Machine Learning
What Must Survive? Exact Task-Information–State Frontiers Under Partial Task Revelation
Ronald Katende
A state may need to be compressed before its exact downstream task is known. For a finite family of linear task operators $\{T_u\}_{u\in\U}$, we characterize exactly how much state must survive when only one of $K$ coarse task messages is available at compression time: $$p^*(K)= \min_{\substack{\Pcal\text{ partition of }\U\\|\Pcal|\le K}} \max_{C\in\Pcal}\rank(T_C),$$ where $T_C$ stacks the tasks that remain unresolved within
cell $C$. Thus task information reduces retained state precisely by separating tasks whose joint task-visible subspace is expensive. We derive the dual bit frontier, an irreducible common-core floor, and a sharp singular-value characterization for nonzero tolerance. For overlapping task families, a cumulative overlap deficit places the exact frontier within an additive $\Delta$ of weighted load balancing. Optimal partitioning is strongly NP-hard, yet direct-sum families admit classical approximation guarantees and a PTAS. We stress-test the theory on learned task operators from CIFAR-10, Fashion-MNIST, SVHN, and Burgers observables. For Burgers with $K=2$ and $\eps=0.35$, a constructive partition attains $p=4$, while balanced random partitions require median $p=6$, with held-out worst standardized RMSE $0.0368$. The results distinguish uniform task sufficiency from distributional and decision-level performance.
Read the full abstract ▾
Computer Vision
Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion
Hang Cheng, Yan Chen, Mingyu Fan et al. (+1 more)
Recent pre-trained foundation models provide rich multi-modal priors for downstream 3D
vision tasks. However, the effectiveness of these representations in few-shot scenarios is limited by two fundamental challenges: High-dimensional features often contain substantial channel redundancy and task-irrelevant noise, while the reliability of different modalities varies across samples. Consequently, direct aggregation of heterogeneous representations overlooks sample-dependent modality reliability and may obscure the discriminative cues essential. To address these limitations, we propose Refine Then Fusion(RTF), a training-free framework for few-shot 3D recognition. RTF first identifies discriminative feature channels by jointly modeling inter-class similarity and intra-class stability, thereby decoupling domain-specific knowledge refinement from the cached representations of pre-trained models. It then introduces a reliability-aware fusion mechanism that estimates sample-wise modality reliability from the distribution shifts induced by feature refinement, enabling adaptive aggregation of multi-modal representations. Furthermore, RTF constructs a
memory cache that integrates instance-level support features with class-level prototypes to infer query labels. Extensive experiments on five
benchmarks demonstrate that RTF consistently outperforms single-modal baselines, partial-fusion variants, and existing lightweight adaptation methods, achieving state-of-the-art few-shot 3D recognition performance without gradient optimization, additional training data, auxiliary training, or parameter updates.
Read the full abstract ▾
All authors Hang Cheng, Yan Chen, Mingyu Fan, Long Zeng
Computer Vision
VidOmni-Bench: A Benchmark for Fine-Grained Video Understanding via Spatio-Temporal Event Verification across Complexity and Duration
Changbeen Kim, Junwon Chang, Kipyo Kim et al. (+3 more)
While
Video Large
Language Models (
Video-LLMs) have recently demonstrated strong performance, reliably evaluating their fine-grained
video understanding remains challenging. Existing
benchmarks often rely on question answering or ground-truth caption matching, where models may succeed through superficial cues and incomplete annotations. To this end, we introduce VidOmni-Bench, a
benchmark that requires models to verify whether each event in dense
video captions is supported by the
video. VidOmni-Bench consists of 500
videos spanning five complexity types and diverse durations from 4 seconds to 90 minutes. After collecting
videos along these axes, we use diverse
Video-LLMs to generate dense captions and obtain human-verified sentence-level labels, where sentences containing incorrect events serve as hard negatives for evaluation. Our experiments on VidOmni-Bench reveal three key findings: (i)
Video-LLMs frequently generate hallucinated descriptions in dense
video captioning; (ii) they also struggle as verifiers, failing to reliably detect plausible but incorrect event descriptions; and (iii) model weaknesses vary across
video complexity and duration, revealing diverse, model-specific bottlenecks in current
Video-LLMs.
Read the full abstract ▾
All authors Changbeen Kim, Junwon Chang, Kipyo Kim, Risa Shinoda, Kuniaki Saito, Donghyun Kim
Artificial Intelligence
Learning-to-Optimize as the Missing Architectural Layer of AI-Native Networks
Giambattista Amati, Federica Mangiatordi, Pierpaolo Salvo et al. (+2 more)
Artificial Intelligence (AI) is becoming a fundamental design principle of future AI-native communication networks, enabling autonomous resource management, adaptive control, and zero-touch network operation. While current AI-native architectures increasingly embed intelligence across network functions, they provide little guidance on how optimisation knowledge should be systematically generated, transferred, and exploited by AI models. This paper argues that the Learning-to-Optimize (L2O) represents the missing architectural layer between optimisation and AI-native intelligence. Rather than viewing optimisation merely as an online decision engine, the proposed paradigm redefines optimisation
algorithms as offline knowledge generators that produce high-quality supervisory information for neural surrogate models. The resulting models inherit optimisation expertise while enabling low-latency runtime inference suitable for dynamic network environments. A generic four-stage L2O workflow is introduced, comprising optimisation, knowledge generation, surrogate learning, and runtime inference. Unlike existing Learning-to-Optimize approaches, which primarily focus on
algorithm acceleration, the proposed framework establishes L2O as an architectural abstraction applicable across heterogeneous communication and computing systems. The proposed paradigm is illustrated by an NR-V2X relay-selection problem, in which optimisation-generated solutions from a Mixed-Integer Linear Programming (MILP) solver are used to train a Graph Neural Network that can reproduce near-optimal decisions in real time. The presented perspective positions Learning-to-Optimize as a key architectural enabler for future AI-native networks.
Read the full abstract ▾
All authors Giambattista Amati, Federica Mangiatordi, Pierpaolo Salvo, Emiliano Pallotti, Simone Angelini
Computer Vision
2D GauSS-MI: Efficient Active Scene Reconstruction with Balanced Visual and Geometric Quality
Yuhan Xie and Jia Pan
Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within limited onboard computational resources. Existing methods face challenges in adequately balancing visual and
geometric quality with the computational efficiency required for real-time operation. In this work, we present an active reconstruction framework based on 2D Gaussian Splatting (2DGS). We develop an efficient online 2DGS mapping pipeline for incremental RGB-D observations and introduce a probabilistic reliability model that characterizes the view-dependent reconstruction quality of individual 2D Gaussian splats. Building on this model, we formulate 2D Gaussian Splatting Shannon Mutual Information (2D GauSS-MI), a mutual-information-based metric that exploits the explicit surface orientation of 2DGS to evaluate the expected information gain of candidate views. The proposed metric enables active view selection to account for both visual and
geometric reconstruction quality. We evaluate the proposed system against three state-of-the-art baselines on eight Replica scenes. Experimental results demonstrate that our method achieves a favorable balance between visual and
geometric reconstruction quality with substantially lower computational cost and competitive model storage.
Read the full abstract ▾
Cryptography and Security
ServeGuard: Verifiable, Bounded-Residual Confinement of Operator-Invisible Channels Without Revealing the Certified Read Factor
Dominik Dahlem and Rui Vieira
Third-party adapters for open-weight
language models ship as opaque weight
matrices; a recipient cannot check whether an adapter hides a
backdoor without trusting the publisher or inspecting the weights, the publisher's core asset. For one important class (payloads placed where a safety monitor is structurally blind), detection is unsound as a defense: every detector that factors through the declared monitor is invariant on its blind subspace, and honest and backdoored adapters overlap on every blind-subspace statistic we evaluate, because benign adaptation uses that subspace too. Rather than detect this channel, we make it structurally absent and prove that we did. The publisher builds the adapter to read the input only through directions the monitor covers and proves this in zero knowledge, revealing nothing about the read factor it certifies. The certificate is cheap because the expensive part, identifying the monitor's blind spot, is a deterministic function of the public base model, so only one linear identity is proved; the served residual is the base model's own public floor, not a prover-chosen tolerance. The result is ServeGuard, a supply-chain primitive: the publisher ships a proof-carrying adapter whose proof lets a consumer or regulator verify, without the certified read factor and without trusting the publisher, that the adapter carries no hidden channel of this class relative to the declared monitor; an admission-time typing guard binds the guarantee to the adapter bytes admitted at serving time. Across eight checkpoints up to 7B from four families, the monitoring budget is architectural: the measured frontier saturates at the value-path rank on grouped-query checkpoints but not on multi-head ones. On a 0.5B model confinement is nearly free for benign adaptation, making monitor quality the security lever.
Read the full abstract ▾
Robotics
Skel-WAM: A Hand-Skeleton-Conditioned World Action Model for Human-to-Robot Manipulation Transfer
Zetao Cai, Yaping Li, Yiqun Wang et al. (+8 more)
Robot demonstrations are expensive to collect and often provide limited distributional coverage of task variations. Human
videos offer a low-cost source of complementary manipulation experience, but learning from them requires bridging embodiment gaps in visual appearance and action spaces. We introduce Skel-WAM, a world action model that bridges these differences through a unified hand-skeleton motion interface. The key insight is to align human and
robot motion through a common hand
topology, combining skeleton overlays that ground motion in the scene with structured 2.5-D keypoints that encode explicit hand kinematics.
Video and Keypoint Experts jointly learn visual and skeletal dynamics through a Mixture-of-
Transformers, while a separate
robot-trained Action Expert maps these predictions to executable controls. This separation enables human and
robot demonstrations to directly supervise shared dynamics without requiring
robot action labels for human
videos. Across four real-world bimanual tasks and seven simulated tasks, Skel-WAM achieves average success rates of 79.86% and 63.29%, surpassing the strongest baseline by 22.22 and 8.28 percentage points, respectively. Human-
robot cotraining more than doubles real-world success on task variations absent from
robot training data, from 38.89% to 86.11%. These results demonstrate that a shared skeletal interface enables joint learning across human and
robot data and expands
robot task coverage through complementary human demonstrations.
Read the full abstract ▾
All authors Zetao Cai, Yaping Li, Yiqun Wang, Xinyu Zhan, Yuyin Yang, Haoxiang Ma, Kailin Li, Tao Lu, Jiangmiao Pang, Linning Xu, Dahua Lin
Numerical Analysis
FrFNO:Injecting the analytic Mittag-Leffler propagator into a resolution-robust neural operator for space-time fractional PDEs
Guofei Pang
Fractional partial differential equations couple a
memory-dependent time derivative with a nonlocal fractional
Laplacian, and their repeated solution under varying fractional orders, initial data, or diffusivity fields is computationally expensive. Neural operators offer a fast surrogate, but standard architectures must relearn the dominant linear fractional
evolution from data. We propose the Fractional
Fourier Neural Operator (FrFNO), a resolution-robust conditional operator. It injects the analytic Mittag–Leffler response of the frozen linear part as a once-precomputed, resolution-independent propagator table, and trains a spectral convolutional network only on the residual induced by variable coefficients and nonlinear advection, conditioned continuously on both fractional orders. The central theoretical result is that under zero-shot super-resolution the injected propagator fills the out-of-band modes that a standard
Fourier neural operator sets to zero, replacing the out-of-band full-field tail by the smaller residual tail (a $K$-independent constant-factor reduction under weak perturbation). The residual and the full solution carry the same Sobolev order, so the advantage is amplitude reduction rather than a steeper tail. Mesh refinement drives the error to a residual-controlled floor. On a nonlinear two-dimensional space–time fractional Burgers problem FrFNO achieves the lowest relative $L^2$ error among six baselines (FNO, PINO, PDNO, CNO, DeepONet, U-Net) at the training resolution and under zero-shot super-resolution, yields the smallest spectral phase error, and remains the best at the integer-order limit and for long integration windows. The same construction extends to coupled fractional systems such as fractional Allen-Cahn and Navier–Stokes equations. Code, training scripts, and reference outputs are available at https://github.com/Derek2021Pang/FrFNO.
Read the full abstract ▾
Robotics
2nd Place Solution to the HANDS 2026 Workshop Challenge-Dexterous Grasp Motion Track: Single-Shot Trajectory Warping for Grasp Motion Generation
Muneeb A. Khan, Woojin Kim, Shinwoo Kim et al. (+3 more)
This report describes our 2nd place solution to the HANDS 2026 workshop challenge (Dexterous Grasp Motion track) in conjunction with ECCV 2026. In this challenge, we address grasp motion generation for the 12-DoF LinkerHand O6, aiming to produce physically plausible reach-and-lift trajectories for unseen objects from randomized initial hand poses in simulation. This task is particularly challenging because each grasp requires a per-step policy to make approximately $70$ twelve-dimensional decisions, with errors accumulating over time, while test objects and physical dynamics may differ from those encountered during training. To address these challenges, we propose editing a single successful GraspM3 demonstration instead of generating the motion step by step: a policy observes the object once and outputs a 12-D warp of the demonstration, which is then replayed open-loop. Moreover, we train the warp policy with one-step PPO over all $4{,}824$ training objects in parallel. As a result, our method achieved success rates of $94.61\%$ on the easy track, the highest of all submissions, and $57.18\%$ on the hard track of the private test set.
Read the full abstract ▾
All authors Muneeb A. Khan, Woojin Kim, Shinwoo Kim, Muhammad Munsif, Binod Bhattarai, Seungryul Baek
Artificial Intelligence
The Communication Bottleneck: A Round-Trip Study of Tree-Structured Expression Serialization in Language Models
Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella et al. (+1 more)
When
language models reason in chain-of-thought or exchange free-text intermediates, they serialize structured information into natural
language. How much tree-structured compositional content survives this bottleneck? We propose a round-trip protocol that answers this question empirically for tree-structured expressions. A generator converts a procedurally generated arithmetic expression into a word problem, a separate extractor recovers the expression from the word problem alone, and symbolic equivalence provides an exact oracle. Evaluating all pairwise combinations of sixteen models yields a communication
matrix whose marginals separate generation quality from extraction quality. Three main findings emerge. First, the channel is lossy and asymmetric: swapping which model generates and which extracts shifts accuracy by up to 60.4 points, and the best pair reaches 92.9% by combining different models on each end rather than the same model on both. Second, at least 73.6% of round-trip failures originate at generation, and difficulty is driven by tree structure (operator count, depth, right-branching) rather than model family. Third, the channel is trainable: ~3600 fine-tuning examples that share the evaluation's operators and tree shapes lift every open-weight model above untrained Gemini-3.1-Pro, an upper bound under matched semantics. A disjoint-domain regime with new operators and vocabulary also raises every open-weight model, confirming the gain is not an artifact of matched semantics, though a gap to the frontier remains. Together these results identify tree-structured expression serialization as a primary limiting factor when models communicate hierarchical structure through natural
language.
Read the full abstract ▾
All authors Xavier Suau, Alex Ferrando de las Morenas, Luca Zappella, Samy Bengio
Robotics
DPed-VLN: A Benchmark for Socially Compliant Vision-and-Language Navigation in Dynamic Pedestrian Environments
Haojie Dai, Xiangyi Wang, Liuyi Wang et al. (+5 more)
Vision-and-
language navigation (VLN) has advanced rapidly in static indoor environments, but
robots operating in human-populated spaces must ground
language while responding to moving pedestrians and social-safety constraints. We present DPed-VLN, a Habitat 3.0
benchmark for dynamic-pedestrian VLN that couples 33,093
navigation episodes with paired global and prior-augmented instructions, ORCA-controlled
humanoid pedestrians, socially constrained expert paths, and metrics that jointly assess
navigation efficiency and social safety. DPed-VLN separates ordinary goal-oriented route guidance from prior-augmented instructions that expose dynamic-pedestrian cues for controlled analysis. To instantiate the
benchmark, we introduce DPet (Dynamic Pedestrian-aware Network), a pedestrian-aware policy network trained with reinforcement learning and imitation learning. We further adapt representative state-of-the-art VLM-based
navigation models, including NaVILA and StreamVLN, to DPed-VLN through LoRA fine-tuning. Experiments show that LoRA adaptation improves zero-shot VLM baselines in several success and safety metrics, especially reducing StreamVLN's collision rate. Among the evaluated methods, DPet-RL achieves the highest SR, SPL, and STL.
Read the full abstract ▾
All authors Haojie Dai, Xiangyi Wang, Liuyi Wang, Kai Sheng, Zongtao He, Chengju Liu, Wei Ye, Qijun Chen
Computer Vision
Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering
Tianchen Deng, Guole Shen, Yilin Shen et al. (+7 more)
Recent 3D foundation models enable generalizable
geometric reasoning from RGB images but remain limited in persistent
memory, scalability, and renderable scene modeling. We present a
memory-centric 3D foundation model for scalable robotic localization, reconstruction, and Gaussian rendering. Its core is an adaptive world
memory mechanism that combines
transformer-based gated updates with test-time temporal-spatial regulation. Learned gates control recurrent
memory propagation, while temporal state
evolution and spatial observation-state consistency regulate
token-wise updates and forgetting over long image sequences. To support large-scale mapping, we organize
memory into local submaps and integrate progressive mapping and tracking, loop closure, and SL(4)-based global refinement to maintain local accuracy and global consistency. A Gaussian reconstruction head decodes
memory-enhanced features into renderable primitives, unifying camera pose estimation, dense point-cloud reconstruction, and photorealistic rendering within a single model. Experiments on public
benchmarks and self-collected
datasets from diverse robotic platforms demonstrate improved trajectory accuracy, reconstruction completeness, and rendering quality over existing 3D foundation reconstruction and SLAM baselines. These results support adaptive
memory as a foundation for persistent robotic world modeling. The
dataset and code will be made publicly available at \href{https://github.com/dtc111111/AWM-3DFM}{https://github.com/dtc111111/AWM-3DFM}.
Read the full abstract ▾
All authors Tianchen Deng, Guole Shen, Yilin Shen, Wenhua Wu, Yilin Fang, Ziqi Ma, Tianjun Zhang, Shenghai Yuan, Wolfram Burgard, Hesheng Wang
Systems and Control
Model-Free Control for Residential Heating: Deployment and Simulation of Nonlinear Data-Enabled Predictive Control
Sebastian Zieglmeier, Chris Verhoek, Jaap Eising et al. (+1 more)
Residential heating accounts for a large share of building energy use, and predictive control strategies can reduce it by anticipating rather than reacting to the room temperature alone. The usual manner of implementing predictive control, model predictive control (MPC), requires an accurate model of each individual residential unit for heating control. Obtaining this model is time-consuming to obtain manually or even impossible, and such models do not transfer across a heterogeneous building stock. Data-enabled predictive control (DeePC) removes this modeling step by designing the controller directly using measured trajectories of the system. The foundations of DeePC, however, are built on the class of deterministic linear time-invariant systems, which is an unrealistic assumption for residential heating. This work applies three recently proposed nonlinear extensions of DeePC, collectively referred to as data-driven predictive control (DPC): Select-DPC, gain-scheduling DPC, and linear parameter-varying DPC. These are compared against standard DeePC and the hysteresis controller, the industry standard in residential heating. The comparison runs over a full heating season on a calibrated digital twin of an occupied research unit, the NEST research building in Switzerland, assessed by heating energy and comfort-band violation. Moreover, gain-scheduling DPC was deployed on the real residential apartment and validated the conclusions from the simulations. Each of the DPC controllers consumes significantly less energy than the hysteresis controller, amounting to roughly $11\%$ over the season, validating the use of DPC. The nonlinear methods further outperform linear DeePC in all assessed scenarios, and we analyze the relative costs and benefits of each nonlinear method.
Read the full abstract ▾
All authors Sebastian Zieglmeier, Chris Verhoek, Jaap Eising, Mathias Hudoba de Badyn
Computer Vision
VoxelTTO: Voxel-Aligned Feed-Forward 3D Gaussian Splatting with Test-Time Optimization
Yibin Zhao, Yihan Pan, Yangwen Li et al. (+2 more)
Recent feed-forward 3D Gaussian Splatting (3DGS) methods typically regress pixel-aligned Gaussian primitives, often causing excessive overlap and artifacts, while inaccuracies in predicted camera poses can lead to misalignment in novel-view synthesis (NVS). We present VoxelTTO, a feed-forward framework for reconstructing geometrically accurate 3DGS scenes from an arbitrary number of images and optional camera parameters. VoxelTTO aggregates dense image features into a global voxel representation and decodes Gaussians from voxel features, breaking the pixel-to-Gaussian correspondence. To exploit known camera parameters while keeping the pretrained visual foundation model (VFM) parameters frozen, we introduce test-time optimization (TTO) that adapts lightweight LoRA modules using pose supervision. We further replace vanilla 3DGS rasterization with
stochastic solid volume rendering during training and inference, improving
geometric fidelity. Training updates only the voxel-aligned Gaussian reconstruction modules, requiring 80 GPU hours. Experiments on Replica, Tanks and Temples, and DTU demonstrate improved RGB-D NVS and camera-pose estimation relative to prior methods.
Read the full abstract ▾
All authors Yibin Zhao, Yihan Pan, Yangwen Li, Jun Nan, Jianjun Yi
Robotics
FORTE: Task-Adaptive Force Capability Optimization for Mobile Manipulators
Xiao Wang, Heng Zhang, Gokhan Solak et al. (+2 more)
Effective physical interaction control in robotic manipulation requires not only kinematically feasible motion but also sufficient force-interaction capability. Existing redundancy resolution methods often ignore task-specific force demands or maximize the force capability indiscriminately, sacrificing dexterity when large force margins are unnecessary. We propose a task-oriented force capability optimization framework for redundant mobile manipulators. A
Vision-
Language Model (VLM) infers object physical properties from an RGB image and a task description, generating a desired task-force sequence that captures gravitational and inertial demands. We then define a task-oriented force capability metric as the signed distance between a task-force uncertainty ball and the dynamic residual force polytope (RFP), quantifying compatibility between task demands and the
robot's remaining actuation capacity. This metric is incorporated, alongside manipulability, joint-limit avoidance, trajectory smoothness, and base-oscillation suppression, into a whole-body multi-objective trajectory-optimization problem. Experiments on a mobile manipulator performing lifting and single-point-holding tasks under varying payload conditions demonstrate that the proposed method provides sufficient force capability for heavy loads while preserving high manipulability for light loads. This yields a task-adaptive balance that fixed capability-maximizing baselines (RFP inscribed radius, RFP cone) and manipulability-only optimization fail to achieve. The core implementation is publicly available at https://github.com/yeying256/FORTE.
Read the full abstract ▾
All authors Xiao Wang, Heng Zhang, Gokhan Solak, Fei Zhao, Arash Ajoudani
Social and Information Networks
Two Fault Lines: Latent Polarity Geometry in X Community Notes
Andreas Andreou and Michael Sirivianos
Community Notes is X's crowdsourced fact-checking system. A note is published beneath the post it corrects only when raters who usually disagree both rate it helpful, a design called bridging. To apply that rule, the system learns who disagrees with whom from the ratings alone, placing every rater and note on one line, the polarity axis. Every scorer in the production pipeline uses a single axis. Refitting the base model these scorers share on the full public data (212.9M ratings, 2.33M notes, 1.07M raters), we find that one axis is too few. The space is at least two-dimensional. The first axis is left/right politics, while the second, which we interpret as trust in institutions, is largely independent of the first. A held-out test confirms that the second axis improves prediction of unseen ratings, while a third adds little. A second rater dimension learned from one set of topics predicts how raters judge COVID and Ukraine notes excluded from the fit, so it does not merely restate subject matter. Among heavily rated notes that barely divide raters politically, the published share falls from 71.5% to 11.7% as second-axis disagreement grows. A one-axis fit records these notes only as weakly polarised and less helpful; the information that raters at one end of the second axis support them is lost. Authors write notes matching their own position on both axes (r = 0.538 and 0.358), and a small minority of raters cast most ratings (Gini = 0.718). Fewer notes are published in the smallest
language communities, but the shortfall is in ratings received, not in how the rule treats them. Keeping ratings per note constant, only Hindi stays below the global rate of 10.85%, and Greek moves from 7.76% to 11.68%. We argue for a bridging model with more than one axis of disagreement, and for recruiting raters in the
languages the current design reaches least.
Read the full abstract ▾
Software Engineering · Cross-listed from stat.CO
Scentree: a framework for generating scenario trees for multistage stochastic programming
Cristian Pachón-García, Albert Solà Vilalta and F-.Javier Heredia
We present scentree, an open-source Python package for constructing a scenario fan and a scenario tree for multistage
stochastic programming from historical data. It combines machine learning and multivariate time series models to obtain a scenario fan that captures inter-stage dependencies in the
stochastic processes. This scenario fan is subsequently transformed into a scenario tree suitable for multistage
stochastic optimization, providing a flexible and extensible framework for uncertainty modeling. A key contribution is the automation of the complete workflow, including model selection, parameter estimation, scenario fan generation, and scenario tree construction. Scentree does not rely on assumptions about the underlying data distribution, reducing the statistical expertise required to produce a scenario tree. Furthermore, it is agnostic to the specific multistage
stochastic problem to be solved.
Read the full abstract ▾
Artificial Intelligence
PolyBridgeBench: Benchmarking Multimodal LLMs for Physics-Grounded Bridge Design
Zicheng Zhao, Dongyin Chen, Rui Xu et al. (+1 more)
Multimodal large
language models, or MLLMs, perform well at visual understanding and structured generation, yet these capabilities do not establish whether an engineering design will work when executed. Existing
benchmarks assess spatial
reasoning, structural validity, or physics-grounded construction, but they do not determine whether MLLMs can synthesize complete load-bearing structures and repair them after simulator execution exposes a failure. We introduce PolyBridgeBench, an executable
benchmark for
multimodal bridge design. A model receives a visual scene and structured engineering constraints and generates a complete node–member–material
topology. Deterministic legality checks gate execution in a native dynamic physics simulation. Following an execution failure, the
benchmark returns temporal visual evidence from the failed rollout and evaluates repair under a fixed interaction budget. Separate measurements of deterministic validity, dynamic functional success, and post-failure recovery identify the stage at which design fails. Experiments with six representative MLLMs across 189 levels expose a substantial gap between deterministic validity and dynamic success, pronounced sensitivity to material budgets, and limited post-failure recovery under the primary strict-budget setting.
Read the full abstract ▾
All authors Zicheng Zhao, Dongyin Chen, Rui Xu, Yinghui Xu
Artificial Intelligence
LogicTrack: Auditing Reasoning Trajectories of Large Language Models with Formal Logic Solvers
Jingyu Hu, Shu Yang, Weiru Liu et al. (+1 more)
Chain-of-Thought (CoT)
reasoning has been shown to improve the performance of large
language models (LLMs), yet existing optimization methods largely rely on outcome-based feedback, leaving the logical validity of intermediate
reasoning steps largely unverified. To address the gap whereby LLMs arrive at correct final answers through logically flawed intermediate
reasoning chains, we propose LogicTrack, a neuro-symbolic framework that audits
reasoning trajectories by auto-formalizing each
reasoning step into symbolic representations and verifying it with automated
theorem provers. LogicTrack introduces Solver-Based Backtracking Reward (SBR), a step-wise scoring mechanism that quantifies logical soundness and guides backtracking tree search at inference time. We further extend LogicTrack to construct supervised fine-tuning (SFT) data with backtracking traces from its trajectories, enabling fine-tuned models to internalize step-wise
auditing as an intrinsic capability. Extensive experiments across 8
reasoning benchmarks and 7 LLMs demonstrate that LogicTrack effectively improves both the verifiability of
reasoning chains and final answer pass rate, thereby enhancing overall CoT quality and trustworthiness in high-stakes domains.
Read the full abstract ▾
All authors Jingyu Hu, Shu Yang, Weiru Liu, Di Wang
Computation and Language
Benchmarking Gender Bias in Machine Translation Evaluation Metrics across Occupations
Orfeas Menis Mastromichalakis, Giorgos Filandrianos, Wafaa Mohammed et al. (+2 more)
Gender bias remains a persistent concern in machine translation (MT), affecting both generated translations and their automatic evaluation. When a source text leaves a person's gender unspecified, translations may realize that person using masculine or feminine forms, and both MT systems and evaluation metrics may exhibit systematic preferences between these alternatives despite the source providing no basis for such a distinction. We study this behavior in the WMT 2026 Automated Translation Quality Evaluation Systems Shared Task using an occupation-balanced subset of GAMBIT+. We consider seven English-source
language pairs, six from the original
dataset, targeting Arabic, Czech, Greek, Icelandic, Russian, and Ukrainian, and extend the original resource with German. The subset contains 1,308 masculine/feminine translation pairs per target
language, with three examples for each of the 436 ISCO-08 occupational groups. We evaluate shared-task submissions and baselines for score prediction and error annotation, examining the direction, magnitude, and frequency of gender-related differences. We find an overall tendency for masculine translations to receive higher scores, as well as differences per occupation following stereotypical gender representations, although the strength and consistency of this preference vary considerably across evaluators and
languages. Our results show that gender bias remains present in MT evaluation, but that capturing its extent requires looking beyond a single aggregate measure to complementary dimensions of evaluator behavior.
Read the full abstract ▾
All authors Orfeas Menis Mastromichalakis, Giorgos Filandrianos, Wafaa Mohammed, Giuseppe Attanasio, Chrysoula Zerva
Artificial Intelligence
Driving on Registers, Reasoning on Risk: Risk-Aware Occupancy for Register-Based End-to-End Autonomous Driving
Jiaxing Chen, Hengduo Zou, YuKai Qin et al. (+3 more)
Multimodal trajectory prediction improves behavioral coverage in end-to-end autonomous driving, but existing methods remain limited by sparse scene representations. Incomplete evidence leads to low-quality candidate generation and unreliable ranking among geometrically similar trajectories. On a register-based baseline, bad and poor candidates constitute 19.74% of the candidate set, while the oracle-best candidate ranks only 33.9th on average. We propose RRDrive, which introduces risk-aware occupancy as a dense, temporally aligned, and trajectory-queryable representation. Its global structure guides high-quality
multimodal generation, while candidate-conditioned risk queries support fine-grained selection. We further construct RiskOcc4D-NAVSIM with automatic risk annotations. RRDrive achieves a selected-trajectory PDMS of 0.951, representing a 1.5% relative improvement over the baseline (0.937), and improves the average candidate PDMS by 7.7%. In challenging scenes, it improves candidate PDMS by 30.2% and increases the Spearman correlation among good candidates by 0.41, from 0.26 to 0.67. To move beyond this oracle setting, we further develop an external RiskOcc predictor, a perception module that estimates risk-aware occupancy directly from sensor inputs. The competitive performance validates the representation's feasibility.
Read the full abstract ▾
All authors Jiaxing Chen, Hengduo Zou, YuKai Qin, Yiren Zhao, Lidong Yu, Bolin Gao
Cryptography and Security
HE-Guardrail: A Homomorphic Guardrail Against Jailbreak Attacks for Encrypted Large Language Model Inference
Byeongseo Min, Yongwoo Lee, Young-Sik Kim et al. (+1 more)
Homomorphic encryption (HE) has emerged as a promising approach to
privacy-preserving machine learning (PPML), enabling computation directly over encrypted data. In HE-based PPML, a client submits an encrypted input to the server, which evaluates models such as large
language models (LLMs) without access to the underlying plaintext. However, we identify a critical security vulnerability in this setting: HE-LLM inference is vulnerable to malicious clients that submit
adversarial prompts, such as jailbreak attacks. The same confidentiality that protects benign clients also prevents the server from inspecting incoming
prompts or generated responses, making
adversarial attempts difficult to detect or block and potentially allowing successful attacks to remain entirely invisible to the server. To address this vulnerability, we propose HE-Guardrail, a framework that evaluates guardrail mechanisms entirely over encrypted data and homomorphically controls whether the target-model response is returned to the client. We instantiate HE-Guardrail with three representative guardrails - Llama Guard, JBShield, and GradSafe. Our results show that HE-Guardrail closely reproduces the decisions of the corresponding plaintext guardrails in the encrypted domain, with distinct security-efficiency-utility trade-offs.
Read the full abstract ▾
All authors Byeongseo Min, Yongwoo Lee, Young-Sik Kim, Yongjune Kim
Distributed Computing
Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap
Ziyu Huang, Yangjie Zhou, Chenhao Zhu et al. (+14 more)
Mixture-of-Experts (MoE) inference under expert parallelism (EP) turns each MoE layer into a distributed computation with costly dispatch and combine communication. State-of-the-art systems reduce this cost through communication-computation overlap, splitting the GPU's SMs for communication and computation respectively. However, this approach still leaves GPU resources wasted along two dimensions. Spatially, the best SM split is determined by each layer's routing result and varies across layers and GPUs, so fixed policies mismatch the workload and waste either NVLink bandwidth or compute throughput. Temporally, complex MoE data dependencies introduce bubbles that leave SMs idle. We present Weave, to our knowledge the first MoE overlap system that performs fine-grained dynamic SM scheduling - deciding per layer and per GPU by routing results at runtime. Once routing completes, each layer's communication and computation volumes become known; Weave exploits this predictability through a lightweight cost model running inside the persistent megakernel: a spatial scheduler partitions SMs into communication workers and computation workers to match the communication/computation throughput ratio, and a temporal scheduler coordinates the two worker groups to minimize SM idleness. On 4x H100 SXM GPUs across six mainstream MoE models, Weave achieves a 2.89x
geometric-mean MoE-layer speedup and a 1.33x
geometric-mean end-to-end speedup over five state-of-the-art baselines.
Read the full abstract ▾
All authors Ziyu Huang, Yangjie Zhou, Chenhao Zhu, Peng Yu, Zihan Liu, Jinyu Liu, Shulai Zhang, Xingxun Tang, Hongzhe Yan, Xinhao Luo, Minyi Guo, Xiu Lin, Yinghao Yu, Guodong Yang, Liping Zhang, Shixuan Sun, Jingwen Leng
Robotics
Adaptive Rollout Truncation Based on Epistemic Uncertainty for Efficient Offline World Model Training
Nikodem Sebastian Zymla, Laurin Thiele and Johannes Pitz
Accurate neural world models are central to model-based robotics, where they enable
robots to predict future states from previously observed trajectories. Multi-step autoregressive training improves long-horizon prediction, but fixed rollout horizons also increase computational cost and can amplify early training errors when the model is still inaccurate. Existing training schemes typically use the same rollout length throughout optimization, independent of the model's current predictive reliability. We propose an epistemic uncertainty-driven adaptive rollout strategy for offline world model training following an auto-curriculum training scheme. Instead of always unrolling to a fixed horizon, the model terminates autoregressive rollouts once epistemic uncertainty exceeds a threshold calibrated from a warm-up phase. We study two uncertainty
estimators: a five-head ensemble with a shared recurrent backbone and Monte Carlo Dropout. A two-stage warm-up procedure stabilizes uncertainty estimates before we enable adaptive truncation. Experiments on ANYmal-D and ANT show that ensemble-based adaptive truncation matches or improves the prediction accuracy of fixed-horizon training and the RWM-U baseline while requiring substantially fewer cumulative rollout steps. Training a world model on ANYmal-D following the presented approach reaches comparable final performance with the baselines with roughly 72% less rollout computation. These results indicate that epistemic uncertainty is useful not only for downstream policy regularization, but also for making world model training itself more compute-efficient.
Read the full abstract ▾
Computer Vision
OpenSAL360: Open-Source Crowdsourcing Platform for Omnidirectional Video Saliency Collection
Alexey Bryncev, Andrey Moskalenko, Kira Shilovskaya et al. (+2 more)
Omnidirectional
video saliency prediction plays an important role in many immersive multimedia applications, including viewport-adaptive streaming and compression, foveated rendering, mesh simplification, perceptual quality assessment. Yet progress in this area remains constrained by the cost and complexity of collecting eye-tracking data with VR headsets, which makes large-scale
dataset creation difficult to extend. We present OpenSAL360, the first open-source platform for scalable, low-cost 360{\deg}
video saliency collection. Unlike conventional VR-based protocols, it requires only a standard screen, mouse, and internet connection, enabling parallel saliency data collection from common crowdsourcing assessors without specialized hardware. We validate our collection protocol against seven well-established VR eye-tracking
datasets and conduct ablation studies on key interface, pre-, and post-processing parameters. To demonstrate the effectiveness and scalability of the proposed methodology, we collect and publicly release a saliency
dataset covering 500 omnidirectional
videos annotated by 2,000+ crowdsourcing assessors, making it, to the best of our knowledge, the largest
dataset in this field. We make OpenSAL360 publicly available at https://github.com/msu-
video-group/OpenSAL360.
Read the full abstract ▾
All authors Alexey Bryncev, Andrey Moskalenko, Kira Shilovskaya, Ivan Kosmynin, Dmitriy Vatolin
Discrete Mathematics · Cross-listed from math.CO
Integrality-Gap Bounds for Weighted Matchoids and Matroid Intersection
Yu Cong and Yajie Zhao
The weighted $k$-matroid intersection problem asks for a maximum-weight set that is independent in each of $k$ matroids on a common ground set. The natural LP relaxation optimizes over the intersection of the $k$ matroid independent set polytopes. It is conjectured that this LP has integrality gap at most $k-1$. The
conjecture is known for $k\le3$, but for $k\ge4$ the best general upper bound was $k$. We improve this bound to $k-1+1/k$. More generally, we prove that the natural LP of a $p$-matchoid has integrality gap at most $p-1+1/p$, with a deterministic LP-relative
algorithm attaining the same factor. The matchoid extension resolves the $p$-matchoid part of a
conjecture of Lee, Sviridenko, and Vondrák; projective planes give explicit tight instances whenever one of order $p-1$ exists.
Read the full abstract ▾
Information Retrieval
Adaptive Preference Modeling via Explicit Indirect Relational Learning for Personalized Fashion Matching
Shuiying Liao, Li Li and P. Y. Mok
Personalized fashion complementary recommendation requires jointly modeling user preferences and item compatibility under sparse and
multimodal data conditions. Existing approaches often capture higher-order relational signals implicitly through graph propagation or rely on direct interaction data, limiting their ability to explicitly model indirect preference and compatibility relationships. To address this limitation, we propose an Adaptive Preference with Contrastive Learning framework (APCL) that explicitly models both direct and indirect relational signals within a unified recommendation architecture. Specifically, APCL constructs indirect user-item and item-item relationships through a correlation-guided adaptive aggregation mechanism and represents them as dedicated personalization and compatibility views. To improve representation learning, we further introduce a functional view contrastive learning strategy that aligns direct and indirect preference representations and direct and indirect compatibility representations, encouraging consistency across relational contexts. By integrating
multimodal visual and textual information with explicit indirect relational modeling, APCL captures richer semantic characteristics while improving robustness in sparse-interaction settings. Experiments on two
benchmark fashion recommendation
datasets demonstrate that APCL consistently outperforms representative baseline methods.
Read the full abstract ▾
Computer Vision
MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation
Yiguang Yang, Jiankun Peng, Xiaoming Wang et al. (+2 more)
Fast-WAM shows that
video-action co-training improves control without generating future
video at inference, making the representation from a single
video diffusion Transformer forward central to action generation. However, future-observation prediction does not explicitly prioritize the future dynamics and visual structure needed for control. We present MT-WAM, which retains the original training objectives and adds complementary supervision for future two-dimensional point trajectories and visual features. A lightweight dual-stream branch copied from the
video backbone's final blocks provides target-specific processing, while a structured
attention mask prevents cross-stream
attention. Motion-stream
tokens supply additional dynamics conditions to the action expert. Future visual-feature prediction provides supervision in a feature space that captures object and spatial structure. This supervision trains the
video backbone to provide more informative visual context for action generation under changing visual conditions, without adding visual-feature-stream
tokens to action conditioning. At inference, MT-WAM uses
video and motion caches computed once per replan and skips future-
video prediction. Without additional
embodied policy pretraining, MT-WAM achieves 98.2% success on LIBERO and 73.7% on LIBERO-Plus, exceeding Fast-WAM by 23.8 percentage points on the latter. On RoboTwin 2.0 Clean2Rand, Random success increases from 6.30% to 19.40%; across four real-world tasks, average success increases from 67.0% to 77.8%.
Read the full abstract ▾
All authors Yiguang Yang, Jiankun Peng, Xiaoming Wang, Yiran Zhang, Zhibo Fang
Artificial Intelligence
Risk-Aware Occupancy for Safety-Oriented End-to-End Autonomous Driving
Jiaxing Chen, Hengduo Zou, Yiren Zhao et al. (+1 more)
Conventional end-to-end driving systems model the environment with sparse objects and lane elements. While efficient, this paradigm discards planning-critical information in crowded and occluded scenarios, particularly for unstructured obstacles, ambiguous free space, and complex interactions. We propose risk-aware occupancy, a dense BEV representation that explicitly fuses
geometric occupancy, map-derived traffic constraints, and future dynamic-
agent occupancy as complementary risk signals. Built upon this representation, we develop ROIDrive, an instance-centric end-to-end framework with a dedicated risk-aware occupancy branch. The predicted occupancy is tokenized via sliding-window sampling and injected into planning queries via cross-
attention, while temporal query consistency mitigates unreliable flickering queries. We also contribute RiskOcc4D-nuScenes, a
benchmark derived from nuScenes and Occ3D-nuScenes with four automated annotation pipelines for multi-dimensional risk supervision. Experiments on representative occupancy architectures verify the learnability and transferability of our representation. Integrated with GenAD, it reduces collision rates by 35.0% (UniAD metric) and 52.9% (ST-P3 metric), confirming the efficacy of the proposed representation modality.
Read the full abstract ▾
All authors Jiaxing Chen, Hengduo Zou, Yiren Zhao, Bolin Gao
Computer Vision
SkillIR: Evolving Scene-Aware Skills for Agentic Image Restoration
Jie Shao, Shengkai Hu, Xu Zhang et al. (+4 more)
This paper studies agentic image restoration, in which
multimodal agents coordinate specialized restoration tools to recover images affected by complex degradations. Existing restoration
agents often derive complete tool-use plans from the original degraded image or retrieve previously successful trajectories, providing limited support for adapting individual actions to evolving intermediate restoration states. We find that accepted tool executions can change the residual degradation state and, consequently, the applicability of subsequent tools. To address this issue, we propose SkillIR, a skill-guided framework that represents restoration experience as degradation-centered action evidence rather than complete tool-use trajectories. SkillIR consolidates context-dependent action outcomes into scene-aware restoration skills that characterize applicable conditions, expected effects, and attributable failure cases. Instead of prescribing a complete restoration plan, the retrieved skills guide one bounded action at a time within a verified residual-state loop: each tool output is treated as a candidate, committed only after transition verification, and followed by reassessment of the active residual degradations. After each rollout, the resulting evidence is used to create, refine, or patch dynamic skills, enabling accumulated restoration experience to improve decision-making for subsequent inputs. Experiments on synthetic and real-world multi-degradation
datasets demonstrate that SkillIR improves restoration quality and enables more reliable and effective tool use.
Read the full abstract ▾
All authors Jie Shao, Shengkai Hu, Xu Zhang, Beihang Song, Yongcheng Jing, Xu Wu, Jun Wan