Machine Learning · Cross-listed from cs.MA
The Value of Variance: Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization
Luoxi Tang, Yuqiao Meng, Joseph Costa et al. (+3 more)
Multi-
agent debate (MAD) systems improve LLM
reasoning through iterative deliberation, but remain vulnerable to debate collapse, a failure type where final
agent decisions are compromised on erroneous
reasoning. Existing methods lack principled mechanisms to detect or prevent such failures. To address this gap, we first propose a hierarchical metric that quantifies behavioral uncertainty at three levels: intra-
agent (individual
reasoning uncertainty), inter-
agent (interactive uncertainty), and system-level (output uncertainty). Empirical analysis across several
benchmarks reveals that our proposed uncertainty quantification reliably indicates system failures, which demonstrates the validity of using them as diagnostic metrics to indicate the system failure. Subsequently, we propose a mitigation strategy by formulating an uncertainty-driven policy optimization to penalize self-contradiction, peer conflict, and low-confidence outputs in a dynamic debating environment. Experiments demonstrate that our proposed uncertainty-driven mitigation reliably calibrates the multi-
agent system by consistently improving decision accuracy while reducing system disagreement.
Read the full abstract ▾
All authors Luoxi Tang, Yuqiao Meng, Joseph Costa, Yingxue Zhang, Muchao Ye, Zhaohan Xi
Machine Learning
Learning Nonlinear Systems In-Context: From Synthetic Data to Real-World Motor Control
Tong Jian, Tianyu Dai and Tao Yu
LLMs have shown strong in-context learning (ICL) abilities, but have not yet been extended to signal processing systems. Inspired by their design, we have proposed for the first time ICL using
transformer models applicable to motor feedforward control, a critical task where classical PI and physics-based methods struggle with nonlinearities and complex load conditions. We propose a
transformer based model architecture that separates signal representation from system behavior, enabling both few-shot finetuning and one-shot ICL. Pretrained on a large corpus of synthetic linear and nonlinear systems, the model learns to generalize to unseen system dynamics of real-world motors only with a handful of examples. In experiments, our approach generalizes across multiple motor load configurations, transforms untuned examples into accurate feedforward predictions, and outperforms PI controllers and physics-based feedforward baselines. These results demonstrate that ICL can bridge synthetic pretraining and real-world adaptability, opening new directions for data efficient control of physical systems.
Read the full abstract ▾
Machine Learning · Cross-listed from physics.med-ph
High-fidelity 3D multi-slab diffusion MRI using Slab-shifting for Harmonized 3D Acquisition and Reconstruction with Profile Encoding Networks (SHARPEN)
Ziyu Li, Karla L. Miller and Wenchuan Wu
Three-dimensional (3D) multi-slab imaging is a promising approach for high-resolution in vivo
diffusion MRI (dMRI) due to its compatibility with short TR (1-2 s), providing optimal signal-to-noise ratio (SNR) efficiency. A major challenge, however, is slab boundary artifacts arising from non-ideal slab-selective RF excitation. Non-rectangular slab profiles reduce signal intensity at slab boundaries, while profile overlap across adjacent slabs introduces inter-slab crosstalk, where repeated excitation shortens the local TR and limits T1 recovery. To mitigate slab boundary artifacts without increasing scan time, we build on slab profile encoding and propose Slab-shifting for Harmonized 3D Acquisition and Reconstruction with Profile Encoding Networks (SHARPEN). For different
diffusion directions, SHARPEN applies inter-volume field-of-view shifts along the slice direction to provide complementary slab profile encoding without prolonging acquisition. Slab profiles are estimated using a lightweight self-supervised neural network that exploits consistency across shifted acquisitions and known physical properties of slab profiles and
diffusion images, and corrected images are reconstructed accordingly. SHARPEN was validated using simulated and prospectively acquired high-resolution in vivo data and demonstrates accurate slab profile estimation and robust boundary artifact correction, even in the presence of inter-volume motion. SHARPEN does not require high-quality reference training data and supports subject-specific training. Its efficient GPU-based implementation delivers faster and more accurate correction than NPEN, yielding slice-wise quantitative profiles that closely match those from reference 2D acquisitions. SHARPEN enables high-quality dMRI at 0.7 mm isotropic resolution on a 3T clinical scanner, highlighting its potential to advance submillimeter dMRI for neuroscience research.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Free Energy Mixer
Jiecheng Lu and Shihao Yang
Standard
attention stores keys/values losslessly but reads them via a per-head convex average, blocking channel-wise selection. We propose the Free Energy Mixer (FEM): a free-energy (log-sum-exp) read that applies a value-driven, per-channel log-linear tilt to a fast prior (e.g., from queries/keys in standard
attention) over indices. Unlike methods that attempt to improve and enrich the $(q,k)$ scoring distribution, FEM treats it as a prior and yields a value-aware posterior read at unchanged complexity, smoothly moving from averaging to per-channel selection as the learnable inverse temperature increases, while still preserving parallelism and the original asymptotic complexity ($O(T^2)$ for softmax; $O(T)$ for linearizable variants). We instantiate a two-level gated FEM that is plug-and-play with standard and linear
attention, linear RNNs and SSMs. It consistently outperforms strong baselines on NLP,
vision, and time-series at matched parameter budgets.
Read the full abstract ▾
Machine Learning
Mimetic Initialization of MLPs
Asher Trockman and J. Zico Kolter
Mimetic initialization uses pretrained models as case studies of good initialization, using observations of structures in trained weights to inspire new, simple initialization techniques. So far, it has been applied only to spatial mixing layers, such convolutional, self-
attention, and state space layers. In this work, we present the first attempt to apply the method to channel mixing layers, namely multilayer perceptrons (MLPs). Our extremely simple technique for MLPs – to give the first layer a nonzero mean – speeds up training on small-scale
vision tasks like CIFAR-10 and ImageNet-1k. Though its effect is much smaller than spatial mixing initializations, it can be used in conjunction with them for an additional positive effect.
Read the full abstract ▾
Machine Learning
Beyond Pooling: Matching for Robust Generalization under Data Heterogeneity
Ayush Roy, Rudrasis Chakraborty, Lav Varshney et al. (+1 more)
Pooling heterogeneous
datasets across domains is a common strategy in representation learning, but naive pooling can amplify distributional asymmetries and yield biased
estimators, especially in settings where zero-shot generalization is required. We propose a matching framework that selects samples relative to an adaptive centroid and iteratively refines the representation distribution. The double robustness and the propensity score matching for the inclusion of data domains make matching more robust than naive pooling and uniform subsampling by filtering out the confounding domains (the main cause of heterogeneity). Theoretical and empirical analyses show that, unlike naive pooling or uniform subsampling, matching achieves better results under asymmetric meta-distributions, which are also extended to non-Gaussian and
multimodal real-world settings. Most importantly, we show that these improvements translate to zero-shot medical anomaly detection, one of the extreme forms of data heterogeneity and asymmetry. The code is available on https://github.com/AyushRoy2001/Beyond-Pooling.
Read the full abstract ▾
All authors Ayush Roy, Rudrasis Chakraborty, Lav Varshney, Vishnu Suresh Lokhande
Machine Learning · Cross-listed from cs.CR
Trojans in Artificial Intelligence (TrojAI) Final Report
Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski et al. (+68 more)
The Intelligence Advanced Research Projects Activity (IARPA) launched the TrojAI program to confront an emerging vulnerability in modern artificial intelligence: the threat of AI Trojans. These AI trojans are malicious, hidden
backdoors intentionally embedded within an AI model that can cause a system to fail in unexpected ways, or allow a malicious actor to hijack the AI model at will. This multi-year initiative helped to map out the complex nature of the threat, pioneered foundational detection methods, and identified unsolved challenges that require ongoing
attention by the burgeoning AI security field. This report synthesizes the program's key findings, including methodologies for detection through weight analysis and trigger inversion, as well as approaches for mitigating Trojan risks in deployed models. Comprehensive test and evaluation results highlight detector performance, sensitivity, and the prevalence of "natural" Trojans. The report concludes with lessons learned and recommendations for advancing AI security research.
Read the full abstract ▾
All authors Kristopher W. Reese, Taylor Kulp-McDowall, Michael Majurski, Tim Blattner, Derek Juba, Peter Bajcsy, Antonio Cardone, Philippe Dessauw, Alden Dima, Anthony J. Kearsley, Melinda Kleczynski, Joel Vasanth, Walid Keyrouz, Chace Ashcraft, Neil Fendley, Ted Staley, Trevor Stout, Josh Carney, Greg Canal, Will Redman, Aurora Schmidt, Cameron Hickert, William Paul, Jared Markowitz, Nathan Drenkow, David Shriver, Marissa Connor, Keltin Grimes, Marco Christiani, Hayden Moore, Jordan Widjaja, Kasimir Gabert, Uma Balakrishnan, Satyanadh Gundimada, John Jacobellis, Sandya Lakkur, Vitus Leung, Jon Roose, Casey Battaglino, Farinaz Koushanfar, Greg Fields, Xihe Gu, Yaman Jandali, Xinqiao Zhang, Tara Javidi, Akash Vartak, Tim Oates, Ben Erichson, Michael Mahoney, Rauf Izmailov, Xiangyu Zhang, Guangyu Shen, Siyuan Cheng, Shiqing Ma, XiaoFeng Wang, Haixu Tang, Di Tang, Xiaoyi Chen, Zihao Wang, Rui Zhu, Susmit Jha, Xiao Lin, Manoj Acharya, Weichao Zhou, Feisi Fu, Panagiota Kiourti, Chenyu Wang, Zijian Guo, H M Sabbir Ahmad, Wenchao Li, Chao Chen
Machine Learning
On Randomness in Agentic Evals
Bjarni Haukur Bjarnason, André Silva and Martin Monperrus
Agentic systems are evaluated on
benchmarks where
agents interact with environments to solve tasks. Most papers report a pass@1 score computed from a single run per task, assuming this gives a reliable performance estimate. We test this assumption by collecting 60,000 agentic trajectories on SWE-Bench-Verified, spanning three models and two scaffolds. We find substantial variance: single-run pass@1 estimates vary by 2.2 to 6.0 percentage points depending on which run is selected, with standard deviations exceeding 1.5 percentage points even at temperature 0. This variance has critical implications: reported improvements of 2–3 percentage points may reflect evaluation noise rather than genuine algorithmic progress. Through
token-level analysis, we show that trajectories diverge early, often within the first few percent of
tokens, and that these small differences cascade into different solution strategies. To enable reliable evaluation of agentic systems, we recommend three concrete practices: (1) estimate pass@1 from multiple independent runs per task, especially when measuring small improvements, (2) use statistical power analysis to determine the number of runs needed to detect expected effect sizes, and (3) consider metrics like pass@k (optimistic bound) and pass^k (pessimistic bound) with k>1 to better characterize the full performance envelope. While these practices increase evaluation cost, they are essential for distinguishing genuine scientific progress from statistical noise.
Read the full abstract ▾
Machine Learning
Convex Dominance in Deep Learning I: A Scaling Law of Loss and Learning Rate
Zhiqi Bu, Shiyun Xu and Jialin Mao
Deep learning has non-convex loss landscape and its optimization dynamics is hard to analyze or control. Nevertheless, the dynamics can be empirically convex-like across various tasks, models, optimizers, hyperparameters, etc. In this work, we examine the applicability of convexity and Lipschitz continuity in deep learning, in order to precisely control the loss dynamics via the learning rate schedules. We illustrate that deep learning quickly becomes weakly convex after a short period of training, and the loss is predicable by an upper bound on the last iterate, which further informs the scaling of optimal learning rate. Through the lens of convexity, we build scaling laws of learning rates and losses that extrapolate as much as 80X across training horizons and 70X across model sizes.
Read the full abstract ▾
Machine Learning
BONSAI: Bayesian Optimization with Natural Simplicity and Interpretability
Samuel Daulton, David Eriksson, Maximilian Balandat et al. (+1 more)
Bayesian optimization (BO) is a popular technique for sample-efficient optimization of black-box functions. In many applications, the parameters being tuned come with a carefully engineered default configuration, and practitioners only want to deviate from this default when necessary. Standard BO, however, does not aim to minimize deviation from the default and, in practice, often pushes weakly relevant parameters to the boundary of the search space. This makes it difficult to distinguish between important and spurious changes and increases the burden of vetting recommendations when the optimization objective omits relevant operational considerations. We introduce BONSAI, a default-aware BO policy that prunes low-impact deviations from a default configuration while explicitly controlling the loss in acquisition value. BONSAI is compatible with a variety of acquisition functions, including expected improvement and upper confidence bound (GP-UCB). We theoretically bound the regret incurred by BONSAI, showing that, under appropriate conditions, it retains the no-regret property of vanilla GP-UCB and removes irrelevant changes. Across many real-world applications, we empirically find that BONSAI substantially reduces the number of non-default parameters in recommended configurations while maintaining competitive optimization performance with little effect on wall time. Its candidate-generation cost averages only $1.5\times$ that of standard BO, compared with $7$-$34\times$ for prior sparse-BO methods.
Read the full abstract ▾
All authors Samuel Daulton, David Eriksson, Maximilian Balandat, Eytan Bakshy
Machine Learning
Featured Reproducing Kernel Banach Spaces for Learning and Neural Networks
Isabel de la Higuera, Francisco Herrera and M. Victoria Velasco
Reproducing kernel
Hilbert spaces provide a foundational framework for kernel-based learning, where regularization and interpolation problems admit finite-dimensional solutions through classical representer
theorems. Many modern learning models, however – including fixed-architecture neural networks equipped with non-quadratic norms – naturally give rise to non-Hilbertian geometries that fall outside this setting. In
Banach spaces, continuity of point-evaluation functionals alone is insufficient to guarantee feature representations or kernel-based learning formulations. In this work, we develop a functional-analytic framework for learning in
Banach spaces based on the notion of featured reproducing kernel
Banach spaces. We identify the precise structural conditions under which feature maps, kernel constructions, and representer-type results can be recovered beyond the Hilbertian regime. Within this framework, supervised learning is formulated as a minimal-norm interpolation or regularization problem, and existence results together with conditional representer
theorems are established. We further extend the theory to vector-valued featured reproducing kernel
Banach spaces and show that fixed-architecture neural networks naturally induce special instances of such spaces. This provides a unified function-space perspective on kernel methods and neural networks and clarifies when kernel-based learning principles extend beyond reproducing kernel
Hilbert spaces.
Read the full abstract ▾
Machine Learning
Landscaper: Understanding Loss Landscapes Through Multi-Dimensional Topological Analysis
Jiaqing Chen, Nicholas Hadler, Tiankai Xie et al. (+8 more)
Loss landscapes are a powerful tool for understanding neural network optimization and generalization, yet traditional low-dimensional analyses often miss complex topological features. We present Landscaper, an open-source Python package for arbitrary-dimensional loss landscape analysis. Landscaper combines Hessian-based subspace construction with topological data analysis to reveal
geometric structures such as basin hierarchy and connectivity. A key component is the Saddle-Minimum Average Distance (SMAD) for quantifying landscape smoothness. We demonstrate Landscaper's effectiveness across various architectures and tasks, including those involving pre-trained
language models, showing that SMAD captures training transitions, such as landscape simplification, that conventional metrics miss. We also illustrate Landscaper's performance in challenging chemical property prediction tasks, where SMAD can serve as a metric for out-of-distribution generalization, offering valuable insights for model diagnostics and architecture design in data-scarce scientific machine learning scenarios.
Read the full abstract ▾
All authors Jiaqing Chen, Nicholas Hadler, Tiankai Xie, Rostyslav Hnatyshyn, Caleb Geniesse, Yaoqing Yang, Michael W. Mahoney, Talita Perciano, John F. Hartwig, Ross Maciejewski, Gunther H. Weber
Machine Learning · Cross-listed from stat.ML
Discrete Adjoint Matching
Oswin So, Brian Karrer, Chuchu Fan et al. (+2 more)
Computation methods for solving
entropy-regularized reward optimization – a class of problems widely used for fine-tuning generative models – have advanced rapidly. Among those, Adjoint Matching (AM, Domingo-Enrich et al., 2025) has proven highly effective in continuous state spaces with differentiable rewards. Transferring these practical successes to discrete generative modeling, however, remains particularly challenging and largely unexplored, mainly due to the drastic shift in generative model classes to discrete state spaces, which are nowhere differentiable. In this work, we propose Discrete Adjoint Matching (DAM) – a discrete variant of AM for fine-tuning discrete generative models characterized by Continuous-Time Markov Chains, such as
diffusion-based large
language models. The core of DAM is the introduction of discrete adjoint-an
estimator of the optimal solution to the original problem but formulated on discrete domains-from which standard matching frameworks can be applied. This is derived via a purely statistical standpoint, in contrast to the control-theoretic viewpoint in AM, thereby opening up new algorithmic opportunities for general adjoint-based
estimators. We showcase DAM's effectiveness on synthetic and mathematical
reasoning tasks.
Read the full abstract ▾
All authors Oswin So, Brian Karrer, Chuchu Fan, Ricky T. Q. Chen, Guan-Horng Liu
Machine Learning
Finding Connections: Membership Inference Attacks for the Multi-Table Synthetic Data Setting
Joshua Ward, Chi-Hua Wang and Guang Cheng
Synthetic tabular data has gained
attention for enabling
privacy-preserving data sharing. While substantial progress has been made in single-table synthetic generation where data are modeled at the row or item level, most real-world data exists in relational databases where a user's information spans items across multiple interconnected tables. Recent advances in synthetic relational data generation have emerged to address this complexity, yet release of these data introduce unique
privacy challenges as information can be leaked not only from individual items but also through the relationships that comprise a complete user entity. To address this, we propose a novel Membership Inference Attack (MIA) setting to audit the empirical user-level
privacy of synthetic relational data and show that single-table MIAs that audit at an item level underestimate user-level
privacy leakage. We then propose Multi-Table Membership Inference Attack (MT-MIA), a novel
adversarial attack under a No-Box threat model that targets learned representations of user entities via Heterogeneous Graph Neural Networks. By incorporating all connected items for a user, MT-MIA better targets user-level vulnerabilities induced by inter-tabular relationships than existing attacks. We evaluate MT-MIA on a range of real-world multi-table
datasets and demonstrate that this vulnerability exists in state-of-the-art relational synthetic data generators, employing MT-MIA to additionally study where this leakage occurs.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.IR
Jianrui Zhang, Anirudh Sundara Rajan, Brandon Han et al. (+3 more)
Universal
Multimodal Retrieval (UMR) seeks any-to-any search across text and
vision, yet modern
embedding models remain brittle when queries require latent
reasoning (e.g., resolving underspecified references or matching compositional constraints). We argue this brittleness is often data-induced: when images carry "silent" evidence and queries leave key semantics implicit, a single
embedding pass must both reason and compress, encouraging spurious feature matching. We propose a data-centric framework that decouples these roles by externalizing
reasoning before
retrieval. Using a strong
Vision–
Language Model, we make implicit semantics explicit by densely captioning visual evidence in corpus entries, resolving ambiguous
multimodal references in queries, and rewriting verbose instructions into concise
retrieval constraints. Inference-time enhancement alone is insufficient; the retriever must be trained on these semantically dense representations to avoid distribution shift and fully exploit the added signal. Across M-BEIR, our
reasoning-augmented training method yields consistent gains over strong baselines, with ablations showing that corpus enhancement chiefly benefits knowledge-intensive queries while query enhancement is critical for compositional modification requests. We publicly release our code at https://github.com/AugmentedRetrieval/ReasoningAugmentedRetrieval.
Read the full abstract ▾
All authors Jianrui Zhang, Anirudh Sundara Rajan, Brandon Han, Soochahn Lee, Sukanta Ganguly, Yong Jae Lee
Machine Learning · Cross-listed from stat.ML
Fast and Robust Likelihood-Guided Diffusion Posterior Sampling with Amortized Variational Inference
Léon Zheng, Thomas Hirtz, Yazid Janati et al. (+1 more)
Zero-shot
diffusion posterior sampling offers a flexible framework for inverse problems by accommodating arbitrary degradation operators at test time, but incurs high computational cost due to repeated likelihood-guided updates. In contrast, previous amortized
diffusion approaches enable fast inference by replacing likelihood-based sampling with implicit inference models, but at the expense of robustness to unseen degradations. We introduce an amortization strategy for
diffusion posterior sampling that preserves explicit likelihood guidance by amortizing the inner optimization problems arising in variational
diffusion posterior sampling. This accelerates inference for in-distribution degradations while maintaining robustness to previously unseen operators, thereby improving the trade-off between efficiency and flexibility in
diffusion-based inverse problems.
Read the full abstract ▾
All authors Léon Zheng, Thomas Hirtz, Yazid Janati, Eric Moulines
Machine Learning · Cross-listed from stat.CO
BayesFlow 2: Multi-Backend Amortized Bayesian Inference in Python
Lars Kühmichel, Jerry M. Huang, Valentin Pratz et al. (+11 more)
Modern
Bayesian inference involves a mixture of computational methods for estimating, validating, and drawing conclusions from probabilistic models as part of principled workflows. An overarching motif of many
Bayesian methods is that they are relatively slow, which often becomes prohibitive when fitting complex models to large data sets. Amortized
Bayesian inference (ABI) offers a path to solving the computational challenges of Bayes. ABI trains neural networks on model simulations, rewarding users with rapid inference of any model-implied quantity, such as point estimates, likelihoods, or full posterior distributions. In this work, we present the Python library BayesFlow, Version 2.0, for general-purpose ABI. Along with direct posterior, likelihood, and ratio estimation, the software includes support for multiple popular deep learning backends, a rich collection of generative networks for sampling and density estimation, complete customization and high-level interfaces, as well as new capabilities for hyperparameter optimization, design optimization, and hierarchical modeling. Using a case study on dynamical system parameter estimation, combined with comparisons to similar software, we show that our streamlined, user-friendly workflow has strong potential to support broad adoption.
Read the full abstract ▾
All authors Lars Kühmichel, Jerry M. Huang, Valentin Pratz, Jonas Arruda, Hans Olischläger, Daniel Habermann, Simon Kucharsky, Lasse Elsemüller, Aayush Mishra, Niels Bracher, Svenja Jedhoff, Marvin Schmitt, Paul-Christian Bürkner, Stefan T. Radev
Machine Learning
Attention-Driven Framework for Non-Rigid Medical Image Registration
Muhammad Zafar Iqbal, Ghazanfar Farooq Siddiqui, Anwar Ul Haq et al. (+1 more)
Deformable medical image registration is a fundamental task in medical image analysis with applications in disease diagnosis, treatment planning, and image-guided interventions. Despite significant advances in deep learning based registration methods, accurately aligning images with large deformations while preserving anatomical plausibility remains a challenging task. In this paper, we propose a novel
Attention-Driven Framework for Non-Rigid Medical Image Registration (AD-RegNet) that employs
attention mechanisms to guide the registration process. Our approach combines a 3D UNet backbone with bidirectional cross-
attention, which establishes correspondences between moving and fixed images at multiple scales. We introduce a regional adaptive
attention mechanism that focuses on anatomically relevant structures, along with a multi-resolution deformation field synthesis approach for accurate
alignment. The method is evaluated on two distinct
datasets: DIRLab for thoracic 4D CT scans and IXI for
brain MRI scans, demonstrating its versatility across different anatomical structures and imaging modalities. Experimental results demonstrate that our approach achieves performance competitive with state-of-the-art methods on the IXI and DIRLab
datasets. The proposed method maintains a favorable balance between registration accuracy and computational efficiency, making it suitable for clinical applications. A comprehensive evaluation using normalized cross-correlation (NCC), mean squared error (MSE), structural similarity (SSIM), Jacobian determinant, and target registration error (TRE) indicates that
attention-guided registration improves
alignment accuracy while ensuring anatomically plausible deformations.
Read the full abstract ▾
All authors Muhammad Zafar Iqbal, Ghazanfar Farooq Siddiqui, Anwar Ul Haq, Imran Razzak
Machine Learning · Cross-listed from physics.chem-ph
Electron-Informed Coarse-Graining Molecular Representation Learning for Real-World Molecular Physics
Gyoung S. Na and Chanyoung Park
Various representation learning methods for molecular structures have been devised to accelerate data-driven chemistry. However, the representation capabilities of existing methods are essentially limited to atom-level information, which is not sufficient to describe real-world molecular physics. Although electron-level information can provide fundamental knowledge about chemical compounds beyond the atom-level information, obtaining the electron-level information in real-world molecules is computationally impractical and sometimes infeasible. We propose a method for learning electron-informed molecular representations without additional computation costs by transferring readily accessible electron-level information about small molecules to large molecules of our interest. The proposed method achieved state-of-the-art prediction accuracy on extensive
benchmark datasets containing experimentally observed molecular physics. The source code for HEDMoL is available at https://github.com/ngs00/HEDMoL.
Read the full abstract ▾
Machine Learning
The Optimal Token Baseline: Variance Reduction for Long-Horizon LLM-RL
Yingru Li, Jiawei Xu, Ziniu Li et al. (+10 more)
Reinforcement Learning (RL) for Large
Language Models (LLMs) often suffers from training collapse in long-horizon tasks due to exploding gradient variance. To mitigate this, a baseline is commonly introduced for advantage computation; however, traditional value models remain difficult to optimize, and standard group-based baselines overlook sequence heterogeneity. Although classic optimal baseline theory can achieve global variance reduction, it neglects
token heterogeneity and requires prohibitive gradient-based computation. In this work, we derive the Optimal
Token Baseline (OTB) from first principles, proving that gradient updates should be weighted inversely to their cumulative gradient norm. To ensure efficiency, we propose the Logit-Gradient Proxy that approximates the gradient norm using only forward-pass probabilities. Our method achieves training stability and matches the performance of large group sizes ($N=32$) with only $N=4$, reducing
token consumption by over 65% across single-turn and tool-integrated
reasoning tasks.
Read the full abstract ▾
All authors Yingru Li, Jiawei Xu, Ziniu Li, Jiacai Liu, Wei Liu, Yuxuan Tong, Longtao Zheng, Zhenghai Xue, Yaxiang Zhang, Tianle Cai, Ge Zhang, Qian Liu, Baoxiang Wang
Machine Learning · Cross-listed from physics.chem-ph
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning
Xinwu Ye, Yicheng Mao, Yuxuan Liao et al. (+16 more)
Current chemical large
language models (LLMs) predominantly rely on explicit Chain-of-Thought (CoT) to solve complex
reasoning problems. However, forcing nonverbal tacit chemical logic into discrete natural
language imposes a fundamental “modality mismatch,” creating an artificial bottleneck for
reasoning. We introduce LatentChem, a
reasoning interface that decouples chemical logic from linguistic generation, enabling the model to process information via continuous thought vectors and dynamic perception. Our investigation reveals a pivotal emergent behavior: spontaneous internalization, defined here as self-selected under outcome-only optimization. When optimized for task success, the model abandons verbose textual derivations in favor of implicit latent computation, suggesting that it identifies the continuous
manifold as a more native substrate for chemical logic. This paradigm shift also proves to be a superior computational strategy: LatentChem achieves a 59.88% non-tie win rate against the strong CoT baseline on the rigorous ChemCoTBench, while delivering a broad 10.84$\times$ average reduction in
reasoning step overhead (5.96$\times$ wall-clock speedup) across all evaluated
benchmarks. Our results provide empirical evidence that chemical
reasoning is more naturally and effectively realized as continuous latent dynamics rather than discretized linguistic trajectories.
Read the full abstract ▾
All authors Xinwu Ye, Yicheng Mao, Yuxuan Liao, Jia Zhang, Yimeng Liu, Li Hao, Fang Wu, Zhiwei Li, Zehong Wang, Zhiyuan Liu, Zhenfei Yin, Li Yuan, Philip Torr, Huan Sun, xiangxiang Zeng, Mengdi Wang, Le Cong, Shenghua Gao, Xiangru Tang
Machine Learning · Cross-listed from cs.CR
Pro-ZD: A Transferable Graph Neural Network Approach for Proactive Zero-Day Threats Mitigation
Nardine Basta, Firas Ben Hmida, Houssem Jmal et al. (+3 more)
In today's enterprise network landscape, the combination of perimeter and distributed firewall rules governs connectivity. To address challenges arising from increased traffic and diverse network architectures, organizations employ automated tools for firewall rule and access policy generation. Yet, effectively managing risks arising from dynamically generated policies, especially concerning critical asset exposure, remains a major challenge. This challenge is amplified by evolving network structures due to trends like remote users, bring-your-own devices, and cloud integration. This paper introduces a novel graph neural network model for identifying weighted shortest paths. The model aids in detecting network misconfigurations and high-risk connectivity paths that threaten critical assets, potentially exploited in zero-day attacks – cyber-attacks exploiting undisclosed vulnerabilities. The proposed Pro-ZD framework adopts a proactive approach, automatically fine-tuning firewall rules and access policies to address high-risk connections and prevent unauthorized access. Experimental results highlight the robustness and transferability of Pro-ZD, achieving over 95% average accuracy in detecting high-risk connections. \
Read the full abstract ▾
All authors Nardine Basta, Firas Ben Hmida, Houssem Jmal, Muhammad Ikram, Mohamed Ali Kaafar, Andy Walker
Machine Learning
Learning a Generative Meta-Model of LLM Activations
Grace Luo, Jiahai Feng, Trevor Darrell et al. (+2 more)
Existing approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as priors that improve intervention fidelity. We explore this direction by training
diffusion models on one billion residual stream activations, creating "meta-models" that learn the distribution of a network's internal states. We find that
diffusion loss decreases smoothly with compute and reliably predicts downstream utility. In particular, applying the meta-model's learned prior to steering interventions improves fluency, with larger gains as loss decreases. Moreover, the meta-model's
neurons increasingly isolate concepts into individual units, with sparse probing scores that scale as loss decreases. These results suggest generative meta-models offer a scalable path toward interpretability without restrictive structural assumptions. Project page: https://generative-latent-prior.github.io.
Read the full abstract ▾
All authors Grace Luo, Jiahai Feng, Trevor Darrell, Alec Radford, Jacob Steinhardt
Machine Learning
Improving Credit Card Fraud Detection with an Optimized Explainable Boosting Machine
Reza E. Fazel, Arash Bakhtiary and Siavash A. Bigdeli
Addressing class imbalance is a central challenge in credit card fraud detection, as it directly impacts predictive reliability in real-world financial systems. To overcome this, the study proposes an enhanced workflow based on the Explainable Boosting Machine (EBM)-a transparent, state-of-the-art implementation of the GA2M
algorithm-optimized through systematic hyperparameter tuning, feature selection, and preprocessing refinement. Rather than relying on conventional sampling techniques that may introduce bias or cause information loss, the optimized EBM achieves an effective balance between accuracy and interpretability, enabling precise detection of fraudulent transactions while providing actionable insights into feature importance and interaction effects. Furthermore, the Taguchi method is employed to optimize both the sequence of data scalers and model hyperparameters, ensuring robust, reproducible, and systematically validated performance improvements. Experimental evaluation on
benchmark credit card data yields an ROC-AUC of 0.983, surpassing prior EBM baselines (0.975) and outperforming Logistic Regression, Random Forest, XGBoost, and Decision Tree models. These results highlight the potential of interpretable machine learning and data-driven optimization for advancing trustworthy fraud analytics in financial systems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.RO
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Shenyuan Gao, William Liang, Kaiyuan Zheng et al. (+27 more)
Being able to simulate the outcomes of actions in varied environments will revolutionize the development of generalist
agents at scale. However, modeling these world dynamics, especially for dexterous robotics tasks, poses significant challenges due to limited data coverage and scarce action labels. As an endeavor towards this end, we introduce DreamDojo, a foundation world model that learns diverse interactions and dexterous controls from 44k hours of
egocentric human
videos. Our data mixture represents the largest
video dataset to date for world model pretraining, spanning a wide range of daily scenarios with diverse objects and skills. To address the scarcity of action labels, we introduce continuous latent actions as unified proxy actions, enhancing interaction knowledge transfer from unlabeled
videos. After post-training on small-scale target
robot data, DreamDojo demonstrates a strong understanding of physics and precise action controllability. We also devise a
distillation pipeline that accelerates DreamDojo to a real-time speed of 10.81 FPS and further improves context consistency. Our work enables several important applications based on generative world models, including live teleoperation, policy evaluation, and model-based planning. Systematic evaluation on multiple challenging out-of-distribution (OOD)
benchmarks verifies the significance of our method for simulating open-world, contact-rich tasks, paving the way for general-purpose
robot world models.
Read the full abstract ▾
All authors Shenyuan Gao, William Liang, Kaiyuan Zheng, Ayaan Malik, Seonghyeon Ye, Sihyun Yu, Wei-Cheng Tseng, Yuzhu Dong, Kaichun Mo, Chen-Hsuan Lin, Qianli Ma, Seungjun Nah, Loic Magne, Jiannan Xiang, Yuqi Xie, Ruijie Zheng, Dantong Niu, You Liang Tan, K.R. Zentner, George Kurian, Suneel Indupuru, Pooya Jannaty, Jinwei Gu, Jun Zhang, Jitendra Malik, Pieter Abbeel, Ming-Yu Liu, Yuke Zhu, Joel Jang, Linxi "Jim" Fan
Machine Learning · Cross-listed from cs.AI
Agentic Uncertainty Reveals Agentic Overconfidence
Jean Kaddour, Srijan Patel, Gbètondji Dovonon et al. (+3 more)
Can AI
agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some
agents that succeed only 22% of the time predict 77% success. Counterintuitively, pre-execution assessment with strictly less information tends to yield better discrimination than standard post-execution review, though differences are not always significant.
Adversarial prompting reframing assessment as bug-finding achieves the best calibration.
Read the full abstract ▾
All authors Jean Kaddour, Srijan Patel, Gbètondji Dovonon, Leo Richter, Pasquale Minervini, Matt J. Kusner
Machine Learning · Cross-listed from eess.SY
Optimal Derivative Feedback Control for an Active Magnetic Levitation System: An Experimental Study on Data-Driven Approaches
Saber Omidi, Rene Akupan Ebunle and Se Young Yoon
This paper presents the design and implementation of data-driven optimal derivative feedback controllers for an active
magnetic levitation system. A direct, model-free control design method based on the reinforcement learning framework is compared with an indirect optimal control design derived from a numerically identified mathematical model of the system. For the direct model-free approach, a policy iteration procedure is proposed, which adds an iteration layer called the epoch loop to gather multiple sets of process data, providing a more diverse
dataset and helping reduce learning biases. This direct control design method is evaluated against a comparable optimal control solution designed from a plant model obtained through the combined Dynamic Mode Decomposition with Control (DMDc) and Prediction Error Minimization (PEM) system identification. Results show that while both controllers can stabilize and improve the performance of the
magnetic levitation system when compared to controllers designed from a nominal model, the direct model-free approach consistently outperforms the indirect solution when multiple epochs are allowed. The iterative refinement of the optimal control law over the epoch loop provides the direct approach a clear advantage over the indirect method, which relies on a single set of system data to determine the identified model and control.
Read the full abstract ▾
Machine Learning
Endogenous Resistance to Activation Steering in Language Models
Alex McKenzie, Keenan Pepper, Stijn Servaes et al. (+6 more)
Large
language models can recover mid-generation from task-misaligned activation steering, producing explicit verbal restarts (e.g., “wait, that's not right”) and continuing on-topic even while the steering perturbation remains active. We term this Endogenous Steering Resistance (ESR). Using sparse autoencoder (SAE) latents to steer model activations, we find that Llama-3.3-70B exhibits explicit ESR at 3.8%, with smaller models from the Llama-3 and Gemma-2 families showing the explicit form less frequently. Two controls dissociate ESR into a detection event and a sustained-resistance component that conditioning on recent on-topic
tokens does not fully explain. We identify 26 SAE latents through contrastive on-topic/off-topic search; zero-ablating them reduces the multi-attempt rate by 25%, with random-latent and held-out-
prompt controls supporting specificity. ESR can also be deliberately enhanced through both meta-prompting and fine-tuning on synthetic self-correction examples. ESR has dual implications for safety: it could harden models against
adversarial activation-space manipulation, but may equally interfere with beneficial steering-based interventions, since the model has no way to distinguish the two. Code is available at https://github.com/agencyenterprise/endogenous-steering-resistance.
Read the full abstract ▾
All authors Alex McKenzie, Keenan Pepper, Stijn Servaes, Martin Leitgab, Murat Cubuktepe, Mike Vaiana, Diogo de Lucena, Judd Rosenblatt, Michael S. A. Graziano
Machine Learning
From Core to Detail: Unsupervised Disentanglement with Entropy-Ordered Flows
Daniel Galperin and Ullrich Köthe
The unsupervised discovery of features that are both semantically meaningful and stable across runs remains a central challenge in representation learning. We introduce
entropy-ordered flows (EOFlows), a normalizing flow (NF) framework that augments standard maximum likelihood training with an orthogonality regularizer on the decoder Jacobian. The regularizer is rooted in Independent Mechanism Analysis and encourages
geometric disentanglement, and a
stochastic estimator makes it tractable at image scale (CelebA at $D=2352$ and $12288$). Learned features form near-orthogonal curvilinear coordinates and can be ordered by their $\textit{explained (manifold) entropy}$ after training, analogous to the ranking by explained variance in PCA, which turns EOFlows into a non-linear generalization of PCA. EOFlows identify an order of magnitude more stable features than existing methods, and these features emerge in distinguishable categories (global, local, and generic) and support tentative semantic interpretations. The local features have strikingly sparse support in pixel space, although our method never enforces this. Retaining only the most important, i.e. highest
entropy, features turns the bijective flow into an autoencoder with adjustable bottleneck, rivaling the rate-distortion performance of dedicated autoencoders.
Read the full abstract ▾
Machine Learning
Cochain Perspectives on Temporal-Difference Signals for Learning Beyond Markov Dynamics
Zuyuan Zhang, Sizhe Tang and Tian Lan
Non-Markovian dynamics are commonly found in real-world environments due to long-range dependencies, partial observability, and
memory effects. The Bellman equation that is the central pillar of Reinforcement learning (RL) becomes only approximately valid under Non-Markovian. Existing work often focus on practical
algorithm designs and offer limited theoretical treatment to address key questions, such as what dynamics are indeed capturable by the Bellman framework and how to inspire new
algorithm classes with optimal approximations. In this paper, we present a novel topological viewpoint on temporal-difference (TD) based RL. We show that TD errors can be viewed as 1-cochain in the topological space of state transitions, while Markov dynamics are then interpreted as topological integrability. This novel view enables us to obtain a Hodge-type decomposition of TD errors into an integrable component and a topological residual, through a Bellman-de Rham projection. We further propose HodgeFlow Policy Search (HFPS) by fitting a potential network to minimize the non-integrable projection residual in RL, achieving stability/sensitivity guarantees. In numerical evaluations, HFPS is shown to significantly improve RL performance under non-Markovian.
Read the full abstract ▾