Computer Vision
Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous Driving
Zhaoxin Fan, Tianbao Zhang, Wenjun Wu et al. (+5 more)
World models offer a promising paradigm for autonomous driving by predicting how traffic scenes may evolve and using such predictions to support action generation. However, existing approaches either separate future prediction from action generation or jointly predict them at the same temporal scale, making it difficult to simultaneously achieve long-horizon anticipation and responsive, observation-grounded decision making. We present Drive-HWM, a hierarchical slow–fast world modeling framework that organizes future representation prediction and action generation at complementary temporal scales. The slow world model predicts multi-step future representations to capture extended scene
evolution. To explicitly model the abundant motion dynamics in driving environments, we introduce Dynamic-Aware Latents learned through optical-flow prediction. Guided by these future representations, the fast model uses a lightweight
multimodal backbone and an autoregressive expert to jointly predict the next frame and the immediate action from the latest observation. Next-frame prediction encourages the fast model to capture imminent scene
evolution, while one-step action generation allows decisions to be continuously updated as new observations arrive. Extensive experiments on NAVSIM v1 and v2 demonstrate the strong driving performance of Drive-HWM. Comprehensive ablation studies further validate the effectiveness of the hierarchical slow–fast design, dynamics-aware future representations, and joint next-frame and action prediction.
Read the full abstract ▾
All authors Zhaoxin Fan, Tianbao Zhang, Wenjun Wu, Xiaofeng Wang, Yeying Jin, Jian Zhao, Zheng Zhu, Shuicheng Yan
Computer Vision
Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMG
Birgit Nierula, Karam Tomotaki-Dawoud, Mert Akguel et al. (+5 more)
Head-mounted displays (HMDs) fundamentally limit
emotion recognition in virtual reality (VR): by occluding the upper face, they render conventional image-based facial expression analysis incomplete, particularly for applications requiring real-time affective assessment. We address this challenge by fusing lower-face
video with facial electromyography (EMG) from the occluded upper face to classify seven emotional categories (six basic
emotions plus neutral). We introduce a synchronized
multimodal dataset from 20 participants, pairing lower-face
video with seven-channel upper-face EMG elicited by validated
emotion stimuli. Under subject-independent test, our proposed late-fusion architecture merging convolutional visual
embeddings with RBF-kernel EMG representations achieves 51% macro-F1, outperforming both image-only (41%) and EMG-only (43%) baselines. These results demonstrate that upper-face EMG provides robust complementary information under HMD-induced visual occlusion and establish a foundation for
multimodal emotion recognition in naturalistic VR environments. This approach facilitates affect-adaptive applications, including communication training and therapeutic interventions. The
dataset will be shared upon request under an ethical-use agreement.
Read the full abstract ▾
All authors Birgit Nierula, Karam Tomotaki-Dawoud, Mert Akguel, Mustafa Tevfik Lafci, David Przewozny, Anna Hilsmann, Peter Eisert, Sebastian Bosse
Robotics
Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic Planning
Muyuan Liu, Yue Huang, Zheng Liang et al. (+1 more)
Action-conditioned JEPA world models enable planning toward visually specified goals without reconstructing future pixels, yet latent prediction alone does not explicitly encourage the learned representations to retain information relevant to robotic control. We introduce an end-to-end JEPA world model that augments latent prediction with inverse dynamics (IDM) and state
alignment (SA). While inverse dynamics discourages latent collapse and makes latent transitions informative of the actions that produced them, state
alignment grounds consecutive representations in their associated physical configuration and motion. Across four
benchmark tasks, our model attains the highest success rates on TwoRoom (100%), PushT (98%), and OGBench-Cube (87%), while performing comparably to LeWorldModel on Reacher. Our ablation further shows that adding state
alignment consistently improves planning success over IDM alone across all four tasks. Although LeWorldModel, our primary baseline, attains higher average straightening on OGBench-Cube, transition-subspace analysis shows that its transition energy is concentrated in a substantially lower-dimensional subspace. Our state-aligned model exhibits a higher effective transition dimension than LeWorldModel and improves planning over IDM alone, supporting state
alignment as an effective complement to inverse dynamics for robotic planning.
Read the full abstract ▾
All authors Muyuan Liu, Yue Huang, Zheng Liang, Xiang Gao
Computer Vision
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Byeongjun Park, Byung-Hoon Kim and Hyungjin Chung
We present FlashRender, a few-step generative rendering framework that retakes a source
video along a target camera trajectory in seconds. We identify sampling-step-dependent camera control as a prominent manifestation of discretization error in existing multi-step generative rendering models and show that resolving this inconsistency substantially lowers denoising trajectory
curvature, facilitating subsequent step
distillation. To this end, we introduce Representation Transformation and
Alignment (RETA), which aligns hidden source-
video representations with target-
video features from a frozen visual geometry model. This directly encodes the
geometric transformation within the source-
video stream, enabling sampling-step-consistent camera control. We then fine-tune the model with the MeanFlow objective on the lower-
curvature denoising trajectory induced by RETA, allowing the model to more effectively address discretization error. Finally, we apply on-policy flow map
distillation to correct self-rollout errors under fixed few-step sampling. Extensive experiments show that RETA, MeanFlow, and on-policy flow map
distillation play complementary roles in few-step generative rendering. Together, they enable our approach to match multi-step baselines in
video quality and
geometric consistency at 25x lower sampling cost while achieving superior camera controllability, even under out-of-distribution target camera trajectories.
Read the full abstract ▾
Distributed Computing
JuPyLive: Seamless Migration of Jupyter Notebook Resources from Laptop to HPC
Sima Attar-Khorasani, Matthias Lieber and Siavash Ghiasvand
This work introduces JuPyLive, a migration mechanism that enables seamless transition of Jupyter notebooks between local resources of user's workstation and remote resources of high-performance computing~(HPC) environments, while preserving the user experience. JuPyLive eliminates the underlying complexities of migration process, enabling users to freely choose among available local and remote resources, directly within the familiar Jupyter notebook environment via a single click. JuPyLive leverages ElasticNotebook to manage in-
memory state migration, it automates resource allocation on HPC cluster and orchestrates required remote communication channels between the source and destination to enable a bidirectional migration. Furthermore, HPC status monitor of JuPyLive provides a live overview of available remote resources, allowing users to make informed decisions on choosing the relevant resources before initiating a migration process. The proposed fully automatic mechanism requires no code changes or configurations by the end user, nor does it demand users to learn a new syntax, instead the migration process can be intuitively initiated and monitored using visual elements from within the Jupyter notebook. By bridging the gap between local workspace and remote resources, JuPyLive offers a seamless experience for scaling local resource-intensive workflows with minimal user intervention, thus further democratizing the usage of HPC clusters among the interdisciplinary researchers.
Read the full abstract ▾
Robotics
TRaIL-Odom: Tightly Coupled Continuous Time Radar-IMU-LiDAR Odometry with Adaptive Doppler Weighting
Chiyun Noh, Turcan Tuna, William Talbot et al. (+3 more)
Existing radar-
LiDAR fusion methods rely on fixed residual weights, even though the informativeness of radar Doppler and
LiDAR geometry is scan- and direction-dependent, leading to uniform radar weighting that misallocates Doppler information across translational directions. To address this limitation, we propose two degeneracy-aware Doppler reweighting modules within a tightly coupled Radar-IMU-
LiDAR odometry framework: per-point radar reweighting and scan-wise radar gain scheduling. Since
geometric degeneracy is directional, we first identify weak translational directions from the
LiDAR geometry and reweight individual radar Doppler constraints based on their
alignment with the weak subspace. We further adjust the overall radar contribution using
LiDAR geometric anisotropy such that radar is emphasized when
LiDAR observability is poor and suppressed when
LiDAR constraints are already reliable. Across 13 evaluated sequences, TRaIL-Odom achieves state-of-the-art overall performance, with clear advantages in geometrically degenerate scenes. In ablation experiments on three degenerate sequences, combining the two adaptive weighting modules reduces RMSE ATE and RTE by 86.0% and 78.5% relative to the fixed-weight baseline. We make our code and an accompanying
dataset publicly available at https://github.com/ChiyunNoh/TRaIL-Odom.
Read the full abstract ▾
All authors Chiyun Noh, Turcan Tuna, William Talbot, Marco Hutter, Laurent Kneip, Ayoung Kim
Networking
A Semantic-Aware Multiple Access Scheme Leveraging Spatial Redundancy for Uplink-Dominant Network Services
Hamidreza Mazandarani, Masoud Shokrnezhad and Tarik Taleb
The transition toward semantic-aware communication offers a paradigm shift for next-generation mobile networks, promising to decouple information significance from raw data transmission. Despite advances in semantic extraction, the integration of semantic intelligence into the Medium Access Control (MAC) layer remains underexplored, particularly in exploiting spatial correlations among users. To address this, we introduce a novel multiple access scheme designed for uplink-dominant network services. This framework optimizes the trade-off between spectrum utilization and sustainability by formulating variable-packet-length access as distinct $\alpha$-
fairness and energy efficiency problems. A key innovation of our approach is the quantification of spatial redundancies through novel metrics of self-throughput and assisted-throughput, which account for the semantic correlation of data across user equipment. We analyze these formulations to identify optimal bounds before proposing PRISM (Protocol for Redundancy Identification in Semantic Multiple-access). Grounded in Model-free Multi-
Agent Deep Reinforcement Learning (MADRL), PRISM enables devices to autonomously govern spectrum access using only local observations. Extensive evaluations demonstrate that PRISM successfully leverages redundancies to outperform semantic-oblivious schemes, achieving up to \({90\%}\) of the centralized optimal
benchmark and improving both objectives by up to \({2\times}\) across diverse user-semantic association
matrices. These results validate PRISM as a viable candidate for future distributed mobile network applications, complemented by orthogonal Multiple Access Schemes where signals are multiplexed in the semantic domain.
Read the full abstract ▾
Computer Vision
Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation
Haoyu Wang, Songchun Zhang, Haoran Li et al. (+3 more)
Action-conditioned
video models require large-scale visual data paired with control signals that are temporally aligned with the resulting scene transitions. Such supervision is difficult to obtain from ordinary real-world
video because the actions that caused each visual change are typically unknown. We present a large-scale synthetic data production pipeline built on Unreal Engine for generating action-conditioned, multi-view
video. To accommodate the different execution requirements of real-time physics and high-quality offline rendering, the pipeline executes trajectory generation and final rendering in two stages: Stage I runs real physics in PIE and records per-frame character states, control inputs, and camera states into an intermediate trajectory representation; Stage II replays those trajectories in a new engine process and renders them offline with Movie Render Queue (MRQ). Around this core, we develop a distributed production system with cache-aware task partitioning, node-local slot scheduling, automated scene screening, aesthetic and luminance filtering, partial-output recovery, asynchronous upload, and continuous cluster health monitoring. The production cluster contains 25 servers with eight NVIDIA RTX 5090 GPUs per server. From 2,384 asset packs, 429 levels were retained for production together with a pool of 40
humanoid characters. The pipeline has produced 2,691 hours of 1080p
video and 6,076 hours of 720p
video. We describe the system architecture, the implementation decisions that emerged from production failures, and the limitations of using perceptual quality proxies for world-model data curation. The pipeline described in this report constitutes the Unreal Engine synthetic-data production component used in EchoWM.
Read the full abstract ▾
All authors Haoyu Wang, Songchun Zhang, Haoran Li, Haoyang Huang, Zeyue Xue, Nan Duan
Computer Vision
WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative Retrieval
Teng Guo, Xin Wang, Jiayou Xu et al. (+3 more)
Generative
retrieval has demonstrated significant success by unifying representation learning and search into a single sequence-to-sequence generation task. However, extending this paradigm to cross-modal
retrieval reveals a critical challenge arising from the inherent information asymmetry across different modalities, such as the gap between concise text queries and dense visual candidates. This structural mismatch causes the autoregressive decoder to suffer from forced
hallucination when generating identifiers via standard trie-constrained beam search, where the model is severely penalized for failing to guess fine-grained details absent from the query, allowing irrelevant candidates to hijack top rankings. To address this issue, we propose Wildcard Inference with Dynamic Expansion (WIDE). WIDE employs Adaptive
Entropy Thresholding (AET) to calibrate layer-specific uncertainty boundaries offline. During the decoding generation phase, Asymmetry-aware Wildcard Decoding (AWD) detects semantic blind spots and emits wildcards instead of forced deterministic identifiers, dynamically expanding the search space without incurring log-probability penalties. Finally, Blind-Spot Re-ranking (BSR) evaluates the expanded candidate pool using a hybrid scoring mechanism that combines discrete generation confidence with continuous semantic similarity. Extensive experiments on the M-BEIR
benchmark demonstrate that WIDE outperforms state-of-the-art generative
retrieval methods, effectively suppressing forced
hallucination while maintaining compact index structures.
Read the full abstract ▾
All authors Teng Guo, Xin Wang, Jiayou Xu, Keying Zhou, Jifeng Shen, Haoxin Ruan
Artificial Intelligence
GPS-Bench: A Governance Policy Benchmark for Automating Policy Analysis
Linh Le, Melanie Bui, My Chiffon Nguyen et al. (+2 more)
Policy analysis requires more than predicting whether a proposal will pass: it requires identifying who will be affected, how those actors respond, and what follows. LLM-based policy simulations model these processes at scale, but their validity is hard to establish when plausible behaviour is never compared with observed outcomes. We introduce GPS-Bench, an evidence-grounded
benchmark for governance policy simulation that links policies to relevant actors, actor actions and downstream impacts using legislative records, lobbying disclosures, regulatory documents, corporate filings, economic data and other public evidence. Actors are reconstructed from the dated record rather than prompted as archetypes, so a persona is an evidence object with provenance; a human-annotated pool forms the Gold evaluation set, while cases labelled by a separate LLM from retrieved evidence are treated as Silver supervision and never as test labels. Because every inference mode reads the same grounded state and emits the same schema, GPS-Bench turns "does multi-
agent simulation help?" into a controlled comparison: we contrast joint
reasoning, independent and communicating actor
agents, graph-based methods and weight-level fine-tuning over one policy state. Fine-tuning on the grounded record gives the strongest actor-level impact prediction, and decomposition does not beat it; what decomposition adds is mechanism.
Agents hold private, non-identical evidence, each seeing its own exposure clause, and address named partners with concrete joint proposals, what they offer, what they need in return, and why acting together beats acting alone, so the coalitions that form can be checked against the commitments the record holds. GPS-Bench therefore gives a common empirical setting for studying when evidence, actor modelling and multi-
agent interaction improve the prediction and interpretation of policy outcomes.
Read the full abstract ▾
All authors Linh Le, Melanie Bui, My Chiffon Nguyen, Zachary Schlosser, David Williams-King
Cryptography and Security
The Native-Signature Boundary in Post-Quantum Distributed Authorization
Dariia Porechna
Post-
quantum signature migration poses a distinct systems problem when authorization is distributed among multiple parties. In native threshold signing, the signature
algorithm may determine key generation, share state, preprocessing, interaction, combination, refresh, and recovery. Architectures that evaluate threshold policy outside the native signing relation can reduce this coupling, but their authorization evidence is not accepted by an unchanged native verifier unless a trusted complete-key signer translates approval into a native signature. This paper organizes that design boundary through three properties: native-signature compatibility, unilateral-signing resistance, and threshold-layer agility. We classify specialized threshold signatures, generic MPC signing, distributed hash-based constructions, programmable multisignature and dual-gate authorization, and threshold-authorized HSM signing. A migration impact surface identifies which components change with the signature
algorithm. Across the surveyed families, no design simultaneously provides native output, unilateral-signing resistance, and threshold-layer agility. This is an architectural tension, not an impossibility claim, and it clarifies why a replaceable API alone does not make distributed authorization cryptographically agile.
Read the full abstract ▾
Artificial Intelligence
Dalek: A Constructive Agent Machine
Wanpeng Xie
We present Dalek, a closed machine designed for
agents that realizes self-maintenance, self-
evolution, self-reproduction, and self-organization on any substrate satisfying a general host contract. The machine is built from three primitives—actors, messages, and channels. Four obligations—a host boundary, a construction
language, admissible transitions, and rule heredity—give its boundary, identity, and closure a structural basis. Von Neumann's 1948 self-reproducing automaton supplies a hereditary constructional core: a self-description together with a constructor, a copier, and a controller. Dalek combines this core with the four obligations and rederives its medium for a text-and-message
agent substrate, adding explicit structures for boundary, identity, history, and growth. A large
language model and a compiler occupy the payload position and form a general capability producer. New capabilities are authored, compiled, installed into the description, and inherited by descendants. The same path produces the machine's own organs and even its runtime, closing heredity and
evolution within the machine.
Read the full abstract ▾
Computer Vision
SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models
Caoyuan Ma, Tian Gu, Wenpu Liu et al. (+11 more)
Existing safety
alignment methods for
vision-
language models usually modify the model behavior globally: once the safety parameters are trained or loaded, they participate in both unsafe and already-safe generations. This always-on intervention can unnecessarily perturb the model's original
reasoning path and degrade general
multimodal capabilities. We argue that safety
alignment should be an on-demand intervention rather than a permanent modification to every decoding trajectory. To this end, we propose a streaming recognition and gated LoRA framework for intrinsic VLM safety. During autoregressive generation, a lightweight recognizer estimates whether the current pre-
token generation state is safe or unsafe. Its output updates the LoRA gate for the following decoding step; otherwise, generation follows the frozen-backbone policy. The LoRA module is trained from unsafe prefixes, transition statements, and safe continuations, so that it learns to redirect unsafe generations back to safe responses after activation. Experiments across multiple safety and general-purpose
benchmarks demonstrate the effectiveness of our method in post-
alignment settings.
Read the full abstract ▾
All authors Caoyuan Ma, Tian Gu, Wenpu Liu, Weichu Xie, Shuai Dong, Yuqi Xu, Ji Zhao, Ziyue Wang, Wenzheng Chang, Taiqiang Wu, Yongfu Zhu, Wenqi Shao, Zheng Wang, Yinqiang Zheng
Databases
Tree Databases
Nicolas Spyratos
We propose a novel database model whose basic structure is a labeled, directed tree with node identities. Intuitively, the root of the tree is seen as an object (or entity), the non-root nodes as attributes of the object and the semantics of each attribute is represented by the unique path leading from the root to the attribute. We define a tree database to be a set of such trees. The trees of the database can be combined to produce new trees using a set of operations on trees that we define in the paper. The query
language of our model offers two types of queries, traversal queries and analytic queries. A query (whether traversal or analytic) is always defined over a tree, which is either a tree in the database or a tree derived from other trees using tree operations. The operations on trees and the query
language are both defined using a simple functional
algebra whose operations are: restriction of a function, composition of functions, pairing of functions and Cartesian product of sets. A distinctive feature of our model is that traversal queries and analytic queries are both defined within the same formal framework; and in fact, traversal queries serve as the building blocks for analytic queries. This is in sharp contrast to the relational model, where analytic queries are defined outside the relational
algebra, in the form of SQL Group-by queries. Therefore our model supports data access and data analysis within the same formal framework. We demonstrate the expressive power of our model by showing: (a) how our model can support inheritance in a seamless manner, (b) how one can define consistent relational databases on top of a tree database - with the tree database playing the role of an underlying semantic layer and (c) how a tree database can be used as a user-friendly interface for accessing and analyzing relational data.
Read the full abstract ▾
Artificial Intelligence
Feature Reconfiguration With Visual Prior for Medical Lesion Segmentation
Yinan Liu, Jiankang Hong, Zhen Gao et al. (+1 more)
Lesion
segmentation in medical images plays a critical role in clinical diagnosis and treatment planning. Despite significant advances, lesion
segmentation remains challenging due to two major factors: (1) complex background interference; (2) diverse lesion morphology. Existing encoder-decoder based methods mainly focus on enhancing feature extraction or redesigning decoding strategies. However, they lack early prior guidance and feature reconfiguration during the encoding stage, limiting their effectiveness in handling these challenges. To address these limitations, we propose FreNet, a feature reconfiguration framework with visual priors, which performs pixel-level reconfiguration before encoding and feature-level reconfiguration during encoding for precise medical lesion
segmentation. To suppress background responses, we propose an Implicit Prior Neural Network (IPNN), which models a continuous spatial field and leverages visual prior from SAM to reconfigure input image before encoding stage. To better handle diverse lesion morphology, we design a Dual-domain Feature Reconfiguration (DFR) module to progressively reconfigure backbone features during encoding stage. Within DFR, the Frequency Decoupling Module (FDM) decouples backbone features in frequency domain to enhance foreground-background discriminability, while the Spatial Localization Module (SLM) spatially relocates and improving spatial stability after frequency decoupling. Extensive experiments on 9 medical image
segmentation benchmarks across three imaging modalities demonstrate that FreNet significantly outperforms state-of-the-art (SOTA) methods. On the challenging ETIS
dataset, our method achieves Dice improvements of 5.0% over SOTA method and 7.2% over SAM.
Read the full abstract ▾
All authors Yinan Liu, Jiankang Hong, Zhen Gao, Ye Luo
Computer Vision
TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates
Theo Morales, Nhat-Quynh Le-Pham, Robin Atkins et al. (+1 more)
3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robustly learning 3D Gaussian primitives from visual input remains challenging. Standard optimization relies on gradient-based updates, but a common issue is the gradient vanishing phenomenon: a pixel far from a Gaussian primitive often has diminishing gradient magnitudes to influence primitive attributes, resulting in suboptimal scene reconstruction. In this paper, we propose a method to address gradient vanishing with a piecewise truncated gradient formulation that improves the optimization stability and robustness to initializations. We show that our method consistently improves 3D Gaussian Splatting with random and COLMAP initializations while being generalizable across static and dynamic Gaussian Splatting. As a by-product, we also examine the limitations of current
benchmarks for dynamic scenes, and introduce a novel
dataset for benchmarking dynamic Gaussian Splatting using synthetic 3D scenes. We demonstrate the effectiveness of our method in both static and dynamic settings for the public
benchmarks and our proposed
dataset.
Read the full abstract ▾
All authors Theo Morales, Nhat-Quynh Le-Pham, Robin Atkins, Binh-Son Hua
Machine Learning
Coupled Scaling: A Representational Accessibility Framework for Neural Scaling Laws
Jie Wang
We ask when two learning systems trained on the same task under a common resource protocol should share a scaling rate and when their rates should differ. Coupled Scaling answers this through representational accessibility: the task-relevant geometry that a specified architecture-optimization system can reach and how that geometry is acquired as resources grow. In an orthogonal model, unsupported target energy sets the asymptotic floor, while unacquired supported energy sets the finite-budget residual. When acquisition can skip high-value directions, the largest fully acquired prefix no longer determines a unique exponent. For target powers $a_j \asymp j^{-b}$, $b>1$, and prefix log-growth rate $0<\rho\leq1$, the sharp attainable interval is $[\rho(b-1),\min\{b-1,\rho b\}]$, and every rate in this interval is realized by a fixed acquisition order on a common support. A rank-window condition identifies when the product law $\alpha=\rho(b-1)$ applies, while a fixed-kernel specialization expresses the same task-system dependence through the task-weighted spectral tail. We then audit released capability trajectories to diagnose measurement and comparison effects and propose a staged test in which independently measured geometry predicts held-out loss, scaling rates, and cross-task reversals.
Read the full abstract ▾
Systems and Control · Cross-listed from math.OC
Beyond Higher-Pulse Rectification: Operational Harmonic Coordination in Renewable P2H Systems
Yangjun Zeng, Yiwei Qiu, Jie Zhu et al. (+6 more)
Thyristor rectifiers (TRs) are cost-effective electrolysis power supplies for renewable power-to-hydrogen (ReP2H) systems, but their harmonics may violate grid-code limits. In contrast to conventional solutions that rely on higher-pulse (such as 24-pulse) rectifiers, this paper proposes an operational harmonic coordination scheme that enables low-cost 12-pulse TRs to meet harmonic requirements through coordinated operation. First, a harmonic model quantifies the effects of rectifier
transformer (RCT) tap positions and electrolytic currents, enabling harmonic cancellation among multiple electrolyzers (ELZs). A two-layer framework then coordinates hydrogen production and harmonic mitigation. Hourly scheduling determines ELZ commitment within the harmonic feasible region under renewable uncertainty using
stochastic programming and a modified progressive hedging
algorithm, while minute-level dispatch tracks renewable power and mitigates harmonics. A decomposition
algorithm separates production dispatch from harmonic mitigation to improve computational efficiency. Case studies based on real-life projects show that the proposed method increases profit by 31% over current-only regulation. Annual simulations further show that coordinated 12-pulse TRs can replace 24-pulse rectifiers for harmonic compliance by exchanging additional RCT tap actions for lower
transformer investment, reducing rectification-stage cost by 37.5%.
Read the full abstract ▾
All authors Yangjun Zeng, Yiwei Qiu, Jie Zhu, Yi Zhou, Tao Wu, Xin Meng, Shi Chen, Buxiang Zhou, Kaigui Xie
Databases
KnowFeat: Knowledge-Guided Feature Engineering via LLM Agents
Chengsong You, Wangyue Li, Weiqiao Que et al. (+5 more)
Automated feature engineering with large
language models (LLMs) can produce semantically meaningful features for tabular data, yet existing methods lack structured domain knowledge, rigorous verification, and explainable provenance. We propose KnowFeat, a knowledge-guided feature engineering framework that organizes domain knowledge into five types – schema metadata, regulatory indicators, detection rules, expert opinions, and court document evidence – and injects them as structured context into an LLM
agent. A three-stage verification pipeline filters candidates through code execution, statistical quality checks, and model effectiveness evaluation. Every accepted feature carries a provenance record tracing its design to specific knowledge assets. Under a strict held-out protocol that eliminates feature-selection leakage, KnowFeat ranks first (avg. rank 2.3) across twelve public
benchmarks among seven methods (one-sided Wilcoxon p=0.017), with a peak gain of +11.6 pp AUC on a telecom churn
dataset. On a real-world Bitcoin anti-money laundering (AML)
dataset (
Elliptic) and a synthetic digital currency AML
benchmark (SimECNY), KnowFeat maintains competitive detection performance with full provenance traceability.
Read the full abstract ▾
All authors Chengsong You, Wangyue Li, Weiqiao Que, Qizhou Chen, Kunyan Wu, Wei Deng, Feng Zhu, Xiaofeng He
Machine Learning
LeanGRPO: Eliminating Redundant Recomputation in Diffusion RL
Sijie Wang, Zhiqiang Tan, Xinrui Yang et al. (+1 more)
Diffusion reinforcement learning (RL) has recently achieved significant success in post-training image and
video generative models. However, most
diffusion RL methods, including DanceGRPO and FlowGRPO, recompute selected timesteps with gradient tracking after rollout. Under on-policy training with the same backend for rollout and update, this recomputation is mathematically redundant. Intuitively, the rollout and policy update steps can reuse the same feed-forward backbone to avoid redundant computation, but doing so can incur a large
memory overhead during rollout. To address the issue, we present LeanGRPO by restructuring the data-parallel layout and introducing two recompute-free training schedules for trajectory-logprob
diffusion RL: (1) LeanGRPO-Retain enables gradient tracking during rollout and directly reuses the resulting computation graphs and saved activations for backward during update, requiring no recomputation; and (2) LeanGRPO-Reweight also enables gradients during rollout, but immediately backpropagates each selected step using a provisional advantage and delays gradient synchronization, then corrects the provisional gradients with the true advantage after the trajectory is completed. These schedules target different model scales and input sizes. Across FlowGRPO/DanceGRPO with FLUX.1-dev and Wan, LeanGRPO achieves up to 1.83x end-to-end speedup while preserving the original optimization objective.
Read the full abstract ▾
All authors Sijie Wang, Zhiqiang Tan, Xinrui Yang, Shaohuai Shi
Artificial Intelligence
NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease Diagnosis
Yinan Liu, Hongtai Xia, Haoran Xu et al. (+4 more)
Neonatal respiratory diseases are a major cause of neonatal morbidity and mortality, posing substantial challenges in clinical practice. Despite recent advances, existing
Multimodal Large
Language Models (MLLMs) face two key limitations in neonatal diagnosis: (1) domain gap arising from predominantly adult training data; (2) insufficient integration of multidimensional clinical context for accurate diagnosis. To address these challenges, we collect two real-world clinical
datasets (NeoCXR and NeoCXR-EV) and propose NeoRed, to the best of our knowledge, the first MLLM tailored for neonatal respiratory disease, filling the gap in neonatal diagnostic reports generation. To enhance joint diagnosis from heterogeneous clinical context and chest X-rays, we design a novel Knowledge-Logic-
Alignment (KLA) framework which constrains model behavior from three perspectives: 1) Knowledge Prior Injection (KPI) incorporates neonatologist-inspired diagnostic priors into
multimodal representations, guiding disease-specific
attention across modalities; 2) Diagnostic Logic Constraint (DLC) aligns the semantics of generated reports with
multimodal diagnostic logic; and 3) Visual Semantic
Alignment (VSA) establishes semantic correspondence between visual features and imaging conclusions. Extensive experiments demonstrate that NeoRed enables accurate neonatal diagnostic reports generation, achieving ROUGE-L of 53.29% and Clinical Efficacy F1 score of 65.19% on NeoCXR, outperforming existing MLLMs. NeoRed also preserves competitive report generation performance on adult
benchmarks (MIMIC-CXR and IU-Xray).
Datasets will be available upon application.
Read the full abstract ▾
All authors Yinan Liu, Hongtai Xia, Haoran Xu, Jiankang Hong, Yu Jianli, Jingkuan Song, Ye Luo
Artificial Intelligence
CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary Reasoning
Bo Zeng, Linfeng Gao, Peiqin Lin et al. (+9 more)
Multimodal language models achieve near-ceiling scores on food recognition
benchmarks, yet it remains unclear whether this success reflects genuine cultural understanding or mere visual matching. To probe this distinction, we introduce CulturalMenuBench, a
benchmark of 4,870 items in 10
languages across 18 regions; its 10 tasks pair final-dish and step-by-step cooking images with ingredients, procedural text, and regional labels, spanning basic recognition to process-grounded cultural attribution. Evaluating 12 models exposes a substantial knowledge-application gap: models exceeding 94% on standard multiple-choice tasks drop to at most 56% when attributing dishes to Chinese regional cuisines, despite an identical four-way format. Diagnostic analyses explain why: error patterns are consistent with random guessing, accuracy tracks visual distinctiveness rather than cultural structure, and models classify cuisines more accurately from dish names alone than from images (+7-18 points). The knowledge is thus present but cannot be activated through visual input. An ablation confirms these tasks genuinely require procedural evidence: removing sequential cooking images selectively degrades process-grounded tasks while others remain stable. Overall, CulturalMenuBench shows that near-perfect recognition can conceal an inability to apply cultural knowledge, motivating training that explicitly connects perception, procedure, and cultural context. Code and data are publicly available.
Read the full abstract ▾
All authors Bo Zeng, Linfeng Gao, Peiqin Lin, Yu Zhao, Mingyan Zeng, Yu Tong, Xintong Wang, Linlong Xu, Longyue Wang, Weihua Luo, Qinggang Zhang, Jinsong Su
Information Retrieval
EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion Recommendation
Tuan-Binh Tran, Thanh Tam Nguyen, Quoc Viet Hung Nguyen et al. (+3 more)
Semantic ID (SID) generative recommendation predicts the next item by generating a short tuple of discrete
tokens. Recent masked-
diffusion methods improve this process through bidirectional context and flexible decoding, yet recommendation ultimately requires selecting among complete catalog items. At each denoising step, a partial SID can correspond to multiple feasible items, while existing methods primarily reason through position-wise
token predictions. We propose Explicit Posterior Item Conditioning (EPIC), which introduces explicit item-level competition into SID denoising. EPIC constructs a personalized posterior over feasible candidate items using the current generation context and the user's recent interactions, then projects this distribution back to unresolved SID positions to guide subsequent
token decisions. The pretrained backbone remains frozen and requires no additional decoder forward pass. Experiments on four Amazon
benchmarks show consistent improvements over strong baselines, while diagnostic analyses indicate that the gains primarily arise from personalized transition evidence that preserves promising item hypotheses during denoising.
Read the full abstract ▾
All authors Tuan-Binh Tran, Thanh Tam Nguyen, Quoc Viet Hung Nguyen, Dung D. Le, Tung Kieu, Thanh Trung Huynh
Computer Vision
Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware Fusion
Chuyue Shan, Songlin Sun, Wang Chenwei et al. (+1 more)
In conditional coding-based neural
video compression, the quality of temporal context directly affects compression per- formance. Existing methods mostly construct context from prop- agated reference features, but they are vulnerable to motion esti- mation and local
alignment errors in regions with complex mo- tion, occlusion, and high-frequency textures, resulting in inaccu- rate temporal information. To address this issue, this paper pro- poses a method combining deformable temporal
alignment and difference-aware spatial selective fusion. A Context-aware Tem- poral
Alignment Module is used to generate complementary tem- poral context, while a Difference-aware Spatial Selective Fusion module adaptively selects reliable temporal information and sup- presses misalignment. Experiments show that the proposed method achieves certain rate-distortion performance improve- ment over DCVC-DC.
Read the full abstract ▾
All authors Chuyue Shan, Songlin Sun, Wang Chenwei, Shen Zihan
Computer Vision
Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object Detection
Yue Zhao, Hua Yu, Yukun Zhao et al. (+6 more)
Infrared-visible object detection (IVOD) integrates complementary evidence from visible and infrared sensors for reliable perception in challenging scenes. In practice, sensors may fail or drop frames, leaving one modality unavailable or intermittent. Existing methods for IVOD assume both modalities are always present, and fixed fusion collapses when one stream is missing. Furthermore, it remains a critical challenge to reliably estimate semantic correlation across heterogeneous modalities, especially under spectral distribution discrepancy. We present FlexibleFusion, a unified and adaptive method that flexibly allocates integration pathways and fusion strength, operating seamlessly across complete and missing-modality regimes. At its core, the Modality-Aware Experts Collaboration (MAEC) mechanism selectively activates and aggregates cross-modal or intra-modal expert pathways. It allows cross-modal fusion when full modalities are available and falls back to self-fusion under missing conditions. Additionally, we design Residual Self-Paced Entropic Optimal Transport (RSPEOT) to align heterogeneous feature distributions from a transport perspective. Instead of relying on the fixed sparsity coefficient in standard entropic optimal transport (EOT), RSPEOT introduces a residual-driven self-paced update that prioritizes reliable matches and progressively refines harder ones. This design alleviates the additional optimization burden of standard EOT while preserving reliable semantic
alignment. Comprehensive experiments under complete and missing-modality protocols show consistent performance across arbitrary modality configurations. Code will be released upon publication.
Read the full abstract ▾
All authors Yue Zhao, Hua Yu, Yukun Zhao, Yuzhi Zhang, Maoguo Gong, Xin Mei, Zhuping Hu, Yanchi Li, A. K. Qin
Artificial Intelligence
What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking Preservation
Bo Zeng, Yu Zhao, Yefeng Liu et al. (+3 more)
Decoding-time KV cache compression research focuses heavily on designing better
token scoring functions, while the temporal rule that aggregates scores across decode steps is often treated as an implementation detail. Under aggressive KV compression, we find that exponential-moving-average (EMA) aggregation makes approximately order-preserving scorer modifications largely indistinguishable at the eviction-set level. Value-norm and
entropy variants remain highly correlated with
attention and produce nearly unchanged retention sets, whereas KeyDiff, key norm, recency, and a learned scorer alter the ranking and degrade substantially. We associate this stability with the evaluated aggregation, which couples layer weighting and temporal retention. Building on this observation, we introduce InertiaKV, an EMA-based decoding-time eviction method, and InertiaKV-Lazy, its periodic-refresh variant, which yields 1.34-1.46x decode throughput relative to full refresh InertiaKV. We also study Score-Free decoding as a separate empirical operating point: it scores the full context once at the first decode step, freezes that ranking, and incurs an average quality change of +0.03 while removing all subsequent scoring. Across six open-weight backbones and the LongBench, LongBench-v2, and RULER
benchmarks, the results identify temporal aggregation and ranking preservation as distinct, consequential design factors; they do not imply that scoring quality is irrelevant in general.
Read the full abstract ▾
All authors Bo Zeng, Yu Zhao, Yefeng Liu, Zhihong Lu, Xuanfan Ni, Xintong Wang
Computation and Language
Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving Perturbations
Karthika Nhayakkat, Rajat Verma, Maharaj Brahma et al. (+4 more)
Large
Language Models (LLMs) demonstrate strong
multilingual reasoning performance, yet their robustness to semantics-preserving structural variation remains underexplored, particularly for relatively free word-order
languages. We investigate the structural sensitivity of
multilingual LLMs using two linguistically grounded perturbation settings in Hindi and Malayalam: constrained constituent reordering and active-passive voice transformation. We introduce a
benchmark dataset IndicReStruct, with two variants, GSM8K-Reordered and GSM8K-Voice, constructed from GSM8K while preserving semantic meaning. Across six state-of-the-art LLMs and multiple prompting strategies, we observe consistent and significant degradation in mathematical
reasoning performance under structurally perturbed inputs. To further understand these failures, we perform qualitative error analysis and mechanistic interpretability experiments using residual-stream activation patching. Our analyses show that
reasoning failures frequently arise from disruptions in entity-quantity
alignment and that intermediate
transformer layers contribute most strongly toward
reasoning restoration. Overall, our findings suggest that current
multilingual LLMs remain highly sensitive to surface syntactic realization and lack robust compositional invariance under structurally different but semantically equivalent inputs.
Read the full abstract ▾
All authors Karthika Nhayakkat, Rajat Verma, Maharaj Brahma, Vetcha Gnana Mahesh, Maunendra Sankar Desarkar, Ganesh Ramakrishnan, Rohit Saluja
Computational Complexity · Cross-listed from math.OC
The Complexity of Recognizing SDP Exactness for the Maximum Cut Problem
Avinash Bhardwaj
The standard semidefinite programming (SDP) relaxation of Max-Cut is exact when its optimum equals the maximum cut value. Delorme and Poljak resolved NP-completeness of recognizing exactness for weighted graphs and left the unweighted case open. We show that recognition is NP-complete even for connected simple unweighted graphs, and hence strongly NP-complete for nonnegative integer edge weights. The reduction provides an explicit SDP optimum and makes the additive integrality gap equal to the minimum number of unsatisfied clauses in the source formula. Recognition remains NP-complete even when an exact rational optimal primal–dual pair is supplied. We also establish strong NP-hardness of recognizing exactness of the Frieze–Jerrum Max-$k$-Cut relaxation for every fixed $k\ge3$, even for connected graphs with nonnegative integer edge weights. An independent bounded-weight construction gives a second proof for Max-Cut. Finally, reductions preserving the additive gap up to explicit factors establish strong NP-completeness of exactness recognition for a basic Max-DiCut SDP and NP-hardness for a Max-Bisection SDP.
Read the full abstract ▾
Machine Learning
LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling Dialogues
Jiayi Li, Bingsheng He and Zhaomin Wu
Large
language models (LLMs) are increasingly used to assess depression in counseling conversations, where psychology evidence suggests that tracking change across sessions matters more than any single score. However, existing dialogue
benchmarks score each session on its own, and an accurate score for every session does not guarantee that a method follows the changes between sessions. We introduce LongCounsel-8, a
benchmark for tracking depression across counseling sessions. Its systematic pipeline takes client profiles from real counseling cases, depression scores from real longitudinal data, and turn length and form from real counseling dialogues, yielding 7,749 five-session trajectories from three LLMs. Every session is generated to express a preset score on the PHQ-8, a standard eight-symptom depression questionnaire. Validation shows that the labels are self-consistent and the dialogues close to real counseling. Following clinical research on treatment monitoring, we propose a trend-based evaluation protocol reflecting real-world tracking needs: changes between sessions, crossings of the screening cutoff, trajectory types, and symptom-level changes. Extensive experiments show all five existing methods tested fall short in tracking trends: none estimates changes better than a no-change baseline, at most 40% of cutoff crossings are detected, and adding earlier sessions lowers change error but causes more missed improvements.
Read the full abstract ▾
Machine Learning
An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic Data
Mahshid Rezakhani, Tolunay Seyfi and Fatemeh Afghah
Anomaly detection in Internet of Things (IoT) networks presents unique challenges due to the diversity of devices, lack of labeled data, and domain variability across environments. In this paper, we propose a novel framework for multivariate time-series anomaly detection that leverages
adversarial learning and contrastive loss within a sequence-based Variational Autoencoder (VAE) architecture. Our method enables zero-shot domain adaptation by jointly optimizing domain-invariant latent representations and semantically structured
embedding spaces, without requiring labeled data or raw feature transfer. To address the heterogeneity of IoT deployments, we introduce encoder and decoder adaptor layers that align feature distributions across domains while preserving contextual semantics. Additionally, we propose a destination-based
segmentation strategy to better model real-world communication structures in IoT traffic. Our framework is comprehensively evaluated on six distinct
datasets spanning industrial, enterprise, general-purpose, smart home, and military automation domains across 44 transfer scenarios. Experimental results demonstrate strong zero-shot generalization in several cross-domain settings and competitive performance against a contrastive domain-adaptation baseline under realistic, heterogeneous, and
privacy-constrained IoT conditions.
Read the full abstract ▾