Machine Learning
CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
Keyu Wang, Bingchen Miao, Wendong Bu et al. (+7 more)
The development of
Multimodal Virtual
Agents has made significant progress through the integration of
Multimodal Large
Language Models. However, mainstream training paradigms face key challenges: Behavior Cloning is simple and effective through imitation but suffers from low behavioral diversity, while Reinforcement Learning is capable of discovering novel strategies through exploration but heavily relies on manually designed reward functions. To address the conflict between these two methods, we present CORE, a Code-based Inverse Self-Training Framework with Graph Expansion that bridges imitation and exploration, offering a novel training framework that promotes behavioral diversity while eliminating the reliance on manually reward design. Specifically, we introduce Semantic Code Abstraction to automatically infers reward functions from expert demonstrations without manual design. The inferred reward function, referred to as the Label Function, is executable code that verifies one key step within a task. Building on this, we propose Strategy Graph Expansion to enhance in-domain behavioral diversity, which constructs a multi-path graph called Strategy Graph that captures diverse valid solutions beyond expert demonstrations. Furthermore, we introduce Trajectory-Guided Extrapolation, which enriches out-of-domain behavioral diversity by utilizing both successful and failed trajectories to expand the task space. Experiments on Web and Android platforms demonstrate that CORE significantly improves both overall performance and generalization, highlighting its potential as a robust and generalizable training paradigm for building powerful virtual
agents.
Read the full abstract ▾
All authors Keyu Wang, Bingchen Miao, Wendong Bu, Yu Wu, Juncheng Li, Shengyu Zhang, Wenqiao Zhang, Siliang Tang, Jun Xiao, Yueting Zhuang
Machine Learning · Cross-listed from cs.CV
Mind the Gap: Continuous Magnification Sampling for Pathology Foundation Models
Alexander Möllers, Julius Hense, Florian Schulz et al. (+3 more)
In histopathology, pathologists examine both tissue architecture at low magnification and fine-grained morphology at high magnification. Yet, the performance of pathology foundation models across magnifications and the effect of magnification sampling during training remain poorly understood. We model magnification sampling as a multi-source domain adaptation problem and develop a simple theoretical framework that reveals systematic trade-offs between sampling strategies. We show that the widely used discrete uniform sampling of magnifications (0.25, 0.5, 1.0, 2.0 mpp) leads to degradation at intermediate magnifications. We introduce continuous magnification sampling, which removes gaps in magnification coverage while preserving performance at standard scales. Further, we derive sampling distributions that optimize representation quality across magnification scales. To evaluate these strategies, we introduce two new
benchmarks (TCGA-MS, BRACS-MS) with appropriate metrics. Our experiments show that continuous sampling substantially improves over discrete sampling at intermediate magnifications, with gains of up to 4 percentage points in balanced classification accuracy, and that optimized distributions can further improve performance. Finally, we evaluate current histopathology foundation models, finding that magnification is a primary driver of performance variation across models. Our work paves the way towards future pathology foundation models that perform reliably across magnifications.
Read the full abstract ▾
All authors Alexander Möllers, Julius Hense, Florian Schulz, Timo Milbich, Maximilian Alber, Lukas Ruff
Machine Learning
ACDZero: MCTS Agent for Mastering Automated Cyber Defense
Yu Li, Sizhe Tang, Rongqian Chen et al. (+5 more)
Automated cyber defense (ACD) seeks to protect computer networks with minimal or no human intervention, reacting to intrusions by taking corrective actions such as isolating hosts, resetting services, deploying decoys, or updating access controls. However, existing approaches for ACD, such as deep reinforcement learning (RL), often face difficult exploration in complex networks with large decision/state spaces and thus require an expensive amount of samples. Inspired by the need to learn sample-efficient defense policies, we frame ACD in CAGE Challenge 4 (CAGE-4 / CC4) as a context-based partially observable Markov decision problem and propose a planning-centric defense policy based on Monte Carlo Tree Search (MCTS). It explicitly models the exploration-exploitation tradeoff in ACD and uses statistical sampling to guide exploration and decision making. We make novel use of graph neural networks (GNNs) to embed observations from the network as attributed graphs, to enable permutation-invariant
reasoning over hosts and their relationships. To make our solution practical in complex search spaces, we guide MCTS with learned graph
embeddings and priors over graph-edit actions, combining model-free generalization and policy
distillation with look-ahead planning. We evaluate the resulting
agent on CC4 scenarios involving diverse network structures and adversary behaviors, and show that our search-guided, graph-
embedding-based planning improves defense reward and robustness relative to state-of-the-art RL baselines.
Read the full abstract ▾
All authors Yu Li, Sizhe Tang, Rongqian Chen, Fei Xu Yu, Guangyu Jiang, Mahdi Imani, Nathaniel D. Bastian, Tian Lan
Machine Learning
Learning with Monotone Adversarial Corruptions
Kasper Green Larsen, Chirag Pabbaraju and Abhishek Shetty
We study the extent to which standard machine learning
algorithms rely on exchangeability and independence of data by introducing a monotone
adversarial corruption model. In this model, an adversary, upon looking at a "clean" i.i.d.
dataset, inserts additional "corrupted" points of their choice into the
dataset. These added points are constrained to be monotone corruptions, in that they get labeled according to the ground-truth target function. Perhaps surprisingly, we demonstrate that in this setting, all known optimal learning
algorithms for binary classification can be made to achieve suboptimal expected error on a new independent test point drawn from the same distribution as the clean
dataset. On the other hand, we show that uniform convergence-based
algorithms do not degrade in their guarantees. Our results showcase how optimal learning
algorithms break down in the face of seemingly helpful monotone corruptions, exposing their overreliance on exchangeability.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
QuIC: A Quantum-Inspired Interaction Classifier for Revitalizing Shallow CNNs in Fine-Grained Recognition
Cheng Ying Wu and Yen Jui Chang
Deploying deep learning models for Fine-Grained Visual Classification (FGVC) on resource-constrained edge devices remains a significant challenge. While deep architectures achieve high accuracy on
benchmarks like CUB-200-2011, their computational cost is often prohibitive. Conversely, shallow networks (e.g., AlexNet, VGG) offer efficiency but fail to distinguish visually similar sub-categories. This is because standard Global Average Pooling (GAP) heads capture only first-order statistics, missing the subtle high-order feature interactions required for FGVC. While Bilinear CNNs address this, they suffer from high feature dimensionality and instability during training. To bridge this gap, we propose the
Quantum-inspired Interaction Classifier (QuIC). Drawing inspiration from
quantum mechanics, QuIC models feature channels as interacting
quantum states and captures second-order feature covariance via a learnable observable operator. Designed as a lightweight, plug-and-play module, QuIC supports stable, single-stage end-to-end training without exploding feature dimensions. Experimental results demonstrate that QuIC significantly revitalizes shallow backbones: it boosts the Top-1 accuracy of VGG16 by nearly 20% and outperforms state-of-the-art
attention mechanisms (SE-Block) on ResNet18. Qualitative analysis, including t-SNE visualization, further confirms that QuIC resolves ambiguous cases by explicitly attending to fine-grained discriminative features and enforcing compact intra-class clustering.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
FormationEval, an open multiple-choice benchmark for petroleum geoscience
Almaz Ermilov
This paper presents FormationEval, an open multiple-choice question
benchmark for evaluating
language models on petroleum geoscience and subsurface disciplines. The
dataset contains 505 questions across seven domains including petrophysics, petroleum geology and reservoir engineering, derived from three authoritative sources using a
reasoning model with detailed instructions and a concept-based approach that avoids verbatim copying of copyrighted text. Each question includes source metadata to support traceability and audit. The evaluation covers 72 models from major providers including OpenAI, Anthropic, Google, Meta and open-weight alternatives. The top performers achieve over 97% accuracy, with Gemini 3 Pro Preview reaching 99.8%, while tier and domain gaps persist. Among open-weight models, GLM-4.7 leads at 98.6%, with several DeepSeek, Llama, Qwen and Mistral models also exceeding 93%. The performance gap between open-weight and closed models is narrower than expected, with several lower-cost open-weight models exceeding 90% accuracy. Petrophysics emerges as the most challenging domain across all models, while smaller models show wider performance variance. Residual length bias in the
dataset (correct answers tend to be longer) is documented along with bias mitigation strategies applied during construction. The
benchmark, evaluation code and results are publicly available.
Read the full abstract ▾
Machine Learning
Entropy-Adaptive Fine-Tuning: Resolving Confident Conflicts to Mitigate Forgetting
Muxi Diao, Lele Yang, Wuxuan Gong et al. (+6 more)
Supervised Fine-Tuning (SFT) is the standard paradigm for domain adaptation, yet it frequently incurs the cost of catastrophic forgetting. In sharp contrast, on-policy Reinforcement Learning (RL) effectively preserves general capabilities. We investigate this discrepancy and identify a fundamental distributional gap: while RL aligns with the model's internal belief, SFT forces the model to fit external supervision. This mismatch often manifests as "Confident Conflicts"
tokens characterized by low probability but low
entropy. In these instances, the model is highly confident in its own prediction but is forced to learn a divergent ground truth, triggering destructive gradient updates. To address this, we propose
Entropy-Adaptive Fine-Tuning (EAFT). Unlike methods relying solely on prediction probability, EAFT utilizes
token-level
entropy as a gating mechanism to distinguish between epistemic uncertainty and knowledge conflict. This allows the model to learn from uncertain samples while suppressing gradients on conflicting data. Extensive experiments on Qwen and GLM series (ranging from 4B to 32B parameters) across mathematical, medical, and agentic domains confirm our hypothesis. EAFT consistently matches the downstream performance of standard SFT while significantly mitigating the degradation of general capabilities.
Read the full abstract ▾
All authors Muxi Diao, Lele Yang, Wuxuan Gong, Yutong Zhang, Zhonghao Yan, Yufei Han, Kongming Liang, Weiran Xu, Zhanyu Ma
Machine Learning · Cross-listed from cs.CV
BiPrompt: Bilateral Prompt Optimization for Visual and Textual Debiasing in Vision-Language Models
Sunny Gupta, Shounak Das and Amit Sethi
Vision language foundation models such as CLIP exhibit impressive zero-shot generalization yet remain vulnerable to spurious correlations across visual and textual modalities. Existing debiasing approaches often address a single modality either visual or textual leading to partial robustness and unstable adaptation under distribution shifts. We propose a bilateral
prompt optimization framework (BiPrompt) that simultaneously mitigates non-causal feature reliance in both modalities during test-time adaptation. On the visual side, it employs structured
attention-guided erasure to suppress background activations and enforce orthogonal prediction consistency between causal and spurious regions. On the textual side, it introduces balanced
prompt normalization, a learnable re-centering mechanism that aligns class
embeddings toward an isotropic semantic space. Together, these modules jointly minimize conditional mutual information between spurious cues and predictions, steering the model toward causal, domain invariant
reasoning without retraining or domain supervision. Extensive evaluations on real-world and synthetic bias
benchmarks demonstrate consistent improvements in both average and worst-group accuracies over prior test-time debiasing methods, establishing a lightweight yet effective path toward trustworthy and causally grounded
vision-
language adaptation.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.geo-ph
Feature-based Inversion of 2.5D Controlled Source Electromagnetic Data using Generative Priors
Hongyu Zhou, Haoran Sun, Rui Guo et al. (+3 more)
In this study, we investigate feature-based 2.5D controlled source marine electromagnetic (mCSEM) data inversion using generative priors. Two-and-half dimensional modeling using finite difference method (FDM) is adopted to compute the response of horizontal electric dipole (HED) excitation. Rather than using a neural network to approximate the entire inverse mapping in a black-box manner, we adopt a plug-andplay strategy in which a variational autoencoder (VAE) is used solely to learn prior information on conductivity distributions. During the inversion process, the conductivity model is iteratively updated using the Gauss Newton method, while the model space is constrained by projections onto the learned VAE decoder. This framework preserves explicit control over data misfit and enables flexible adaptation to different survey configurations. Numerical and field experiments demonstrate that the proposed approach effectively incorporates prior information, improves reconstruction accuracy, and exhibits good generalization performance.
Read the full abstract ▾
All authors Hongyu Zhou, Haoran Sun, Rui Guo, Maokun Li, Fan Yang, Shenheng Xu
Machine Learning
Edge-aware GAT-based protein binding site prediction
Weisen Yang, Hanqing Zhang, Wangren Qiu et al. (+2 more)
Accurate identification of
protein binding sites is crucial for understanding biomolecular interaction mechanisms and for the rational design of drug targets. Traditional predictive methods often struggle to balance prediction accuracy with computational efficiency when capturing complex spatial conformations. To address this challenge, we propose an Edge-aware Graph
Attention Network (Edge-aware GAT) model for the fine-grained prediction of binding sites across various biomolecules, including
proteins, DNA/RNA, ions, ligands, and lipids. Our method constructs atom-level graphs and integrates multidimensional structural features, including
geometric descriptors, DSSP-derived secondary structure, and relative solvent accessibility (RSA), to generate spatially aware
embedding vectors. By incorporating interatomic distances and directional vectors as edge features within the
attention mechanism, the model significantly enhances its representation capacity. On
benchmark datasets, our model achieves an ROC-AUC of 0.93 for
protein-
protein binding site prediction, outperforming several state-of-the-art methods. The use of directional tensor propagation and residue-level
attention pooling further improves both binding site localization and the capture of local structural details. Visualizations using PyMOL confirm the model's practical utility and interpretability. To facilitate community access and application, we have deployed a publicly accessible web server at http://119.45.201.89:5000/. In summary, our approach offers a novel and efficient solution that balances prediction accuracy, generalization, and interpretability for identifying functional sites in
proteins.
Read the full abstract ▾
All authors Weisen Yang, Hanqing Zhang, Wangren Qiu, Xuan Xiao, Weizhong Lin
Machine Learning · Cross-listed from cs.CV
Car Drag Coefficient Prediction from 3D Point Clouds Using a Slice-Based Surrogate Model
Utkarsh Singh, Absaar Ali and Adarsh Roy
The automotive industry's pursuit of enhanced fuel economy and performance necessitates efficient aerodynamic design. However, traditional evaluation methods such as computational fluid dynamics (CFD) and wind tunnel testing are resource intensive, hindering rapid iteration in the early design stages. Machine learning-based surrogate models offer a promising alternative, yet many existing approaches suffer from high computational complexity, limited interpretability, or insufficient accuracy for detailed
geometric inputs. This paper introduces a novel lightweight surrogate model for the prediction of the aerodynamic drag coefficient (Cd) based on a sequential slice-wise processing of the geometry of the 3D vehicle. Inspired by medical imaging, 3D point clouds of vehicles are decomposed into an ordered sequence of 2D cross-sectional slices along the stream-wise axis. Each slice is encoded by a lightweight PointNet2D module, and the sequence of slice
embeddings is processed by a bidirectional LSTM to capture longitudinal
geometric evolution. The model, trained and evaluated on the DrivAerNet++
dataset, achieves a high coefficient of determination (R^2 > 0.9528) and a low mean absolute error (MAE approx 6.046 x 10^{-3}) in Cd prediction. With an inference time of approximately 0.025 seconds per sample on a consumer-grade GPU, our approach provides fast, accurate, and interpretable aerodynamic feedback, facilitating more agile and informed automotive design exploration.
Read the full abstract ▾
Machine Learning
Prototype-Based Learning for Healthcare: A Demonstration of Interpretable AI
Ashish Rana, Ammar Shaker, Sascha Saralajew et al. (+6 more)
Despite recent advances in machine learning and explainable AI, a gap remains in personalized preventive healthcare: predictions, interventions, and recommendations should be both understandable and verifiable for all stakeholders in the healthcare sector. We present a demonstration of how prototype-based learning can address these needs. Our proposed framework, ProtoPal, features both front- and back-end modes; it achieves superior quantitative performance while also providing an intuitive presentation of interventions and their simulated outcomes.
Read the full abstract ▾
All authors Ashish Rana, Ammar Shaker, Sascha Saralajew, Takashi Suzuki, Kosuke Yasuda, Shintaro Kato, Toshikazu Wada, Toshiyuki Fujikawa, Toru Kikutsuji
Machine Learning
LION-DG: Layer-Informed Initialization with Deep Gradient Protocols for Accelerated Neural Network Training
Hyunjun Kim
Weight initialization remains decisive for neural network optimization, yet existing methods are largely layer-agnostic. We study initialization for deeply-supervised architectures with auxiliary classifiers, where untrained auxiliary heads can destabilize early training through gradient interference. We propose LION-DG, a layer-informed initialization that zero-initializes auxiliary classifier heads while applying standard He-initialization to the backbone. We prove that this implements Gradient Awakening: auxiliary gradients are exactly zero at initialization, then phase in naturally as weights grow – providing an implicit warmup without hyperparameters. Experiments on CIFAR-10 and CIFAR-100 with DenseNet-DS and ResNet-DS architectures demonstrate: (1) DenseNet-DS: +8.3% faster convergence on CIFAR-10 with comparable accuracy, (2) Hybrid approach: Combining LSUV with LION-DG achieves best accuracy (81.92% on CIFAR-10), (3) ResNet-DS: Positive speedup on CIFAR-100 (+11.3%) with side-tap auxiliary design. We identify architecture-specific trade-offs and provide clear guidelines for practitioners. LION-DG is simple, requires zero hyperparameters, and adds no computational overhead.
Read the full abstract ▾
Machine Learning
Horizon Activation Mapping for Neural Networks in Time Series Forecasting
Krupakar Hans and V A Kandappan
Neural networks for time series
forecasting have relied on error metrics and architecture-specific interpretability approaches for model selection that don't apply across models of different families. To interpret
forecasting models agnostic to the types of layers across state-of-the-art model families, we introduce Horizon Activation Mapping (HAM), a visual interpretability technique inspired by grad-CAM that uses gradient norm averages to study the horizon's subseries where grad-CAM studies
attention maps over image data. We introduce causal and anti-causal modes to calculate gradient update norm averages across subseries at every timestep and lines of proportionality signifying uniform distributions of the norm averages. Optimization landscape studies with respect to changes in batch sizes, early stopping, train-val-test splits, architectural choices, univariate
forecasting and dropouts are studied with respect to performances and subseries in HAM. Interestingly, batch size based differences in activities seem to indicate potential for existence of an exponential approximation across them per epoch relative to each other. Multivariate
forecasting models including MLP-based CycleNet, N-Linear, N-HITS, self
attention-based FEDformer, Pyraformer, SSM-based SpaceTime and
diffusion-based Multi-Resolution DDPM over different horizon sizes trained over the ETTm2
dataset are used for HAM plots in this study. NHITS' neural approximation
theorem and SpaceTime's exponential autoregressive activities have been attributed to trends in HAM plots over their training, validation and test sets. In general, HAM can be used for granular model selection, validation set choices and comparisons across different neural network model families.
Read the full abstract ▾
Machine Learning
ASSS: A Differentiable Adversarial Framework for Task-Aware Data Reduction
Jiacheng Lyu, Bihua Bao and Shiyun Yan
Massive
datasets often contain redundancy that inflates computational costs without improving generalization. Existing data reduction methods are typically task-agnostic, discarding informative boundary samples and yielding suboptimal performance. We propose
Adversarial Soft-Selection Subsampling (ASSS), a differentiable framework that casts data reduction as a minimax game between a learnable selector and a task network. Using Gumbel-Softmax relaxation, ASSS enables end-to-end gradient flow and is theoretically grounded in the information bottleneck principle. Experiments on multiple
benchmarks show that ASSS achieves a performance retention rate (PRR) of 98.9% while using only 30% of the data, significantly outperforming random sampling, K-means, and gradient-based methods. Visualizations confirm that ASSS preferentially retains samples near decision boundaries. The framework is scalable, fully differentiable, and easily integrated into existing training pipelines. This work introduces a new paradigm for task-aware data reduction that directly optimizes subset selection for the downstream objective, offering a principled and practical solution to the scalability challenges in modern deep learning.
Read the full abstract ▾
Machine Learning
The Homogeneity Trap: Spectral Collapse in Doubly-Stochastic Deep Networks
Yizhi Liu
Doubly-
stochastic matrices (DSM) are increasingly utilized in structure-preserving deep architectures – such as Optimal Transport layers and Sinkhorn-based
attention – to enforce numerical stability and probabilistic interpretability. In this work, we identify a critical spectral degradation phenomenon inherent to these constraints, termed the Homogeneity Trap. We demonstrate that the maximum-
entropy bias, typical of Sinkhorn-based projections, drives the mixing operator towards the uniform barycenter, thereby suppressing the subdominant singular value \sigma_2 and filtering out high-frequency feature components. We derive a spectral bound linking \sigma_2 to the network's effective depth, showing that high-
entropy constraints restrict feature transformation to a shallow effective receptive field. Furthermore, we formally demonstrate that Layer Normalization fails to mitigate this collapse in noise-dominated regimes; specifically, when spectral filtering degrades the Signal-to-Noise Ratio (SNR) below a critical threshold,
geometric structure is irreversibly lost to noise-induced orthogonal collapse. Our findings highlight a fundamental trade-off between entropic stability and spectral expressivity in DSM-constrained networks.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CE
MDAgent2: Large Language Model for Code Generation and Knowledge Q&A in Molecular Dynamics
Zhuofan Shi, Hubao A, Yufei Shao et al. (+8 more)
Molecular dynamics (MD) simulations are essential for understanding atomic-scale behaviors in materials science, yet writing LAMMPS scripts remains highly specialized and time-consuming tasks. Although LLMs show promise in code generation and domain-specific question answering, their performance in MD scenarios is limited by scarce domain data, the high deployment cost of state-of-the-art LLMs, and low code executability. Building upon our prior MDAgent, we present MDAgent2, the first end-to-end framework capable of performing both knowledge Q&A and code generation within the MD domain. We construct a domain-specific data-construction pipeline that yields three high-quality
datasets spanning MD knowledge, question answering, and code generation. Based on these
datasets, we adopt a three stage post-training strategy–continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL)–to train two domain-adapted models, MD-Instruct and MD-Code. Furthermore, we introduce MD-GRPO, a closed-loop RL method that leverages simulation outcomes as reward signals and recycles low-reward trajectories for continual refinement. We further build MDAgent2-RUNTIME, a deployable multi-
agent system that integrates code generation, execution, evaluation, and self-correction. Together with MD-EvalBench proposed in this work, the first
benchmark for LAMMPS code generation and question answering, our models and system achieve performance surpassing several strong baselines.This work systematically demonstrates the adaptability and generalization capability of large
language models in industrial simulation tasks, laying a methodological foundation for automatic code generation in AI for Science and industrial-scale simulations. URL: https://github.com/FredericVAN/PKU_MDAgent2
Read the full abstract ▾
All authors Zhuofan Shi, Hubao A, Yufei Shao, Dongliang Huang, Hongxu An, Chunxiao Xin, Haiyang Shen, Zhenyu Wang, Yunshan Na, Gang Huang, Xiang Jing
Machine Learning · Cross-listed from cs.AI
Higher-Order Action Regularization in Deep Reinforcement Learning: From Continuous Control to Building Energy Management
Faizan Ahmed, Aniket Dixit and James Brusey
Deep reinforcement learning
agents often exhibit erratic, high-frequency control behaviors that hinder real-world deployment due to excessive energy consumption and mechanical wear. We systematically investigate action smoothness regularization through higher-order derivative penalties, progressing from theoretical understanding in continuous control
benchmarks to practical validation in building energy management. Our comprehensive evaluation across four continuous control environments demonstrates that third-order derivative penalties (jerk minimization) consistently achieve superior smoothness while maintaining competitive performance. We extend these findings to HVAC control systems where smooth policies reduce equipment switching by 60%, translating to significant operational benefits. Our work establishes higher-order action regularization as an effective bridge between RL optimization and operational constraints in energy-critical applications.
Read the full abstract ▾
Machine Learning
Explore the Ideology of Deep Learning in ENSO Forecasts
Yanhai Gan, Yipeng Chen, Ning Li et al. (+3 more)
The El Ni{~n}o-Southern Oscillation (ENSO) exerts profound influence on global
climate variability, yet its prediction remains a grand challenge. Recent advances in deep learning have significantly improved
forecasting skill, but the opacity of these models hampers scientific trust and operational deployment. Here, we introduce a mathematically grounded interpretability framework based on bounded variation function. By rescuing the "dead"
neurons from the saturation zone of the activation function, we enhance the model's expressive capacity. Our analysis reveals that ENSO predictability emerges dominantly from the tropical Pacific, with contributions from the Indian and Atlantic Oceans, consistent with physical understanding. Controlled experiments affirm the robustness of our method and its
alignment with established predictors. Notably, we probe the persistent Spring Predictability Barrier (SPB), finding that despite expanded sensitivity during spring, predictive performance declines-likely due to suboptimal variable selection. These results suggest that incorporating additional ocean-atmosphere variables may help transcend SPB limitations and advance long-range ENSO prediction.
Read the full abstract ▾
All authors Yanhai Gan, Yipeng Chen, Ning Li, Xingguo Liu, Junyu Dong, Xianyao Chen
Machine Learning
Multivariate Time-series Anomaly Detection via Dynamic Model Pool & Ensembling
Wei Hu, Zewei Yu and Jianqiu Xu
Multivariate time-series (MTS) anomaly detection is critical in domains such as service monitor, IoT, and network security. While multi-model methods based on selection or ensembling outperform single-model ones, they still face limitations: (i) selection methods rely on a single chosen model and are sensitive to the strategy; (ii) ensembling methods often combine all models or are restricted to univariate data; and (iii) most methods depend on fixed data dimensionality, limiting scalability. To address these, we propose DMPEAD, a Dynamic Model Pool and Ensembling framework for MTS Anomaly Detection. The framework first (i) constructs a diverse model pool via parameter transfer and diversity metric, then (ii) updates it with a meta-model and similarity-based strategy for adaptive pool expansion, subset selection, and pool merging, finally (iii) ensembles top-ranked models through proxy metric ranking and top-k aggregation in the selected subset, outputting the final anomaly detection result. Extensive experiments on 8 real-world
datasets show that our model outperforms all baselines, demonstrating superior adaptability and scalability.
Read the full abstract ▾
Machine Learning
GDRO: Group-level Reward Post-training Suitable for Diffusion Models
Yiyang Wang, Xi Chen, Xiaogang Xu et al. (+2 more)
Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow
diffusion models for reward
alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it faces challenges including low efficiency, dependency on
stochastic samplers, and reward hacking. The problem is that rectified flow models are fundamentally different from LLMs: 1) For efficiency, online image sampling takes much more time and dominates the time of training. 2) For stochasticity, rectified flow is deterministic once the initial noise is fixed. Aiming at these problems and inspired by the effects of group-level rewards from LLMs, we design Group-level Direct Reward Optimization (GDRO). GDRO is a new post-training paradigm for group-level reward
alignment that combines the characteristics of rectified flow models. Through rigorous theoretical analysis, we point out that GDRO supports full offline training that saves the large time cost for image rollout sampling. Also, it is
diffusion-sampler-independent, which eliminates the need for the ODE-to-SDE approximation to obtain stochasticity. We also empirically study the reward hacking trap that may mislead the evaluation, and involve this factor in the evaluation using a corrected score that not only considers the original evaluation reward but also the trend of reward hacking. Extensive experiments demonstrate that GDRO effectively and efficiently improves the reward score of the
diffusion model through group-wise offline optimization across the OCR and GenEval tasks, while demonstrating strong stability and robustness in mitigating reward hacking.
Read the full abstract ▾
All authors Yiyang Wang, Xi Chen, Xiaogang Xu, Yu Liu, Hengshuang Zhao
Machine Learning
Output Embedding Centering for Stable LLM Pretraining
Felix Stollenwerk, Anna Lokrantz and Niclas Hertzberg
Pretraining of large
language models is not only expensive but also prone to certain training instabilities. A specific instability that often occurs at the end of training is output logit divergence. The most widely used mitigation strategies, z-loss and logit soft-capping, merely address the symptoms rather than the underlying cause of the problem. In this paper, we analyze the instability from the perspective of the output
embeddings' geometry and identify anisotropic
embeddings as its source. Based on this, we propose output
embedding centering (OEC) as a new mitigation strategy, and demonstrate that it suppresses output logit divergence. OEC can be implemented in two different ways: as a deterministic operation called $\mu$-centering, or a regularization method called $\mu$-loss. Our experiments show that both variants outperform z-loss in terms of training stability, while being on par with logit soft-capping. This holds true both in the presence and the absence of weight tying. As a secondary result, we find that $\mu$-loss is significantly less sensitive to regularization hyperparameter tuning than z-loss.
Read the full abstract ▾
Machine Learning
Prior Diffusiveness and Regret in the Linear-Gaussian Bandit
Yifan Zhu, John C. Duchi and Benjamin Van Roy
We prove that Thompson sampling exhibits $\tilde{O}(\sigma d \sqrt{T} + d r \sqrt{\mathrm{Tr}(\Sigma_0)})$
Bayesian regret in the linear-Gaussian bandit with a $\mathcal{N}(\mu_0, \Sigma_0)$ prior distribution on the coefficients, where $d$ is the dimension, $T$ is the time horizon, $r$ is the maximum $\ell_2$ norm of the actions, and $\sigma^2$ is the noise variance. In contrast to existing regret bounds, this shows that to within logarithmic factors, the prior-dependent “burn-in” term $d r \sqrt{\mathrm{Tr}(\Sigma_0)}$ decouples additively from the minimax (long run) regret $\sigma d \sqrt{T}$. Previous regret bounds exhibit a multiplicative dependence on these terms. We establish these results via a new “elliptical potential” lemma, and also provide a lower bound indicating that the burn-in term is unavoidable.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach
Matthias Bartolo, Dylan Seychell, Gabriel Hili et al. (+4 more)
This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection to exploit fine-grained, descriptive information available during training but not at inference. We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks, saliency maps, and depth cues-into deep learning-based object detectors through a teacher-student architecture. Experiments are conducted across five state-of-the-art object detection models and multiple public
benchmarks, including
UAV-based litter detection
datasets and Pascal VOC 2012, to assess the impact on accuracy, generalization, and computational efficiency. Our results demonstrate that LUPI-trained students consistently outperform their baseline counterparts, achieving significant boosts in detection accuracy with no increase in inference complexity or model size. Performance improvements are especially marked for medium and large objects, while ablation studies reveal that intermediate weighting of teacher guidance optimally balances learning from privileged and standard inputs. The findings affirm that the LUPI framework provides an effective and practical strategy for advancing object detection systems in both resource-constrained and real-world settings.
Read the full abstract ▾
All authors Matthias Bartolo, Dylan Seychell, Gabriel Hili, Matthew Montebello, Carl James Debono, Saviour Formosa, Konstantinos Makantasis
Machine Learning
SerpentFlow: Generative Unpaired Domain Alignment via Shared-Structure Decomposition
Julie Keisler, Anastase Alexandre Charantonis, Yannig Goude et al. (+2 more)
Domain
alignment refers broadly to learning correspondences between data distributions from distinct domains. In this work, we focus on a setting where domains share underlying structural patterns despite differences in their specific realizations. The task is particularly challenging in the absence of paired observations, which removes direct supervision across domains. We introduce a generative framework, called SerpentFlow (SharEd-structuRe decomPosition for gEnerative domaiN adapTation), for unpaired domain
alignment. SerpentFlow decomposes data within a latent space into a shared component common to both domains and a domain-specific one. By isolating the shared structure and replacing the domain-specific component with
stochastic noise, we construct synthetic training pairs between shared representations and target-domain samples, thereby enabling the use of conditional generative models that are traditionally restricted to paired settings. We apply this approach to super-resolution tasks, where the shared component naturally corresponds to low-frequency content while high-frequency details capture domain-specific variability. The cutoff frequency separating low- and high-frequency components is determined automatically using a classifier-based criterion, ensuring a data-driven and domain-adaptive decomposition. By generating pseudo-pairs that preserve low-frequency structures while injecting
stochastic high-frequency realizations, we learn the conditional distribution of the target domain given the shared representation. We implement SerpentFlow using Flow Matching as the generative pipeline, although the framework is compatible with other conditional generative approaches. Experiments on synthetic images, physical process simulations, and a
climate downscaling task demonstrate that the method effectively reconstructs high-frequency structures consistent with underlying low-frequency patterns, supporting shared-structure decomposition as an effective strategy for unpaired domain
alignment.
Read the full abstract ▾
All authors Julie Keisler, Anastase Alexandre Charantonis, Yannig Goude, Boutheina Oueslati, Claire Monteleoni
Machine Learning · Cross-listed from cs.CL
Hidden State Poisoning Attacks against Mamba-based Language Models
Alexandre Le Mercier, Chris Develder and Thomas Demeester
State space models (SSMs) like Mamba offer efficient alternatives to
Transformer-based
language models, with linear time complexity. Yet, their
adversarial robustness remains critically unexplored. This paper studies the phenomenon whereby specific short input phrases induce a partial amnesia effect in such models, by irreversibly overwriting information in their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA). Our
benchmark RoBench-25 allows evaluating a model's information
retrieval capabilities when subject to HiSPAs, and confirms the vulnerability of SSMs against such attacks. Even the recent Jamba-1.7-Mini SSM–
Transformer (a 52B hybrid model) collapses on RoBench-25 under some HiSPA triggers, whereas pure
Transformers do not. We also observe that HiSPA triggers significantly weaken the Jamba model on the popular Open-
Prompt-Injections
benchmark, unlike pure
Transformers. We further show that the theoretical and empirical findings extend to Mamba-2, and also analyse a Mamba-2-based hybrid (Nemotron-3-Nano). Finally, our interpretability study reveals patterns in Mamba's hidden layers during HiSPAs that could be used to build a HiSPA mitigation system. The full code and data to reproduce the experiments can be found at https://github.com/TortueSagace/hispa.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
A Multilayered Approach to Classifying Customer Responsiveness and Credit Risk
Ayomide Afolabi, Ebere Ogburu and Symon Kimitei
This study evaluates the performance of various classifiers in three distinct models: response, risk, and response-risk, concerning credit card mail campaigns and default prediction. In the response model, the Extra Trees classifier demonstrates the highest recall level (79.1%), emphasizing its effectiveness in identifying potential responders to targeted credit card offers. Conversely, in the risk model, the Random Forest classifier exhibits remarkable specificity of 84.1%, crucial for identifying customers least likely to default. Furthermore, in the multi-class response-risk model, the Random Forest classifier achieves the highest accuracy (83.2%), indicating its efficacy in discerning both potential responders to credit card mail campaign and low-risk credit card users. In this study, we optimized various performance metrics to solve a specific credit risk and mail responsiveness business problem.
Read the full abstract ▾
Machine Learning
Refinement Provenance Inference: Detecting LLM-Refined Training Prompts from Model Behavior
Bo Yin, Qi Li, Runpeng Yu et al. (+1 more)
Instruction tuning increasingly relies on LLM-based
prompt refinement, where
prompts in the training corpus are selectively rewritten by an external refiner to improve clarity and instruction
alignment. This motivates an instance-level audit problem: for a fine-tuned model and a training
prompt-response pair, can we infer whether the model was trained on the original
prompt or its LLM-refined version within a mixed corpus? This matters for
dataset governance and dispute resolution when training data are contested. However, it is non-trivial in practice: refined and raw instances are interleaved in the training corpus with unknown, source-dependent mixture ratios, making it harder to develop provenance methods that generalize across models and training setups. In this paper, we formalize this audit task as Refinement Provenance Inference (RPI) and show that
prompt refinement yields stable, detectable shifts in teacher-forced
token distributions, even when semantic differences are not obvious. Building on this phenomenon, we propose RePro, a logit-based provenance framework that fuses teacher-forced likelihood features with logit-ranking signals. During training, RePro learns a transferable representation via shadow fine-tuning, and uses a lightweight linear head to infer provenance on unseen victims without training-data access. Empirically, RePro consistently attains strong performance and transfers well across refiners, suggesting that it exploits refiner-agnostic distribution shifts rather than rewrite-style artifacts.
Read the full abstract ▾
All authors Bo Yin, Qi Li, Runpeng Yu, Xinchao Wang
Machine Learning · Cross-listed from cs.CV
Forget Less by Learning Together through Concept Consolidation
Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande et al. (+2 more)
Custom
Diffusion Models (CDMs) have gained significant
attention due to their remarkable ability to personalize generative processes. However, existing CDMs suffer from catastrophic forgetting when continuously learning new concepts. Most prior works attempt to mitigate this issue under the sequential learning setting with a fixed order of concept inflow and neglect inter-concept interactions. In this paper, we propose a novel framework - Forget Less by Learning Together (FL2T) - that enables concurrent and order-agnostic concept learning while addressing catastrophic forgetting. Specifically, we introduce a set-invariant inter-concept learning module where proxies guide feature selection across concepts, facilitating improved knowledge retention and transfer. By leveraging inter-concept guidance, our approach preserves old concepts while efficiently incorporating new ones. Extensive experiments, across three
datasets, demonstrates that our method significantly improves concept retention and mitigates catastrophic forgetting, highlighting the effectiveness of inter-concept catalytic behavior in incremental concept learning of ten tasks with at least 2% gain on average CLIP Image
Alignment scores.
Read the full abstract ▾
All authors Arjun Ramesh Kaushik, Naresh Kumar Devulapally, Vishnu Suresh Lokhande, Nalini Ratha, Venu Govindaraju
Machine Learning
SynRXN: An Open Benchmark and Curated Dataset for Computational Reaction Modeling
Tieu-Long Phan, Nhu-Ngoc Nguyen Song and Peter F. Stadler
We present SynRXN, a unified benchmarking framework and open-data resource for computer-aided synthesis planning (CASP). SynRXN decomposes end-to-end synthesis planning into five task families, covering reaction rebalancing, atom-to-atom mapping, reaction classification, reaction property prediction, and synthesis route design. Curated, provenance-tracked reaction corpora are assembled from heterogeneous public sources into a harmonized representation and packaged as versioned
datasets for each task family, with explicit source metadata, licence tags, and machine-readable manifests that record checksums, and row counts. For every task, SynRXN provides transparent splitting functions that generate leakage-aware train, validation, and test partitions, together with standardized evaluation workflows and metric suites tailored to classification, regression, and structured prediction settings. For sensitive benchmarking, we combine public training and validation data with held-out gold-standard test sets, and contamination-prone tasks such as reaction rebalancing and atom-to-atom mapping are distributed only as evaluation sets and are explicitly not intended for model training. Scripted build recipes enable bitwise-reproducible regeneration of all corpora across machines and over time, and the entire resource is released under permissive open licences to support reuse and extension. By removing
dataset heterogeneity and packaging transparent, reusable evaluation scaffolding, SynRXN enables fair longitudinal comparison of CASP methods, supports rigorous ablations and stress tests along the full reaction-informatics pipeline, and lowers the barrier for practitioners who seek robust and comparable performance estimates for real-world synthesis planning workloads.
Read the full abstract ▾