Machine Learning
Causal Graph Learning via Distributional Invariance of Cause-Effect Relationship
Nang Hung Nguyen, Phi Le Nguyen, Thao Nguyen Truong et al. (+2 more)
This paper introduces a new framework for recovering causal graphs from observational data, leveraging the observation that the distribution of an effect, conditioned on its causes, remains invariant to changes in the prior distribution of those causes. This insight enables a direct test for potential causal relationships by checking the variance of their corresponding effect-cause conditional distributions across multiple downsampled subsets of the data. These subsets are selected to reflect different prior cause distributions, while preserving the effect-cause conditional relationships. Using this invariance test and exploiting an (empirical) sparsity of most causal graphs, we develop an
algorithm that efficiently uncovers causal relationships with quadratic complexity in the number of observational variables, reducing the processing time by up to 25x compared to state-of-the-art methods. Our empirical experiments on a varied
benchmark of large-scale
datasets show superior or equivalent performance compared to existing works, while achieving enhanced scalability.
Read the full abstract ▾
All authors Nang Hung Nguyen, Phi Le Nguyen, Thao Nguyen Truong, Trong Nghia Hoang, Masashi Sugiyama
Machine Learning · Cross-listed from cs.AI
Building Interpretable Models for Moral Decision-Making
Mayank Goel, Aritra Das and Paras Chopra
We build a custom
transformer model to study how neural networks make moral decisions on trolley-style dilemmas. The model processes structured scenarios using
embeddings that encode who is affected, how many people, and which outcome they belong to. Our 2-layer architecture achieves 77% accuracy on Moral Machine data while remaining small enough for detailed analysis. We use different interpretability techniques to uncover how moral
reasoning distributes across the network, demonstrating that biases localize to distinct computational stages among other findings.
Read the full abstract ▾
Machine Learning
Robustness as an Emergent Property of Task Performance
Shir Ashury-Tahan, Ariel Gera, Elron Bandel et al. (+2 more)
Robustness is widely viewed as a key challenge for real-world applications. However, because current research focuses only on difficult tasks, it partially captures real-world readiness. In this paper, we argue and verify that robustness, defined as consistency across semantically equivalent inputs, closely follows task difficulty: once models master a task, robustness emerges naturally. Through an empirical analysis of multiple models across diverse
datasets and configurations (e.g., paraphrases, temperature changes), we observe a strong positive correlation between task performance and robustness. Furthermore, our findings indicate that robustness is driven primarily by task-specific competence rather than inherent model attributes, challenging the common view of robustness as an independent capability. This perspective implies that as tasks mature and model performance saturates, robustness on those tasks will similarly emerge. For researchers, this suggests that explicit efforts to measure robustness may deserve reduced emphasis, as robustness is likely to improve alongside performance. For practitioners, it signals that while many existing
benchmarks are still unstable, models are already reliable on earlier tasks and suitable for deployment.
Read the full abstract ▾
All authors Shir Ashury-Tahan, Ariel Gera, Elron Bandel, Michal Shmueli-Scheuer, Leshem Choshen
Machine Learning · Cross-listed from cs.CV
Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
Bryan Sangwoo Kim, Jonghyun Park and Jong Chul Ye
Text-conditioned
diffusion models have advanced image and
video super-resolution by using
prompts as semantic priors, and modern super-resolution pipelines typically rely on latent tiling to scale to high resolutions. In practice, a single global caption is used with the latent tiling, often causing
prompt misguidance. Specifically, a coarse global
prompt often misses localized details (errors of omission) and provides locally irrelevant guidance (errors of commission) which leads to substandard results at the tile level. To solve this, we propose Tiled
Prompts, a unified framework for image and
video super-resolution that generates a tile-specific
prompt for each latent tile and performs super-resolution under locally text-conditioned posteriors to resolve
prompt misguidance with minimal overhead. Our experiments on high resolution real-world images and
videos show that tiled
prompts bring consistent gains in perceptual quality and fidelity, while reducing
hallucinations and tile-level artifacts that can be found in global-
prompt baselines. Project Page: https://bryanswkim.github.io/tiled-
prompts/.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Accurate Failure Prediction in Agents Does Not Imply Effective Failure Prevention
Rakshith Vasudev, Melisa Russak, Dan Bikel et al. (+1 more)
Proactive interventions by LLM critic models are often assumed to improve reliability, yet their effects at deployment time are poorly understood. We show that a binary LLM critic with strong offline accuracy (AUROC 0.94) can nevertheless cause severe performance degradation, inducing a 26 percentage point (pp) collapse on one model while affecting another by near zero pp. This variability demonstrates that LLM critic accuracy alone is insufficient to determine whether intervention is safe. We identify a disruption-recovery tradeoff: interventions may recover failing trajectories but also disrupt trajectories that would have succeeded. Based on this insight, we propose a pre-deployment test that uses a small pilot of 50 tasks to estimate whether intervention is likely to help or harm, without requiring full deployment. Across
benchmarks, the test correctly anticipates outcomes: intervention degrades performance on high-success tasks (0 to -26 pp), while yielding a modest improvement on the high-failure ALFWorld
benchmark (+2.8 pp, p=0.014). The primary value of our framework is therefore identifying when not to intervene, preventing severe regressions before deployment.
Read the full abstract ▾
All authors Rakshith Vasudev, Melisa Russak, Dan Bikel, Waseem Alshikh
Machine Learning
Bayesian Conformal Prediction as a Decision Risk Problem
Fanyi Wu, Veronika Lohmanova, Samuel Kaski et al. (+1 more)
We propose
Bayesian Conformal Prediction (BCP), a framework that combines
Bayesian posterior predictive distributions with PAC-style conformal risk control to produce prediction sets with finite-sample coverage guarantees. Standard
quantile-threshold conformal methods often construct prediction sets using a single fixed threshold, which typically yields connected prediction sets. While valid, such sets can be inefficient when the posterior predictive distribution is
multimodal, since they may span low-density regions between separated modes. The main contribution of BCP is to formulate conformal prediction as a decision-risk optimisation problem, extending standard fixed
quantile-threshold sets to optimised highest posterior density (HPD) prediction sets. These sets can be disjoint, concentrating probability mass on separated high-density regions. Validity is enforced using a PAC-style risk constraint, which provides coverage control even when the
Bayesian model is misspecified. In standard nested-threshold settings, BCP recovers the smallest feasible threshold, aligning with existing PAC-based approaches. In the
multimodal experiment, HPD geometry substantially improves efficiency, reducing mean prediction set size from $4.82$ to $2.07$ while satisfying the target PAC pass rate. Across regression, classification, and distribution-shift experiments, BCP maintains reliable coverage under model misspecification, whereas
Bayesian credible intervals can fail to preserve nominal coverage.
Read the full abstract ▾
All authors Fanyi Wu, Veronika Lohmanova, Samuel Kaski, Michele Caprio
Machine Learning
From Inexact Gradients to Byzantine Robustness: Acceleration and Optimization under Similarity
Renaud Gaucher, Aymeric Dieuleveut and Hadrien Hendrikx
Standard
federated learning
algorithms are vulnerable to
adversarial nodes, a.k.a. Byzantine failures. To solve this issue, robust distributed learning
algorithms have been developed, which typically replace parameter averaging by robust aggregations. While generic conditions on these aggregations exist to guarantee the convergence of (
Stochastic) Gradient Descent (SGD), the analyses remain rather ad-hoc. This hinders the development of more complex robust
algorithms, such as accelerated ones. In this work, we show that Byzantine-robust distributed optimization can, under standard generic assumptions, be cast as a general optimization with inexact gradient oracles (with both additive and multiplicative error terms), an active field of research. This allows for instance to directly show that GD on top of standard robust aggregation procedures obtains optimal asymptotic error in the Byzantine setting. Going further, we propose two optimization schemes to speed up the convergence. The first one is a Nesterov-type accelerated scheme whose proof directly derives from accelerated inexact gradient results applied to our formulation. The second one hinges on Optimization under Similarity, in which the server leverages an auxiliary loss function that approximates the global loss. Both approaches allow to drastically reduce the communication complexity compared to previous methods, as we show theoretically and empirically.
Read the full abstract ▾
Machine Learning · Cross-listed from q-fin.PM
A Novel approach to portfolio construction
T. Di Matteo, L. Riso and M.G. Zoia
This paper proposes a machine learning-based framework for asset selection and portfolio construction, termed the Best-Path
Algorithm Sparse Graphical Model (BPASGM). The method extends the Best-Path
Algorithm (BPA) by mapping linear and non-linear dependencies among a large set of financial assets into a sparse graphical model satisfying a structural Markov property. Based on this representation, BPASGM performs a dependence-driven screening that removes positively or redundantly connected assets, isolating subsets that are conditionally independent or negatively correlated. This step is designed to enhance diversification and reduce estimation error in high-dimensional portfolio settings. Portfolio optimization is then conducted on the selected subset using standard mean-variance techniques. BPASGM does not aim to improve the theoretical mean-variance optimum under known population parameters, but rather to enhance realized performance in finite samples, where sample-based Markowitz portfolios are highly sensitive to estimation error. Monte Carlo simulations show that BPASGM-based portfolios achieve more stable risk-return profiles, lower realized
volatility, and superior risk-adjusted performance compared to standard mean-variance portfolios. Empirical results for U.S. equities, global stock indices, and foreign exchange rates over 1990-2025 confirm these findings and demonstrate a substantial reduction in portfolio cardinality. Overall, BPASGM offers a statistically grounded and computationally efficient framework that integrates sparse graphical modeling with portfolio theory for dependence-aware asset selection.
Read the full abstract ▾
Machine Learning
Information-Theoretic Multi-Model Fusion for Target-Oriented Adaptive Sampling in Materials Design
Yixuan Zhang, Zhiyuan Li, Weijia He et al. (+4 more)
Target-oriented discovery under limited evaluation budgets requires making reliable progress in high-dimensional, heterogeneous design spaces where each new measurement is costly, whether experimental or high-fidelity simulation. We present an information-theoretic framework for target-oriented adaptive sampling that reframes optimization as trajectory discovery: instead of approximating the full response surface, the method maintains and refines a low-
entropy information state that concentrates search on target-relevant directions. The approach couples data, model beliefs, and physics/structure priors through dimension-aware information budgeting, adaptive bootstrapped
distillation over a heterogeneous surrogate reservoir, and structure-aware candidate
manifold analysis with Kalman-inspired multi-model fusion to balance consensus-driven exploitation and disagreement-driven exploration. Evaluated under a single unified protocol without
dataset-specific tuning, the framework improves sample efficiency and reliability across 14 single- and multi-objective materials design tasks spanning candidate pools from $600$ to $4 \times 10^6$ and feature dimensions from $10$ to $10^3$, typically reaching top-performing regions within 100 evaluations. Complementary 20-dimensional synthetic
benchmarks (Ackley, Rastrigin, Schwefel) further demonstrate robustness to rugged and
multimodal landscapes.
Read the full abstract ▾
All authors Yixuan Zhang, Zhiyuan Li, Weijia He, Mian Dai, Chen Shen, Teng Long, Hongbin Zhang
Machine Learning · Cross-listed from stat.ML
Multiparameter Uncertainty Mapping in Quantitative Molecular MRI using a Physics-Structured Variational Autoencoder (PS-VAE)
Alex Finkelstein, Ron Moneta, Or Zohar et al. (+4 more)
Quantitative imaging methods, such as
magnetic resonance fingerprinting (MRF), aim to extract interpretable pathology biomarkers by estimating biophysical tissue parameters from signal evolutions. However, the pattern-matching
algorithms or neural networks used in such inverse problems often lack principled uncertainty quantification, which limits the trustworthiness and transparency, required for clinical acceptance. Here, we describe a physics-structured variational autoencoder (PS-VAE) designed for rapid extraction of voxelwise multi-parameter posterior distributions. Our approach integrates a differentiable
spin physics simulator with self-supervised learning, and provides a full covariance that captures the inter-parameter correlations of the latent biophysical space. The method was validated in a multi-
proton pool chemical exchange saturation transfer (CEST) and semisolid magnetization transfer (MT) molecular MRF study, across in-vitro phantoms, tumor-bearing mice, healthy human volunteers, and a subject with glioblastoma. The resulting multi-parametric posteriors are in good agreement with those calculated using a brute-force
Bayesian analysis, while providing an orders-of-magnitude acceleration in whole
brain quantification. In addition, we demonstrate how monitoring the multi-parameter posterior dynamics across progressively acquired signals provides practical insights for protocol optimization and may facilitate real-time adaptive acquisition.
Read the full abstract ▾
All authors Alex Finkelstein, Ron Moneta, Or Zohar, Michal Rivlin, Moritz Zaiss, Dinora Friedmann Morvinski, Or Perlman
Machine Learning · Cross-listed from cs.RO
RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalization
Songming Liu, Bangguo Li, Kai Ma et al. (+5 more)
Vision-
Language-Action (VLA) models hold promise for generalist robotics but currently struggle with data scarcity, architectural inefficiencies, and the inability to generalize across different hardware platforms. We introduce RDT2, a robotic foundation model built upon a 7B parameter VLM designed to enable zero-shot deployment on novel embodiments for open-vocabulary tasks. To achieve this, we collected one of the largest open-source robotic
datasets–over 10,000 hours of demonstrations in diverse families–using an enhanced, embodiment-agnostic Universal Manipulation Interface (UMI). Our approach employs a novel three-stage training recipe that aligns discrete linguistic knowledge with continuous control via Residual Vector Quantization (RVQ), flow-matching, and
distillation for real-time inference. Consequently, RDT2 becomes one of the first models that simultaneously zero-shot generalizes to unseen objects, scenes, instructions, and even robotic platforms. Besides, it outperforms state-of-the-art baselines in dexterous, long-horizon, and dynamic downstream tasks like playing table tennis. See https://rdt-robotics.github.io/rdt2/ for more information.
Read the full abstract ▾
All authors Songming Liu, Bangguo Li, Kai Ma, Lingxuan Wu, Hengkai Tan, Xiao Ouyang, Hang Su, Jun Zhu
Machine Learning
Entropy-Gated Selective Policy Optimization:Token-Level Gradient Allocation for Hybrid Training of Large Language Models
Yuelin Hu, Zhengxue Cheng, Wei Liu et al. (+1 more)
Hybrid training methods for large
language models combine supervised fine tuning (SFT) on expert demonstrations with reinforcement learning (RL) on model rollouts, typically at the sample level. We propose
Entropy Gated Selective Policy Optimization (EGSPO), a three stage framework that extends sample level mixing with
token level gradient modulation. Stage 1, SFT expert learning, establishes a reliable warm up policy using expert demonstrations with a pure SFT loss. Stage 2, RL rollout generation, samples trajectories from the current policy and computes per
token predictive
entropy. Stage 3, the EGSPO mechanism, applies
entropy gated gradient allocation: a predictive
entropy module routes high
entropy tokens to full PPO updates to encourage exploration, and low
entropy tokens to attenuated PPO updates to reduce variance and preserve knowledge. Critically, both branches incorporate the advantage function A_t, ensuring that incorrect trajectories receive consistent negative learning signals and preventing reinforcement of confident errors. EGSPO achieves consistent improvements on mathematical
reasoning benchmarks, with gains of 3.8 percent on AIME and 2.9 percent on MATH over the CHORD phi baseline, while incurring only 3.4 percent additional computational overhead.
Read the full abstract ▾
All authors Yuelin Hu, Zhengxue Cheng, Wei Liu, Li Song
Machine Learning
medR: Reward Engineering for Clinical Offline Reinforcement Learning via Tri-Drive Potential Functions
Qianyi Xu, Gousia Habib, Feng Wu et al. (+5 more)
Reinforcement Learning (RL) offers a powerful framework for optimizing dynamic treatment regimes (DTRs). However, clinical RL is fundamentally bottlenecked by reward engineering: the challenge of defining signals that safely and effectively guide policy learning in complex, sparse offline environments. Existing approaches often rely on manual heuristics that fail to generalize across diverse pathologies. To address this, we propose an automated pipeline leveraging Large
Language Models (LLMs) for offline reward design and verification. We formulate the reward function using potential functions consisted of three core components: survival, confidence, and competence. We further introduce quantitative metrics to rigorously evaluate and select the optimal reward structure prior to deployment. By integrating LLM-driven domain knowledge, our framework automates the design of reward functions for specific diseases while significantly enhancing the performance of the resulting policies.
Read the full abstract ▾
All authors Qianyi Xu, Gousia Habib, Feng Wu, Yanrui Du, Zhihui Chen, Swapnil Mishra, Dilruk Perera, Mengling Feng
Machine Learning
Periodic Regularized Q-Learning
Hyukjun Yang, Han-Dong Lim and Donghwan Lee
In reinforcement learning (RL), Q-learning is a fundamental
algorithm whose convergence is guaranteed in the tabular setting. However, this convergence guarantee does not hold under linear function approximation. To overcome this limitation, a significant line of research has introduced regularization techniques to ensure stable convergence under function approximation. In this work, we propose a new
algorithm, periodic regularized Q-learning (PRQ). We first introduce regularization at the level of the projection operator and explicitly construct a regularized projected value iteration (RP-VI), subsequently extending it to a sample-based RL
algorithm. By appropriately regularizing the projection operator, the resulting projected value iteration becomes a contraction. By extending this regularized projection into the
stochastic setting, we establish the PRQ
algorithm and provide a rigorous theoretical analysis that proves finite-time convergence guarantees for PRQ under linear function approximation.
Read the full abstract ▾
Machine Learning
R1-SyntheticVL: Is Synthetic Data from Generative Models Ready for Multimodal Large Language Model?
Jingyi Zhang, Tianyi Lin, Huanjin Yao et al. (+3 more)
In this work, we aim to develop effective data synthesis techniques that autonomously synthesize
multimodal training data for enhancing MLLMs in solving complex real-world tasks. To this end, we propose Collective
Adversarial Data Synthesis (CADS), a novel and general approach to synthesize high-quality, diverse and challenging
multimodal data for MLLMs. The core idea of CADS is to leverage collective intelligence to ensure high-quality and diverse generation, while exploring
adversarial learning to synthesize challenging samples for effectively driving model improvement. Specifically, CADS operates with two cyclic phases, i.e., Collective
Adversarial Data Generation (CAD-Generate) and Collective
Adversarial Data Judgment (CAD-Judge). CAD-Generate leverages collective knowledge to jointly generate new and diverse
multimodal data, while CAD-Judge collaboratively assesses the quality of synthesized data. In addition, CADS introduces an
Adversarial Context Optimization mechanism to optimize the generation context to encourage challenging and high-value data generation. With CADS, we construct MMSynthetic-20K and train our model R1-SyntheticVL, which demonstrates superior performance on various
benchmarks.
Read the full abstract ▾
All authors Jingyi Zhang, Tianyi Lin, Huanjin Yao, Xiang Lan, Shunyu Liu, Jiaxing Huang
Machine Learning
Lipschitz Multiscale Deep Equilibrium Models: A Theoretically Guaranteed and Accelerated Approach
Naoki Sato and Hideaki Iiduka
Deep
equilibrium models (DEQs) achieve infinitely deep network representations without stacking layers by exploring fixed points of layer transformations in neural networks. Such models constitute an innovative approach that achieves performance comparable to state-of-the-art methods in many large-scale numerical experiments, despite requiring significantly less
memory. However, DEQs face the challenge of requiring vastly more computational time for training and inference than conventional methods, as they repeatedly perform fixed-point iterations with no convergence guarantee upon each input. Therefore, this study explored an approach to improve fixed-point convergence and consequently reduce computational time by restructuring the model architecture to guarantee fixed-point convergence. Our proposed approach for image classification, Lipschitz multiscale DEQ, has theoretically guaranteed fixed-point convergence for both forward and backward passes by hyperparameter adjustment, achieving up to a 4.75$\times$ speed-up in numerical experiments on CIFAR-10 at the cost of a minor drop in accuracy.
Read the full abstract ▾
Machine Learning
Anomaly Detection via Mean Shift Density Enhancement
Pritam Kar, Rahul Bordoloi, Olaf Wolkenhauer et al. (+1 more)
Unsupervised anomaly detection stands as an important problem in machine learning. Existing unsupervised anomaly detection
algorithms rarely perform well across different anomaly types, often excelling only under specific structural assumptions. This lack of robustness also becomes particularly evident under noisy settings. We propose Mean Shift Density Enhancement (MSDE), a fully unsupervised framework that detects anomalies through their
geometric response to density-driven
manifold evolution. MSDE is designed as a general purpose anomaly detection framework, based on the principle that normal samples, being well supported by local density, remain stable under iterative density enhancement, whereas anomalous samples undergo large cumulative displacements as they are attracted toward nearby density modes. To operationalize this idea, MSDE employs a weighted mean-shift procedure with adaptive, sample-specific density weights derived from a
manifold learning-based fuzzy neighborhood graph. We evaluate MSDE on an anomaly detection
benchmark comprising 46 real-world tabular
datasets, four realistic anomaly generation mechanisms, and six noise levels. Compared to 13 established unsupervised baselines, MSDE achieves consistently strong, balanced and robust performance for several standard classification metrics, at several noise levels and on average over several types of anomalies. These results demonstrate that displacement-based scoring provides a robust alternative to the existing state-of-the-art for unsupervised anomaly detection.
Read the full abstract ▾
All authors Pritam Kar, Rahul Bordoloi, Olaf Wolkenhauer, Saptarshi Bej
Machine Learning
Universal Approximation of Continuous Functionals on Compact Subsets via Linear Measurements and Scalar Nonlinearities
Andrey Krylov and Maksim Penkin
We study universal approximation of continuous functionals on compact subsets of products of
Hilbert spaces. We prove that any such functional can be uniformly approximated by models that first take finitely many continuous linear measurements of the inputs and then combine these measurements through continuous scalar nonlinearities. We also extend the approximation principle to maps with values in a
Banach space, yielding finite-rank approximations. These results provide a compact-set justification for the common “measure, apply scalar nonlinearities, then combine” design pattern used in operator learning and imaging.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Agentic Proposing: Enhancing Large Language Model Reasoning via Compositional Skill Synthesis
Zhengbo Jiao, Shaobo Wang, Zifan Zhang et al. (+5 more)
Advancing complex
reasoning in large
language models relies on high-quality, verifiable
datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synthesis paradigms often face a recurring trade-off: maintaining structural validity typically restricts problem complexity, while relaxing constraints to increase difficulty frequently leads to inconsistent or unsolvable instances. To address this, we propose Agentic Proposing, a framework that models problem synthesis as a goal-driven sequential decision process where a specialized
agent dynamically selects and composes modular
reasoning skills. Through an iterative workflow of internal reflection and tool-use, we develop the Agentic-Proposer-4B using Multi-Granularity Policy Optimization (MGPO) to generate high-precision, verifiable training trajectories across mathematics, coding, and science. Empirical results demonstrate that downstream solvers trained on
agent-synthesized data significantly outperform leading baselines and exhibit robust cross-domain generalization. Notably, a 30B solver trained on only 11,000 synthesized trajectories achieves a state-of-the-art 91.6% accuracy on AIME25, rivaling frontier-scale proprietary models such as GPT-5 and proving that a small volume of high-quality synthetic signals can effectively substitute for massive human-curated
datasets.
Read the full abstract ▾
All authors Zhengbo Jiao, Shaobo Wang, Zifan Zhang, Xuan Ren, Wei Wang, Bing Zhao, Hu Wei, Linfeng Zhang
Machine Learning
BlockRR: A Unified Framework of RR-type Algorithms for Label Differential Privacy
Haixia Liu and Yi Ding
In this paper, we introduce BlockRR, a novel and unified randomized-response mechanism for label differential
privacy. This framework generalizes existed RR-type mechanisms as special cases under specific parameter settings, which eliminates the need for separate, case-by-case analysis. Theoretically, we prove that BlockRR satisfies $\epsilon$-label DP. We also design a partition method for BlockRR based on a weight
matrix derived from label prior information; the parallel composition principle ensures that the composition of two such mechanisms remains $\epsilon$-label DP. Empirically, we evaluate BlockRR on two variants of CIFAR-10 with varying degrees of class imbalance. Results show that in the high-
privacy and moderate-
privacy regimes ($\epsilon \leq 3.0$), our propsed method gets a better balance between test accuaracy and the average of per-class accuracy. In the low-
privacy regime ($\epsilon \geq 4.0$), all methods reduce BlockRR to standard RR without additional performance loss.
Read the full abstract ▾
Machine Learning
Unveiling Covert Toxicity in Multimodal Data via Toxicity Association Graphs: A Graph-Based Metric and Interpretable Detection Framework
Guanzong Wu, Zihao Zhu, Siwei Lyu et al. (+1 more)
Detecting toxicity in
multimodal data remains a significant challenge, as harmful meanings often lurk beneath seemingly benign individual modalities: only emerging when modalities are combined and semantic associations are activated. To address this, we propose a novel detection framework based on Toxicity Association Graphs (TAGs), which systematically model semantic associations between innocuous entities and latent toxic implications. Leveraging TAGs, we introduce the first quantifiable metric for hidden toxicity, the
Multimodal Toxicity Covertness (MTC), which measures the degree of concealment in toxic
multimodal expressions. By integrating our detection framework with the MTC metric, our approach enables precise identification of covert toxicity while preserving full interpretability of the decision-making process, significantly enhancing transparency in
multimodal toxicity detection. To validate our method, we construct the Covert Toxic
Dataset, the first
benchmark specifically designed to capture high-covertness toxic
multimodal instances. This
dataset encodes nuanced cross-modal associations and serves as a rigorous testbed for evaluating both the proposed metric and detection framework. Extensive experiments demonstrate that our approach outperforms existing methods across both low- and high-covertness toxicity regimes, while delivering clear, interpretable, and auditable detection outcomes. Together, our contributions advance the state of the art in explainable
multimodal toxicity detection and lay the foundation for future context-aware and interpretable approaches. Content Warning: This paper contains examples of toxic
multimodal content that may be offensive or disturbing to some readers. Reader discretion is advised.
Read the full abstract ▾
All authors Guanzong Wu, Zihao Zhu, Siwei Lyu, Baoyuan Wu
Machine Learning
Beyond Suffixes: Token Position in GCG Adversarial Attacks on Large Language Models
Hicham Eddoubi, Umar Faruk Abdullahi and Fadi Hassan
Large
Language Models (LLMs) have seen widespread adoption across multiple domains, creating an urgent need for robust safety
alignment mechanisms. However, robustness remains challenging due to jailbreak attacks that bypass
alignment via
adversarial prompts. In this work, we focus on the prevalent Greedy Coordinate Gradient (GCG) attack and identify a previously underexplored attack axis in jailbreak attacks typically framed as suffix-based: the placement of
adversarial tokens within the
prompt. Using GCG as a case study, we show that both optimizing attacks to generate prefixes instead of suffixes and varying
adversarial token position during evaluation substantially influence attack success rates. Our findings highlight a critical blind spot in current safety evaluations and underline the need to account for the position of
adversarial tokens in the
adversarial robustness evaluation of LLMs.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
HypCBC: Domain-Invariant Hyperbolic Cross-Branch Consistency for Generalizable Medical Image Analysis
Francesco Di Salvo, Sebastian Doerrich, Jonas Alle et al. (+1 more)
Robust generalization beyond training distributions remains a critical challenge for deep neural networks. This is especially pronounced in medical image analysis, where data is often scarce and
covariate shifts arise from different hardware devices, imaging protocols, and heterogeneous patient populations. These factors collectively hinder reliable performance and slow down clinical adoption. Despite recent progress, existing learning paradigms primarily rely on the Euclidean
manifold, whose flat geometry fails to capture the complex, hierarchical structures present in clinical data. In this work, we exploit the advantages of
hyperbolic manifolds to model complex data characteristics. We present the first comprehensive validation of
hyperbolic representation learning for medical image analysis and demonstrate statistically significant gains across eleven in-distribution
datasets and three ViT models. We further propose an unsupervised, domain-invariant
hyperbolic cross-branch consistency constraint. Extensive experiments confirm that our proposed method promotes domain-invariant features and outperforms state-of-the-art Euclidean methods by an average of $+2.1\%$ AUC on three domain generalization
benchmarks: Fitzpatrick17k, Camelyon17-WILDS, and a cross-
dataset setup for retinal imaging. These
datasets span different imaging modalities, data sizes, and label granularities, confirming generalization capabilities across substantially different conditions. The code is available at https://github.com/francescodisalvo05/
hyperbolic-cross-branch-consistency .
Read the full abstract ▾
All authors Francesco Di Salvo, Sebastian Doerrich, Jonas Alle, Christian Ledig
Machine Learning · Cross-listed from stat.ML
Principled Federated Random Forests for Heterogeneous Data
Rémi Khellaf, Erwan Scornet, Aurélien Bellet et al. (+1 more)
Random Forests (RF) are among the most powerful and widely used predictive models for centralized tabular data, yet few methods exist to adapt them to the
federated learning setting. Unlike most
federated learning approaches, the piecewise-constant nature of RF prevents exact gradient-based optimization. As a result, existing
federated RF implementations rely on unprincipled heuristics: for instance, aggregating decision trees trained independently on clients fails to optimize the global
impurity criterion, even under simple distribution shifts. We propose FedForest, a new
federated RF
algorithm for horizontally partitioned data that naturally accommodates diverse forms of client data heterogeneity, from
covariate shift to more complex outcome shift mechanisms. We prove that our splitting procedure, based on aggregating carefully chosen client statistics, closely approximates the split selected by a centralized
algorithm. Moreover, FedForest allows splits on client indicators, enabling a non-parametric form of personalization that is absent from prior
federated random forest methods. Empirically, we demonstrate that the resulting
federated forests closely match centralized performance across heterogeneous
benchmarks while remaining communication-efficient.
Read the full abstract ▾
All authors Rémi Khellaf, Erwan Scornet, Aurélien Bellet, Julie Josse
Machine Learning
GraDE: A Graph Diffusion Estimator for Frequent Subgraph Discovery in Neural Architectures
Yikang Yang, Zhengxin Yang, Minghao Luo et al. (+5 more)
Finding frequently occurring subgraph patterns or network motifs in neural architectures is crucial for optimizing efficiency, accelerating design, and uncovering structural insights. However, as the subgraph size increases, enumeration-based methods are perfectly accurate but computationally prohibitive, while sampling-based methods are computationally tractable but suffer from a severe decline in discovery capability. To address these challenges, this paper proposes GraDE, a
diffusion-guided search framework that ensures both computational feasibility and discovery capability. The key innovation is the Graph
Diffusion Estimator (GraDE), which is the first to introduce graph
diffusion models to identify frequent subgraphs by scoring their typicality within the learned distribution. Comprehensive experiments demonstrate that the
estimator achieves superior ranking accuracy, with up to 114% improvement compared to sampling-based baselines. Benefiting from this, the proposed framework successfully discovers large-scale frequent patterns, achieving up to 30$\times$ higher median frequency than sampling-based methods.
Read the full abstract ▾
All authors Yikang Yang, Zhengxin Yang, Minghao Luo, Luzhou Peng, Hongxiao Li, Wanling Gao, Lei Wang, Jianfeng Zhan
Machine Learning · Cross-listed from cs.AI
Accordion-Thinking: Self-Regulated Step Summaries for Efficient and Readable LLM Reasoning
Zhicheng Yang, Zhijiang Guo, Yinya Huang et al. (+5 more)
Scaling test-time compute via long Chain-of-Thought unlocks remarkable gains in
reasoning capabilities, yet it faces practical limits due to the linear growth of KV cache and quadratic
attention complexity. In this paper, we introduce Accordion-Thinking, an end-to-end framework where LLMs learn to self-regulate the granularity of the
reasoning steps through dynamic summarization. This mechanism enables a Fold inference mode, where the model periodically summarizes its thought process and discards former thoughts to reduce dependency on historical
tokens. We apply reinforcement learning to incentivize this capability further, uncovering a critical insight: the accuracy gap between the highly efficient Fold mode and the exhaustive Unfold mode progressively narrows and eventually vanishes over the course of training. This phenomenon demonstrates that the model learns to encode essential
reasoning information into compact summaries, achieving effective compression of the
reasoning context. Our Accordion-Thinking demonstrates that with learned self-compression, LLMs can tackle complex
reasoning tasks with minimal dependency
token overhead without compromising solution quality, and it achieves a three times throughput while maintaining accuracy on a 48GB GPU
memory configuration, while the structured step summaries provide a human-readable account of the
reasoning process.
Read the full abstract ▾
All authors Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Wenlei Shi, Yiwei Wang, Xiaodan Liang, Jing Tang
Machine Learning
Merging Beyond: Streaming LLM Updates via Activation-Guided Rotations
Yuxuan Yao, Haonan Sheng, Qingsong Lv et al. (+11 more)
The escalating scale of Large
Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc refinements or focus on mitigating task interference, often failing to capture the dynamic optimization benefits of supervised fine-tuning (SFT). In this work, we propose Streaming Merging, an innovative model updating paradigm that conceptualizes merging as an iterative optimization process. Central to this paradigm is ARM (Activation-guided Rotation-aware Merging), a strategy designed to approximate gradient descent dynamics. By treating merging coefficients as learning rates and deriving rotation vectors from activation subspaces, ARM effectively steers parameter updates along data-driven trajectories. Unlike conventional linear interpolation, ARM aligns semantic subspaces to preserve the
geometric structure of high-dimensional parameter
evolution. Remarkably, ARM requires only early SFT checkpoints and, through iterative merging, surpasses the fully converged SFT model. Experimental results across model scales (1.7B to 14B) and diverse domains (e.g., math, code) demonstrate that ARM can transcend converged checkpoints. Extensive experiments show that ARM provides a scalable and lightweight framework for efficient model adaptation.
Read the full abstract ▾
All authors Yuxuan Yao, Haonan Sheng, Qingsong Lv, Han Wu, Shuqi Liu, Zehua Liu, Zengyan Liu, Jiahui Gao, Haochen Tan, Xiaojin Fu, Haoli Bai, Hing Cheung So, Zhijiang Guo, Linqi Song
Machine Learning
BayeSQP: Bayesian Optimization through Sequential Quadratic Programming
Paul Brunzema and Sebastian Trimpe
We introduce BayeSQP, a novel
algorithm for general black-box optimization that merges the structure of sequential quadratic programming with concepts from
Bayesian optimization. BayeSQP employs second-order Gaussian process surrogates for both the objective and constraints to jointly model the function values, gradients, and Hessian from only zero-order information. At each iteration, a local subproblem is constructed using the GP posterior estimates and solved to obtain a search direction. Crucially, the formulation of the subproblem explicitly incorporates uncertainty in both the function and derivative estimates, resulting in a tractable second-order cone program for high probability improvements under model uncertainty. A subsequent one-dimensional line search via constrained Thompson sampling selects the next evaluation point. Empirical results show thatBayeSQP outperforms state-of-the-art methods in specific high-dimensional settings. Our
algorithm offers a principled and flexible framework that bridges classical optimization techniques with modern approaches to black-box optimization.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarking
Yu Cheng, Yongkang Hu, Jiuan Zhou et al. (+8 more)
Test-time
evolution of
agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex
reasoning through experience accumulation without requiring parameter updates. However, even during benign task
evolution,
agent safety
alignment remains vulnerable, a phenomenon known as
Agent Memory Misevolution. To evaluate this phenomenon, we construct the Trust-Memevo
benchmark and find that
agents exhibit an overall decline in trustworthiness across multiple tasks during benign task
evolution. To address this issue, we propose TAME, a trust-aware
memory evolution framework in which a shared
memory bank is jointly governed by an Executor and an Evaluator. The Executor retrieves and applies transferable experiences to support task solving, while the Evaluator assesses the contribution of each utilized experience to the outcome and produces trust-aware feedback to guide subsequent
memory use. This executor-evaluator loop enables
memory to be selectively reinforced, cautiously reused, and continuously expanded over time. Experiments show that TAME mitigates
memory misevolution while achieving strong task performance. In particular, on the GPT-5.2 AIME
benchmark, TAME improves accuracy by 14.6 percentage points over the strongest existing method and maintains competitive trustworthiness.
Read the full abstract ▾
All authors Yu Cheng, Yongkang Hu, Jiuan Zhou, Yushuo Zhang, Yihang Chen, Huichi Zhou, Mingang Chen, Zhizhong Zhang, Kun Shao, Yuan Xie, Zhaoxia Yin
Machine Learning
Topology Matters: A Cautionary Case Study of Graph SSL on Neuro-Inspired Benchmarks
May Kristine Jonson Carlon, Su Myat Noe, Haojiong Wang et al. (+1 more)
Understanding how local interactions give rise to global
brain organization requires models that can represent information across multiple scales. We introduce a hierarchical self-supervised learning (SSL) framework that jointly learns node-, edge-, and graph-level
embeddings, inspired by
multimodal neuroimaging. We construct a controllable synthetic
benchmark mimicking the topological properties of connectomes. Our four-stage evaluation protocol reveals a critical failure: the invariance-based SSL model is fundamentally misaligned with the
benchmark's topological properties and is catastrophically outperformed by classical,
topology-aware heuristics. Ablations confirm an objective mismatch: SSL objectives designed to be invariant to topological perturbations learn to ignore the very community structure that classical methods exploit. Our results expose a fundamental pitfall in applying generic graph SSL to connectome-like data. We present this framework as a cautionary case study, highlighting the need for new,
topology-aware SSL objectives for neuro-AI research that explicitly reward the preservation of structure (e.g., modularity or motifs).
Read the full abstract ▾
All authors May Kristine Jonson Carlon, Su Myat Noe, Haojiong Wang, Yasuo Kuniyoshi