Computer Vision
M-plicits: Neural Implicit Surfaces via Nested Multiscale Residuals
Vinícius da Silva, Isabelle Melo, Matheus Bessa et al. (+8 more)
Encoding input coordinates with sinusoidal functions into multi-layer perceptrons (MLPs) has proven effective for implicit neural representations (INRs) of surfaces defined as zero-level sets. However, existing methods often struggle to balance training efficiency, rendering speed, and noise robustness: single-MLP approaches are expensive at inference, grid-based representations are fast but can limit surface smoothness and overfit input noise, and previous multiscale approaches frequently capture noise and produce artifacts due to hard spectral truncation. To address these limitations, we propose M-plicits, a multiscale framework that models surfaces as a residual sum of MLPs trained via a sequence of nested neighborhoods. Unlike existing residual approaches that rely on standard domain-wide sampling and require costly mesh extraction for visualization, our method strictly localizes supervision to narrow bands around the previous zero-level sets. This nested design naturally provides robustness against noisy input data: the coarse network acts as a low-pass filter that establishes a clean
geometric prior, while subsequent residuals progressively refine the geometry without fitting to high-frequency artifacts. We further introduce a multiscale sphere-tracing
algorithm and a GEMM-based analytical normal computation that bypasses auto-differentiation entirely, yielding high-fidelity real-time rendering. On Stanford and Thingi32, M-plicits achieves the best mean Chamfer distance in the coarse configuration and the best median Chamfer distance and IoU in the fine configuration, with substantially better noise robustness than iNGP, BACON, and IDF, while using an order of magnitude fewer parameters than grid-based baselines. Code, models, and data are available at https://github.com/dsilvavinicius/m-plicits.
Read the full abstract ▾
All authors Vinícius da Silva, Isabelle Melo, Matheus Bessa, Guilherme Schardong, Luiz Schirmer, André Araújo, Nuno Gonçalves, Hélio Lopes, Alberto Raposo, Luiz Velho, Tiago Novello
Machine Learning
Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models
Zehao Liu and Vasant G. Honavar
Post-training hybrid
reasoning models in NoThink mode has attracted growing interest as a way to improve performance while keeping inference fast. However, these gains may draw on thinking behavior already accessible through the base model's Think mode. We formulate this thinking leakage in a causal mediation framework and audit its contribution using bidirectional interventions along a simple base-derived activation direction. Across three models and three post-training methods on competition math
benchmarks, we find that leakage is real, causal, and substantial: behavioral and representational analyses reveal shifts toward Think, steering the base model along this direction reproduces most of the post-training accuracy gain, and counter-steering a checkpoint removes a substantial share of what it gains. Across nine aligned checkpoints with positive NoThink gains, the resulting leakage ratio ranges from 42% to 79%. These interventions support a substantial causal contribution of thinking leakage. Our findings show that a post-training method's apparent advantage can therefore reflect greater drift toward Think, obscuring whether it improves capability within NoThink or more effectively re-invokes existing Think behavior.
Read the full abstract ▾
Computation and Language
Benchmarking Argumentative Behaviour of LLMs: A Study of Defences Against Character Attacks
Ewelina Gajewska, Katarzyna Budzynska and Jaroslaw Chudziak
Large
Language Models (LLMs) are increasingly deployed as argumentative
agents in persuasive dialogues, necessitating rigorous evaluation of their debating competence relative to human interlocutors. In this study, we focus on character attacks (ad hominem arguments), traditionally dismissed as fallacies, which play a pivotal role in political persuasive dialogues where ethos often rivals propositional content. Specifically, we investigate whether modern LLMs can replicate human competence to strategically use and respond to such attacks. We analyse a corpus of natural
language political dialogues to identify defensive strategies human interlocutors naturally employ in ethos-centred debates and structure them into a dialogue game. Empirically, we
benchmark LLM-generated dialogues against the ElecDeb60to16-fallacy corpus of U.S. presidential debates, contrasting human debaters' repertoire of defensive strategies with those of artificial
agents. Results reveal a substantial difference: most LLMs rigidly prioritise logical defences, failing to exploit ethotic counterattacks as valid moves in political discourse. We argue that current safety fine-tuning constraints the strategic action space of these LLMs, making them unable to fully engage in naturalistic interactions within domains where character contestation is a normative expectation rather than a mere fallacy.
Read the full abstract ▾
Human-Computer Interaction
Available but Not Usable: Dark Patterns and Interaction Cost in Social Media Privacy and Safety Settings for Teens
Jingxin Dong, Lingyun Chen, Chen Ling et al. (+1 more)
Social media platforms are central to teenagers' lives, and their designs can expose users to
privacy, safety, and wellbeing harms. Platforms increasingly offer protective settings, though the presence of a control reveals little about whether teenagers can find, use, and benefit from it over time. We paired an expert evaluation of six
privacy and safety tasks across TikTok, Instagram, Snapchat, and YouTube with moderated think aloud sessions in which 11 teenagers aged 14 to 17 attempted the tasks. Interaction cost and dark patterns analysis allowed us to compare the complexity designed into each task with the effort participants incurred as they located, configured, and interpreted controls. Recurring dark patterns appeared across tasks, and most participant attempts exceeded the expert baseline. Protective settings therefore risk being insufficiently usable or durable in practice, and we propose a wayfinding audit that integrates expert evaluation, usability testing, interaction cost, and dark pattern analysis.
Read the full abstract ▾
All authors Jingxin Dong, Lingyun Chen, Chen Ling, Colin M. Gray
Machine Learning
Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies
Alex Schutz, Nick Hawes and Victor-Alexandru Darvariu
Graph-based world models have recently emerged as a means of learning transitions over relational state representations. However, existing approaches are largely limited to fixed-
topology graphs or deterministic, fully observable environments. We propose the Graph Dynamics Model (GDM), a world model for graph-structured observations that is designed to handle the more general setting of evolving
topologies in
stochastic and partially observable environments. The GDM uses a sparse recurrent adjacency
matrix to model
topology updates and perform message passing, together with a recurrent state-space architecture for modelling
stochastic transitions. Furthermore, we identify a gap in the evaluation of graph-based world models, as existing methods do not provide a means of comparing predicted and true distributions over the joint graph state comprising the interdependent
topology, node features, and graph features. We therefore introduce the Graph Distribution Distance (GDD) metric, which uses maximum mean discrepancy with a graph kernel to comprehensively compare joint next-state distributions. We evaluate the GDM across several environments, including
stochastic and partially observable settings. We demonstrate that GDM outperforms baseline models and displays zero-shot generalisation on large graphs.
Read the full abstract ▾
Machine Learning
OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds
Miroslav Lžičař
A virtual screening campaign may produce thousands of promising candidates, but only a small number can be purchased, synthesized, or tested. The practical question is how to select a set of compounds that both rank well and are diverse enough: this poses a genuine tradeoff, where selecting the highest-scoring molecules yields limited diversity, while diversity selection sacrifices some well-scoring molecules. We introduce OPDiv, a diversity selection and evaluation
algorithm solving this tradeoff by finding an optimal subset of molecules using integer optimization. We demonstrate the selection
algorithm in practice with fingerprint distance, shape and electrostatic diversity and compare the resulting diversity spectra. We argue that virtual screening is not merely a ranking problem, but also an implicit constrained optimization task: when redundant chemotypes are undesirable, pipelines should be compared based on the top-k compound selections satisfying the desired diversity constraints. OPDiv makes it possible to find the optimal compound set under a given diversity threshold efficiently and serves as a fair
benchmark of the best diverse selection achievable by a given structure-based or ligand-based virtual screening pipeline, molecular search or generative model.
Read the full abstract ▾
Robotics
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
Tara Sadjadpour, Siming He, C.K. Wolfe et al. (+5 more)
Human hand-object interactions (HOIs) provide a rich source of demonstrations for dexterous manipulation, but learning directly from them presents challenges in bridging morphology gaps, ensuring dynamical feasibility, and sim-to-real deployment. We present Morphometric Imitation, a three-stage framework that transforms reconstructed HOIs into zero-shot sim-to-real visuomotor policies. First, morphometric optimization (MMO) kinematically retargets human motion across hand morphologies while preserving demonstrated contacts. Second, residual reinforcement learning (RL) refines the kinematic reference using object pose and contact information from the human motion to produce dynamically feasible
robot demonstrations. Third, these demonstrations are distilled into visuomotor policies. Across three
robot hands and ten HOIs, MMO outperforms five baselines in contact F1, improving on the strongest ones by 8 to 28 points, while improving the success rate of downstream dynamic retargeting by as much as 35 points. On a Sharpa hand, the visuomotor policies achieve 89.3% zero-shot success in 300 real-world trials on 30 objects spanning 10 categories. Project page: https://morphometricimitation.github.io
Read the full abstract ▾
All authors Tara Sadjadpour, Siming He, C.K. Wolfe, Haozhi Qi, Lea Wilken, S. Shankar Sastry, Claire Tomlin, Jitendra Malik
Cryptography and Security
"What I See is What I Hear": Deepfake Detection Across Diverse Hearing Abilities
Magdalena Pasternak, Malvika Jadhav, Palavi V. Bhole et al. (+8 more)
The proliferation of audiovisual deepfakes has lowered the cost of fraud, impersonation, and misinformation, but their success ultimately depends on human perception. Detection requires integrating auditory and visual cues, yet security and
privacy research has largely overlooked d/Deaf and hard-of-hearing (DHH) populations. We address this gap with an in-person, mixed-methods study of 80 participants: 31 hearing persons (HPs), 15 hard-of-hearing (HoH) participants, 17 d/Deaf participants, and 17 cochlear implant (CI) users. Each participant judged the authenticity of 30 clips, where manipulations spanned text-to-
speech, voice conversion, lip-sync, or face-swap. DHH participants were less accurate than HPs overall (76.4% vs. 88.0%, p<.001), primarily because they more often classified authentic clips as manipulated (FPR: 29.7% vs. 11.2%). Differences depended strongly on the manipulated channel. For audio-only manipulations, HoH participants matched HPs (90.0% vs. 90.3%), followed by CI users (79.4%) and d/Deaf participants (41.2%). When clips contained an audiovisual manipulation, accuracy clustered between 84% and 87%, although performance still varied by manipulation method. Our work systematically characterizes how deepfakes affect DHH populations, highlighting the asymmetric risks audiovisual manipulations may pose to groups with different hearing abilities and the need for accessible, tailored defenses that support all users.
Read the full abstract ▾
All authors Magdalena Pasternak, Malvika Jadhav, Palavi V. Bhole, Aviva Smith, Elaina Trapatsos, Vincent Bindschaedler, Roshan Peiris, Ersin Uzun, Patrick Traynor, Matthew Wright, Kevin R. B. Butler
Artificial Intelligence
Training Object Permanence in World Models
Haotian Zhang, Fengyuan Yu, Dezhi Luo et al. (+28 more)
Object permanence and solidity are hallmarks of human cognitive priors. Recent studies show that
video generation models, a paradigmatic class of current world models, have begun to show emerged
reasoning abilities, making them ideal candidates for building human-like physical intelligence. Do
video models have emerged object permanence in them? If not, could we train them with a core-cognition inspired
dataset? We introduce WROP (World
Reasoning with Object Permanence), a data infrastructure of 150 hand-designed cognitive science inspired tasks, divided into six cognitive categories. We build Blender generators that randomize speed, lighting, camera angle, and other nuisance parameters while preserving each task's cognitive structure, yielding 10,000+ samples per task. We release a 1.5M-sample training corpus and a 300-question exam. On this exam we evaluate 14
video models: 3 reference-to-
video, 7 edit, and 4 continuation, among which PWM-WROP, our 16B world model. In a blind pairwise Elo study, PWM-WROP ranks first among continuation models and third overall, behind only a statistical tie between two reference-to-
video models. We release the data, exam, model answers, scores, weights, and PWM, our native-PyTorch training stack on AWS Trainium2.
Read the full abstract ▾
All authors Haotian Zhang, Fengyuan Yu, Dezhi Luo, Haoran Sun, Zehong Zhao, Qingying Gao, Yihan Li, Siyuan An, Huayi Qin, Yilan Zhang, Zhengze Jiang, Pinyuan Feng, Renrui Zhang, Ziyu Guo, Letian Wang, Mengyue Yang, Kangfu Mei, Maijunxian Wang, Ran Ji, Vikash Kumar, Freda Shi, Chandra Sripada, Vincent C. Muller, Philip Torr, Alan Yuille, Nikolaus Kriegeskorte, Felix Juefei-Xu, Lvmin Zhang, Jieneng Chen, Yilun Du, Hokin Deng
Information Retrieval
The Fellowship of the Query: Learning Retrieval Actions
Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer et al. (+1 more)
Retrieval-augmented question answering requires control decisions about when to decompose a question, search, reformulate, extract evidence, synthesize facts, verify progress, and stop. We study whether trajectory fine-tuning can improve small
language models (SLMs) as next-action controllers. We additionally evaluate a low-resource setting in which a single SLM serves as both the controller and the final-answer generator. From accepted teacher search traces, we build a seven-way action-prediction task, where the model predicts the next structured teacher action from the current trajectory state, and evaluate LoRA-supervised fine-tuning across SLMs and xSLMs as controllers. On 1,646 held-out action examples, Granite 4.1 3B trained on 13,194 actions reaches macro-F1 0.6536, compared with 0.1736 for zero-shot prompting of the same model and 0.5399 for a TF-IDF logistic-regression baseline. In an end-to-end controller/generator swap evaluation over 149 held-out trajectories, using the fine-tuned model for both roles improves Exact Match from 0.7530 to 0.7946 and
token F1 from 0.7783 to 0.8295 compared with using the base model as both controller and generator. The cross-role conditions show that the fine-tuned controller increases evidence-fact recording when the generator is fixed, while controller-only final-answer gains are not statistically clear. Overall, trajectory supervision improves action prediction and evidence-recording behaviour in this evaluated pipeline. Code is available at https://github.com/padas-lab-de/
agent-action-controller
Read the full abstract ▾
All authors Mohammed Al-Maamari, Saber Zerhoudi, Michael Granitzer, Jelena Mitrović
Computer Vision
PePESeg3D: Perception Prior Enhances Multi-Scale Segmentation for 3D Gaussian Splatting
Sungjae Choi, Seunghee Koh and Junmo Kim
Recent advancements in 3D Gaussian Splatting (3DGS) have extended its capabilities to multi-scale
segmentation. Existing methods reconstruct a scene with Gaussian primitives and learn multi-scale
segmentation features separately, which leaves the geometry unaware of semantic structure and the feature learning dependent on incomplete mask supervision. To address these limitations, we present PePESeg3D, a novel framework that injects perception priors into a multi-scale 3D Gaussian
segmentation pipeline. To fully exploit perception priors, we integrate them not only into contrastive feature learning but also into the upstream geometry reconstruction. Specifically, PePE Reconstruction incorporates
monocular depth and mask constraints to ensure semantically coherent object structures. Building on this aligned geometry, PePE Contrastive Learning leverages dense depth-color cues and view-consistent centroid supervision to compensate for the incompleteness of multi-scale masks obtained from a 2D foundation model. Extensive experiments on the
SPIn-NeRF, LERF-Mask, and NVOS
benchmarks demonstrate that PePESeg3D achieves state-of-the-art performance in both multi-scale
segmentation and scene reconstruction, highlighting the importance of integrating perception priors into both geometry optimization and feature learning for accurate multi-scale 3D
segmentation. Our code is available at https://github.com/BeCow5X5/PePESeg3D.
Read the full abstract ▾
Information Theory · Cross-listed from quant-ph
Continuity of Regularized Channel Rényi Divergences
Jinzhao Wang and Yuxiang Yang
We prove that the regularized, stabilized sandwiched Rényi divergence of finite-dimensional
quantum channels converges to their regularized relative
entropy as the Rényi order tends to one. The key tool is the channel hockey-stick divergence: Gour's Stinespring approximation bound and a Schatten norm estimate amplify an asymptotic bound below one into exponential decay at higher threshold rates. For channel pairs with finite max-relative
entropy, known operational connections then give exponential strong converses for parallel and adaptive discrimination, a sharp zero–one testing law, and the subchannel asymptotic equipartition property.
Read the full abstract ▾
Machine Learning
RLVR landscapes for iterated multiplications can be benign: Insights from spin-glass theory
Noa Rubin and Zohar Ringel
Despite the importance of reinforcement learning with verifiable rewards (RLVR), the extent to which it can learn new
reasoning capabilities remains debated. Here we study the optimization landscape of RLVR on algorithmic tasks, such as iterated group and quasigroup multiplication. To this end, we map
entropy-regularized RLVR over myopic tabular policies onto an energy-based (
spin-glass) model over deterministic policies. This mapping upper-bounds what RLVR can achieve, and lets us rigorously characterize the landscape in this tabular setting. We show, both theoretically and experimentally, that for a wide class of models and tasks with uncorrelated inputs, this landscape is benign, containing no local minima that could trap RLVR training. Rather, the practical difficulty of these tasks appears to stem, at least in part, from issues such as diffusive barriers and gradient-estimation error in traversing the landscape. These are genuine obstacles that can prevent a solution from being found, but they are distinct from the landscape itself being rugged. We show that these obstacles can often be mitigated through the choice of
entropy regulator. Consistent with this theory, we find that a
transformer trained from scratch, using only last-
token rewards, successfully learns an algorithmic chain of thought for iterated non-Abelian group multiplications.
Read the full abstract ▾
Computation and Language
Reward Hacking Challenges Oversight of Autonomous Research Agents
Yue Huang, Zhangchen Xu, Yuchen Ma et al. (+12 more)
Autonomous research
agents can design experiments, evaluate results, and write reports, giving them control over both a scientific result and the evidence used to support it. This creates a risk of reward hacking: meeting the reward criteria without achieving the intended goal. We study (1) how often models reward-hack without instructions to do so, (2) how effective and detectable their methods are when hacking is allowed, and (3) how they adapt when an LLM review panel returns its decision and reasons. Across 17
language models and 38 tasks, the spontaneous reward-hacking rate is 30.5% on open-ended research-pipeline tasks and 2.9% on task-specific kernels. When hacking is allowed on tasks whose pass thresholds exceed our best compliant baselines, 505/677 attempts (74.6%) are confirmed reward hacks: they both clear the threshold and receive mechanism-verification panel confirmation of an evaluation exploit. An LLM panel reviewing only submitted code and reported scores misses 33/505 confirmed hacks (6.5%). Direct methods that achieve the highest scores are often easy to detect, while less direct methods evade more often. In a five-round loop, the number of model-task pairs with an evasion rises from 7 to 56. Among 79 pairs evaluated under two feedback conditions, cumulative evasion reaches 40.5% with detailed feedback and 20.3% with generic rejection. The detailed condition includes the review decision, reasons, and attempt history, so this comparison does not isolate the effect of explanations. These findings highlight the need for stronger defenses, including metrics kept outside the
agent's control and independent recomputation on data chosen to expose likely exploits.
Read the full abstract ▾
All authors Yue Huang, Zhangchen Xu, Yuchen Ma, Wenjie Wang, Zheyuan Liu, Ziwei Xu, Pin-Yu Chen, Michel Galley, Zinan Lin, Stefan Feuerriegel, Radha Poovendran, Misha Sra, Alex Pentland, Xiangliang Zhang, Zichen Chen
Cryptography and Security
Decision Hijacking: Prompt Injection Attacks on Jev's Typed Probabilistic Decisions
Tiantong Wu and Wei Yang Bryan Lim
Most studies of
prompt injection focus on generative
agents, leaving their effects on models with schema-defined outputs unclear. We examine these effects in Jev, a non-generative decision model, using 510 reconstructed InjecAgent cases. Malicious content shifts action probabilities but rarely causes Jev to select the attacker's target. Override markers reduce this influence, while claims of contextual relatedness have small effects. Adaptive attacks using score feedback double the mean highest attacker-target probability found during optimization, while success on fresh validation calls rises from 1.8% to 3.5%. Exploratory analysis links these successes to small initial decision margins or greater attacker control over the observation. Together, these findings show that schema-defined outputs change but do not eliminate
prompt-injection risk, highlighting the need to evaluate how untrusted content influences choices within the allowed action set.
Read the full abstract ▾
Numerical Analysis
Global Convergence of Third-Order Langevin Dynamics for Non-Convex Optimization via Simulated Annealing
Yingli Wang and Lingjiong Zhu
We study global convergence guarantees of third-order Langevin dynamics for non-convex optimization via simulated annealing with fixed friction and decreasing noise. An explicit three-block distorted
entropy transfers dissipation from the noisy auxiliary variable to the full state. Under dissipativity, regularity, and low-temperature functional-inequality assumptions, logarithmic cooling drives the objective values to the global minimum in probability at the barrier-controlled kinetic rate. For the exact-force-integral and midpoint three-stage discretizations, polynomially decreasing steps preserve this rate on the physical time scale. The cubic local endpoint estimate gives a less restrictive sufficient step-size condition than the available frozen-force kinetic result. A comparison with the one-gradient UBU integrator shows how its centered
stochastic local error leads, under the same strong-coupling analysis, to a smaller sufficient iteration exponent. Numerical experiments are conducted to illustrate our theory. For a double well objective, third-order Langevin terminal-success point estimates are higher than UBU at both a common horizon and an equal gradient budget. For a high-dimensional nonconvex neural-network objective using synthetic data, independently tuned UBU and third-order Langevin schemes both outperform overdamped Langevin dynamics; the third-order Langevin point estimate is higher. For the same neural-network objective on real data, we show the same point-estimate ordering for best-basin probability and post-quench test accuracy. Numerical code and associated experiment results are publicly available at https://github.com/gagawjbytw/simulated-annealing-third-order-langevin.
Read the full abstract ▾
Computer Vision
UltraBench 2: Towards Robust Evaluation of Vision Foundation Models on Ultrasound
Ashwath Radhachandran, Adam Tupper, Christian Gagné et al. (+1 more)
Benchmarking is an increasingly critical part of research in machine learning and the domains where it is applied, including healthcare. Yet, despite the steady development of new ultrasound foundation models in recent years, the development of well-designed
benchmarks to evaluate them has lagged behind. This deficiency has led to fragmented and inconsistent evaluations of competing models, making it difficult to measure progress. To address this issue, we introduce UltraBench 2, a comprehensive
benchmark with wide anatomical and task coverage, and a focus on standardization, reproducibility, and ease-of-use. Using this
benchmark, we compare existing
vision foundation models for ultrasound image analysis. Our analyses demonstrate that ultrasound-specific pretraining still leads on classification, but that state-of-the-art general-purpose models have drawn level on
segmentation.
Read the full abstract ▾
All authors Ashwath Radhachandran, Adam Tupper, Christian Gagné, William Speier
Artificial Intelligence
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
Zheng Zhang, Liu Liu, Qi Chai et al. (+4 more)
Role-playing
agents based on large
language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically train on a fixed scenario pool collected before learning begins. This creates a distributional bottleneck: as the
agent improves, the scenarios where it performs poorly also change, while the training distribution remains static. Therefore, we propose AdvRole, an
adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum. AdvRole alternates between an Actor that learns to role-play and a Rewriter that edits character profiles and dialogue contexts into actor-specific hard scenarios. The Rewriter is trained with a performance-gap reward, which favors rewrites that reduce the current Actor's score relative to the original scenario. As a result, the scenario pool evolves with the Actor and continuously targets under-mastered regions of the character-context space. Experiments on three role-playing
benchmarks covering English and Chinese, as well as a new
multilingual benchmark we release, show that AdvRole consistently outperforms baselines.
Read the full abstract ▾
All authors Zheng Zhang, Liu Liu, Qi Chai, Deheng Ye, Peilin Zhao, Mao Zheng, Hao Wang
Cryptography and Security
CONCURDEP: Event-Guided Analysis of Dependency Invalidation in CPython Concurrency
Baihong Chen, Hadley Westover and Wen Li
Removing CPython's Global Interpreter Lock (GIL) exposes native code to concurrency absent from ordinary C types. Mutation or re-entry can revoke a borrowed object, storage pointer, traversal state, or lease between acquisition and use while its owner remains alive, causing native
memory errors and runtime-state corruption. Race analyses track conflicting accesses. Python/C lifecycle analyses track individual object states. These reporting units leave implicit owner-subject-storage relations disconnected from later uses under parallel and re-entrant events. We present CONCURDEP, a source-level static analysis of dependency invalidation. Its key insight is to represent the runtime property a native use requires and ask which target-matched event can revoke it within the dependency's live region. CONCURDEP recovers runtime-semantic dependencies, connects them to events through an event-aware native concurrency dependency graph, and applies property-specific state and protection transfers through a shared engine and six mechanism plugins. CONCURDEP correctly classifies all 180 matched semantic-conformance cases and analyzes each of three production CPython releases with five-run medians of 22.13-27.66 seconds and 670-784 MiB peak resident
memory. Source
auditing confirms 1,094 of 4,273 unique production fingerprints (25.60% confirmation yield). Removing derived relation recovery loses 25-44 represented roots per release; removing cross-entry events loses 73-94. The study identifies 144 distinct bugs across free-threaded and conventional-GIL builds, including 95 previously unreported in public sources. These results show that explicit dependency, event, and property semantics expose consequential runtime failures across API boundaries and execution modes at release scale.
Read the full abstract ▾
Machine Learning
fable.intermittent: benchmarking probabilistic forecasting methods for intermittent time series
Stefano Damato, Lorenzo Zambon, Giorgio Corani et al. (+1 more)
Intermittent time series are common in spare-parts demand and retail sales. Since the cost of forecast errors is typically asymmetric, decisions such as inventory control require the full predictive distribution rather than a point forecast. Many probabilistic
forecasting methods have been proposed; their implementations, however, are scattered across different software frameworks, making it difficult to compare them systematically. We introduce fable$.$intermittent, an R package that implements several probabilistic
forecasting methods for intermittent series within the fable framework. The package allows several models to be fitted and evaluated on a collection of time series through a single, simple
forecasting pipeline. We also introduce TWEES, a new exponential smoothing model with a Tweedie predictive distribution. Fitting TWEES requires repeated evaluation of the computationally demanding Tweedie density. We also release the R package tweedieDistr, whose implementation of the Tweedie distribution is substantially faster than the existing one while preserving the same numerical accuracy. We evaluate the methods implemented in fable$.$intermittent on four
datasets, also released in the package.
Read the full abstract ▾
All authors Stefano Damato, Lorenzo Zambon, Giorgio Corani, Dario Azzimonti
Machine Learning
UO-FIE: Combining Exact-Label Supervision with Graded Utility for Factivity Inference
Xinchen Xiao
The Factivity Inference Evaluation 2026 (FIE2026) classifies Chinese context-hypothesis pairs into nine ordered factivity intervals. Its evaluation metric rewards both exact predictions and proximity to the correct interval, while 64.1% of the 566 training examples belong to a single class. In preliminary experiments, several mDeBERTa classification models predominantly predict the dominant class, whereas a Huber-regression baseline produces more predictions near the correct interval but fewer exact matches. We introduce Utility-Oriented Factivity Inference (UO-FIE), a parameter-efficient system that combines exact-label supervision with graded utility. UO-FIE predicts a distribution over the nine classes and combines hard-label supervision, utility-based soft targets, scheduled class weights, and an ordinal loss. We evaluate expected-utility decoding in controlled comparisons and use ordinal calibration selected on out-of-fold predictions for the submitted system. Based on Qwen3.5-9B with LoRA, UO-FIE ranks first in the fine-tuning track with a macro utility of 0.8316. A separate
prompt-based ensemble ranks third in the non-fine-tuning track with a macro utility of 0.8450.
Read the full abstract ▾
Machine Learning
Physics-Informed Self-Supervised Learning for Joint Wire Calibration and Interaction Position Reconstruction in Multi-Wire Parallel Plate Avalanche Counters
Antoine Lemasson and Maurycy Rejmund
Scientific instruments require accurate calibration to convert detector signals into reliable physical observables. Conventional calibration procedures typically rely on dedicated calibration measurements, analytical response models or labelled reference data, limiting their ability to adapt to changing operating conditions and detector aging. We present a physics-informed self-supervised learning framework that jointly performs wire calibration and interaction position reconstruction in Multi-Wire Parallel Plate Avalanche Counters (MWPPACs) without requiring labelled position measurements or dedicated calibration runs. The method formulates detector calibration as a latent optimization problem in which global wire gains and event-wise interaction positions are estimated simultaneously using supervision derived exclusively from detector geometry and charge-energy consistency constraints. A detector-independent neural network reconstructs sub-wire interaction positions from local charge distributions, eliminating the need to assume analytical induction profiles by learning the detector response directly from experimental data. The end-to-end differentiable framework enables continuous detector self-calibration while improving the uniformity and accuracy of position reconstruction. Experimental evaluation on the entrance MWPPAC tracking detectors of the VAMOS++
magnetic spectrometer demonstrates stable convergence, improved spatial homogeneity and enhanced position resolution. Beyond the detector studied, the method establishes a general framework for physics-informed self-supervised calibration of scientific instruments and is a step toward autonomous intelligent instrumentation capable of continuous adaptation during operation. In this paradigm, detector calibration is no longer a prerequisite for an experiment but an integral part of the measurement process itself.
Read the full abstract ▾
Machine Learning
Learning to Discover Interesting Mathematics
Niket Patel, Ahmad Rammal, Amaury Hayat et al. (+2 more)
Recently, Large
Language Models (LLMs) have been increasingly able to solve advanced mathematical problems, including many that have been open for decades. This opens the door to expansion of mathematical knowledge at unprecedented scale. Yet, while LLMs may be able to
conjecture and prove more and more
theorems, it remains open whether this new mathematical knowledge is interesting or useful. We define intrinsic interestingness of a
theorem as the ratio between the length of its proof and the length of its statement. We show that this correlates strongly with an extrinsic measure of the downstream utility of a
theorem. We identify the difficulty of a proof conditioned on a set of premises as a useful primitive for computing these metrics, and train a 27B model that predicts proof difficulty more accurately than frontier general-purpose models. Optimizing for our metric creates a model capable of producing more interesting
theorems, while also reducing substantial or full overlap with Mathlib from 91.9% to 30.6%, showcasing the creation of more out-of-distribution math. We show that our system can generate candidate
theorems, select the most interesting among them, and iteratively build on a self-expanding mathematical library. These metrics provide a practical and quantifiable signal for ranking
conjectures and guiding proof search within formal mathematical libraries. Our framework provides a path towards self-expanding, machine-verified mathematical libraries that can choose worthwhile statements without relying on human-supplied targets.
Read the full abstract ▾
All authors Niket Patel, Ahmad Rammal, Amaury Hayat, Remi Munos, Julia Kempe
Machine Learning · Cross-listed from physics.ao-ph
HClimRep-Ocean: A Global Ocean Emulator on an Unstructured Mesh
Kacper Nowak, Aleksei Koldunov, Nikolay Koldunov et al. (+7 more)
Machine-learning (ML) emulators for atmospheric processes have advanced rapidly in recent years, transforming weather
forecasting. Although early ML ocean
forecasting models now exist, they remain less developed than their atmospheric counterparts. Unlike the atmosphere, much of the ocean's kinetic energy resides in mesoscale eddies whose characteristic spatial scales are approximately an order of magnitude smaller than those of comparable atmospheric features. Moreover, complex coastlines, narrow straits, and ice-covered seas make boundary representation a central challenge that atmospheric models do not face. Consequently, numerical ocean simulations commonly use locally refined or even completely unstructured meshes. However, their data-driven counterparts have so far been built around latitude-longitude grids. We present HClimRep-Ocean, an ocean emulator that operates directly on the native unstructured mesh of FESOM2. The emulator is trained on a 209-year AWI-CM3 control integration and is run without atmospheric forcing, receiving the atmospheric state only at initialisation time, which isolates the predictability carried by the ocean state itself. Skill is strongly field-dependent: for currents, HClimRep-Ocean outperforms every reference at 30 day forecast, whereas for temperature and salinity a damped-anomaly persistence forecast remains the more accurate
estimator. This behaviour is physically interpretable: current variability is largely geostrophic and internally generated, whereas sea-surface temperature and salinity fluctuations are driven by atmospheric forcing through weather state. Evaluated independently on the OceanBench
benchmark, a reanalysis-trained variant of HClimRep-Ocean achieves the lowest RMSE against GLORYS reanalysis among all assessed systems, confirming the competitiveness of the native-mesh approach.
Read the full abstract ▾
All authors Kacper Nowak, Aleksei Koldunov, Nikolay Koldunov, Savvas Melidonis, Ankit Patnala, Simon Grasse, Julius Polz, Christian Lessig, Martin Schultz, Thomas Jung
Software Engineering
Developing a Unified Verification and Validation Activity Standard at JPL
Maximilian Vierlboeck, Ellen Van Wyk, Natalia Sanchez et al. (+6 more)
Verification and validation practices (V&V) at NASA's Jet Propulsion Laboratory (JPL) have diverged over the past decade, creating fragmentation that increases overhead, reduces cross-project efficiencies, and inhibits institutional knowledge transfer. We present a unified V&V activity schema developed through human-centered design workshops involving 29 practitioners across multiple mission types and disciplines. The schema builds on a relationship-based architecture that allows for separating methods (Test, Analysis, Inspection, Demonstration, and Review of Design) while maintaining a common attribute set. Formalized as a platform-agnostic SysML model, the schema defines bidirectional relationships between requirements, V&V activities, venues, and evidence. Implementation in JPL's Jama platform demonstrates controlled customization through templates and modular item types, balancing rigor with agility while enabling automations, pattern reuse, and digital thread integration.
Read the full abstract ▾
All authors Maximilian Vierlboeck, Ellen Van Wyk, Natalia Sanchez, Bogdan Oaida, Torrance James Eberhart, Marie Piette Gomez, Christopher Delp, Marijke G. Jorritsma, Alex Desharnais
Cryptography and Security
BRFID: Toward Byzantine-Robust Federated Intrusion Detection
Asmah Muallem, Firdous Kausar, Sajid Hussain et al. (+1 more)
Flipping 60% of training labels from a single Byzantine client using label-flipping model poisoning self-degrades an attacker's own
federated detection accuracy, $99.96\%$ (at no poisoning rate) to $84.33\%$ in a three-client
federated IDS. Where the
Federated global ensemble maintains stable accuracy across all tested poison rates, without a defense mechanism in place and without coordination between attackers. In this paper, we present empirical results quantifying the impact of label-flipping poisoning attacks on a three-client
federated IDS trained on CICIDS2017 with non-IID attack subtype distributions across clients. We demonstrate that the signal of the
adversarial self-compromise represents a detectable anomaly for exploitation for Byzantine client identification in the absence of target data exfiltration. We note that the aggregation step uses a
Federated Forest (tree concatenation) rather than a parametric FedAvg; the results therefore measure the impact of poisoning on per-client performance under ensemble aggregation, and extension to genuine FedAvg with a parametric classifier is planned for future work.
Read the full abstract ▾
All authors Asmah Muallem, Firdous Kausar, Sajid Hussain, Lei Qian
Machine Learning
TAM-Chain: Multi-Scale Thyroid Cytology Classification via Absorbing Markov Chains and Shannon Entropy Uncertainty Quantification for False-Negative Suppression and Domain-Shift Adaptation
Hai Pham Ngoc
Background & Problem: Thyroid Fine-Needle Aspiration Biopsy (FNAB) cytology based on the Bethesda System plays a pivotal role in early thyroid cancer detection; however, deep learning approaches face substantial challenges regarding high false-negative rates and overconfidence under clinical domain shift. Methods: In this study, we propose TAM-Chain, a multi-scale (10x, 20x, 40x) thyroid cytology classification framework leveraging Absorbing Markov Chain theory combined with Shannon
Entropy-based Uncertainty Quantification. The framework dynamically models multi-magnification feature extraction as an absorbing
stochastic process, enabling optimal stopping criteria and a human-in-the-loop referral mechanism to strictly suppress critical diagnostic errors. Results: Extensive evaluation on an internal test set (N = 235) demonstrates a Macro F1 score of 0.9741 with an absolute False-Negative Rate (FNR) of 0.00%. On an independent external validation set (N = 1015) presenting severe domain shift, TAM-Chain maintains superior stability and classification performance (Macro F1 = 0.7026) by adaptively adjusting the expected stopping step and triggering specialist referrals, significantly outperforming single-magnification baselines. Conclusion: The TAM-Chain framework proves to be a highly effective, safe, and adaptable solution for digital pathology workflows, successfully harmonizing automated diagnostic efficiency with stringent biological safety.
Read the full abstract ▾
Information Retrieval
OneTrans-V2: Unifying Retrieval, Pre-rank, and Fine-rank with One Transformer in Industrial Recommender
Hannan Cao, Jun Guo, Haolei Pei et al. (+18 more)
Industrial recommendation systems typically operate as a cascade of
retrieval, pre-rank, and fine-rank, but these stages are usually trained and served as separate models, causing repeated user-sequence encoding, isolated optimization, and duplicated engineering effort. Building on OneTrans' model-level unification, we present OneTrans-V2, one
Transformer that unifies the entire cascade. It encodes the user behavior sequence once as a shared context while preserving stage-specific candidate features and computation. Joint training lets the three stages reinforce one another and enables in-model knowledge
distillation from fine-rank to pre-rank. We scale the shared backbone with sparse mixture-of-experts (MoE), which increases capacity with bounded activated computation, and stabilize scaling with $\mu$P-style parameterization. To consolidate objective-specific
retrieval channels, we introduce Decision-Conditioned Generative
Retrieval (DCGR). DCGR predicts a decision prefix describing the upcoming interaction and generates items conditioned on it, allowing business objectives to steer a single generative process. Finally, Sequence-Native Training (SNT) organizes training around each user's lifelong behavior sequence and amortizes its encoding across exposures. Deployed across all three stages of a large-scale industrial recommendation system, OneTrans-V2 improves gross merchandise value (GMV) by 9.74% and, with a co-designed serving stack, delivers $3.2\times$ the throughput of the cascade it replaces under the same hardware budget.
Read the full abstract ▾
All authors Hannan Cao, Jun Guo, Haolei Pei, Zhaoqi Zhang, Tianyu Wang, Ziyang Wang, Youchen Sun, Yue Xue, Yucheng Mao, Lintao Yan, Yufei Feng, Shaowei Liu, Rongkun Xing, Feiling Gong, Xinyu Chenli, Cong Xu, Mingge Zhang, Yunjia Zhu, Yajing Zhang, Pengfei Ren, Yue Lin
Information Theory
Sensing Assisted Satellite Backhaul with FBL UL and Broadcast DL for Massive IoT
Tijana Devaja, Milica Petkovic, Israel Leyva-Mayorga et al. (+2 more)
Massive Internet of Things (IoT) networks operate with short packets whose reliability is limited by finite block- length (FBL) effects, while remote deployments increasingly rely on Low Earth Orbit (LEO) satellites for backhaul connectivity that is sensitive to atmospheric attenuation. In this paper, we pro- pose a unified end-to-end framework for satellite-assisted massive IoT networks that jointly models uplink FBL random access, sensing assisted satellite backhaul, and worst user broadcast downlink transmission. Uplink reliability is characterized using
stochastic geometry, while atmospheric sensing and conservative SNR margins enable FBL-safe backhaul adaptation. Numerical results reveal an optimal uplink access probability due to the tradeoff between spatial reuse and FBL reliability, and show that sensing assisted backhaul margins significantly improve robustness against attenuation uncertainty.
Read the full abstract ▾
All authors Tijana Devaja, Milica Petkovic, Israel Leyva-Mayorga, Dejan Vukobratovic, Cedomir Stefanovic
Artificial Intelligence · Cross-listed from stat.ML
NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees
Weiwei Ye, Hangchen Liu and Renhe Jiang
Large
language models can interpret natural lan- guage, yet robust decisions remain challenging. Jev-like models expose structured choices, but these interfaces do not directly provide numeri- cal values at a requested precision. We propose NUMERICJEV, a training-free numerical decod- ing
algorithm that enables numerical output from any LLM with a Jev-like structured-choice in- terface. Surprisingly, on our arithmetic bench- mark, it outperforms direct selection from a can- didate list containing the correct answer by 2.93 percentage points (Figure 1). Our motivation comes from the observation that numerical range selection is itself a decision problem that Jev- like LLMs can address. NUMERICJEV recur- sively refines a range through a multiway deci- sion tree while retaining the original question in context, without parameter updates or hidden- state access. On a 100-value grid, a ten-way tree requires only two decision rounds. Range- normalized MAE is 1.84% versus 5.18% for di- rect choice. A separate three-date historical- index study yields 4.58% mean relative recall er- ror and 0% readout error when the value is sup- plied. Code is available at https://github. com/Bring-AI/jev-numeric.
Read the full abstract ▾