEval (about 1.5B parameters). A single linear attention module reduces FLOPs by about 61 percent compared to softmax attention. Code and models are available at: https://github.com/techmonsterwang/LINA.

---

### Denoising Time Matters:Diverse Generation in Diffusion Language Models

Authors: Jingxuan Wu, Zhenglin Wan, Yuzhe Yang, Yiqiao Huang, Chubin Zhang, Xingrui Yu, Ivor Tsang, Yang You
Published: 2026-01-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.22629v3

Diffusion language models (Diffusion-LMs) generate text through iterative denoising, exposing a temporal structure that is largely absent from autoregressive decoding. In this paper, we show that this temporal structure provides a useful control axis for generation diversity: early denoising steps mainly determine high-level semantic trajectories, while later steps refine lexical realization. Motivated by this observation, we propose Time-Annealed Perturbation Sampling (TAPS), a training-free inference strategy that samples nearby conditioning trajectories through time-aware, manifold-constrained perturbations. TAPS encourages semantic branching during early denoising and anneals the perturbation away before refinement, improving exploration while preserving prompt alignment, generation quality, and reasoning ability. Experiments on multiple Diffusion-LM backbones, including non-autoregressive and semi-autoregressive models, show that TAPS consistently improves semantic and lexical diversity across open-ended and instruction-following generation tasks, while preserving reasoning ability on verifiable reasoning benchmarks with negligible overhead.

---

### TTCS: Test-Time Curriculum Synthesis for Self-Evolving

Authors: Chengyi Yang, Zhishang Xiang, Yunbo Tang, Zongpei Teng, Chengsong Huang, Fei Long, Yuhan Liu, Jinsong Su
Published: 2026-01-30
Categories: cs.LG, cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.22628v1

Test-Time Training offers a promising way to improve the reasoning ability of large language models (LLMs) by adapting the model using only the test questions. However, existing methods struggle with difficult reasoning problems for two reasons: raw test questions are often too difficult to yield high-quality pseudo-labels, and the limited size of test sets makes continuous online updates prone to instability. To address these limitations, we propose TTCS, a co-evolving test-time training framework. Specifically, TTCS initializes two policies from the same pretrained model: a question synthesizer and a reasoning solver. These policies evolve through iterative optimization: the synthesizer generates progressively challenging question variants conditioned on the test questions, creating a structured curriculum tailored to the solver's current capability, while the solver updates itself using self-consistency rewards computed from multiple sampled responses on both original test and synthetic questions. Crucially, the solver's feedback guides the synthesizer to generate questions aligned with the model's current capability, and the generated question variants in turn stabilize the solver's test-time training. Experiments show that TTCS consistently strengthens the reasoning ability on challenging mathematical benchmarks and transfers to general-domain tasks across different LLM backbones, highlighting a scalable path towards dynamically constructing test-time curricula for self-evolving. Our code and implementation details are available at https://github.com/XMUDeepLIT/TTCS.

---

### RPWithPrior: Label Differential Privacy in Regression

Authors: Haixia Liu, Ruifan Huang
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22625v1

With the wide application of machine learning techniques in practice, privacy preservation has gained increasing attention. Protecting user privacy with minimal accuracy loss is a fundamental task in the data analysis and mining community. In this paper, we focus on regression tasks under $ε$-label differential privacy guarantees. Some existing methods for regression with $ε$-label differential privacy, such as the RR-On-Bins mechanism, discretized the output space into finite bins and then applied RR algorithm. To efficiently determine these finite bins, the authors rounded the original responses down to integer values. However, such operations does not align well with real-world scenarios. To overcome these limitations, we model both original and randomized responses as continuous random variables, avoiding discretization entirely. Our novel approach estimates an optimal interval for randomized responses and introduces new algorithms designed for scenarios where a prior is either known or unknown. Additionally, we prove that our algorithm, RPWithPrior, guarantees $ε$-label differential privacy. Numerical results demonstrate that our approach gets better performance compared with the Gaussian, Laplace, Staircase, and RRonBins, Unbiased mechanisms on the Communities and Crime, Criteo Sponsored Search Conversion Log, California Housing datasets.

---

### COBRA++: Enhanced COBRA Optimizer with Augmented Surrogate Pool and Reinforced Surrogate Selection

Authors: Zipei Yu, Zhiyang Huang, Hongshu Guo, Yue-Jiao Gong, Zeyuan Ma
Published: 2026-01-30
Categories: cs.NE
arXiv: https://arxiv.org/abs/2601.22624v2

The optimization problems in realistic world present significant challenges onto optimization algorithms, such as the expensive evaluation issue and complex constraint conditions. COBRA optimizer (including its up-to-date variants) is a representative and effective tool for addressing such optimization problems, which introduces 1) RBF surrogate to reduce online evaluation and 2) bi-stage optimization process to alternate search for feasible solution and optimal solution. Though promising, its design space, i.e., surrogate model pool and selection standard, is still manually decided by human expert, resulting in labor-intensive fine-tuning for novel tasks. In this paper, we propose a learning-based adaptive strategy (COBRA++) that enhances COBRA in two aspects: 1) An augmented surrogate pool to break the tie with RBF-like surrogate and hence enhances model diversity and approximation capability; 2) A reinforcement learning-based online model selection policy that empowers efficient and accurate optimization process. The model selection policy is trained to maximize overall performance of COBRA++ across a distribution of constrained optimization problems with diverse properties. We have conducted multi-dimensional validation experiments and demonstrate that COBRA++ achieves substantial performance improvement against vanilla COBRA and its adaptive variant. Ablation studies are provided to support correctness of each design component in COBRA++.

---

### SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly

Authors: Wei Zhu, Zhiwen Tang, Kun Yue
Published: 2026-01-30
Categories: cs.AI, cs.MA
arXiv: https://arxiv.org/abs/2601.22623v1

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose Synergistic Multi-agent Planning with Heterogeneous langauge model assembly (SYMPHONY), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

---

### Layer-wise Swapping for Generalizable Multilingual Safety

Authors: Hyunseo Shin, Wonseok Hwang
Published: 2026-01-30
Categories: cs.CL
arXiv: https://arxiv.org/abs/2601.22620v2

Despite the rapid advancements of Large Language Models (LLMs), safety risks remain a critical challenge for low-resource languages. Existing safety datasets are predominantly English centric, limiting progress in multilingual safety alignment. As a result, low resource expert models, finetuned on their respective instruction datasets, tend to exhibit higher unsafety rates compared to their high resource counterparts. In this work, we propose a safety aware layer swapping method that transfers safety alignment from an English safety expert to low resource language experts without additional training. To further enhance transfer ability, our method adaptively selects or blends modules based on their degree of specialization. Our approach preserves performance on general language understanding tasks while enhancing safety in the target languages. Experimental results show that the proposed method achieves comparable performance to the language expert on general benchmarks such as MMMLU, BELEBELE, and MGSM, while producing more aligned and less harmful responses on the MultiJail safety benchmark.

---

### EntroCut: Entropy-Guided Adaptive Truncation for Efficient Chain-of-Thought Reasoning in Small-scale Large Reasoning Models

Authors: Hongxi Yan, Qingjie Liu, Yunhong Wang
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22617v1

Large Reasoning Models (LRMs) excel at complex reasoning tasks through extended chain-of-thought generation, but their reliance on lengthy intermediate steps incurs substantial computational cost. We find that the entropy of the model's output distribution in early reasoning steps reliably distinguishes correct from incorrect reasoning. Motivated by this observation, we propose EntroCut, a training-free method that dynamically truncates reasoning by identifying high-confidence states where reasoning can be safely terminated. To comprehensively evaluate the trade-off between efficiency and accuracy, we introduce the Efficiency-Performance Ratio (EPR), a unified metric that quantifies relative token savings per unit accuracy loss. Experiments on four benchmarks show that EntroCut reduces token usage by up to 40\% with minimal accuracy sacrifice, achieving superior efficiency-performance trade-offs compared with existing training-free methods. These results demonstrate that entropy-guided dynamic truncation provides a practical approach to mitigate the inefficiency of LRMs.

---

### UniGeo: A Unified 3D Indoor Object Detection Framework Integrating Geometry-Aware Learning and Dynamic Channel Gating

Authors: Xing Yi, Jinyang Huang, Feng-Qi Cui, Anyang Tong, Ruimin Wang, Liu Liu, Dan Guo
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22616v1

The growing adoption of robotics and augmented reality in real-world applications has driven considerable research interest in 3D object detection based on point clouds. While previous methods address unified training across multiple datasets, they fail to model geometric relationships in sparse point cloud scenes and ignore the feature distribution in significant areas, which ultimately restricts their performance. To deal with this issue, a unified 3D indoor detection framework, called UniGeo, is proposed. To model geometric relations in scenes, we first propose a geometry-aware learning module that establishes a learnable mapping from spatial relationships to feature weights, which enabes explicit geometric feature enhancement. Then, to further enhance point cloud feature representation, we propose a dynamic channel gating mechanism that leverages learnable channel-wise weighting. This mechanism adaptively optimizes features generated by the sparse 3D U-Net network, significantly enhancing key geometric information. Extensive experiments on six different indoor scene datasets clearly validate the superior performance of our method.

---

### TTSA3R: Training-Free Temporal-Spatial Adaptive Persistent State for Streaming 3D Reconstruction

Authors: Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22615v3

Streaming recurrent models enable efficient 3D reconstruction by maintaining persistent state representations. However, they suffer from catastrophic forgetting over long sequences due to balancing historical information with new observations. Recent methods alleviate this by deriving adaptive signals from the attention perspective, but they operate on single dimensions without considering temporal and spatial consistency. To this end, we propose a training-free framework termed TTSA3R that leverages both temporal state evolution and spatial observation quality for adaptive state updates in 3D reconstruction. In particular, we devise a Temporal Adaptive Update Module that regulates update magnitude by analyzing temporal state evolution patterns. Then, a Spatial Contextual Update Module is introduced to localize spatial regions that require updates through observation-state alignment and scene dynamics. These complementary signals are finally fused to determine the state updating strategies. Extensive experiments show that TTSA3R achieves competitive performance on standard short-sequence benchmarks and provides substantially stronger robustness on extended sequences. On NRGBD, as sequences extend from 50 to 250 frames, TTSA3R exhibits only a 1.33x error increase, compared with over 4x degradation for CUT3R. This highlights the practical value of temporal-spatial adaptive updates for long-term reconstruction stability. Our code is available at https://github.com/anonus2357/ttsa3r.

---

### Stabilizing Transformer Training Through Consensus

Authors: Shyam Venkatasubramanian, Sean Moushegian, Michael Lin, Mir Park, Ankit Singhal, Connor Lee
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22614v1

Standard attention-based transformers are known to exhibit instability under learning rate overspecification during training, particularly at high learning rates. While various methods have been proposed to improve resilience to such overspecification by modifying the optimization procedure, fundamental architectural innovations to this end remain underexplored. In this work, we illustrate that the consensus mechanism, a drop-in replacement for attention, stabilizes transformer training across a wider effective range of learning rates. We formulate consensus as a graphical model and provide extensive empirical analysis demonstrating improved stability across learning rate sweeps on text, DNA, and protein modalities. We further propose a hybrid consensus-attention framework that preserves performance while improving stability. We provide theoretical analysis characterizing the properties of consensus.

---

### Local-Global Multimodal Contrastive Learning for Molecular Property Prediction

Authors: Xiayu Liu, Zhengyi Lu, Yunhong Liao, Chan Fan, Hou-biao Li
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22610v1

Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-global multimodal contrastive learning framework that jointly models molecular graphs and textual representations derived from SMILES and chemistry-aware augmented texts. Local functional group information and global molecular topology are captured using AttentiveFP and Graph Transformer encoders, respectively, and aligned through self-supervised contrastive learning. In addition, chemically enriched textual descriptions are contrasted with original SMILES to incorporate physicochemical semantics in a task-agnostic manner. During fine-tuning, molecular fingerprints are further integrated via Dual Cross-attention multimodal fusion. Extensive experiments on MoleculeNet benchmarks demonstrate that LGM-CL achieves consistent and competitive performance across both classification and regression tasks, validating the effectiveness of unified local-global and multimodal representation learning.

---

### From Self-Evolving Synthetic Data to Verifiable-Reward RL: Post-Training Multi-turn Interactive Tool-Using Agents

Authors: Jiaxuan Gao, Jiaao Chen, Chuyi He, Shusheng Xu, Di Jin, Yi Wu
Published: 2026-01-30
Categories: cs.AI, cs.CL
arXiv: https://arxiv.org/abs/2601.22607v3

Interactive tool-using agents must solve real-world tasks via multi-turn interaction with both humans and external environments, requiring dialogue state tracking, multi-step tool execution, while following complex instructions. Post-training such agents is challenging because synthesis for high-quality multi-turn tool-use data is difficult to scale, and reinforcement learning (RL) could face noisy signals caused by user simulation, leading to degraded training efficiency. We propose a unified framework that combines a self-evolving data agent with verifier-based RL. Our system, EigenData, is a hierarchical multi-agent engine that synthesizes tool-grounded dialogues together with executable per-instance checkers, and improves generation reliability via closed-loop self-evolving process that updates prompts and workflow. Building on the synthetic data, we develop an RL recipe that first fine-tunes the user model and then applies GRPO-style training with trajectory-level group-relative advantages and dynamic filtering, yielding consistent improvements beyond SFT. Evaluated on tau^2-bench, our best model reaches 73.0% pass^1 on Airline and 98.3% pass^1 on Telecom, matching or exceeding frontier models. Overall, our results suggest a scalable pathway for bootstrapping complex tool-using behaviors without expensive human annotation.

---

### \textsc{Lethe}: Principled Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning

Authors: Wentai Wu, Hanwei Tan, Yijun Quan, Haixia Peng, Ligang He, Bin Yang, C. L. Philip Chen
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22601v3

Federated unlearning (FU) aims to erase knowledge from a global model. Existing studies commonly assume that federated collaboration terminates after unlearning, overlooking a deployment-realistic scenario where training continues on the remaining clients after deletion requests are fulfilled. In this work, we identify a critical failure mode, termed knowledge resurfacing, revealing that continued training on retained data alone can reactivate unlearned knowledge in a few rounds. Empirically, we demonstrate that many state-of-the-art FU methods are prone to knowledge resurfacing. We then propose Lethe, a novel unlearning method for persistent knowledge erasure in federated settings. In each iteration, Lethe operates on a forget stream from the unlearning client and a retain stream from the retained clients. It redirects unlearning updates toward a region where the two streams are anti-aligned, discouraging retained-data training from moving back toward the forgotten knowledge. Consequently, Lethe ensures stronger unlearning persistence during subsequent federated training. Extensive experiments across diverse models, datasets, and unlearning levels validate that Lethe supports all levels of unlearning in a unified manner across both CV and NLP tasks, demonstrating consistently low RR, below 1% in most cases, even after an extremely long horizon of follow-up training.

---

### An Efficient Algorithm for Thresholding Monte Carlo Tree Search

Authors: Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama, Koji Tabata
Published: 2026-01-30
Categories: stat.ML, cs.LG
arXiv: https://arxiv.org/abs/2601.22600v1

We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree $\mathcal{T}$ and a threshold $θ$, a player must answer whether the root node value of $\mathcal{T}$ is at least $θ$ or not. In the given tree, `MAX' or `MIN' is labeled on each internal node, and the value of a `MAX'-labeled (`MIN'-labeled) internal node is the maximum (minimum) of its child values. The value of a leaf node is the mean reward of an unknown distribution, from which the player can sample rewards. For this problem, we develop a $δ$-correct sequential sampling algorithm based on the Track-and-Stop strategy that has asymptotically optimal sample complexity. We show that a ratio-based modification of the D-Tracking arm-pulling strategy leads to a substantial improvement in empirical sample complexity, as well as reducing the per-round computational cost from linear to logarithmic in the number of arms.

---

### TimeMachine-bench: A Benchmark for Evaluating Model Capabilities in Repository-Level Migration Tasks

Authors: Ryo Fujii, Makoto Morishita, Kazuki Yano, Jun Suzuki
Published: 2026-01-30
Categories: cs.SE, cs.CL
arXiv: https://arxiv.org/abs/2601.22597v1

With the advancement of automated software engineering, research focus is increasingly shifting toward practical tasks reflecting the day-to-day work of software engineers. Among these tasks, software migration, a critical process of adapting code to evolving environments, has been largely overlooked. In this study, we introduce TimeMachine-bench, a benchmark designed to evaluate software migration in real-world Python projects. Our benchmark consists of GitHub repositories whose tests begin to fail in response to dependency updates. The construction process is fully automated, enabling live updates of the benchmark. Furthermore, we curated a human-verified subset to ensure problem solvability. We evaluated agent-based baselines built on top of 11 models, including both strong open-weight and state-of-the-art LLMs on this verified subset. Our results indicated that, while LLMs show some promise for migration tasks, they continue to face substantial reliability challenges, including spurious solutions that exploit low test coverage and unnecessary edits stemming from suboptimal tool-use strategies. Our dataset and implementation are available at https://github.com/tohoku-nlp/timemachine-bench.

---

### FOTBCD: A Large-Scale Building Change Detection Benchmark from French Orthophotos and Topographic Data

Authors: Abdelrrahman Moubane
Published: 2026-01-30
Categories: cs.CV
arXiv: https://arxiv.org/abs/2601.22596v1

We introduce FOTBCD, a large-scale building change detection dataset derived from authoritative French orthophotos and topographic building data provided by IGN France. Unlike existing benchmarks that are geographically constrained to single cities or limited regions, FOTBCD spans 28 departments across mainland France, with 25 used for training and three geographically disjoint departments held out for evaluation. The dataset covers diverse urban, suburban, and rural environments at 0.2m/pixel resolution. We publicly release FOTBCD-Binary, a dataset comprising approximately 28,000 before/after image pairs with pixel-wise binary building change masks, each associated with patch-level spatial metadata. The dataset is designed for large-scale benchmarking and evaluation under geographic domain shift, with validation and test samples drawn from held-out departments and manually verified to ensure label quality. In addition, we publicly release FOTBCD-Instances, a publicly available instance-level annotated subset comprising several thousand image pairs, which illustrates the complete annotation schema used in the full instance-level version of FOTBCD. Using a fixed reference baseline, we benchmark FOTBCD-Binary against LEVIR-CD+ and WHU-CD, providing strong empirical evidence that geographic diversity at the dataset level is associated with improved cross-domain generalization in building change detection.

---

### Learn More with Less: Uncertainty Consistency Guided Query Selection for RLVR

Authors: Hao Yi, Yulan Hu, Xin Li, Sheng Ouyang, Lizhong Ding, Yong Liu
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22595v1

Large Language Models (LLMs) have recently improved mathematical reasoning through Reinforcement Learning with Verifiable Reward (RLVR). However, existing RLVR algorithms require large query budgets, making annotation costly. We investigate whether fewer but more informative queries can yield similar or superior performance, introducing active learning (AL) into RLVR. We identify that classic AL sampling strategies fail to outperform random selection in this setting, due to ignoring objective uncertainty when only selecting by subjective uncertainty. This work proposes an uncertainty consistency metric to evaluate how well subjective uncertainty aligns with objective uncertainty. In the offline setting, this alignment is measured using the Point-Biserial Correlation Coefficient (PBC). For online training, because of limited sampling and dynamically shifting output distributions, PBC estimation is difficult. Therefore, we introduce a new online variant, computed from normalized advantage and subjective uncertainty. Theoretically, we prove that the online variant is strictly negatively correlated with offline PBC and supports better sample selection. Experiments show our method consistently outperforms random and classic AL baselines, achieving full-dataset performance while training on only 30% of the data, effectively reducing the cost of RLVR for reasoning tasks.

---

### Language Model Circuits Are Sparse in the Neuron Basis

Authors: Aryaman Arora, Zhengxuan Wu, Jacob Steinhardt, Sarah Schwettmann
Published: 2026-01-30
Categories: cs.CL, cs.AI
arXiv: https://arxiv.org/abs/2601.22594v2

The high-level concepts that a neural network uses to perform computation need not be aligned to individual neurons (Smolensky, 1986). Language model interpretability research has thus turned to techniques which decompose the neuron basis into more interpretable units of model computation, such as sparse autoencoders (SAEs). However, not all neuron-based representations are uninterpretable. For the first time, we empirically show that MLP neurons are as sparse a feature basis as SAEs. We use this finding to develop an end-to-end gradient-based attribution pipeline for circuit tracing on the MLP neuron basis, which surfaces causally effective neurons on a variety of tasks. On a standard subject-verb agreement benchmark (Marks et al., 2025), a circuit of $\approx 10^2$ MLP neurons is enough to control model behaviour. On the multi-hop city-state-capital task from (Lindsey et al., 2025), we find a circuit in which small sets of neurons encode specific latent reasoning steps (e.g. mapping a city to its state), and can be steered to change the model's output. This work thus advances automated interpretability of language models without imposing additional training costs.

---

### Heterogeneous Graph Alignment for Joint Reasoning and Interpretability

Authors: Zahra Moslemi, Ziyi Liang, Norbert Fortin, Babak Shahbaba
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22593v1

Multi-graph learning is crucial for extracting meaningful signals from collections of heterogeneous graphs. However, effectively integrating information across graphs with differing topologies, scales, and semantics, often in the absence of shared node identities, remains a significant challenge. We present the Multi-Graph Meta-Transformer (MGMT), a unified, scalable, and interpretable framework for cross-graph learning. MGMT first applies Graph Transformer encoders to each graph, mapping structure and attributes into a shared latent space. It then selects task-relevant supernodes via attention and builds a meta-graph that connects functionally aligned supernodes across graphs using similarity in the latent space. Additional Graph Transformer layers on this meta-graph enable joint reasoning over intra- and inter-graph structure. The meta-graph provides built-in interpretability: supernodes and superedges highlight influential substructures and cross-graph alignments. Evaluating MGMT on both synthetic datasets and real-world neuroscience applications, we show that MGMT consistently outperforms existing state-of-the-art models in graph-level prediction tasks while offering interpretable representations that facilitate scientific discoveries. Our work establishes MGMT as a unified framework for structured multi-graph learning, advancing representation techniques in domains where graph-based data plays a central role.

---

### FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery

Authors: Yue Li, Mingmin Chu, Xilei Yang, Da Xiao, Ziqi Xu, Wei Shao, Qipeng Song, Hui Li
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22589v1

Federated learning (FL) enables collaborative model training without centralizing raw data, but privacy regulations such as the right to be forgotten require FL systems to remove the influence of previously used training data upon request. Retraining a federated model from scratch is prohibitively expensive, motivating federated unlearning (FU). However, existing FU methods suffer from high unlearning overhead, utility degradation caused by entangled knowledge, and unintended relearning during post-unlearning recovery. In this paper, we propose FedCARE, a unified and low overhead FU framework that enables conflict-aware unlearning and relearning-resistant recovery. FedCARE leverages gradient ascent for efficient forgetting when target data are locally available and employs data free model inversion to construct class level proxies of shared knowledge. Based on these insights, FedCARE integrates a pseudo-sample generator, conflict-aware projected gradient ascent for utility preserving unlearning, and a recovery strategy that suppresses rollback toward the pre-unlearning model. FedCARE supports client, instance, and class level unlearning with modest overhead. Extensive experiments on multiple datasets and model architectures under both IID and non-IID settings show that FedCARE achieves effective forgetting, improved utility retention, and reduced relearning risk compared to state of the art FU baselines.

---

### Rethinking LLM-as-a-Judge: Representation-as-a-Judge with Small Language Models via Semantic Capacity Asymmetry

Authors: Zhuochun Li, Yong Zhang, Ming Li, Yuelyu Ji, Yiming Zeng, Ning Cheng, Yun Zhu, Yanmeng Wang, Shaojun Wang, Jing Xiao, Daqing He
Published: 2026-01-30
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22588v2

Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this "LLM-as-a-Judge" paradigm is costly, opaque, and sensitive to prompt design. In this work, we investigate whether smaller models can serve as efficient evaluators by leveraging internal representations instead of surface generation. We uncover a consistent empirical pattern: small LMs, despite with weak generative ability, encode rich evaluative signals in their hidden states. This motivates us to propose the Semantic Capacity Asymmetry Hypothesis: evaluation requires significantly less semantic capacity than generation and can be grounded in intermediate representations, suggesting that evaluation does not necessarily need to rely on large-scale generative models but can instead leverage latent features from smaller ones. Our findings motivate a paradigm shift from LLM-as-a-Judge to Representation-as-a-Judge, a decoding-free evaluation strategy that probes internal model structure rather than relying on prompted output. We instantiate this paradigm through INSPECTOR, a probing-based framework that predicts aspect-level evaluation scores from small model representations. Experiments on reasoning benchmarks (GSM8K, MATH, GPQA) show that INSPECTOR substantially outperforms prompting-based small LMs and closely approximates full LLM judges, while offering a more efficient, reliable, and interpretable alternative for scalable evaluation. The code and data are available at: https://github.com/zhuochunli/Representation-as-a-judge

---

### WED-Net: A Weather-Effect Disentanglement Network with Causal Augmentation for Urban Flow Prediction

Authors: Qian Hong, Siyuan Chang, Xiao Zhou
Published: 2026-01-30
Categories: cs.AI
arXiv: https://arxiv.org/abs/2601.22586v1

Urban spatio-temporal prediction under extreme conditions (e.g., heavy rain) is challenging due to event rarity and dynamics. Existing data-driven approaches that incorporate weather as auxiliary input often rely on coarse-grained descriptors and lack dedicated mechanisms to capture fine-grained spatio-temporal effects. Although recent methods adopt causal techniques to improve out-of-distribution generalization, they typically overlook temporal dynamics or depend on fixed confounder stratification. To address these limitations, we propose WED-Net (Weather-Effect Disentanglement Network), a dual-branch Transformer architecture that separates intrinsic and weather-induced traffic patterns via self- and cross-attention, enhanced with memory banks and fused through adaptive gating. To further promote disentanglement, we introduce a discriminator that explicitly distinguishes weather conditions. Additionally, we design a causal data augmentation strategy that perturbs non-causal parts while preserving causal structures, enabling improved generalization under rare scenarios. Experiments on taxi-flow datasets from three cities demonstrate that WED-Net delivers robust performance under extreme weather conditions, highlighting its potential to support safer mobility, highlighting its potential to support safer mobility, disaster preparedness, and urban resilience in real-world settings. The code is publicly available at https://github.com/HQ-LV/WED-Net.

---

### HetCCL: Accelerating LLM Training with Heterogeneous GPUs

Authors: Heehoon Kim, Jaehwan Lee, Taejeoung Kim, Jongwon Park, Jinpyo Kim, Pyongwon Suh, Ryan H. Choi, Sangwoo Lee, Jaejin Lee
Published: 2026-01-30
Categories: cs.DC, cs.LG
arXiv: https://arxiv.org/abs/2601.22585v1

The rapid growth of large language models is driving organizations to expand their GPU clusters, often with GPUs from multiple vendors. However, current deep learning frameworks lack support for collective communication across heterogeneous GPUs, leading to inefficiency and higher costs. We present HetCCL, a collective communication library that unifies vendor-specific backends and enables RDMA-based communication across GPUs without requiring driver modifications. HetCCL introduces two novel mechanisms that enable cross-vendor communication while leveraging optimized vendor libraries, NVIDIA NCCL and AMD RCCL. Evaluations on a multi-vendor GPU cluster show that HetCCL matches NCCL and RCCL performance in homogeneous setups while uniquely scaling in heterogeneous environments, enabling practical, high-performance training with both NVIDIA and AMD GPUs without changes to existing deep learning applications.

---

### MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning

Authors: Youngeun Kim
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22582v1

Group-relative policy optimization methods train language models by generating multiple rollouts per prompt and normalizing rewards with a shared mean reward baseline. In resource-constrained settings where the rollout budget is small, accuracy often degrades. We find that noise in the shared baseline induces advantage sign flips, where some rollouts receive an incorrect advantage sign, and the update direction is reversed. To address this, we propose Median-Centered Group Relative Policy Optimization (MC-GRPO), a simple and effective solution for small-rollout training. Our main idea is to replace the mean baseline with a median baseline: the median is far less sensitive to outlier rewards than the mean, mitigating the sign flips under small rollout size (G). We generate one additional rollout for median reference (G+1), and compute advantages by using the group median. With an odd-sized group, exactly one completion is the median and receives zero advantage, we exclude this pivot rollout from backpropagation so the number of gradient-contributing samples per prompt remains G, preserving the core update cost of standard G-rollout training. Across various GRPO-family methods and a wide range of models and scales, this median-centered training consistently improves stability and final accuracy in the low-rollout regime, reducing the gap between G=2 and G=8 to within 1%. Code is available at https://github.com/lotusroot-kim/MC-GRPO

---

### Cross-Domain Few-Shot Learning for Hyperspectral Image Classification Based on Mixup Foundation Model

Authors: Naeem Paeedeh, Mahardhika Pratama, Ary Shiddiqi, Zehong Cao, Mukesh Prasad, Wisnu Jatmiko
Published: 2026-01-30
Categories: cs.CV, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22581v2

Although cross-domain few-shot learning (CDFSL) for hyper-spectral image (HSI) classification has attracted significant research interest, existing works often rely on an unrealistic data augmentation procedure in the form of external noise to enlarge the sample size, thus greatly simplifying the issue of data scarcity. They involve a large number of parameters for model updates, being prone to the overfitting problem. To the best of our knowledge, none has explored the strength of the foundation model, having strong generalization power to be quickly adapted to downstream tasks. This paper proposes the MIxup FOundation MOdel (MIFOMO) for CDFSL of HSI classifications. MIFOMO is built upon the concept of a remote sensing (RS) foundation model, pre-trained across a large scale of RS problems, thus featuring generalizable features. The notion of coalescent projection (CP) is introduced to quickly adapt the foundation model to downstream tasks while freezing the backbone network. The concept of mixup domain adaptation (MDM) is proposed to address the extreme domain discrepancy problem. Last but not least, the label smoothing concept is implemented to cope with noisy pseudo-label problems. Our rigorous experiments demonstrate the advantage of MIFOMO, where it beats prior arts with up to 14% margin. The source code of MIFOMO is open-sourced at https://github.com/Naeem-Paeedeh/MIFOMO for reproducibility and convenient further study.

---

### SpanNorm: Reconciling Training Stability and Performance in Deep Transformers

Authors: Chao Wang, Bei Li, Jiaqi Zhang, Xinyu Liu, Yuchun Fan, Linkun Lyu, Xin Chen, Jingang Wang, Tong Xiao, Peng Pei, Xunliang Cai
Published: 2026-01-30
Categories: cs.CL, cs.AI, cs.LG
arXiv: https://arxiv.org/abs/2601.22580v2

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture ensures training stability at the cost of potential performance degradation in deep models, while the ``PostNorm'' architecture offers strong performance but suffers from severe training instability. In this work, we propose SpanNorm, a novel technique designed to resolve this dilemma by integrating the strengths of both paradigms. Structurally, SpanNorm establishes a clean residual connection that spans the entire transformer block to stabilize signal propagation, while employing a PostNorm-style computation that normalizes the aggregated output to enhance model performance. We provide a theoretical analysis demonstrating that SpanNorm, combined with a principled scaling strategy, maintains bounded signal variance throughout the network, preventing the gradient issues that plague PostNorm models, and also alleviating the representation collapse of PreNorm. Empirically, SpanNorm consistently outperforms standard normalization schemes in both dense and Mixture-of-Experts (MoE) scenarios, paving the way for more powerful and stable Transformer architectures.

---

### Non-Intrusive Graph-Based Bot Detection for E-Commerce Using Inductive Graph Neural Networks

Authors: Sichen Zhao, Zhiming Xue, Yalun Qi, Xianling Zeng, Zihan Yu
Published: 2026-01-30
Categories: cs.LG
arXiv: https://arxiv.org/abs/2601.22579v6

Malicious bots pose a growing threat to e-commerce platforms by scraping data, hoarding inventory, and perpetrating fraud. Traditional bot mitigation techniques, including IP blacklists and CAPTCHA-based challenges, are increasingly ineffective or intrusive, as modern bots leverage proxies, botnets, and AI-assisted evasion strategies. This work proposes a non-intrusive graph-based bot detection framework for e-commerce that models user session behavior through a graph representation and applies an inductive graph neural network for classification. The approach captures both relational structure and behavioral semantics, enabling accurate identification of subtle automated activity that evades feature-based methods. Experiments on real-world e-commerce traffic demonstrate that the proposed inductive graph model outperforms a strong session-level multilayer perceptron baseline in terms of AUC and F1 score. Additional adversarial perturbation and cold-start simulations show that the model remains robust under moderate graph modifications and generalizes effectively to previously unseen sessions and URLs. The proposed framework is deployment-friendly, integrates with existing systems without client-side instrumentation, and supports real-time inference and incremental updates, making it suitable for practical e-commerce security deployments.

---

### FedDis: A Causal Disentanglement Framework for Federated Traffic Prediction

Authors: Chengyang Zhou, Zijian Zhang, Chunxu Zhang, Hao Miao, Yulin Zhang, Kedi Lyu, Juncheng Hu
Published: 2026-01-30
Categories: cs.LG, cs.AI
arXiv: https://arxiv.org/abs/2601.22578v1

Federated learning offers a promising paradigm for privacy-preserving traffic prediction, yet its performance is often challenged by the non-identically and independently distributed (non-IID) nature of decentralized traffic data. Existing federated methods frequently struggle with this data heterogeneity, typically entangling globally shared patterns with client-specific local dynamics within a single representation. In this work, we postulate that this heterogeneity stems from the entanglement of two distinct generative sources: client-specific localized dynamics and cross-client global spatial-temporal patterns. Motivated by this perspective, we introduce FedDis, a novel framework that, to the best of our knowledge, is the first to leverage causal disentanglement for federated spatial-temporal prediction. Architecturally, FedDis comprises a dual-branch design wherein a Personalized Bank learns to capture client-specific factors, while a Global Pattern Bank distills common knowledge. This separation enables robust cross-client knowledge transfer while preserving high adaptability to unique local environments. Crucially, a mutual information minimization objective is employed to enforce informational orthogonality between the two branches, thereby ensuring effective disentanglement. Comprehensive experiments conducted on four real-world benchmark datasets demonstrate that FedDis consistently achieves state-of-the-art performance, promising efficiency, and superior expandability.

---

### Bonnet: Ultra-fast whole-body bone segmentation from CT scans

Authors: Hanjiang Zhu, Pedro Martelleto Rezende, Zhang Yang, Tong Ye, Bruce Z. Gao, Feng Luo, Siyu Huang, Jiancheng Yang
Published: 2026-01-30
Categories: eess.IV, cs.CV
arXiv: https://arxiv.org/abs/2601.22576v1

This work proposes Bonnet, an ultra-fast sparse-volume pipeline for whole-body bone segmentation from CT scans. Accurate bone segmentation is important for surgical planning and anatomical analysis, but existing 3D voxel-based models such as nnU-Net and STU-Net require heavy computation and often take several minutes per scan, which limits time-critical use. The proposed Bonnet addresses this by integrating a series of novel framework components including HU-based bone thresholding, patch-wise inference with a sparse spconv-based U-Net, and multi-window fusion into a full-volume prediction. Trained on TotalSegmentator and evaluated without additional tuning on RibSeg, CT-Pelvic1K, and CT-Spine1K, Bonnet achieves high Dice across ribs, pelvis, and spine while running in only 2.69 seconds per scan on an RTX A6000. Compared to strong voxel baselines, Bonnet attains a similar accuracy but reduces inference time by roughly 25x on the same hardware and tiling setup. The toolkit and pre-trained models will be released at https://github.com/HINTLab/Bonnet.

---