Machine Learning
Dynamic Graph Prompting via Topology-Routed Mixed-Curvature Experts
Quanxin Wang, Xuanting Xie, Bingheng Li et al. (+4 more)
Dynamic graph prompting freezes a pre-trained temporal backbone and adapts it to label-scarce downstream tasks using lightweight
prompts. However, existing methods operate within a single, fixed
embedding space. In this work, we reveal that temporal shifts in local clustering and degree heterogeneity actively reorganize the edge
curvature spectrum—indicating that the optimal representation geometry dynamically evolves with local
topology over time. We formalize this unaddressed mismatch as geometry under-adaptation. To overcome this limitation, we propose CurvPrompt, a
topology-routed geometry prompting framework for dynamic graphs. Instead of relying on a single space, CurvPrompt maintains a bank of
curvature-diverse Riemannian experts, each paired with a learnable
prompt. A
topology-aware gate dynamically routes each node–time instance to a sparse subset of experts, constructing a personalized mixed-
curvature representation. To ensure parameter efficiency and training stability under extreme label scarcity, CurvPrompt employs soft routing during pre-training to build a continuous
topology–geometry mapping, and transitions to hard Top-K routing with uniform weights during downstream adaptation. Extensive experiments across four
benchmark datasets show that CurvPrompt significantly advances few-shot link prediction while delivering strong, consistent performance on node classification tasks, validating the necessity of geometry-adaptive prompting.
Read the full abstract ▾
All authors Quanxin Wang, Xuanting Xie, Bingheng Li, Xingtong Yu, Shuo Wang, Ruiyi Fang, Zhao Kang
Machine Learning
Hybrid-Adaptive Thread Tuning to Mitigate Simulation Execution Bottlenecks in High-Performance Reinforcement Learning Inference
Jiming Su, Hantao Hua, Lujia Yin et al. (+2 more)
In simulation-in-the-loop decision-making systems, reinforcement learning (RL) inference is often constrained by simulator-side execution overhead, where workloads are highly dynamic and sensitive to runtime thread configurations. Existing multithreaded strategies struggle to match thread resources before or during execution, causing resource contention, scheduling overhead, and reduced throughput. Through empirical analysis, we identify the ratio of task execution time to scheduling time as the key factor determining the optimal thread count. Building on this insight, we propose AutoThread, a hybrid adaptive thread-tuning method for mitigating simulation bottlenecks in RL inference. AutoThread employs a Physics-Informed Neural Operator (PINO) as a thread-count predictor and incorporates a finite-source M/M/1 queueing model to constrain and guide prediction, enabling fast and accurate estimation under dynamic workloads. It further performs load-aware online fine-tuning to compensate for prediction errors and refine resource allocation. Experiments show that AutoThread improves average speedup by 18.4% over static strategies, achieves average throughput of 1.7x and 1.8x that of XGBoost and Reinforcer, respectively, and reduces execution time by up to 83.8% compared with state-of-the-art methods. Our code and
dataset are publicly available at https://github.com/suchenjm/AutoThread.
Read the full abstract ▾
All authors Jiming Su, Hantao Hua, Lujia Yin, Yiping Yao, Feng Zhu
Machine Learning
BioKD: Selective Physiology-to-Video Knowledge Distillation via Reliability Gate for Emotion Recognition
Bojing Hou, Ruohao Li, Yitong Zhu et al. (+3 more)
To address the limitations of
video-based
emotion recognition under ambiguous or socially masked behavioral cues, as well as the poor deployability of physiological signals, this paper proposes a reliability-aware physiology-to-
video knowledge
distillation framework, termed BioKD. The proposed framework leverages physiological signals as privileged information during training to guide a
video-based student model in learning deep affective representations, while relying solely on non-intrusive
video inputs at inference time. To cope with the high noise and instability of physiological teacher supervision caused by inter-subject variability, signal artifacts, and temporal inconsistency, BioKD incorporates a sample-wise reliability-aware gating mechanism together with a progressive
distillation strategy. By adaptively regulating the strength of knowledge transfer, the framework suppresses negative transfer induced by unreliable physiological supervision and enables more stable cross-modal
distillation. Experiments on DEAP and AMIGOS show that BioKD consistently outperforms representative baselines under both trial-wise and subject-wise evaluation protocols for valence and arousal recognition. For example, BioKD achieves 68.01% on DEAP (trial-wise arousal) and 65.29% under the more challenging subject-wise setting, demonstrating improved performance under a subject-independent evaluation setting. Further analyses show that BioKD effectively mitigates overconfident teacher errors and outperforms an
entropy-only weighting strategy, confirming the importance of explicitly modeling supervision reliability. In addition, BioKD introduces no additional inference-time overhead relative to the same
video student architecture and removes the need for physiological sensing and
multimodal synchronization.
Read the full abstract ▾
All authors Bojing Hou, Ruohao Li, Yitong Zhu, Hongjun Liu, Luwen Yu, Yuyang Wang
Machine Learning · Cross-listed from cs.AI
From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models
Jiale Han, Xiang Li, Jing Qian et al. (+7 more)
Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous
agents, their beliefs and actions, and the
market and institutional mechanisms through which their interactions produce aggregate outcomes. This paper develops an implementation roadmap for building economic world models as generative engines in which heterogeneous
agents act, interact, adapt, and co-evolve with
markets and institutions, thereby producing economic dynamics from the inside. We organize EWM systems into a six-level capability ladder, from fixed rule-based
agent worlds to adaptive and LLM-based
agent worlds, self-evolving
agents, evolving institutional worlds, and sim-to-real economic twins aligned with real observations. A systematic literature survey across these levels reveals that existing work remains concentrated in lower-level
agent and simulation environments, while systems with self-evolving
agents, endogenous institutions, persistent empirical
alignment, and validated economic mechanisms remain rare. By translating the EWM agenda into an implementation blueprint, this paper aims to accelerate the development of the next generation of economic simulation environments that can serve as high-fidelity sandboxes for human decision-makers and as training, planning, evaluation, and safety substrates for AI
agents. We release a curated paper list and related resources to support future research.
Read the full abstract ▾
All authors Jiale Han, Xiang Li, Jing Qian, Wenyuan Gu, Pin Gao, Ye Luo, Hongyuan Zha, Dacheng Tao, Benyou Wang, Lin William Cong
Machine Learning
ProDVI: Programmatic Dynamics Priors for Value Network Initialization
Xinwei Liu, Junyuan Liang, Jianting Zhang et al. (+1 more)
Deep Reinforcement Learning (RL) is notoriously sample inefficient. One contributing factor is that RL
agents are typically initialized from scratch, forcing them to acquire task-relevant knowledge through online interaction. Existing approaches obtain informative initializations through pre-collected
datasets, high-fidelity simulators, or meta-learning over related tasks, but these prerequisites may be difficult to access or even unavailable. In this paper, we propose Programmatic Dynamics Priors for Value Network Initialization (ProDVI), a framework that leverages the commonsense and domain knowledge encoded in large
language models to initialize RL
agents without relying on these resources. Specifically, ProDVI
prompts a code-generating
language model to produce executable Python functions that encode coarse hypotheses about environment dynamics. These functions are then used to generate synthetic transitions. Based on these transitions, we construct an auxiliary dynamics prediction objective to pretrain the state-action encoder of the value network in an actor-critic framework. The learned representation provides dynamics-aware inductive biases before online RL begins. Importantly, the generated programs are used only for representation pretraining and are not required to faithfully simulate the target environment. While the generated programs may be inaccurate, their induced initialization can be corrected through online learning from real transitions and rewards. Experiments on OpenAI Gym and DeepMind Control Suite tasks show that ProDVI can effectively improve the sample efficiency of model-free RL
algorithms.
Read the full abstract ▾
All authors Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
Machine Learning
Do Tabular Foundation Models Agree with Themselves?
Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme et al. (+1 more)
Tabular Foundation Models (TFMs) are currently the best approach to tabular prediction problems. They are constructed as
transformers that approximate the
Bayesian posterior predictive distribution based on a pre-training prior. These univariate predictors can be converted into multivariate ones autoregressively by sampling one target and adding it to the features. However, the faithfulness of the resulting joint has not been investigated. Furthermore, TFMs cannot be evaluated against the posterior itself, at least not on real-world
datasets, because the ground-truth distribution is unknown. We therefore propose asking a different question: could a model's predictions result from any joint distribution? To answer this question, we pose two requirements that any such model must satisfy. The first is marginalization consistency, which demands that marginalized conditionals are equal to directly predicted marginals. The second is factorization consistency, which demands that different factorization orders result in equal joint distributions. Every TFM that we evaluate violates both of these requirements for both classification and regression across all
datasets.
Read the full abstract ▾
All authors Christian Klötergens, Vijaya Krishna Yalavarthi, Lars Schmidt-Thieme, Tom Hanika
Machine Learning
A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Risk
Frieder Wizgall, Georg Tirpitz, Moritz Seiler et al. (+2 more)
Reliable uncertainty estimates are critical in safety-sensitive applications. For such estimates to be useful in practice, it is crucial to understand the sources underlying a model's uncertainty, motivating the disentanglement of total uncertainty into epistemic and aleatoric uncertainty. Existing notions of uncertainty differ in the sources they capture and, consequently, in their definitions of aleatoric and epistemic uncertainty, with no universally accepted definition. We define uncertainty through sample-conditional pointwise posterior risk, which is the expected loss of a predictor under the distribution of plausible ground-truth functions given the observed sample. This definition unifies probabilistic and risk-based concepts of uncertainty. To assess state-of-the-art uncertainty disentanglement methods, we develop a framework that directly compares their estimates against ground-truth uncertainty defined primarily by posterior risk, alongside commonly used alternative uncertainty definitions. We find that Spectral-normalized Neural Gaussian Processes and Variational Latent Gaussian Processes most closely recover the ground-truth uncertainty, while most methods track posterior variance more closely than posterior risk, missing the predictors' bias. Beyond method rankings, we investigate how strongly estimated aleatoric and epistemic uncertainty are entangled and how sensitive uncertainty quality is to modeling choices, yielding practical guidance for uncertainty disentanglement. To support further method development and validation, we release 13 semi-synthetic UCI/OpenML
datasets with known posteriors, enabling the computation of ground-truth uncertainty. Code and data will be made publicly available upon acceptance.
Read the full abstract ▾
All authors Frieder Wizgall, Georg Tirpitz, Moritz Seiler, Kerstin Ritter, Bálint Mucsányi
Machine Learning
Observation-Grounded Self-Predictive Reinforcement Learning for Visual Continuous Control
Xinwei Liu, Junyuan Liang, Jianting Zhang et al. (+1 more)
Sample-efficient policy learning from pixels is a long-standing challenge in reinforcement learning (RL). Recent dynamics-based representation learning methods have significantly improved the sample efficiency of model-free visual RL by learning dynamics-aware representations through auxiliary prediction performed either in latent space (self-prediction) or observation space (observation prediction). However, state-of-the-art methods from both categories still struggle on challenging visual control tasks when training data is limited. We posit that relying on either predictive objective alone may be insufficient. In contrast, observation prediction grounds learned representations in observation-level dynamics, but does not directly regularize the temporal predictability of latent representations over extended horizons. In this paper, we propose Observation-Grounded Self-Predictive Representations (OG-SPR), a model-free visual RL
algorithm for continuous control that learns representations that are both temporally predictive in latent space and grounded in observation-level dynamics. OG-SPR incorporates two core auxiliary objectives: multi-step latent self-prediction and next-observation prediction. We empirically show that directly imposing latent self-prediction on the shared representation may over-constrain it and does not necessarily improve performance. To address this issue, OG-SPR introduces two lightweight adapters for latent self-prediction, allowing the shared representation to benefit from temporally predictive signals without being forced to directly satisfy the self-prediction objective. Experiments on 28 visual control tasks from the DeepMind Control Suite show that OG-SPR improves aggregate performance over state-of-the-art self-predictive and observation-predictive RL methods, with particularly pronounced gains in challenging domains such as dog and
humanoid.
Read the full abstract ▾
All authors Xinwei Liu, Junyuan Liang, Jianting Zhang, Wuhui Chen
Machine Learning · Cross-listed from cs.AI
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao et al. (+10 more)
Reinforcement learning (RL) with verifiable rewards constructs trajectory-level advantage estimates, yet it often fails to credit the few pivotal decisions that determine outcomes in long-horizon, multi-turn agentic tasks. Recent work introduces privileged self-
distillation for credit assignment, providing denser supervision, but it remains unclear how such local signals should represent sequential credit. We propose AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning. AgentOPSD aggregates
token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a
Bayesian belief state in log-odds space. This yields a principled reweighting scheme that converts sparse outcome supervision into turn-level credit signals and identifies pivotal turns through the marginal belief revision between consecutive states. The method is fully compatible with standard policy optimization and requires neither an additional critic nor extra rollouts. We evaluate AgentOPSD on ALFWorld, WebShop, and Search-QA using Qwen2.5 models at two scales (3B and 7B). AgentOPSD outperforms GRPO and strong self-
distillation baselines, achieving 89.1% success on ALFWorld with Qwen2.5-7B. Ablation studies attribute the gains to turn-level aggregation and history-dependent recursive belief updates.
Read the full abstract ▾
All authors Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Jie Wu, Zhengzhou Cai, Yueqing Sun, Ziang Ye, Linji Hao, Qi Gu, Xunliang Cai, Yongliang Shen, Yujiu Yang
Machine Learning
THBKG: A Temporal Biomedical Knowledge Graph for Decision-Aligned Clinical Advancement Prediction
Pui Chung Siu, Claudia Cabrera, Mani Mudaliar et al. (+1 more)
Inadequate target–disease linkage accounts for 40–50% of Phase~II efficacy failures, so anticipating which programmes will advance would let sponsors back the hypotheses most likely to reach patients. What a programme can be judged on is the evidence that supported its linkage when it entered the clinic. No existing biomedical knowledge graph allows that evidence profile to be assembled as of a past date. We present the Temporal Heterogeneous Biomedical Knowledge Graph (THBKG), which describes and predicts therapeutic target–disease links through time: 110,396 entities and 11.1M edges across nineteen relation types, each edge carrying the year its evidence changed, so a pair's profile can be recovered as it stood when its own decision fell due. On this graph we define a decision-aligned
benchmark that predicts, for a target–disease pair entering Phase~II, whether it advances to Phase~III on evidence datable before that decision. Graph propagation over the THBKG outranks every direct-evidence reference scored under the same decision-aligned protocol, reaching a relative success of 4.3–4.5 at the top ten pairs per therapeutic area. The gain concentrates on the 72.8% of pairs with no direct target–disease evidence at their decision point, where a direct-edge model has nothing to read: the encoders still rank five- to sixfold above chance, recovering the signal by propagating over the intervening biology. Adapting a path-based explainer to the decision-time subgraph decomposes each prediction into the evidence landscape behind the hypothesis for explainable prediction. We release the THBKG as a continually updated substrate for studying therapeutic target hypotheses by retrospective validation.
Read the full abstract ▾
All authors Pui Chung Siu, Claudia Cabrera, Mani Mudaliar, Arkaitz Zubiaga
Machine Learning · Cross-listed from cs.AI
Temporal Bridges for Spatial Resolution: Enhancing Climate Data Super-Resolution with Bidirectional Alignment
Yichen Zhang, Yixiong Xiao, Congxi Xiao et al. (+1 more)
High-resolution
climate data is crucial for meteorological predictions and for informing decision support across diverse domains. However, the acquisition of such high-resolution
climate information is often prohibitively costly, necessitating the development of data-driven meteorological prediction models. These models aim to generate fine-grained
climate data from low-resolution inputs, a process termed
climate data super-resolution (SR). Nevertheless, recent advancements in deep learning for
climate data SR have primarily focused on leveraging single-frame spatial information, largely neglecting the temporal correlations between different time frames that could enhance SR outcomes. Furthermore,
climate data are inherently
stochastic and noisy, rendering widely used temporal
alignment methods, such as optical flow models, ineffective in this context. Consequently, the development of a framework tailored for
climate data SR that effectively captures implicit temporal correlations remains an unresolved challenge. To this end, we propose a novel Temporal-Enhanced framework with bidirectional temporal
alignment. In essence, our framework establishes a temporal bridge to enhance spatial resolution in
climate data SR through bidirectional
alignment, leading to improved SR performance. Within this framework, Paired Latent Mapping achieves spatial
alignment and noise reduction by unifying latent spaces. Then a Bidirectional Temporal
Alignment captures temporal correlations by training forward and backward networks on consecutive latent frames. Temporal Enhanced Super-resolution then optimizes the entire framework for
climate data SR. Experiments on large-scale real-world
datasets demonstrated the superior performance of our framework.
Read the full abstract ▾
All authors Yichen Zhang, Yixiong Xiao, Congxi Xiao, Jingbo Zhou
Machine Learning
How Far Do Simple Transformations Translate Across Text Embedding Models?
Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin et al. (+1 more)
We investigate whether simple transformations can translate representations across heterogeneous text
embedding models. Understanding how independently trained models organize semantic information is an enabler for AI-to-AI latent communication without decoding into human-readable text. Focusing on lightweight translators such as linear mappings, we test the literature hypothesis of latent universality in a realistic text setting beyond simplified
benchmarks. Across nine
embedding models differing in architecture, pooling strategy, and training objective, we evaluate compatibility using CKA, downstream transfer, fidelity, and
retrieval. Simple translators recover meaningful shared structure and support transfer for some compatible pairs, but fail sharply for others. Compatibility depends jointly on architecture, training objective, pooling, and data distribution. Overall, the results show that heterogeneous
embedding spaces are not universally related by simple mappings as often suggested in some literature.
Read the full abstract ▾
All authors Sid Ali Hamideche, Louis-Adrien Dufrène, Quentin Lampin, Guillaume Larue
Machine Learning · Cross-listed from cs.AI
Training a Conditioned Video Game Agent on a VLM Annotated Dataset
Katrin Schmid and Iuri Frosio
Reinforcement Learning (RL) is a powerful but far from easy-to-use technique for policy learning. In the specific case of
video games, access to the game engine is required to get rewards for training (e.g. to collect rewards from the environment). Furthermore, the proper identification and weighting of the rewards generally requires a difficult trial-and-error approach. Lastly, rewards are often sparse and understanding how they eventually affect the learned policy is a non-trivial exercise. To ease these issues we propose annotating a
video game
dataset with
Vision Language Models (VLMs) instructed to extract human defined rewards. We show that offline RL can then be used to train a conditioned
agent that responds accordingly to the desired returns and we discuss the difficulties and limitations that emerged in our early experiments.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
VLMs for Videogame Data Annotation
Katrin Schmid and Iuri Frosio
Vision Language Models (VLMs) and Artificial Intelligence (AI)
agents have revolutionized how engineers approach complex problems in real-world applications. Their adoption in
video games is on the other hand limited by the extreme variability of the synthetic scenarios and their poor compliance with real-world physics. Here we investigate the use of VLMs for annotating
video game frame sequences with reward signals, a task with several potential applications including, among others, conditioned training and offline reinforcement learning. We show that VLMs often struggle to answer basic questions on racing
video games (although we observed a similar behavior on other game genres) and discuss countermeasures such as VLM output mixing and
prompt optimization. We also show how input sequence length, resolution, and question batching affect the annotation quality and its
token consumption.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.DC
Operating Multi-Node Full Fine-Tuning on NVIDIA B300: A Field Report on Telemetry-Based Triage, Negative Results, and Operational Hardening
Seon Ho Kim, Ui Jeong Jeon, Su Hyeon Kim et al. (+1 more)
We report operational experience full-fine-tuning a 32.76B-parameter dense model (Qwen3-32B) on 16 x NVIDIA B300 (two nodes, FSDP / ZeRO-3) – among the first published field accounts on this accelerator. We claim no new
algorithm. The individual mechanisms we use are established practice; our contribution is the integrated field experience and a set of calibrated measurements on new hardware. Concretely we offer four practitioner artifacts. (1) A B300-calibrated power-draw triage table that distinguishes compute / communication / data-starvation / checkpoint-or-deadlock / idle by board wattage (utilization% reads 100% during an NCCL hang). (2) A set of honest negative results that dispel common optimization folklore at this scale: a controlled A/B in which per-step NFS reading matches a pretokenized local cache (~53k tok/s) because the corpus fits in page cache and the job is compute-bound; and a reconstruction of an earlier "throughput collapse" as NFS/CPU contention rather than a storage-medium limit. (3) Calibrated 4/8/16-GPU strong-scaling and GPU-hour numbers on B300 (near-linear, as expected in this regime; we report absolute values as reference data). (4) A worked failure case – an epoch-end NCCL deadlock from per-rank
token-packing imbalance – together with a 2.7-second pre-run invariant gate and an external watcher that turn multi-hour silent failures into instant rejections. This deadlock and its remedy correspond to PyTorch's documented Join / equalize-to-minimum practice; we position our instantiation against that prior art and report the GPU-hours the failure cost and the gate saves. The transferable takeaway is operational, not algorithmic: for data-dependent data-parallel jobs, watch power rather than utilization, and verify invariants before launch – a passing smoke test is not evidence of a safe full run.
Read the full abstract ▾
All authors Seon Ho Kim, Ui Jeong Jeon, Su Hyeon Kim, Min Tae Hwang
Machine Learning · Cross-listed from cs.CV
MirrorNet: Can Medical Image Anonymization Really Protect Patient Identity?
Attila Simkó
Medical images are routinely de-identified—names, dates, and other metadata removed—and then shared for research, teaching, and public
benchmarks under the assumption that this renders them anonymous. Such de-identification protects the metadata but not the pixels, and—apart from scans that directly contain facial structures—whether the image content itself identifies the patient has received little scrutiny. We investigate this question by learning a cycle-consistent correspondence between a cross-sectional medical image and a non-medical, patient-identifying image, using a pair of coupled, cycle-consistent variational autoencoders. From a held-out scan, the model recovers a recognisable likeness of the patient (identity-region MAE = 0.163); conversely, it synthesises a scan from such an image. These results indicate that a de-identified medical scan remains identifying—it is, in effect, a photograph of the patient—and that imaging data should be governed as biometric data rather than as anonymisable records. To support reproducibility, the code and trained models are shared at https://github.com/attilasimko/public-repository.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.ML
Deep Generalised Mixed Models: a Novel Neural Network Structure for Analysing Hierarchical Data
Nina van Gerwen, Dimitris Rizopoulos, Manon Hillegers et al. (+2 more)
The experience sampling method (ESM) is a longitudinal research design where participants report their thoughts, emotional states and behaviours multiple times a day. Our work is motivated by such data collected by the GrowIt! app, which was released to investigate daily
emotions among adolescents during the COVID-19 pandemic. Current procedures to analyse ESM data face various challenges. While standard statistical techniques may not scale well to a high-dimensional setting, machine learning procedures can give biased results due to selection bias introduced by missingness. In our motivating
dataset, adolescents dropped out due to previous strong feelings of negative
emotions. Hence, the implied missing data are of the missing-at-random type that standard machine learning procedures cannot accommodate. We develop a novel neural network architecture that generalises mixed effects models to deep learning to overcome these challenges. It allows semi-parametric and flexible modelling of data's mean and correlation structure through fixed and random effects. For estimation, we use an adaptation of variational auto-encoders and a
Bayesian data augmentation
algorithm. Through this approach, the model can accommodate longitudinal outcomes following generic distributions, scale well to high-dimensional settings and provide valid inference when data are missing-at-random. We applied the Deep Generalised Mixed Model to the GrowIt! study and various simulations. The results show potential for the Deep Generalised Mixed Model, yet suboptimal performance due to model instability.
Read the full abstract ▾
All authors Nina van Gerwen, Dimitris Rizopoulos, Manon Hillegers, Loes Keijsers, Sten Willemsen
Machine Learning
Graph-structured joint-embedding prediction for single-cell transcriptomics
Yuhao Wang, Zelin Zang, Yuxuan Liu et al. (+2 more)
Single-
cell transcriptomes are sparse, unordered measurements of coordinated biological activity, yet many self-supervised models define their learning target at the level of individual genes or reconstructed expression values. Here we introduce GB-JEPA, a joint-
embedding predictive architecture in which graph-connected gene blocks form the latent prediction units. A student encoder observes the genes outside each target block, whereas an exponential-moving-average teacher represents the full observed gene set. Teacher states are aggregated within a block before the prediction error is evaluated, converting thousands of sparse gene-level targets into a small collection of intermediate-scale latent targets. The graph therefore serves not only as prior information, but also as a mechanism for controlling the structure, scale and predictability of self-supervision. We evaluate the resulting frozen
cell representations through objective diagnostics,
cell-state annotation, continuous-expression and pathway probes, perturbation-response prediction, computational measurements and direct biological interrogation. This study presents a graph-structured route for adapting JEPA learning to molecular observations and a general framework for designing prediction units from relationships native to a biological modality.
Read the full abstract ▾
All authors Yuhao Wang, Zelin Zang, Yuxuan Liu, Zhen Lei, Stan Z. Li
Machine Learning
CohortHijack: Robustness of Single Cell Annotation to Companion Cell Removal
Arash Vashagh and Yasmin Vashagh
Many single-
cell annotation tools refine an initial
cell label using nearby
cells or cluster-level voting. We study whether this refinement can be manipulated without changing the target
cell. We introduce CohortHijack, a robustness audit that removes selected non-target
cells from the query cohort while preserving the target expression profile, base prediction, and trained model. We evaluate random and structured removal methods, together with greedy, multi-start, and beam search, on PBMC3K and Paul15 using logistic regression and calibrated linear SVM classifiers. Structured removal was consistently stronger than random removal on Paul15. Multi-start search changed 24.33% of linear-SVM targets and 19.67% of logistic-regression targets while removing a small fraction of the cohort and keeping mean collateral changes below 0.4%. Ablations confirmed that the effect disappeared when neighborhood refinement was disabled. We also evaluated CellTypist majority voting, where independent predictions remained unchanged across all evaluations, but refined labels changed after small companion-
cell removals. These findings identify query cohort composition as a target-preserving attack surface in single-
cell annotation.
Read the full abstract ▾
Machine Learning
Alternating Levenberg-Marquardt Training of Physics-Informed Neural Networks with Fourier-Enhanced Features
Yulun Wu, Matthieu Barreau, Miguel Aguiar et al. (+1 more)
Physics-informed neural networks (PINNs) often fail to accurately resolve partial differential equations (PDEs) with high-frequency or multi-scale solutions, as well as strongly nonlinear problems. Two factors underlie this difficulty: spectral bias, the tendency of neural networks to underfit high-frequency features; and representation-coefficient coupling, the
entanglement of representation learning and coefficient fitting within a single nonconvex optimization objective. In this work, we propose the
Fourier-enhanced alternating Levenberg–Marquardt PINN (FALM-PINN), an optimization framework that decouples representation learning from coefficient fitting. The upper-level problem learns a
Fourier-enhanced basis that enriches the latent space with high-frequency components, while the lower-level problem resolves the coupling by fitting the projection coefficients on this basis, solving a nonlinear least-squares problem with the Levenberg–Marquardt
algorithm. The framework applies to general nonlinear and coupled PDE systems, and reduces to a single-step convex optimization problem for linear PDEs. We prove global convergence of the alternating training scheme in both cases. Numerical examples on multiple challenging high-frequency and nonlinear PDEs show that FALM-PINN achieves relative $L^2$ errors up to two orders of magnitude lower than state-of-the-art baselines.
Read the full abstract ▾
All authors Yulun Wu, Matthieu Barreau, Miguel Aguiar, Karl H. Johansson
Machine Learning
Beyond Feature Importance: A Comparative Analysis of Pattern Detection Methods in Cluster Interpretation
Benjamin Connor, Anna Jurek-Loughrey, Lu Bai et al. (+1 more)
Interpreting clustering outcomes remains a fundamental challenge in data analysis, particularly in domains such as healthcare where meaningful patterns must be extracted from high-dimensional data. While numerous explainability techniques exist, they are primarily designed to assess feature importance or provide local instance-level explanations rather than to identify structured patterns present within clusters. This work presents a comparative evaluation of commonly used post-hoc analysis methods for pattern detection in clustering results. To enable controlled evaluation, we introduce a suite of synthetic
datasets in which predefined patterns are systematically injected. Three widely used techniques are evaluated: a Random Forest surrogate model with permutation feature importance, LIME (Local Interpretable Model-agnostic Explanations), and principal component analysis. Results demonstrate that although each method can successfully recover relevant features, none consistently detects all injected pattern types. These findings high- light a critical gap between existing explainability tools and the requirements of pattern-level cluster interpretation, motivating the development of dedicated pattern detection methodologies.
Read the full abstract ▾
All authors Benjamin Connor, Anna Jurek-Loughrey, Lu Bai, Muhammad Fahim
Machine Learning
Evidential Rule Learning for Interpretable Classification with Abstention
Javier Fumanal-Idocin and Javier Andreu-Perez
Interpretable classification often requires more than accurate predictions for real-life deployment: models should be transparent about the evidence behind their decisions and abstain when they cannot decide reliably. We introduce Fast Evidential Rule Learning (FERL), a method that learns interpretable, accurate fuzzy rule models whose outputs are evidential. Unlike post-hoc calibration, FERL's belief, plausibility, and abstention capabilities arise directly from the fuzzy memberships in a single deterministic pass, with no auxiliary head, held-out set, or repeated inference. Our theoretical analysis further shows that FERL is Lipschitz stable, which means that its evidential outputs vary smoothly with the input. Against state-of-the-art rule learners, FERL is statistically significantly more accurate across a 30 tabular-
dataset benchmark ($+2.6\%$ average accuracy over the second best). Its native set predictions attain the best utility-discounted accuracy among credal classifiers ($u_{65}/u_{80}=0.80/0.83$ vs.\ $0.79/0.80$ for the naive credal classifier), at higher set coverage ($0.92$ vs.\ $\le0.82$). FERL also matches dedicated out-of-distribution detectors on tabular near-OOD detection ($77.7$ vs.\ $77.4$ AUROC for the strongest baseline). Under detector-class-disjoint concept-bottleneck evaluation, its it is within $2.3$ AUROC points of the strongest dedicated detector on both CUB and AwA2, while attaining the best AwA2 AUPR-Out ($68.3$) and novel-class rejection ($57.2$), while being able to name which attributes are anomalous.
Read the full abstract ▾
Machine Learning · Cross-listed from math.NA
A neural operator view on U-Nets for inverse imaging problems
Alexander Auras, Martin Burger, Samira Kabri et al. (+2 more)
Deep neural networks have shown great empirical success in the solution of a wide variety of ill-posed inverse problems in imaging. Yet, very few works have studied their behavior in the limit that turns the discretized ill-conditioned problems into truly ill-posed ones, i.e., for an increasing resolution of the discretization. In this work, we review common approaches to neural operator learning in architectures that resemble a U-Net, one of the most common classical architectures for inverse imaging problems. We discuss advantages and drawbacks of the respective approaches, consider a 1D toy example for improved interpretability, and present extensive numerical experiments on how different types of neural operator U-Nets can improve a first (crude) limited angle CT-reconstruction. In particular, we study how well networks trained for a certain resolution of the discretization generalize to other resolutions. Our finding is that while U-shaped neural operator architectures are by design resolution-invariant, the classical U-Net architecture seems to be more robust with respect to resolution changes than expected.
Read the full abstract ▾
All authors Alexander Auras, Martin Burger, Samira Kabri, Michael Moeller, Michael Schopf-Kuester
Machine Learning
Learning to Rank Tensor Network Contraction Plans for GPU-Accelerated Quantum Circuit Simulation
Alfred M. Pastor, Maribel Castillo and Jose M. Badia
Classical simulation remains essential for developing and validating
quantum algorithms, but its cost grows rapidly with
circuit size. Tensor-network contraction can reduce this cost by exploiting
circuit structure, although its efficiency depends strongly on the chosen contraction plan. On GPUs, plans with similar theoretical complexity may perform very differently because execution also depends on parallelism, reduction structure,
memory traffic, and contraction geometry. We present a learning-to-rank framework for selecting efficient contraction plans before executing them. Each plan is represented by structural features derived directly from its sequence of pairwise contractions, and gradient-boosted rankers are trained from GPU measurements using listwise and pairwise objectives. We evaluate the resulting models on diverse
circuit families, using separate in-distribution and
circuit-family-shift test sets, and compare them with random and MinFill-based baselines. The learned rankers generally identify better plans, with the listwise model providing the strongest overall decision quality. We also study backend shift by comparing empirical plan orderings on two GPU architectures and evaluating the source-trained models on the second device without retraining. The rankings remain substantially, though not perfectly, stable across GPUs, and the models retain useful decision quality. These results support Learning to Rank as a practical way to reduce contraction-plan search, while showing that performance remains partly backend dependent.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Byeongho Heo, Jaehui Hwang, Sangdoo Yun et al. (+1 more)
On-Policy
Distillation (OPD) is emerging as a promising alternative to reinforcement learning for LLM post-training, yet its effectiveness in
multilingual settings remains underexplored. We study OPD and its advanced variant, On-Policy Delta
Distillation (OPD$^2$), for mathematical
reasoning in English, Korean, and Japanese. OPD$^2$ improves OPD by using the probability gap between a post-trained teacher and its base model as the learning signal. Experiments with Qwen3 show that OPD$^2$ consistently outperforms the original OPD, with particularly strong improvements in Korean and Japanese, and generally narrows the English-Korean performance gap. We further find that English-only OPD can also increase performance for Korean and Japanese, but often shifts the responses toward English, highlighting the importance of
multilingual data to preserving target-
language responses.
Read the full abstract ▾
All authors Byeongho Heo, Jaehui Hwang, Sangdoo Yun, Dongyoon Han
Machine Learning · Cross-listed from cs.CV
KVAE: Family of Tokenizers for Multimodal Generative Models
Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov et al. (+11 more)
Latent
diffusion modeling (LDM), a prominent paradigm, utilizes tokenizers to map input signal to compressed representation. This dependency positions tokenizer as an integral part of generation process itself, since it affects learning speed, quality of synthesized samples and lay foundation for later applications. This report presents series of KVAE tokenizers for audio, image and
video, all designed for subsequent text-conditioned generation: KVAE-Audio, a continuous full-band 48 kHz tokenizer with a 50 Hz latent of 64 channels; KVAE-3D – two causal
video tokenizers for 4x16x16 and 4x8x8 compression; KVAE-2D, an image model, compressing input by factor of 8 with 32 channels. We demonstrate that reconstruction (PSNR, LPIPS, PESQ, etc.) and generation results on objective (Frechet Distance, CLIP score, CLAP score, etc.) and subjective (side-by-side evaluation) metrics matches or surpasses frontier opensource tokenizers, such as VAEs from Wan-2.2, HunyuanVideo-1.5, FLUX.2, MovieGen, StableAudio and MMAudio. Considering difficulty of development, we share with community training details, model selection method and ablation on design choices. The code is publicly available at https://github.com/kandinskylab/kvae and https://github.com/kandinskylab/kvae-audio.
Read the full abstract ▾
All authors Andrey Shutkin, Denis Parkhomenko, Ivan Kirillov, Kirill Chernyshev, Kirill Malakhov, Ilia Vasiliev, Ilia Trushkin, Valeriya Kobenko, David Chikovani, Alexander Ivanov, Azat Saginbaev, Egor Silvestrov, Ivan Mikheev, Konstantin Zakharov
Machine Learning
Predicting Task Difficulty Without Rollouts
Stefan Krsteski and Charlotte Meyer
A fundamental challenge in evaluating and training autonomous
agents is measuring the intrinsic difficulty of the tasks they attempt. Estimating this quantity can be useful for environment designers creating synthetic data or
benchmarks, as well as for constructing training curricula, thereby offering a way to reduce compute costs. Such an estimation becomes increasingly important as
agents (particularly LLM-based) move into longer-horizon domains, where empirical trial-and-error becomes a severe computational bottleneck. However existing work is largely confined to static tasks and relies on evaluation metrics that, as we show, can give an incomplete picture of predictive performance. In this paper we study ex ante difficulty prediction across 17 agentic
benchmarks spanning coding, mathematics, machine learning, web
navigation, function calling, and other domains. We find that AUC can mask poor difficulty estimates, identify
token-level
entropy as a useful predictive signal, and demonstrate how residuals between expected and observed difficulty can expose environment flaws such as contamination and infeasibility.
Read the full abstract ▾
Machine Learning
GROM: Gradient-Free Rapid One-Shot Machine Unlearning
Paweł Batorski, Przemysław Spurek and Paul Swoboda
Machine unlearning has become a critical capability for safely removing specific, sensitive knowledge from large
language models (LLMs). Current state-of-the-art approaches primarily rely on iterative, training-time unlearning via fine-tuning. However, even when utilizing parameter-efficient dimensionality reduction techniques like LoRA, gradient-based optimization remains computationally expensive and lacks explicit analytical formulations. It can also leave the targeted knowledge merely hidden rather than removed, to the point that simply quantizing the unlearned model restores much of what it was supposed to have erased. To resolve this, we propose a novel one-shot unlearning approach, abandoning iterative optimization in favor of a direct, exact analytical solution. We frame the unlearning process as a ridge-regularized least-squares optimization problem, deriving a closed-form additive update for targeted weight
matrices. This update forces the selected layer to suppress unwanted content while strictly preserving its behavior on retained data. Computed from gradient-free forward passes alone, with no backpropagation and no iteration to convergence, GROM applies the weight edit in mere seconds, which makes it orders of magnitude faster than traditional fine-tuning. Extensive evaluations demonstrate that GROM achieves state-of-the-art forgetting-utility trade-offs on TOFU-5%, TOFU-10%, MUSE-Books, MUSE-News and WMDP, significantly reducing computational overhead without sacrificing overall model performance. Because the update removes the targeted content from the weights instead of masking it, GROM also withstands the low-bit quantization attack that recovers much of the content a gradient-based baseline had appeared to forget. Our code is publicly available at https://github.com/Batorskq/GROM.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
VSMP-IMU: Video-Grounded Semantic Motion Programs for Sensor-Aware Synthetic IMU Generation
Lala Shakti Swarup Ray, Vitor Fortes Rey, Mengxi Liu et al. (+2 more)
Wearable human activity recognition (HAR) is often limited by the scarcity of labeled sensor data, especially in low-resource, class-imbalanced, and subject-generalization settings. Synthetic IMU generation can reduce this dependency and enhance HAR machine learning model's performance, but existing approaches face a trade-off without addressing all factors:
video-driven methods are visually grounded but sensitive to pose-estimation errors, while text-driven methods are controllable but often weakly grounded in how activities are actually performed. We present VSMP-IMU, a
video-grounded framework for controllable synthetic IMU generation based on a structured Semantic Motion Program (SMP), which separates activity-defining semantics from label-preserving variation. Given an input
video, VSMP-IMU extracts and augments an SMP, uses it to synthesize motion, converts the motion into virtual IMU signals, and grounds the resulting signals to the target wearable domain. We evaluate VSMP-IMU against state-of-the-art synthetic data generation methods on five public IMU-HAR
datasets under leave-one-person-out evaluation. VSMP-IMU achieves an average Macro-F1 of 78.33%, improving over real-only training by 9.77% and over the strongest prior synthetic baseline by 4.04%. In low-resource settings with reduced training data-samples, it improves over real-only training by 18.54% and over the strongest prior synthetic baselines by more than 6% on average. Under long-tail evaluation in imbalanced
datasets, it improves tail-class Macro-F1 by 19.86% over Real-only training and by 4.76% over SOTA. These results show that structured
video-grounded semantics provide a practical foundation for controllable, wearable-relevant synthetic sensor data generation.
Read the full abstract ▾
All authors Lala Shakti Swarup Ray, Vitor Fortes Rey, Mengxi Liu, Paul Lukowicz, Bo Zhou
Machine Learning · Cross-listed from cs.CV
SR-JEPA: Learning Predictive Latent State in 3D Scenes
Zihan Zhou, Qifu Wen and Xi Zeng
Joint-
embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce. We ask what a trained predictive pathway itself infers when an entire entity is absent from a native 3D scene. We introduce SR-JEPA, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied location. At evaluation, every point of one object is removed before encoding and replaced by the same shape-free 32-point query at its centroid. Training uses only self-contained 3D EMA targets: no reconstruction, semantic labels,
language, or lifted 2D features. On 5,953 held-out ARKitScenes objects, the imputed latent reaches 43.13% semantic-identity macro accuracy, 22.18 points above the strongest floor. Randomizing the prediction path removes 9.78 points, while substituting matched donor context removes 21.98 points. On 8,570 Sr3D support pairs, the full latent reaches 41.15 AP; identity decoded from the missing-object latent, combined with anchor identity and geometry, reaches 39.37 AP, leaving an unresolved 1.78-point residual. These results reveal a queryable, compositional 3D predictive state: the model completes context-dependent entity content, which downstream computation combines with metric geometry.
Read the full abstract ▾