Machine Learning
Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation
Habibeh Naderi, Behrouz Haji Soleimani and Stan Matwin
We introduce CoCo-LoRA, a
multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. Existing PEFT approaches such as LoRA are efficient but typically deterministic, while recent
Bayesian low-rank adapters model uncertainty in a lightweight way yet remain largely unimodal and condition uncertainty primarily on internal text features. This leaves them poorly equipped to reflect uncertainty driven by external acoustic factors such as background noise, channel variability, or speaking style, which can materially affect reliability in
speech-centered applications. CoCo-LoRA addresses this gap by conditioning a contextual variational posterior in the low-rank space on both local text-derived adapter features and an audio-derived context signal. A pooled audio
embedding is projected once into a shared context space and then adapted through lightweight layer-wise heads, enabling global-to-local, depth-specific modulation of the adapter uncertainty and update without high-dimensional
multimodal fusion. Stochasticity is confined to a compact latent component in the rank space, preserving PEFT scalability while producing audio-sensitive, heteroscedastic uncertainty. Based on our evaluations across diverse tasks and backbone combinations, CoCo-LoRA consistently matches or outperforms text-only PEFT and conventional feature-fusion transfer baselines, particularly on high-coverage labels where reliable adaptation is critical. The results indicate that using audio as a contextual uncertainty signal, rather than as a fused feature stream, provides a robust and parameter-efficient alternative for
multimodal low-resource prediction.
Read the full abstract ▾
Machine Learning
FedLLM: A Privacy-Preserving Federated Large Language Model for Explainable Traffic Flow Prediction
Seerat Kaur, Sukhjit Singh Sehra and Dariush Ebrahimi
Traffic prediction plays a central role in intelligent transportation systems (ITS) by supporting real-time decision-making, congestion management, and long-term planning. However, many existing approaches face practical limitations. Most spatio-temporal models are trained on centralized data, rely on numerical representations, and offer limited explainability. Recent Large
Language Model (LLM) methods improve
reasoning capabilities but typically assume centralized data availability and do not fully capture the distributed and heterogeneous nature of real-world traffic systems. To address these challenges, this study proposes FedLLM (
Federated LLM), a
privacy-preserving and distributed framework for explainable multi-horizon short-term traffic flow prediction (15-60 minutes). The framework introduces four key contributions: 1) a Composite Selection Score (CSS) for data-driven freeway selection that captures structural diversity across traffic regions 2) a domain-adapted LLM fine-tuned on structured traffic
prompts encoding spatial, temporal, and statistical context 3) FedLLM framework, that enables collaborative training across heterogeneous clients while exchanging only lightweight LoRA adapter parameters, 4) a structured
prompt representation that supports contextual
reasoning and cross-region generalization. The FedLLM design allows each client to learn from local traffic patterns while contributing to a shared global model through efficient parameter exchange, reducing communication overhead and keeping data private. This setup supports learning under non-IID traffic distributions. Experimental results show that FedLLM achieves improved predictive performance over centralized baselines, while producing structured and explainable outputs. These findings highlight the potential of combining FL with domain-adapted LLMs for scalable,
privacy-aware, and explainable traffic prediction.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Fairness Constraints in High-Dimensional Generalized Linear Models
Yixiao Lin and James Booth
Most
fairness-aware learning methods assume that sensitive attributes are observed, an assumption that may fail due to
privacy, legal, or data-collection constraints. We develop a framework for
fairness-aware generalized linear models when the sensitive attribute is latent, possibly multi-category, and the predictors may be high-dimensional. Candidate proxy variables are modeled using Gaussian mixtures for continuous predictors and product-multinomial mixtures for categorical predictors. The resulting posterior group-membership probabilities are used to residualize the predictors and reduce their association with the latent sensitive structure. For continuous outcomes, we use constrained least squares to limit the contribution of the estimated sensitive attribute to prediction variability. For binary outcomes, we use penalized logistic regression to reduce dependence between predicted probabilities and estimated group membership. In high-dimensional settings, the procedure is combined with SEMMS variable selection to obtain sparse models. We establish identifiability and latent-class recovery results for Gaussian and categorical mixtures and derive expressions that quantify the loss of predictive power after residualization.Simulations and real-data applications demonstrate favorable accuracy-
fairness performance.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CR
SafeLM: Unified Privacy-Aware Optimization for Trustworthy Federated Large Language Models
Noor Islam S. Mohammad and Uluğ Bayaz{\i}t
Large
language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:
privacy, security, misinformation, and
adversarial robustness. SafeLM combines
federated training with gradient smartification and Paillier encryption for
privacy, integrates defenses against training and inference-time attacks, employs contrastive grounding with calibrated decoding to reduce
hallucinations, and introduces
alignment-aware binarized aggregation to enhance robustness while maintaining bounded reconstruction quality. Across
benchmarks on factuality, toxicity, and membership inference, SafeLM achieves 98.0% harmful content detection accuracy, reduces communication by 96.9%, and lowers gradient inversion PSNR from 31.7 dB to 15.1 dB. Ablations show that each component contributes independently, whereas their integration yields a strong
privacy utility efficiency trade-off for deploying trustworthy LLMs.
Read the full abstract ▾
Machine Learning
Randomized Antipodal Search Done Right for Data Pareto Improvement of LLM Unlearning
Ziwen Liu, Huawei Lin, Yide Ran et al. (+5 more)
Large
language models (LLMs) sometimes memorize undesirable knowledge, which must be removed after deployment. Prior work on machine unlearning has focused largely on optimization methods that adjust parameters to enforce forgetting while preserving retention. However, these approaches assume that the forget and retain sets are readily available, which rarely holds in practice. Unlearning is typically triggered by an undesired generation at inference time, making the
retrieval of relevant data the central challenge. We introduce the notion of data Pareto improvement for LLM unlearning, which formalizes how
retrieval can expand the achievable trade-off frontier between forgetting and retention. To realize this principle, we propose Randomized Antipodal Search on Linearized Influence Kernel (RASLIK), a
retrieval algorithm that combines permutation-projection hashing with randomized antipodal search. RASLIK reduces selection variance, achieves sublinear complexity, and yields a double gain in both quality and efficiency. Across multiple models,
datasets, and unlearning
algorithms, RASLIK consistently outperforms deterministic baselines and even oracle sampling, establishing randomized search as a principled and scalable solution for data-centric unlearning.
Read the full abstract ▾
All authors Ziwen Liu, Huawei Lin, Yide Ran, Denghui Zhang, Jianwen Xie, Chuan Li, Weijie Zhao, Zhaozhuo Xu
Machine Learning
Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Earth System Prediction
Xiao Wang, Zezhong Zhang, Isaac Lyngaas et al. (+10 more)
Accurate Earth system prediction requires state inference from incomplete observations, but conventional two-stage data assimilation (DA) is computationally prohibitive because repeated PDE-based ensemble forecasts, observation updates, and intermediate data movement limit ensemble size at high resolution. We introduce STORM, a one-stage generative AI framework that reformulates DA as
diffusion-based
Bayesian posterior sampling, replacing online PDE ensemble forecasts with scalable AI inference. It further combines a spatiotemporal
transformer with a global-
attention algorithm that reduces complexity from quadratic to linear through scalable gradient propagation, enabling high-resolution, long-context Earth modeling. STORM scales to 74,400 GPUs on Frontier with 96–99% strong-scaling efficiency and up to 6 ExaFLOPs sustained BF16 throughput, while enabling 32,768-member ensembles for uncertainty quantification in 34 seconds on 4,096 GPUs. It scales to 20 billion spatiotemporal
tokens and 177,000 temporal frames. Hurricane tracking and long-term
climate reanalysis demonstrate improved accuracy, including benefits from longer temporal context and recovery of temperature extremes missed by forecast-only predictions.
Read the full abstract ▾
All authors Xiao Wang, Zezhong Zhang, Isaac Lyngaas, Hong-Jun Yoon, Jong-Youl Choi, Siming Liang, Janet Wang, Hristo G. Chipilski, Ashwin M. Aji, Feng Bao, Peter Jan van Leeuwen, Dan Lu, Guannan Zhang
Machine Learning
Hybrid Spectro-Temporal Fusion Framework for Structural Health Monitoring
Jongyeop Kim, Jinki Kim and Doyun Lee
Structural health monitoring plays a critical role in ensuring structural safety by analyzing vibration responses from engineering systems. This paper proposes a Spectro-Temporal
Alignment framework and a Hybrid Spectro-Temporal Fusion framework that integrate arrival-time interval descriptors with spectral features to capture both fine-scale and coarse-scale vibration dynamics. Experiments conducted on data collected from an LDS V406 electrodynamic shaker demonstrate that the proposed spectro-temporal representations significantly outperform conventional input formulations. The results indicate that a temporal resolution ({\Delta}{\tau}) of 0.008 of 0.02 favors traditional machine learning models, whereas a finer resolution ({\Delta}{\tau}) of 0.008 effectively unlocks the performance potential of deep learning architectures. Beyond classification accuracy, a comprehensive stability analysis based on condensed indices, including mean performance, standard deviation, coefficient of variation, and balanced score, shows that the proposed hybrid framework consistently achieves higher accuracy with substantially lower variability compared to baseline and
alignment-only approaches. Overall, these results demonstrate that the proposed framework provides a robust, accurate, and reliable solution for vibration-based structural health monitoring.
Read the full abstract ▾
Machine Learning
A Systematic Survey and Benchmark of Deep Learning for Molecular Property Prediction in the Foundation Model Era
Zongru Li, Xingsheng Chen, Honggang Wen et al. (+8 more)
Molecular property prediction integrates
quantum chemistry, cheminformatics, and deep learning to connect molecular structure with physicochemical and biological behavior. This survey traces four complementary paradigms, including
Quantum, Descriptor Machine Learning,
Geometric Deep Learning, and Foundation Models, and outlines a unified taxonomy linking molecular representations, model architectures, and interdisciplinary applications.
Benchmark analyses integrate evidence from both widely used
datasets and
datasets reflecting industry perspectives, encompassing
quantum, physicochemical, physiological, and biophysical domains. The survey examines current standards in data curation, splitting strategies, and evaluation protocols, highlighting challenges including inconsistent stereochemistry, heterogeneous assay sources, and reproducibility limitations under random or poorly defined splits. These observations motivate the modernization of
benchmark design toward more transparent, time- and scaffold-aware methodologies. We further propose three forward-looking directions: (i) physics-aware learning
embedding quantum consistency, (ii) uncertainty-calibrated foundation models for trustworthy inference, and (iii) realistic
multimodal benchmark ecosystems integrating computational and experimental data. Repository: https://github.com/Zongru-Li/Survey-and-
Benchmarks-of-DL-for-Molecular-Property-Prediction-in-the-Foundation-Model-Era.
Read the full abstract ▾
All authors Zongru Li, Xingsheng Chen, Honggang Wen, Regina Qianru Zhang, Ming Li, Xiaojin Zhang, Hongzhi Yin, Qiang Yang, Kwok-Yan Lam, Pietro Lio, Siu-Ming Yiu
Machine Learning
The Global Neural World Model: Spatially Grounded Discrete Topologies for Action-Conditioned Planning
Noureddine Kermiche
We present the Global Neural World Model (GNWM), a self-stabilizing framework that achieves topological quantization through balanced continuous
entropy constraints. Operating as a continuous, action-conditioned Joint-
Embedding Predictive Architecture (JEPA), the GNWM maps environments onto a discrete 2D grid, enforcing translational equivariance without pixel-level reconstruction. Our results show this architecture prevents
manifold drift during autoregressive rollouts by using grid “snapping” as a native error-correction mechanism. Furthermore, by training via maximum
entropy exploration (random walks), the model learns generalized transition dynamics rather than memorizing specific expert trajectories. We validate the GNWM across passive observation, active
agent control, and abstract sequence regimes, demonstrating its capacity to act not just as a spatial physics simulator, but as a causal discovery model capable of organizing continuous, predictable concepts into structured topological maps.
Read the full abstract ▾
Machine Learning
POLAR: Online Learning for LoRA Adapter Caching and Routing in Edge LLM Serving
Shaoang Li and Jian Li
Edge deployment of large
language models (LLMs) increasingly relies on libraries of lightweight LoRA adapters, yet GPU/DRAM can keep only a small resident subset at a time. Serving a request through a non-resident adapter requires paging its weights from storage, incurring measurable latency. This creates a two-timescale online control problem: on a slow timescale, the system selects which adapters remain resident in fast
memory, while on a fast timescale it routes each request to an adapter whose context-dependent utility is unknown a priori. The two decisions are tightly coupled: the cache determines the cost of exploration, and the router determines which adapters receive informative feedback. We formulate this joint caching-and-routing problem as a two-timescale contextual bandit and propose POLAR (Paging and Online Learning for Adapter Routing). POLAR pairs a cache-aware LinUCB router with an epoch-based cache controller. We study two variants. A fixed-epoch version provides a robust baseline with worst-case regret guarantees under arbitrary contexts. An epoch-doubling version, POLAR+, adds forced exploration and improved cache optimization to achieve $\widetilde{\mathcal{O}}(d\sqrt{NT}+\sqrt{KT})$ sublinear regret under
stochastic regularity and cacheability conditions, where $N$ is the adapter count, $K$ the cache size, $d$ the context dimension, and $T$ the horizon. The routing term matches the standard contextual-bandit rate up to logarithmic factors, showing that the
memory hierarchy does not fundamentally slow routing learning. Experiments using 15 real LoRA adapters for Qwen2.5-7B together with measured GPU paging latencies show that adaptive cache control substantially outperforms non-adaptive baselines and exhibits scaling trends consistent with the theory.
Read the full abstract ▾
Machine Learning
NCO4CVRP: Neural Combinatorial Optimization for the Capacitated Vehicle Routing Problem
Mahir Labib Dihan, Md. Ashrafur Rahman Khan, Wasif Jalal et al. (+2 more)
Neural Combinatorial Optimization (NCO) has emerged as a powerful framework for solving combinatorial optimization problems by integrating deep learning-based models. This work focuses on improving existing inference techniques to enhance solution quality and generalization. Specifically, we modify the Random Re-Construct (RRC) approach of the Light Encoder Heavy Decoder (LEHD) model by incorporating Simulated Annealing (SA). Unlike the conventional RRC, which greedily replaces suboptimal segments, our SA-based modification introduces a probabilistic acceptance mechanism that allows the model to escape local optima and explore a more diverse solution space. Additionally, we enhance the Policy Optimization with Multiple Optima (POMO) approach by integrating Beam Search, enabling systematic exploration of multiple promising solutions while maintaining diversity in the search space. We further investigate different inference strategies, including Softmax Sampling, Greedy, Gumbel-Softmax, and Epsilon-Greedy, analyzing their impact on solution quality. Furthermore, we explore instance augmentation techniques, such as horizontal and vertical flipping and rotation-based augmentations, to improve model generalization across different CVRP instances. Our extensive experiments demonstrate that these modifications significantly reduce the optimality gap across various Capacitated Vehicle Routing Problem (CVRP)
benchmarks, with Beam Search and SA-based RRC consistently yielding superior performance. By refining inference techniques and leveraging enhanced search strategies, our work contributes to the broader applicability of NCO models in real-world combinatorial optimization tasks.
Read the full abstract ▾
All authors Mahir Labib Dihan, Md. Ashrafur Rahman Khan, Wasif Jalal, Md. Roqunuzzaman Sojib, Mashroor Hasan Bhuiyan
Machine Learning
Continuous ageing trajectory representations for knee-aware lifetime prediction of lithium-ion batteries across heterogeneous dataset
Agnieszka Pregowska and Stefan Marynowicz
Accurate assessment of lithium-ion battery ageing is challenged by
cell-to-
cell variability, heterogeneous cycling protocols, and limited transferability of data-driven models across
datasets. In particular, robust identification of degradation transitions, such as the knee point, and reliable early-life prediction of remaining useful life (RUL) remain open problems. This study proposes a unified framework for battery ageing analysis based on continuous representations of voltage-capacity and capacity-cycle trajectories learned from heterogeneous public
datasets (NASA, CALCE, ISU-ILCC). The continuous formulation enables consistent extraction of degradation descriptors, including
curvature, plateau length and knee-related metrics, while reducing sensitivity to
dataset-specific discretisation. Across more than 250
cells, statistically significant correlations between knee onset and end-of-life (Pearson 0.75-0.84) are observed. Additional early-life analysis confirms that knee-related features retain predictive value when estimated from partial trajectories. Early-life models provide increasingly stable RUL predictions as the number of observed cycles increases, with meaningful predictive performance emerging within the first 5-20 cycles and remain robust under cross-
dataset domain shift. The framework integrates continuous modelling, feature extraction and uncertainty-aware prediction, providing an interpretable and
dataset-consistent approach demonstrating robustness across heterogeneous
dataset types. Compared with conventional discrete or feature-based methods, the proposed representation reduces sensitivity to sampling resolution and improves cross-
dataset consistency. The study is limited to laboratory-scale
datasets and capacity-based end-of-life definitions.
Read the full abstract ▾
Machine Learning
EviDep: Uncertainty-Aware Multimodal Depression Estimation via Disentangled Evidential Learning
Fangyuan Liu, Sirui Zhao, Yangsong Zhang et al. (+5 more)
Audio–visual recordings provide complementary cues for estimating depression severity, but their informativeness varies across time and modalities. Point predictions alone do not express the uncertainty associated with these estimates. We present EviDep, a
multimodal evidential regression framework that integrates multi-scale temporal modeling and shared–private representation learning for uncertainty-aware depression estimation. Frequency-aware Feature Extraction decomposes behavioral feature sequences into multiple frequency bands and refines them with scale-specific experts. Disentangled Evidential Learning encourages the disentanglement of cross-modal shared and modality-specific information in the refined features. Multi-branch Evidential Regression maps the resulting shared and private representations to three Normal-Inverse-Gamma (NIG) outputs and uses evidence-weighted aggregation to estimate depression severity and quantify aleatoric and epistemic uncertainty. Experiments on AVEC 2013, AVEC 2014, DAIC-WOZ, and E-DAIC show competitive prediction accuracy, with ablation studies supporting the contributions of frequency-aware refinement and shared–private disentanglement. Further analyses show that estimated epistemic uncertainty helps identify higher-error predictions, while both uncertainty estimates generally increase under controlled feature degradation.
Read the full abstract ▾
All authors Fangyuan Liu, Sirui Zhao, Yangsong Zhang, Jinyang Huang, Feng-Qi Cui, Bin Luo, Tong Xu, Enhong Chen
Machine Learning
Evaluating Temporal and Structural Anomaly Detection Paradigms for DDoS Traffic
Yasmin Souza Lima, Rodrigo Moreira, Larissa F. Rodrigues Moreira et al. (+2 more)
Unsupervised anomaly detection is widely used to detect Distributed Denial-of-Service (DDoS) attacks in cloud-native 5G networks, yet most studies assume a fixed traffic representation, either temporal or structural, without validating which feature space best matches the data. We propose a lightweight decision framework that prioritizes temporal or structural features before training, using two diagnostics: lag-1 autocorrelation of an aggregated flow signal and PCA cumulative explained variance. When the probes are inconclusive, the framework reserves a hybrid option as a future fallback rather than an empirically validated branch. Experiments on two statistically distinct
datasets with Isolation Forest, One-Class SVM, and KMeans show that structural features consistently match or outperform temporal ones, with the performance gap widening as temporal dependence weakens.
Read the full abstract ▾
All authors Yasmin Souza Lima, Rodrigo Moreira, Larissa F. Rodrigues Moreira, Tereza Cristina M. de B. Carvalho, Flávio de Oliveira Silva
Machine Learning
FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling
Xingyan Chen, Tian Du, Changqiao Xu et al. (+4 more)
Federated Learning (FL) faces challenges from client data heterogeneity and resource-constrained mobile devices, which can degrade model accuracy. Personalized
Federated Learning (PFL) addresses this issue by adapting shared global knowledge to local data distributions. A promising approach in PFL is model decoupling, which separates the model into global and personalized parameters, raising the key question of which parameters should be personalized to balance global knowledge sharing and local adaptation. In this paper, we propose a
Federated Optimal
Brain Personalization (FedOBP)
algorithm with a
quantile-based thresholding mechanism and introduce an element-wise importance score. This score extends Optimal
Brain Damage (OBD)
pruning theory by incorporating a
federated approximation of the first-order derivative in the Taylor expansion to evaluate the importance of each parameter for personalization. Moreover, we move the metric computation originally performed on clients to the server side, to alleviate the burden on resource-constrained mobile devices. To the best of our knowledge, this is the first work to bridge classical saliency-based
pruning theory with
federated parameter decoupling, providing a rigorous theoretical justification for selecting personalized parameters based on their sensitivity to local loss landscapes. Extensive experiments demonstrate that FedOBP outperforms state-of-the-art methods across diverse
datasets and heterogeneity scenarios, while requiring personalization of only a very small number of personalized parameters.
Read the full abstract ▾
All authors Xingyan Chen, Tian Du, Changqiao Xu, Fuzhen Zhuang, Lujie Zhong, Gabriel-Miro Muntean, Enmao Diao
Machine Learning
From User Recognition to Activity Counting: An Identity-Agnostic Approach to Multi-User WiFi Sensing
Kemal Bayik, Olayinka Ajayi, Daniel Roggen et al. (+1 more)
WiFi Channel State Information (CSI) enables device-free human activity recognition, but multi-user methods typically assume a fixed set of known users and degrade on unseen individuals. We reformulate multi-user recognition as identity-agnostic activity counting, estimating how many users perform each activity without assigning actions to individuals. For a controlled comparison, identity-dependent predictions are converted to activity counts and evaluated with the same integer-valued metrics using a shared pipeline that differs only in output head and objective. On WiMANS, identity-agnostic counting achieves lower integer-count MAE than derived identity-dependent counts (0.0815 versus 0.0909 on a 0-5 count scale) despite using coarser supervision. This ordering holds across all eight environment-band conditions, while derived counts lead only in exact-match accuracy. Under leave-users-out evaluation, identity-dependent macro-F1 drops from 80.02% to 33.85%, its derived counts perform only slightly better than an all-zero predictor, and the exact-match advantage reverses, while identity-agnostic counting leads on all counting metrics. Silhouette analysis shows that identity-dependent
embeddings cluster by user identity, whereas identity-agnostic
embeddings cluster by activity composition. Activity counting therefore provides a more accurate and robust formulation for scene-level activity composition estimation without requiring a predefined user set.
Read the full abstract ▾
All authors Kemal Bayik, Olayinka Ajayi, Daniel Roggen, Philip Birch
Machine Learning
In Search of Lost DNA Sequence Pretraining
Zhijiang Tang, Jiaxin Qi, Yan Cui et al. (+3 more)
DNA sequence encoding is fundamental to gene function prediction,
protein synthesis, and diverse downstream biological tasks. Despite the substantial progress achieved by large-scale DNA sequence pretraining, existing studies have overwhelmingly emphasized pretraining scale and custom downstream evaluation
datasets, while neglecting some essential components of the pretraining paradigm. In this paper, we reveal three critical yet heretofore overlooked problems in DNA pretraining: inappropriate downstream
datasets, inherent flaws in the neighbor-masking strategy, and the lack of detailed discussion on vocabulary. Therefore, we undertake comprehensive investigations and propose principled guidelines, including selection criteria for evaluation
datasets, guiding task design, and in-depth vocabulary analysis. Extensive experiments validate the significance of our identified problems and support the rationale behind our recommendations. Finally, we introduce a standardized testbed that enables reproducible and rigorous benchmarking of DNA pretraining methods to advance the development of genomic foundation models.
Read the full abstract ▾
All authors Zhijiang Tang, Jiaxin Qi, Yan Cui, Jinli Ou, Yuhua Zheng, Jianqiang Huang
Machine Learning
Jiaoyang Ruan, Xin Gao, Yinda Chen et al. (+5 more)
While
Diffusion Large
Language Models (dLLMs) offer structural advantages for global planning, efficiently verifying that they arrive at correct answers via valid
reasoning traces remains a critical challenge. In this work, we propose a
geometric perspective:
Reasoning on the
Manifold. We hypothesize that valid generation trajectories reside as stable attractors on the high-density
manifold of the learned distribution, whereas invalid paths exhibit off-
manifold drift. To operationalize this, we introduce Bidirectional
Manifold Consistency (BMC), a training-free, unsupervised metric that quantifies the stability of the generated sequence through a forward-masking and backward-reconstruction cycle. Empirically, we demonstrate BMC's versatility across the full
reasoning lifecycle: (1) in Diagnosis, it serves as a robust discriminator of solution validity without ground truth answer; (2) in Inference, it enables rejection resampling to effectively concentrate computational resources on complex
reasoning tasks; and (3) in
Alignment, it functions as a dense
geometric reward that transforms sparse outcome supervision into fine-grained guidance, empowering models to self-evolve beyond standard baselines. Our results establish intrinsic
geometric stability as a robust indicator of correctness for dLLMs.
Read the full abstract ▾
All authors Jiaoyang Ruan, Xin Gao, Yinda Chen, Hengyu Zeng, Liang Du, Guanghao Li, Jie Fu, Jian Pu
Machine Learning
Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing
Zhixiong Yang, Long Jing, Yao Li et al. (+3 more)
AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imbalance exists across RF modalities, with abundant WiFi data but scarce mmWave and RFID data due to high acquisition cost. This makes it difficult to train high-quality generative models for these data-scarce modalities. In this work, we propose RF-CMG, a
diffusion-based cross-modal generative method that leverages data-rich WiFi signals to synthesize high-fidelity RF data for scarce modalities including mmWave and RFID. The key insight of RF-CMG is to decouple cross-modal generation into high-frequency guidance and low-frequency constraint, which respectively learn high-frequency distribution from limited target modality data and preserve the underlying physical structure via low-frequency constraints during generation. On this basis, we introduce a Modality-Guided
Embedding (MGE) module to steer the reverse
diffusion trajectory toward the target high-frequency distribution, and a Low-Frequency Modality Consistency (LFMC) module to progressively enforce low-frequency constraints to suppress the accumulation of source-modality structural biases during inference, enabling high-quality target-modality generation. Performance comparison with several prevalent generative models demonstrates that RF-CMG achieves superior performance in synthesizing RFID and mmWave signals. We further showcase the effectiveness of the data generated by RF-CMG in gesture recognition tasks, and analyze the impact of the proportion of synthetic data on downstream performance.
Read the full abstract ▾
All authors Zhixiong Yang, Long Jing, Yao Li, Shuli Cheng, Guoxuan Chi, Chenyu Wen
Machine Learning
S-GRPO: Unified Post-Training for Large Vision-Language Models
Yuming Yan, Kai Tang, Sihong Chen et al. (+4 more)
Current post-training methodologies for adapting Large
Vision-
Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). Despite their prevalence, both approaches suffer from inefficiencies when applied in isolation. SFT forces the model's generation along a single expert trajectory, often inducing catastrophic forgetting of general
multimodal capabilities due to distributional shifts. Conversely, RL explores multiple generated trajectories but frequently encounters optimization collapse - a cold-start problem where an unaligned model fails to spontaneously sample any domain-valid trajectories in sparse-reward visual tasks. In this paper, we propose Supervised Group Relative Policy Optimization (S-GRPO), a unified post-training framework that integrates the guidance of imitation learning into the multi-trajectory exploration of preference optimization. Tailored for direct-generation visual tasks, S-GRPO introduces Conditional Ground-Truth Trajectory Injection (CGI). When a binary verifier detects a complete exploratory failure within a sampled group of trajectories, CGI injects the verified ground-truth trajectory into the candidate pool. By assigning a deterministic maximal reward to this injected anchor, S-GRPO enforces a positive signal within the group-relative advantage estimation. This mechanism reformulates the supervised learning objective as a high-advantage component of the policy gradient, compelling the model to dynamically balance between exploiting the expert trajectory and exploring novel visual concepts. Theoretical analysis and empirical results demonstrate that S-GRPO gracefully bridges the gap between SFT and RL, drastically accelerates convergence, and achieves superior domain adaptation while preserving the base model's general-purpose capabilities.
Read the full abstract ▾
All authors Yuming Yan, Kai Tang, Sihong Chen, Ke Xu, Dan Hu, Qun Yu, Pengfei Hu
Machine Learning
LLM as a Tool, Not an Agent: Code-Mined Tree Transformations for Neural Architecture Search
Masakazu Yoshimura, Zitang Sun, Yuiko Sakuma et al. (+3 more)
Neural Architecture Search (NAS) aims to automatically discover high-performing deep neural network (DNN) architectures. However, conventional
algorithm-driven NAS relies on carefully hand-crafted search spaces to ensure executability, which restricts open-ended exploration. Recent coding-based agentic approaches using large
language models (LLMs) reduce manual design, but current LLMs struggle to reliably generate complex, valid architectures, and their proposals are often biased toward a narrow set of patterns observed in their training data. To bridge reliable algorithmic search with powerful LLM assistance, we propose LLMasTool, a hierarchical tree-based NAS framework for stable and open-ended model
evolution. Our method automatically extracts reusable modules from arbitrary source code and represents full architectures as hierarchical trees, enabling
evolution through reliable tree transformations rather than code generation. At each
evolution step, coarse-level planning is governed by a diversity-guided
algorithm that leverages
Bayesian modeling to improve exploration efficiency, while the LLM resolves the remaining degrees of freedom to ensure a meaningful evolutionary trajectory and an executable generated architecture. With this formulation, instead of fully agentic LLM approaches, our method explores diverse directions beyond the inherent biases in the LLM. Our method improves over existing NAS methods by 0.69, 1.83, and 2.68 points on CIFAR-10, CIFAR-100, and ImageNet16-120, demonstrating its effectiveness.
Read the full abstract ▾
All authors Masakazu Yoshimura, Zitang Sun, Yuiko Sakuma, Junji Otsuka, Atsushi Irie, Takeshi Ohashi
Machine Learning
An Interpretable Framework Applying Protein Words to Predict Protein-Small Molecule Complementary Pairing Rules
Jingke Chen, Jingrui Zhong, Tazneen Hossain Tani et al. (+3 more)
Despite the high accuracy of 'black box' deep learning models, drug discovery still relies on
protein-ligand interaction principles and heuristics. To improve interpretability of
protein-small molecule binding predictions, we developed the PWRules framework, which applies binding affinity data to identify privileged small molecule fragments and subsequently defines complementary pairing rules between these fragments and
protein words (semantic sequence units) through an interpretability module. The resulting word-fragment rules are then ranked by the PWScore function to prioritize active compounds. Evaluations on
benchmark datasets show that PWScore achieves competitive performance comparable to the physics-based model (Glide) and the deep learning model (PSICHIC) and shows broad applicability for
protein targets outside the training
dataset, e.g., SARS-CoV-2 main protease. Notably, PWScore captures complementary interaction information, yielding superior enrichment performance when integrated with these established methods. Structural analysis of
protein-ligand complexes indicates that learned word-fragment rules are significantly enriched near ligand-binding pockets, despite training without explicit structural guidance. By extracting and applying complementary pairing rules, PWRules provides an interpretable framework for drug discovery.
Read the full abstract ▾
All authors Jingke Chen, Jingrui Zhong, Tazneen Hossain Tani, Zidong Su, Xiaochun Zhang, Boxue Tian
Machine Learning
Geometric regularization of autoencoders via observed stochastic dynamics
Sean Hill and Felix X.-F. Ye
Stochastic dynamical systems with slow or metastable behavior evolve, on long time scales, on an unknown low-dimensional
manifold in high-dimensional ambient space. Building a reduced simulator from short-burst ambient ensembles is a long-standing problem: local-chart methods like ATLAS suffer from exponential landmark scaling and per-step reprojection, while autoencoder alternatives leave tangent-bundle geometry poorly constrained, and the errors propagate into the learned drift and
diffusion. We observe that the ambient covariance~$\Lambda$ already encodes coordinate-invariant tangent-space information, its range spanning the tangent bundle. Using this, we construct a tangent-bundle penalty and an inverse-consistency penalty for a three-stage pipeline (chart learning, latent drift, latent
diffusion) that learns a single nonlinear chart and the latent SDE. The penalties induce a function-space metric, the $\rho$-metric, strictly weaker than the Sobolev $H^1$ norm yet achieving the same chart-quality generalization rate up to logarithmic factors. For the drift, we derive an encoder-pullback target via Itô's formula on the learned encoder and prove a bias decomposition showing the standard decoder-side formula carries systematic error for any imperfect chart. Under a $W^{2,\infty}$ chart-convergence assumption, chart-level error propagates controllably to weak convergence of the ambient dynamics and to convergence of radial mean first-passage times. Experiments on four surfaces embedded in up to $201$ ambient dimensions reduce radial MFPT error by $50$–$70\%$ under rotation dynamics and achieve the lowest inter-well MFPT error on most surface–transition pairs under metastable Müller–Brown Langevin dynamics, while reducing end-to-end ambient coefficient errors by up to an order of magnitude relative to an unregularized autoencoder.
Read the full abstract ▾
Machine Learning
Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design
Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir et al. (+5 more)
Large
Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However, their practical utility remains unclear due to the lack of
benchmarks that reflect real-world scenarios. In this work, we introduce a suite of chemically-grounded tasks spanning molecular property prediction, molecular representation transformations, and molecular design. Importantly, we formulate these tasks as reinforcement learning (RL) environments, enabling a unified approach for evaluation and post-training. Across three model families, we find that frontier models are increasingly proficient at chemical tasks, but that there is significant room for improvement, especially in experimental settings with low data. Critically, we show that RL-based post-training can substantially improve performance. A smaller model post-trained on our environments becomes competitive with state-of-the-art frontier models, despite a significantly weaker base model. This suggests a practical route toward employing LLMs in drug discovery; by combining carefully-designed evaluation tasks with targeted post-training, we can both elucidate and close critical capability gaps.
Read the full abstract ▾
All authors Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir, Colin Grambow, John Bradshaw, Patricia Suriana, Chen Cheng, Kangway Chuang
Machine Learning · Cross-listed from cs.AI
Learning to Reason with Insight for Informal Theorem Proving
Yunhe Li, Hao Shi, Bowen Deng et al. (+8 more)
Although most of the automated
theorem-proving approaches depend on formal proof systems, informal
theorem proving can align better with large
language models' (LLMs) strength in natural
language processing. In this work, we identify a primary bottleneck in informal
theorem proving as a lack of insight, namely the difficulty of recognizing the core techniques required to solve complex problems. To address this, we propose $\texttt{DeepInsight}$, a unified training framework designed to cultivate this essential
reasoning skill and enable LLMs to perform insightful
reasoning. Our framework consists of three components: (1) $\texttt{DeepInsightTheorem}$, a hierarchical
dataset that structures informal proofs by explicitly extracting core techniques and proof sketches alongside the final proof; (2) a Progressive Multi-Stage SFT strategy that mimics the human learning process, teaching the model proof writing, planning, and insight identification; and (3) $\texttt{InsightPO}$, a policy optimization method that assigns structured rewards over this insight hierarchy. Our experiments on challenging mathematical
benchmarks demonstrate that this insight-aware generation strategy significantly outperforms baselines. These results demonstrate that teaching models to identify and apply core techniques can substantially improve their mathematical
reasoning.
Read the full abstract ▾
All authors Yunhe Li, Hao Shi, Bowen Deng, Wei Wang, Mengzhe Ruan, Hanxu Hou, Zhongxiang Dai, Siyang Gao, Chao Wang, Shuang Qiu, Linqi Song
Machine Learning
FL-MHSM: Spatially-adaptive Fusion and Ensemble Learning for Flood-Landslide Multi-Hazard Susceptibility Mapping at Regional Scale
Aswathi Mundayatt and Jaya Sreevalsan-Nair
Existing multi-hazard susceptibility mapping (MHSM) studies often rely on spatially uniform models, treat hazards independently, and provide limited representation of cross-hazard dependence and uncertainty. To address these limitations, this study proposes a deep learning (DL) workflow for joint flood-landslide multi-hazard susceptibility mapping (FL-MHSM) that combines two-level spatial partitioning, probabilistic Early Fusion (EF), a tree-based Late Fusion (LF) baseline, and a soft-gating Mixture of Experts (MoE) model, with MoE serving as final predictive model. The proposed design preserves spatial heterogeneity through zonal partitions and enables data-parallel large-area prediction using overlapping
lattice grids. In Kerala, EF remained competitive with LF, improving flood recall from 0.816 to 0.840 and reducing Brier score from 0.092 to 0.086, while MoE provided strongest performance for flood susceptibility, achieving an AUC-ROC of 0.905, recall of 0.930, and F1-score of 0.722. In Nepal, EF similarly improved flood recall from 0.820 to 0.858 and reduced Brier score from 0.057 to 0.049 relative to LF, while MoE outperformed both EF and LF for landslide susceptibility, achieving an AUC-ROC of 0.914, recall of 0.901, and F1-score of 0.559. GeoDetector analysis of MoE outputs further showed that dominant factors varied more across zones in Kerala, where susceptibility was shaped by different combinations of topographic, land-cover, and drainage-related controls, while Nepal showed a more consistent influence of topographic and glacier-related factors across zones. These findings show that EF and LF provide complementary predictive behavior, and that their spatially adaptive integration through MoE yields robust overall predictive performance for FL-MHSM while supporting interpretable characterization of multi-hazard susceptibility in spatially heterogeneous landscapes.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
Information Router for Mitigating Modality Dominance in Vision-Language Models
Seulgi Kim, Mohit Prabhushankar and Ghassan AlRegib
Vision Language models (VLMs) have demonstrated strong performance across a wide range of
benchmarks, yet they often suffer from modality dominance, where predictions rely disproportionately on a single modality. Prior approaches primarily address this issue by steering model's
attention allocation, implicitly assuming that all modalities provide sufficient information. However,
attention only determines where the model focuses, and cannot enrich information that is missing or ambiguous. In the real world, input modalities often differ in information density and their signal-to-noise ratios. In such cases, simply adjusting model's
attention does not resolve the underlying lack of information. In this paper, we propose MoIR: Multi-modal Information Router, an information-level fusion method that explicitly reduces information disparity prior to fusion. MoIR identifies less informative
tokens and routes complementary information from a stronger modality, constructing information-dense
token representations before they are processed by a large
language model. By modifying information availability, MoIR enables reliable shifts in modality dominance, even when one modality is degraded. We evaluate MoIR on three widely used multi-modal
benchmarks across multiple model backbones. Experimental results show that MoIR consistently demonstrates more balanced modality contribution, and improves robustness and downstream performance, particularly even under modality degradation. These findings demonstrate that explicitly modifying cross-modal information is an effective and complementary strategy for mitigating modality dominance in multi-modal
reasoning models.
Read the full abstract ▾
Machine Learning
Beyond Distribution Sharpening: The Importance of Task Rewards
Sarthak Mittal, Leo Gagnon and Guillaume Lajoie
Frontier models have demonstrated exceptional capabilities following the integration of task-reward-based reinforcement learning (RL) into their training pipelines, enabling systems to evolve from pure
reasoning models into sophisticated
agents. However, debate persists regarding whether RL genuinely instills new skills within a base model or merely sharpens its existing distribution to elicit latent capabilities. To address this dichotomy, we present an explicit comparison between distribution sharpening and task-reward-based learning, utilizing RL as a tool to implement both paradigms. Our analysis reveals the inherent limitations of distribution sharpening, demonstrating from first principles how and why the optima can be unfavorable and the approach fundamentally unstable. Furthermore, our experiments using Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct and Qwen3-4B-Instruct-2507 on math
datasets confirm that sharpening yields limited gains, whereas incorporating task-based reward signal can greatly help achieve robust performance improvements and stable learning.
Read the full abstract ▾
Machine Learning
Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization
Habibeh Naderi, Behrouz Haji Soleimani and Stan Matwin
We propose
HILBERT (HIerarchical Long-sequence Balanced
Embedding with Reciprocal contrastive Training), a cross-attentive
multimodal framework for learning document-level audio-text representations from long, segmented sequences in low-resource data settings.
HILBERT leverages frozen pre-trained
speech and
language encoders to extract segment-level features, which are aggregated via cross-modal
attention and self-attentive pooling to form modality-specific document representations and a joint cross-attentive
embedding. To align modalities while preserving modality-specific structure under severe audio-text dimensional imbalance, we introduce a reciprocal dual contrastive objective that simultaneously aligns audio-to-joint and text-to-joint representations, rather than directly contrasting audio and text alone. Two auxiliary regularizers further stabilize long-sequence fusion: a Centered Kernel
Alignment (CKA) loss that preserves structural consistency between each modality and the joint
embedding, and a mutual information balancing loss that prevents dominance of a single modality by equalizing information flow from audio and text into the joint space. For downstream prediction,
HILBERT employs a Mixture-of-Experts (MoE) classifier over concatenated audio, text, and joint representations to accommodate heterogeneous label regimes. Extensive evaluation across multiple audio-text backbone combinations demonstrates that
HILBERT learns semantically meaningful long-sequence representations and achieves superior performance on highly imbalanced multi-class settings.
Read the full abstract ▾
Machine Learning
Detecting and Suppressing Reward Hacking with Gradient Fingerprints
Songtao Wang, Quang Hieu Pham, Fangcong Yin et al. (+4 more)
Reinforcement learning with verifiable rewards (RLVR) typically optimizes for outcome rewards without imposing constraints on intermediate
reasoning. This leaves training susceptible to reward hacking, where models exploit loopholes (e.g., spurious patterns in training data) in the reward function to achieve high scores without solving the intended task. These reward-hacking behaviors are often implicit, as the intermediate chain-of-thought (CoT) may appear plausible on the surface, limiting the effectiveness of purely text-based monitoring. We propose Gradient Fingerprint (GRIFT), a method for detecting reward hacking using models' internal computations. Given a
prompt and a model-generated CoT, GRIFT computes gradients of the CoT conditioned on the
prompt and compresses them into a compact representation, which is then used to assess whether the CoT reflects reward hacking behavior. Across verifiable
reasoning benchmarks spanning math, code, and logical
reasoning, GRIFT substantially outperforms strong baselines, including CoT Monitor and TRACE, achieving over 25% relative improvement in detecting reward hacking behavior. Moreover, integrating GRIFT into the rejection fine-tuning pipeline for
reasoning tasks reduces reward hacking and improves performance on the true task objective. Our results highlight a promising direction of leveraging gradient level representations for assessing the quality of CoT
reasoning traces. Our code is available at: https://github.com/songtao-x/reward_hack.
Read the full abstract ▾
All authors Songtao Wang, Quang Hieu Pham, Fangcong Yin, Xinpeng Wang, Jocelyn Qiaochu Chen, Greg Durrett, Xi Ye