Machine Learning · Cross-listed from cs.AI
TRIPROBE: Probing Task Separability Beyond Classification for XAI
Amirhossein Sadough, Freek Hens, Aleksa Bokšan et al. (+2 more)
Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG
benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.
Read the full abstract ▾
All authors Amirhossein Sadough, Freek Hens, Aleksa Bokšan, Mohammad Mahdi Dehshibi, Mahyar Shahsavari
Machine Learning · Cross-listed from cs.DC
COMPASS-ABS: Reducing Fragmentation in Shared GPU Clusters for Deep Learning Training Workloads
Yukai Zhou and Hongfan Wu
With the rapid advancement of deep learning technology, shared GPU clusters receive an increasing number of deep learning training (DLT) jobs. Yet resource fragmentation make such clusters underutilized and forces the DLT jobs running on them to endure long turnaround times. Extensive research has been devoted to quantifying fragmentation and developing scheduling
algorithms that alleviate its impact. However, existing fragmentation measures break down in the absence of workload distribution information, while current schedulers cannot continuously maintain resource fragmentation at a low level. To tackle these problems, we first introduce Scheduler-Induced Fragmentation (SIF), a metric built on the notion of partial-nodes that is independent of historical workload knowledge. We then propose COMPASS-ABS, which employs the COMPact-ASSured (COMPASS)
algorithm to confine the cluster state within a tight Anchor-Based Space (ABS), whose construction fully leverages the topological
alignment between dominant workload size and node capacity. Moreover. We also prove that it ensures SIF is bounded by $\frac{2}{N}$ under a workload composition condition that matches both theory and production. Evaluations implemented on a physical cluster and a simulated cluster demonstrate COMPASS-ABS effectiveness at improving resource utilization, reducing DLT job completion time by reducing fragmentation.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Beyond Routine Compliance: Cunning Data Cultivates Safety Vigilance in Large Language Models
Youjia Wang, Lin Xu, Yang Sun et al. (+3 more)
Safety
alignment teaches large
language models (LLMs) to recognize harmful requests and reject risky instructions. Yet aligned models can fail when harmful intent is concealed within seemingly benign contexts. Robust safety therefore requires both knowledge of safety boundaries and vigilance: the ability to detect unusual premises, misleading
reasoning, and latent risks beneath surface-level semantics. Vigilance requires models to scrutinize a request's underlying intent and assumptions before acting. To cultivate this capability, we introduce cunning questions, which are not necessarily safety-related but contain misleading premises, atypical
reasoning, or subtle inconsistencies. We hypothesize that learning to look beyond such
reasoning traps can transfer to safety-critical scenarios. Experiments show that Cunning training improves robustness to out-of-distribution jailbreak attacks and strengthens subsequent safety fine-tuning. Furthermore, augmenting an existing state-of-the-art safety
alignment pipeline with Cunning establishes a new state of the art across our evaluated settings, reducing mean ASR across nine backbone–
benchmark combinations from 17.40% to 15.05%. Trace analysis after matched safety fine-tuning suggests that safety judgments are more likely to govern responses before harmful planning begins. A conditional theoretical analysis further characterizes when invariance learned from cunning data can transfer to safety-related inputs. These findings suggest that cunning data can strengthen model vigilance and complement conventional safety
alignment.
Read the full abstract ▾
All authors Youjia Wang, Lin Xu, Yang Sun, Yuxiao Lu, Chengfang Fang, Jie Shi
Machine Learning · Cross-listed from cs.RO
ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware
Shuai Zhou, Kaisheng Pang, Wenxuan Song et al. (+3 more)
Active perception is essential for robotic manipulation when fixed viewpoints leave task-relevant information occluded or unobserved. However, enabling
vision-
language-action (VLA) models to reason across changing viewpoints and actively acquire informative observations remains challenging. We present ActiveScale, a framework that advances active perception through coordinated model, data, and hardware designs. Our model augments a VLA with historical
video observations and explicit camera-pose supervision, using per-frame pose
tokens and a lightweight prediction head to associate observations across viewpoints and support a coherent understanding of the scene. To learn from the camera motion naturally present in human activity, we introduce a scalable human–
robot mid-training recipe using 1000 hours of
egocentric and robotic data, adapting the model to temporal inputs and pose supervision. We further introduce Active-perception Mobile-manipulation Platform (AMP), a robotic platform that supports active perception and mobile manipulation through single-operator teleoperation, enabling scalable collection of demonstrations that coordinate viewpoint changes and manipulation. Experiments demonstrate improved success rates on active-perception tasks, while ablation studies validate the contributions of camera-pose-aware modeling and
egocentric mid-training. Together, these components provide an integrated foundation for studying and developing active perception in robotic manipulation.
Read the full abstract ▾
All authors Shuai Zhou, Kaisheng Pang, Wenxuan Song, Wenjie Zhang, Xinhu Zheng, Haoang Li
Machine Learning · Cross-listed from cs.CV
Learning from Distributed Eyes: Leveraging Collaborative Perception for Automated Model Adaptation
Yanan Ma, Yihang Tao, Zhengru Fang et al. (+4 more)
In autonomous driving, perception models often struggle to generalize to new environments due to domain shifts. While unsupervised model adaptation offers a feasible solution without labor-intensive manual labeling, existing methods that rely solely on the ego-vehicle's data often lead to inferior pseudo-labeling performance. To address this critical issue, we propose LDE, Learning from Distributed “Eyes", a novel framework that transforms collaborative perception (CP) into a source of high-quality supervision for model adaptation. This pseudo-labeling approach is hyperparameter-insensitive and relatively reliable, assuming CP often outperforms single-
agent's perception. However, naively implementing this approach encounters (1) the communication bottleneck of sharing rich features under time and bandwidth constraints, (2) the view discrepancy between the CP view and the learner's Field of View (FoV), and (3) the unreliability even in CP-generated labels. To address these issues, we design an adaptation-oriented feature sharing mechanism that selectively transmits the most critical information for adaptation, an FoV filtering method that meticulously eliminates mismatched labels, and a curriculum learning strategy to progressively exploit pseudo labels. Extensive experiments on 3D object detection tasks demonstrate that LDE consistently outperforms both the pre-trained models and state-of-the-art unsupervised adaptation methods.
Read the full abstract ▾
All authors Yanan Ma, Yihang Tao, Zhengru Fang, Zihan Fang, Yiqin Deng, Xianhao Chen, Yuguang Fang
Machine Learning · Cross-listed from physics.ao-ph
Butterfly Effect and the Kinetic Energy Cascade in Probabilistic Machine Learning Weather Prediction Models
Jiakai Chen, Joel Oskarsson, Simon Driscoll et al. (+1 more)
This study analyses kinetic energy (KE) spectra, difference kinetic energy (DKE) spectra, and signatures of KE transfer across spatial scales in four state-of-the-art probabilistic machine learning weather prediction (MLWP) models: NeuralGCM-ENS, FourCastNet 3, AIFS-ENS, and GenCast. Results are compared with those from the physics-based numerical weather prediction model IFS-ENS. While NeuralGCM-ENS successfully reproduces the expected upscale transfer of KE, noise injection at its encoder stage underestimates mesoscale KE. Conversely, AIFS-ENS, GenCast, and FourCastNet 3 produce realistic KE spectral magnitudes but do not capture the expected upscale transfer of KE. In particular, AIFS-ENS and GenCast, which employ spatially uncorrelated
stochastic perturbations, exhibit enhanced accumulation of KE at high wavenumbers. All examined models exhibit upscale error growth, reflected by the progressive shift of the DKE spectral peak toward larger wavelengths over time. However, the MLWP models struggle to reproduce the rapid initial growth of ensemble spread at small spatial scales associated with the butterfly effect. The results show that MLWP models can misrepresent the known scale transfer of kinetic energy despite producing skilful weather forecasts.
Read the full abstract ▾
All authors Jiakai Chen, Joel Oskarsson, Simon Driscoll, Sebastian Schemm
Machine Learning · Cross-listed from cs.CV
Beyond Random Couplings: Contrastive Noise Alignment in Generative Flows
Lennart Wittke and Vinicius Azevedo
Diffusion and flow-matching models are typically trained by corrupting data through independently sampled Gaussian noise. While simple and scalable, this forward process induces arbitrary data-noise couplings, forcing the network to learn high-
curvature transports between unrelated endpoints. Existing optimal-transport methods reduce this burden by reassigning fixed noise samples to data, but the source noise distribution itself remains passive. To address this, we introduce Contrastive Noise
Alignment (CNA), a training-time method that creates dynamic, contrastive couplings by optimizing the noise representations directly. By modeling the noise batch as an interacting particle system, CNA employs a cross-modal InfoNCE objective to align noise particles with their paired data targets. To prevent spatial collapse, this
alignment is regularized using an angular
entropy term and a radial norm penalty. We show theoretically that this
equilibrium asymptotically preserves Gaussian structures, maintaining tractability during inference. Empirically, CNA improves the
alignment between noise and data, reduces flow
curvature, and provides better generation quality with fewer required sampling steps. For few-step, pixel-space generation (2-4 NFEs), CNA reduces FID by over 50% compared to standard rectified flow, and by at least 24% against Optimal Transport baselines.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Hyperbolic Graph Representation Learning for Differential Diagnosis on Biomedical Knowledge Graphs
Pietro Miotto, Lucia Mellini, Tommaso Marzi et al. (+5 more)
Biomedical knowledge graphs combine ontology-derived hierarchies with transversal associations among heterogeneous entities such as phenotypes, diseases, genes,
proteins, and patients. This hybrid structure raises the question of whether
hyperbolic embeddings, which naturally capture tree-like organization, remain useful beyond purely hierarchical graphs. We present a preliminary study of
hyperbolic graph representation learning for Mendelian-disease differential diagnosis on a patient-integrated biomedical graph. Experiments on isolated ontology subgraphs show that
hyperbolic models achieve strong performance in substantially lower dimensions than Euclidean baselines. We then evaluate the models on a link-prediction task that ranks candidate diseases for each patient. Results suggest that
hyperbolic embeddings can exploit biomedical hierarchical structure while supporting diagnostic
reasoning over heterogeneous patient-level graphs.
Read the full abstract ▾
All authors Pietro Miotto, Lucia Mellini, Tommaso Marzi, Cesare Alippi, Elena Casiraghi, Alberto Paccanaro, Giorgio Valentini, Mauricio Soto-Gomez
Machine Learning
Spatially Adaptive Noise Injection
Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen et al. (+1 more)
Diffusion samplers reverse a learned noising process using either
stochastic (DDPM) or deterministic (DDIM) updates, which represent endpoints of a single family controlled by a scalar noise-injection variance that is applied identically at every spatial location. This uniform approach neglects the geometry of natural images: high-
curvature regions such as edges and textures, where the denoiser is uncertain, benefit from
stochastic correction, whereas smooth regions, where the score is precise, are degraded by injected noise. This work investigates whether each pixel requires
stochastic correction at a given timestep and introduces Spatially Adaptive Noise Injection (SANI), a novel sampling framework that dynamically adjusts noise application on a per-pixel basis. SANI integrates a probabilistic gating mechanism with a derived spatially adaptive variance, ensuring that noise is injected precisely where needed to refine complex features while preserving well-formed structures. Experimental results and decoupling ablations demonstrate that SANI consistently improves Fréchet Inception Distance (FID) over the vanilla DDPM and DDIM endpoint samplers across diverse sampling timesteps, while remaining competitive with variance-learning baselines, highlighting the importance of spatial adaptivity in
diffusion sampling.
Read the full abstract ▾
All authors Frantzeska Lavda, Maciej Falkiewicz, Van Khoa Nguyen, Alexandros Kalousis
Machine Learning · Cross-listed from cs.AI
Disentangling Long-Term Memory via Latent Neuro-Symbolic Reasoning
Cai Ke, Xinghao Chen, Xiaoyu Shen et al. (+6 more)
Personalized
agents are required to reason over long-term history interactions to infer both explicit preferences and implicit behavioral evidence. While early flat
retrieval methods score
memory fragments independently and neglect the distributed information, current structured
memory frameworks rely on query-agnostic static graphs that fail to capture the context-dependent relations. Crucially, raw textual
memories are inherently entangled and noisy, making fine-grained personalization and cross-session
reasoning computationally prohibitive. To this end, we present LGM, a novel neuro-symbolic framework that shifts long-term
memory disentanglement into a continuous latent space. Specifically, (i) instead of persisting fixed graphs, we design a tailored latent graph construction with a sparse autoencoder. Subject to each query, it maps historical interactions into latent
memory nodes and disentangles the
memory traces into sparse concept activations, dynamically synthesizing query-aware relational edge weights. (ii) A graph encoder then treats the query
embedding as a conditioning preference to direct non-linear message passing across the task-specific latent subgraph. This yields a highly expressive
memory representation for effective activations. Extensive experiments on long-term personalization
benchmarks demonstrate that LGM significantly outperforms state-of-the-art baselines in capturing both explicit and implicit preferences while enabling personalized responses.
Read the full abstract ▾
All authors Cai Ke, Xinghao Chen, Xiaoyu Shen, Keyu Chen, Siyu An, Junnan Dong, Ruifeng Xu, Ruizhi Qiao, Xing Sun
Machine Learning · Cross-listed from cs.AI
Risk-Aware World Modeling with Flow-Guided Occupancy Evolution for Selective Trajectory Planning in Automated Driving
Rongxiang Zeng, Linsen Cai, Jiafu Zhang et al. (+7 more)
Safe motion planning in automated driving requires anticipating evolving traffic risks and deciding when to revise the current planned trajectory. We introduce RiskWorld, a risk-aware world modeling framework for shared occupancy
forecasting and selective trajectory replacement. Spatial risk fields and temporal actor context are fused with visual bird's-eye-view features. Flow-guided
evolution transports occupancy and scene features, while signed residuals correct occupancy after transport. One forecast is generated per planning step and reused across candidates. Each candidate is compared with a current-state persistence reference, yielding a nonnegative collision-score correction. The trajectory selected by current-world evaluation serves as the planning anchor and is replaced only when additional predicted risk triggers intervention and an alternative satisfies component-wise constraints on predicted risk and trajectory error. Candidate geometries remain unchanged. We evaluate RiskWorld for open-loop planning on nuScenes using camera features, annotation-derived current and historical actor states, and
dataset-provided map context. RiskWorld achieves the lowest collision rate at a long evaluation horizon of 3 s, and the second-best average L2 error among various state-of-the-art baselines, while running at 11.5 FPS on a single NVIDIA RTX 4090 with 90.81 M parameters. Within-setting ablations show that RiskWorld achieves lower collision rates than the current-state rescoring baseline, while forecast reuse enables additional candidates to be evaluated at low marginal computational cost.
Read the full abstract ▾
All authors Rongxiang Zeng, Linsen Cai, Jiafu Zhang, Yijie Zhong, Yide Tao, Shuai Wang, Nan Zheng, Hai L. Vu, Alvaro Garcia Hernandez, Yongqi Dong
Machine Learning · Cross-listed from cs.AI
HPOQuest: A Rare-Disease Diagnostic Agent Using Active Phenotype Acquisition
Kamilia Zaripova, Nassir Navab, Azade Farshad et al. (+1 more)
More than 300 million people worldwide are affected by one of over 7,000 known rare diseases, yet diagnosis remains difficult because patients initially present with incomplete and heterogeneous phenotypes. We present HPOQuest, a training-free framework for sequential phenotype acquisition in rare-disease diagnosis. Starting from a small set of observed patient phenotypes, HPOQuest maintains a probabilistic disease ranking and iteratively selects informative follow-up questions to support clinicians during patient assessment. Confirmed phenotypes update the disease ranking, while all responses update the candidate question set. Across four
benchmark cohorts, HPOQuest substantially improves diagnosis from sparse initial phenotypes, with gains of up to 30% points at Recall@1 and 45% points at Recall@5. These results demonstrate that sequential phenotype acquisition can substantially improve rare-disease diagnosis from limited initial clinical evidence.
Read the full abstract ▾
All authors Kamilia Zaripova, Nassir Navab, Azade Farshad, Annalisa Marsico
Machine Learning · Cross-listed from math.NA
HiLNO: A Hierarchical Latent Neural Operator with Multi-Scale Supervision for PDEs on General Geometries
Zhicheng Hu, Jiacheng Li and Min Yang
Latent neural operators improve the efficiency of operator learning for partial differential equations (PDEs) by performing the main computation on compact latent representations. However, directly compressing the input representation to obtain such compact representations may discard solution-relevant spatial information, especially for PDE solutions with multiscale structures. To address this problem, we propose HiLNO, a hierarchical latent neural operator that constructs a fine-to-coarse-to-fine latent space and further introduces multi-scale supervision (MSS) and anisotropic Gaussian
attention. The hierarchy mitigates potential information loss during compression, while MSS aligns intermediate predictions with downsampled target fields, encouraging solution-relevant structures to be captured across multiple spatial scales. Anisotropic Gaussian
attention enables feature transfer across the hierarchy, making HiLNO applicable to general geometries. Experiments on representative PDE
benchmarks and a large-scale automotive aerodynamics task show that HiLNO achieves competitive predictive accuracy, while reducing the parameter count by an average of 84.4% and FLOPs by an average of 69.2% compared with LinearNO. Additional experiments demonstrate effective generalization to unseen spatial resolutions. Code is available at https://github.com/JcLimath/HiLNO.
Read the full abstract ▾
Machine Learning · Cross-listed from math.OC
Gradient Descent with Stochastic Subspaces via Persistence of Memory
Subhroshekhar Ghosh, Clement Z. Q. Ng, Pierre-Louis Poirion et al. (+1 more)
Stochastic subspace methods have gained popularity as gradient descent based techniques for large scale optimisation problems, especially in distributed settings. In this paper, we introduce the technique of "persistence of
memory" to greatly extend and improve the random subspace methods. To this end, we leverage a vector that is only weakly correlated with the gradient in order to provide a guiding structure to the generative process of the random subspace along which the descent is going to take place. This guidance vector may be fixed for a large number of iterations, only to be refreshed at wide intervals (on whose size we can provide guarantees in terms of problem parameters). In important machine learning settings, such as optimisation problems embodying sparsity or a minibatch structure, we show that the guidance vector can be obtained in an effective and computationally inexpensive manner by leveraging the structured properties of the problem. En route, we establish to our knowledge the first theoretical analysis of classical SSD methods for sparse functions. In a local neighbourhood of the optimum, we demonstrate an
alignment phenomenon of our gradient estimates with a low-lying eigenvector of the Hessian, allowing a once-for-all computation of the guidance vector which renders the method computationally favourable even in scenarios with unstructured objectives.
Read the full abstract ▾
All authors Subhroshekhar Ghosh, Clement Z. Q. Ng, Pierre-Louis Poirion, Akiko Takeda
Machine Learning
TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
Shunya Nagashima and Yuta Funayama
Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight
memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza
benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the
memory itself.
Read the full abstract ▾
Machine Learning
Reliable Virtual Sensing: A Multi-Domain Benchmark for Robustness Under Sensor Failures
Jens U. Brandt, Noah C. Puetz, Alexander Windmann et al. (+4 more)
Virtual sensing, the estimation of hard-to-measure quantities from available sensor measurements, is a critical enabler for control and monitoring in cyber-physical systems. However, when sensors fail, learning-based predictors can produce physically implausible estimates that propagate to system-level failures. We argue that real-world deployment demands robustness and introduce MuViS-C, the first multi-domain
benchmark of robustness against common sensor failures in learning-based virtual sensing. Building on an existing nominal-performance
benchmark and established corruption taxonomies, it covers ten sensor failure modes, from subtle drifts to catastrophic signal dropouts, at multiple severities. These are paired with complementary robustness measures capturing average error under corruption, relative degradation, and worst-case fragility. Across nine
datasets from six domains, we
benchmark six architectures spanning gradient-boosted trees and the major inductive biases for sequence modeling: convolution, recurrence,
attention, and MLP-mixing. On the
attention-based architecture, we further probe three robustification strategies. We find that (i) every model degrades substantially under corruption, becoming worse than a naïve predictor on at least one corruption setting, (ii) gradient-boosted tree ensembles achieve strong robustness, and (iii) dedicated robustification closes the gap between the
attention-based architecture and the most robust models, though each strategy hurts nominal performance. The
benchmark's multi-domain design proves essential, as model rankings shift across
datasets, and no single domain captures the full robustness picture. MuViS-C is open-source and extensible to new
datasets, failure modes, measures, and models.
Read the full abstract ▾
All authors Jens U. Brandt, Noah C. Puetz, Alexander Windmann, Marc Hilbert, Elena Raponi, Thomas Bäck, Thomas Bartz-Beielstein
Machine Learning
Every Fixed Metric Has a Blind Spot: A Learned Atmospheric Critic for Scoring Forecast Realism
Younes Elberkennou, Dmitri Demler, Thierry Meier et al. (+3 more)
Despite their high accuracy on point-wise metrics, machine learning weather
forecasting models can exhibit different failure modes such as blurring, periodic irregularities, and other unphysical spatial artifacts. This has motivated a variety of metrics to detect known failure cases. Existing metrics fix a representation or transformation in advance, and that choice limits the artifacts they can detect. We propose to train a discriminator for separating reference data from the model's output, and using its output logit to obtain a divergence-like realism score. The discriminator learns whatever separates the model's fields from real weather, adapting to whichever failure mode that model exhibits. We compare our learned atmospheric critic to existing metrics using various synthetic corruptions applied to ERA5 reanalysis data. Our method successfully identifies the corruptions and ranks their severity, while existing metrics fail on at least one corruption. Additionally, we evaluate forecasts from real weather models, and find that the realism score degrades with longer lead times and the metric generally assigns higher realism to numerical models than to machine learning models.
Read the full abstract ▾
All authors Younes Elberkennou, Dmitri Demler, Thierry Meier, Luca Rispoli, Fanny Lehmann, Joel Oskarsson
Machine Learning · Cross-listed from eess.SP
Semantic CSI Feedback for Beam Selection: When Task-Aware Embeddings from Sparse Pilots Outperform Full-Bandwidth Reconstruction
Cristian J. Vaca-Rubio, Konstantinos Vandikas and Aneta Vulgarakis Feljan
Classical CSI feedback in FDD massive
MIMO transmits a compressed reconstruction of the channel, optimizing fidelity to the original signal regardless of the downstream task. We propose a semantic communication perspective: instead of reconstructing the channel, the UE transmits a learned semantic
embedding optimized end-to-end for beam selection at the gNB. Comparing reconstruction-oriented feedback (CsiNet) against task-aware semantic feedback across two input domains and three observation scenarios, we show that a semantic
embedding of just $d=8$ real values from only 43 NR CSI-RS pilots in the angular-delay domain achieves the highest beam prediction accuracy, outperforming every method with access to the full 512-subcarrier channel. The key insight is that beam-relevant information is intrinsically low-dimensional: the semantic encoder learns to discard reconstruction-irrelevant structure and retain only a compact representation that is relevant to beam selection, realizing the core principle of semantic communication: transmit the intent, not the signal.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Bad Genius: Counterfactual-Guided Harness Evolution Beyond Task-Specific Shortcuts
Guojun Zhu, Xunheng Huang, Peng Yin et al. (+3 more)
Reliable
agent evaluation is complicated by automatic harness optimization, which repeatedly uses a released
benchmark $B_{\mathrm{rel}}$ to guide a Proposer that edits
prompts,
memory,
retrieval, tools, and control code around a fixed foundation model. Task holdout is commonly used to guard against harness overfitting. It varies semantic tasks but leaves the
benchmark protocol fixed, so a bad genius Proposer can produce a cheating harness whose improvement over the initial harness on $B_{\mathrm{rel}}$ depends on a
benchmark-wide shortcut. We introduce Counterfactual Harness Search and
Evolution (CHASE), which casts harness
evolution as constraint generation over valid counterfactual
benchmarks. After each Proposer update, a Challenger searches for an executable protocol transformation with large gain destruction. A validity firewall checks that task semantics are preserved, while a held-out confirmation set determines whether the counterfactual enters a finite archive. We formalize an ideal shortcut-neutralized
benchmark $B_0$ and establish theoretical guarantees linking finite counterfactual archives to $B_0$ and characterizing sequential Challenger search. We evaluate CHASE on Syn-Ledger and OfficeQA, where CHASE retains strong released-
benchmark gains while substantially reducing gain destruction under valid protocol transformations.
Read the full abstract ▾
All authors Guojun Zhu, Xunheng Huang, Peng Yin, Jiahui Xie, Sanguo Zhang, Doudou Zhou
Machine Learning · Cross-listed from cs.RO
RecMorph: Topology-Guided Spatial Recurrence for Generalized Morphology Control
Quanrui Rao, Yong Liu, Xueming Xiao et al. (+4 more)
Generalized morphology control requires a single policy to transform information across limbs with different physical roles, coordinate whole-body motion, and remain efficient as body size grows. Existing communication mechanisms address these requirements only partially. We introduce RecMorph, a
topology-guided spatial recurrent architecture that uses recurrent sequence computation to jointly perform cross-limb communication and representation transformation. A depth-first traversal converts the kinematic tree into a morphology-derived sequence, along which shared bidirectional transitions progressively transform limb information before action decoding. Residual preservation, RMS normalization, and input-dependent channel modulation stabilize this repeated spatial transformation, yielding linear
token complexity at fixed model width and depth. Across five UNIMAL tasks, RecMorph achieves the strongest mean final training performance among the evaluated generalized morphology controllers and the highest measured inference throughput on FT, while generalizing to unseen variations and bodies with up to 30 limbs. We further migrate representative generalized controllers from UNIMAL
benchmarks to a four-platform quadruped setting. RecMorph achieves the best macro-averaged performance under nominal and high friction, reduces nominal velocity RMSE by 43.5% relative to specialist MLPs, and one shared policy completes 40 physical Go1/Go2 trials without falls. These results show that
topology-guided recurrent transformation provides an effective and efficient communication mechanism for Generalized Morphology Control and remains effective when transferred from procedural bodies to physical
robot platforms. Code and experimental resources are publicly available at https://github.com/quanruirao/RecMorph.
Read the full abstract ▾
All authors Quanrui Rao, Yong Liu, Xueming Xiao, Yingbo Luo, Kun Wu, Zhenyu Xu, Meibao Yao
Machine Learning
Trajectory Learnability for Offline On-Policy Distillation with Imperfect Teachers
Yihao Ai, Beibei Lin, Weilong Yan et al. (+1 more)
Offline on-policy
distillation gains efficiency by collecting student trajectories and teacher supervision once and reusing them throughout optimization. The same reuse makes imperfect supervision persistent. Since even strong teachers can fail, we ask what remains learnable from imperfect teacher supervision? Teacher failure is only a coarse problem-level signal and does not imply that all supervision along the associated student trajectory is unhelpful. A natural alternative is to estimate teacher recoverability along the trajectory, but repeated continuations largely erase the efficiency advantage of offline
distillation. We instead use teacher-successful problems to define a cheap reference for what the student can learn. We train on teacher-successful problems and measure how the likelihood of each observed
token in trajectories from teacher-failed problems changes. We use these signed likelihood changes as an operational learnability signal: larger increases indicate behavior more strongly promoted by successful-only learning. We aggregate this signal into trajectory-level weights for the original
distillation loss. Unlike continuation-based estimates, our learnability requires no additional generation and can be computed once from stored trajectories and model checkpoints. Across mathematical
reasoning and code generation, our method improves an offline OPD baseline by up to 2.7 percentage points and matches or outperforms online OPD variants on multiple
benchmarks. Despite the additional successful-only
distillation stage, it uses 2 GPUs and about 22 GPU hours, compared with 3 GPUs and 36–48 GPU hours for representative online OPD methods.
Read the full abstract ▾
All authors Yihao Ai, Beibei Lin, Weilong Yan, Huaijian Zhang
Machine Learning · Cross-listed from cs.CL
Shardul P. More and Tanuja S. Pawar
Large
Language Models (LLMs) frequently exhibit
hallucinations, presenting a major barrier to reliability in complex
reasoning tasks. While traditional detection methods rely on output-based confidence metrics, these logits are often miscalibrated by modern
alignment techniques. In this paper, we investigate the temporal
volatility of internal
attention mechanisms as an alternative diagnostic signal for
hallucination that does not depend on output calibration. By introducing an unsupervised metric for
attention dispersion, we show that epistemic uncertainty leaves a measurable trace within intermediate layers, where spikes in
attention entropy are associated with
reasoning breakdowns. We evaluate our approach on mathematical
reasoning benchmarks (GSM8K and MATH-500) using the Qwen2.5 model family (1.5B and 3B parameters), finding statistically significant AUC improvements of up to +0.076 over output-based baselines across all tested conditions. These findings suggest that
attention dispersion is a promising complement to traditional
hallucination detection methods, requiring further investigation across broader model families and task domains.
Read the full abstract ▾
Machine Learning
Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency
Jiangfeng Liu and Yanfang Fan
Non-intrusive load monitoring (NILM) estimates appliance power sequences from aggregate power, but models trained on source households commonly lose accuracy in unseen households. Aggregate power also contains loads from other appliances and measurement error, so predictions may depend on the residual background that co-occurs with source-household targets. Time-aligned submetered measurements and the additive decomposition of aggregate power expose a relation unused by window-wise supervision: an aggregate window can be recomposed by replacing only its residual background while preserving all modeled target-appliance power sequences pointwise. We combine label-preserving aggregate recomposition with prediction consistency. Both windows receive complete power and operating-state supervision. For each appliance, disagreement between the two power predictions is penalized only when both satisfy a fixed reliability criterion and only to the extent that it exceeds a fixed margin. The proposed method is implemented using a multi-appliance architecture with two-stage shared-to-specific mixture-of-experts routing. On REDD, UK-DALE, and REFIT, the proposed method lowers appliance-averaged mean absolute error relative to single-window training from 14.75 to 13.14 W, from 8.88 to 8.51 W, and from 15.83 to 14.55 W. Label-preserving aggregate recomposition and prediction consistency are used only during training, and add no inference-time module or parameter.
Read the full abstract ▾
Machine Learning
Beyond Quadratic Loss: The Stability Phase Diagram of Adam
Gaoxiang Tang, Huanran Chen and Ziming Liu
Loss spikes are recurrent instabilities in neural-network training and can arise from multiple mechanisms. For Adam in particular, macroscopic loss spikes have been linked to optimizer dynamics, yet how its two momentum timescales govern them remains unclear. We investigate this dependence by mapping training dynamics across the $(\beta_1,\beta_2)$ plane. Across a range of model–task settings, an approximately linear boundary, $1-\beta_2=C(1-\beta_1)$, separates spiky from non-spiky dynamics, whereas a one-dimensional quadratic loss produces approximately cubic slope. A one-dimensional superquadratic loss $L(x)\propto|x|^n$ recovers the near-linear scaling and links the boundary coefficient to the effective loss exponent $n$. We further show that confident cross-
entropy losses develop a core–wall landscape comprising a narrow quadratic core followed by a steep wall, which produces effective superquadratic behavior at the scale of an optimizer update. Together, these results connect Adam loss spikes to both the mismatch between momentum timescales and finite-scale superquadratic loss geometry beyond the Hessian.
Read the full abstract ▾
Machine Learning
Bias Amplification in Multi-Agent Network: How Biased Agents Shape Opinions and Rhetoric
Omran Berjawi, Giuseppe Fenza and Rida Khatoun
Large
language models (LLMs) are increasingly deployed in applications involving interaction between
agents, where their output plays a role in collective
reasoning and decision-making processes. Despite significant research into the functioning of LLMs in such multi-
agent systems, the processes of bias propagation in such systems are still a challenge. This work studies how biased opinions are propagated in the form of textual interaction in an environment of LLMs, in which a minority of
agents maintain persistent extreme opinions, while the remaining
agents iteratively update their beliefs through structured textual interactions. The findings show that even the presence of a small percentage of biased
agents in such a system leads to significant shifts in the opinions of non-biased
agents. It suggests that for the same percentage of biased
agents, the shifts occur more quickly for the Llama~3.2 model when compared to a classical Friedkin-Johnsen (FJ) model. Further semantic analysis demonstrates that rhetorical consistency in textual explanations increases systematically with biased exposure and, importantly, is partially decoupled from numerical convergenumericalutral
agents adopt the vocabulary employed by the biased
agents even in configurations where their numerical opinion shifts remain moderate. The research helps explain how bias and
language develop together in multi-
agent language model ecosystems.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum
Carolina Fortuna, Vid Hanžel, Tim Strnad et al. (+1 more)
As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large
language models (LLMs) execute multi-step
reasoning, invoke diagnostic tools, retrieve domain knowledge, and coordinate across
agent teams, are increasingly embedded across the edge-cloud continuum. While the biological
brain accomplishes complex cognition on an exceptionally modest metabolic power budget of approximately 20W contemporary LLMs are profoundly energy- and
memory-intensive, making sustainable lifecycle orchestration a critical operational priority. However, existing AI lifecycle metrics evaluate only isolated, single-model inferences or overlook multi-
agent execution graphs entirely. Consequently, network operators lack foundational models to determine whether distributed
agent communication incurs meaningful energy costs and where across edge-cloud tiers
agent teams should physically reside. To address this gap, we introduce agentic-eCAL, generalizing the Energy Cost of AI Lifecycle (eCAL) metric to directed multi-
agent workflows by coupling a closed-form two-rate single-call energy model (compute-bound prefill and
memory-bound decode) with 7-layer OSI data transport. Grounded in hundreds of GPU
benchmark configurations on NVIDIA A100 and H100, 16 open-weight models and 8 orchestration
topologies, we validate components of the metric and study workflow placement implications. Our findings demonstrate that inter-
agent text transport incurs 0.25% of workflow energy across 5G RAN, metro, and optical links. Therefore in edge-cloud
agent placement the dominant energy cost of distribution is often not the transmission of inter-
agent text itself, but the additional inference and context processing induced by that communication.
Read the full abstract ▾
All authors Carolina Fortuna, Vid Hanžel, Tim Strnad, Blaž Bertalanič
Machine Learning
A GAN-Based Framework for Robust DDoS Attack Detection
Makram Chehayeb, Walid Fahs, Amina Rizk et al. (+2 more)
The availability and consistency of online services remain vulnerable due to Distributed Denial of Service (DDoS) attacks. These attacks are evolving by adopting more complex strategies to evade traditional network security systems. Despite the effectiveness of machine learning models in detecting DDoS traffic, targeted
adversarial attacks can degrade their classification accuracy. This work proposes a robust detection framework that integrates generative
adversarial modelling with advanced machine learning models. We trained Random Forests, Deep Neural Ensembles, and
Transformer-based models using the CICDDoS2019
dataset to establish the frameworks baseline performance. To enhance the models defensive capacity, we generated synthetic
adversarial flows that simulate potential evasion attempts and
adversarial traffic using a Wasserstein Generative
Adversarial Network with Gradient Penalty (WGAN-GP). Then, we combined the generated traffic with benign and malicious traffic to construct hybrid
datasets to train the models to learn more generalizable decision boundaries. The experimental results indicate that the proposed methodology significantly enhances detection accuracy and resilience, especially against unseen
adversarial traffic. We also tested the designed framework using real-world generated traffic, which demonstrates its capability in practical settings. The scalable and efficient solution against
adversarial DDoS attacks, introduced in this work, paves the way towards more resilient and adaptive network defense systems that combine generative
adversarial augmentation with recent advances in learning models.
Read the full abstract ▾
All authors Makram Chehayeb, Walid Fahs, Amina Rizk, Rida Khatoun, Omran Berjawi
Machine Learning
Behavioral Fingerprinting and Navigation Prediction in Web Browsing
Ralph Elsaghbini, Omran Berjawi, Walid Fahs et al. (+1 more)
Web browsing often appears ephemeral: users visit a few websites, complete a task, and move on. However, even short fragments of browsing activity can contain rich and structured behavioral signals. In this work, we conduct a comparative empirical study of two complementary behavioral inference tasks: session-level user identification and next-domain prediction. Both tasks are derived from the same cleaned event stream and evaluated on large-scale anonymous browsing traces, with sessionization and splitting adapted to the temporal requirements of each task. For user identification, we evaluate classical and neural models operating on session-level behavioral and domain features. For next-domain prediction, we combine graph-based modeling with Large
Language Models (LLMs). Experimental results show that short browsing sessions are highly identifiable, while future
navigation actions are highly predictable from long-term interaction structure combined with recent behavioral context. Furthermore, LLM-derived semantic features yield only marginal gains over purely structural and sequential models, indicating that repeated interaction patterns remain the dominant predictive signal in the evaluated web-browsing setup. These findings highlight the extent to which interaction history substantially contributes to both user identifiability and
navigation predictability in browsing traces.
Read the full abstract ▾
All authors Ralph Elsaghbini, Omran Berjawi, Walid Fahs, Rida Khatoun
Machine Learning · Cross-listed from cs.RO
Acting in Meters: Learning Metric Interactions for Precise Robotic Manipulation
Lijie Wang, Zheng Lu, Yiming Wang et al. (+12 more)
Vision-
Language-Action models and World-Action Models have advanced
language-conditioned robotic manipulation, yet often leave metric relations among actions, objects, and scene geometry implicit. Human manipulation combines semantic understanding of task-relevant objects with spatial feedback that guides hand motion relative to objects and their surroundings. Inspired by this, we introduce a metric interaction framework that models object-level and scene-level interactions in physical Cartesian space at a shared metric scale. At the object level, Interaction-Centric
Tokens (ICTs) explicitly represent end-effector pose trajectories relative to manipulated objects and are jointly denoised with actions, providing physically grounded interaction supervision. At the scene level, the Metric Action Interaction Field (MAIF) uses action and ICT queries to attend to metric scene point-cloud features and learns geometry-conditioned action corrections. Through two-stage adaptation, our framework improves diverse VLA and WAM baselines with a small number of additional parameters and training steps. Experiments demonstrate average success-rate gains of 0.80 and 3.59 percentage points on LIBERO and RoboTwin 2.0, respectively, alongside gains of 6.80 percentage points on real-world tasks and 7.45 percentage points on their out-of-distribution variants.
Read the full abstract ▾
All authors Lijie Wang, Zheng Lu, Yiming Wang, Heyang Yu, Kenghou Hoi, Bowen Hu, Di Cui, Tianyu Xin, Haoran Liao, Wanqi Zhong, Xingjie Fan, Yizhao Xu, Ziliang Wang, Fei Gao, Yiming Li
Machine Learning
F-DACE: Fuzzy Disagreement-Aware Causal Evidence Fusion for Abstention-Safe Conversational Retail Decision Support
Sourish Dey
Observational decision-support systems often expose one causal estimate as a recommendation even when plausible
estimators disagree. The inherent engine of the proposed system is causal machine learning: a conditional-average-treatment-effect estimand identified by
backdoor adjustment, estimated by an EconML DML causal forest and DoWhy linear regression, checked by two-way fixed effects, and converted into candidate levers by constrained optimisation. F-DACE is the decision layer on that engine. It represents precision, propensity overlap, placebo-refutation stability, interval overlap, and directional agreement as fuzzy memberships. Hard vetoes force abstention after estimand mismatch, failed diagnostics, informative sign conflict, or weak evidence. In 180 panel simulations spanning six identification conditions, F-DACE made a decision in 67.2% of runs and limited false recommendations to 17.2%; the corresponding rates were 33.3% for the causal forest and 35.6% for
backdoor regression, matching deterministic unanimity rather than dominating it. Nearly all (30 of 31) false recommendations occurred under shared unmeasured confounding, which no fusion rule can diagnose when every component shares the omitted variable. The retail application aggregates a public Walmart panel to 6,435 store-weeks across 45 stores. F-DACE abstains for all five markdown indicators: some estimates are imprecise, one refutation fails, and MarkDown5 has a direct sign conflict. A LangGraph conversational
agent exposes impact, what-if, and lever-optimization tools while a deterministic verifier preserves causal-layer status. On 24 live questions it achieved 100.0% tool-routing accuracy, 100.0% status fidelity, and 0.983 mean groundedness. On ten
adversarial questions it resisted all injected instructions.
Read the full abstract ▾