Networking
CALM-5G: Event-Level Conformal Risk Control for Predictive Service-Assurance Alarms
Ömer Faruk İşcanl{\i} and Yağmur Sabucu Sandal
Predictive service assurance converts forecasts of key performance indicators into alarms, and that conversion decides whether the assurance function is deployable. We present CALM-5G, an assurance layer that operates above any forecasting backbone and issues alarms with distribution-free, finite-sample guarantees. It calibrates on service-level violation events, scores violation onset directly, selects its calibration scheme out of sample, and reports the alarm duty cycle with every certified miss rate. Four corpora are evaluated separately, namely a production cellular network, commercial 5G traces, an open
radio access network testbed and our 5G standalone testbed. Risk control on the regression-derived score yields duty cycles of 0.24 to 0.91. Onset targeting with cross-validated calibration reduces time-in-alarm by 56.3% to 89.7% on three corpora, with no significant change on the fourth. The realised miss rate stays within a two-standard-error tolerance on three corpora and within one standard error of it on the fourth. Under label shift, pooled batch calibration exceeds that tolerance structurally, by 10.9 standard errors on the production corpus. Online calibration restores compliance. Calibration schemes cannot be ranked on the split that fits their thresholds. Miss rate and duty cycle are certified jointly where within-entity dependence leaves sufficient calibration units.
Read the full abstract ▾
Networking
Shortcut in Generalization: Rethinking Evaluation Protocol for Encrypted Traffic Classification
Qiming Yu, Chungang Lin, Zhengyi Ma et al. (+4 more)
Encrypted traffic classification is commonly evaluated under a range of experimental protocols, with classification performance reported as the primary measure. However, the reported performance may be influenced by shortcuts left uncontrolled in the evaluation protocol, such as shortcut features and cross-partition sharing, rather than reflect generalizable traffic patterns. And test-only feature transformations may further introduce train-test mismatch. In this paper, we study how current evaluation protocols are affected by shortcut-related factors, including field-level shortcuts, cross-partition sharing, and train-test processing. We compare feature importance, retrained feature removal, and field-only split sensitivity. We also vary Source-IP overlap and packets per flow, compare test-only IP transformations with matched train-test transformations. Experiments on three public
datasets show that the performance of existing methods are affected by both cross-partition sharing and the consistency of train-test transformations. Specifically, increasing Source-IP overlap from 0% to 100% raises accuracy by about 32-33 points before identifier masking, compared with only about 8 points after masking. For two state-of-the-art pretrained models (i.e., YaTC and NetMamba), the 11-13 points loss caused by test-only IP zeroing is almost fully recovered when the same transformation is applied during both training and testing.
Read the full abstract ▾
All authors Qiming Yu, Chungang Lin, Zhengyi Ma, Zijia Song, Yuliang Lu, Guozheng Yang, Dongzhen Qi
Computation and Language
Xibo Ding, Guoxia Wang, Jinle Zeng et al. (+4 more)
The design of
attention mechanisms in long-context large
language models faces an “impossible triangle” among KV cache size, training and prefill FLOPs, and model quality. GQA achieves strong quality but incurs high KV cache overhead; alternative approaches such as MLA and MFA can compress the cache, but MLA suffers from quality loss while MFA substantially increases training and prefill compute. We propose Virtual Head
Attention (VHA), which simultaneously improves all three vertices through two lightweight linear operations: Q Premix applies a near-identity transformation to queries within each KV group to recover virtual head diversity from halved physical query heads, and Linear Postmix fuses inter-head features via a low-rank $I + AB^\top$ residual structure. Since VHA introduces no nonlinear operations, Premix can be folded into the query projection and Postmix into the output projection at inference time, reducing the model to a standard GQA-2 architecture that directly reuses all existing GQA inference optimizations. With only two KV heads, the group size in large models readily reaches 64, fully exploiting Tensor Core parallelism during decoding. Across four scales with 4K-context 50B-
token pretraining, VHA consistently surpasses the standard GQA baseline at every scale ($+$0.05% to $+$0.81%), while reducing KV cache by $4\times$ vs.\ GQA-8 at dense scales and $2\times$ vs.\ GQA-4 at the MoE scale, and lowering training and prefill FLOPs by 7.9% (1.7B, $S{=}4096$). On an industrial 30B-A3B MoE model trained on 500B
tokens at 8K context, VHA outperforms both MLA and GQA-4 by $+$0.70\,/\,$+$2.60\,% on a 12-
benchmark base-model evaluation suite; in a separate matched 10B-A1B MoE comparison after long-context mid-training, VHA attains an average RULER score of 84.4 over 8K–128K versus 73.0 for GQA, while using two rather than four KV heads in the full-
attention layers.
Read the full abstract ▾
All authors Xibo Ding, Guoxia Wang, Jinle Zeng, Jiabin Yang, Sirui Tao, Chao Yang, Dianhai Yu
Data Structures and Algorithms
Mining Correlated Motifs with Wildcards in PPI Networks: Exact and Optimal
Lucas P. Oliveira, Ben Bals, Aalt D. J. van Dijk et al. (+1 more)
A
protein-
protein interaction (PPI) network is a graph whose nodes are
protein sequences and whose edges represent physical interactions between
proteins. Correlated Motif Mining (CMM) seeks pairs of sequence motifs whose co-occurrence in interacting
proteins reveals binding sites and interaction mechanisms. Formally, in the $(\ell,d)$-CMM problem, we are given a graph $G=(V,E)$, with $V\subseteq\Sigma^*$ for an alphabet $\Sigma$, and integers $0\leq d<\ell$, and we seek a pair $\{X,Y\}$ of motifs, each of length $\ell$ and containing $d$ wildcards, that maximizes a support measure $f(G,\{X,Y\})$; e.g., the count $f_E$ of edges $\{u,v\}\in E$ such that $X$ matches a substring of $u$ and $Y$ matches a substring of $v$, or vice versa. Although existing approaches have produced biologically meaningful results, they are either inefficient or heuristic-based, as the underlying optimization problem is NP-hard. Here, we revisit $(\ell,d)$-CMM. For $d=0$, we give an exact $\mathcal{O}(N^2)$-time and $\mathcal{O}(N)$-space
algorithm, where $N$ is the total length of the node strings, and prove that this time is conditionally optimal under the Strong Exponential-Time Hypothesis. For any $d>0$, we give an exact $\mathcal{O}\!\left(\binom{\ell}{d}^2N^2\right)$-time and $\mathcal{O}(N)$-space
algorithm, and observe that the problem is W[1]-hard parameterized by $d$. The latter
algorithm improves the state of the art by exponentially large factors in both time and space. We further demonstrate experimentally that our
algorithms are practical on real-world PPI networks and find significantly higher-scoring motif pairs than the state of the art. Moreover, we show that our
algorithms find many top-scoring motif pairs that the state of the art misses entirely. Taken together, our results suggest that exact CMM with wildcards is more tractable in practice than previously assumed.
Read the full abstract ▾
All authors Lucas P. Oliveira, Ben Bals, Aalt D. J. van Dijk, Solon P. Pissis
Machine Learning · Cross-listed from stat.ML
Learning Distributions from Samples and Qualities
Marc Jourdan and Nicolas Flammarion
We study parameter estimation when each sample from a continuous parametric distribution is accompanied by a binary quality label governed by the same unknown parameter. By imposing hard feasibility constraints, deterministic labels can accelerate estimation from the classical $n^{-1/2}$ rate of smooth quality-aware M-
estimators to $n^{-1}$. Combining PAC guarantees with local error-to-parameter conversions, we establish this rate for both identifiable and finitely ambiguous quality classifiers, with likelihood information resolving the latter ambiguity. When the quality model is known only up to an additive constant, we construct threshold-free pairwise preferences from oppositely labeled samples and retain the accelerated rate despite the unknown threshold. We further show that pointwise qualities and pairwise preferences are incomparable: either can be strictly more informative than the other. Our assumptions hold for Gaussian, Laplace, and exponential families under thresholded log-likelihood rewards. Finally, a minimax lower bound establishes the optimal $n^{-1}$ dependence on sample size, up to logarithmic and dimension-dependent factors, while experiments confirm the benefits of constraint-based estimation.
Read the full abstract ▾
Computation and Language
Agent-Reflex: Teaching Language Agents to Act Reflectively
Guanting Dong, Xinyu Yang, Jiajie Jin et al. (+9 more)
Large
language models have evolved from single-turn chatbots into interactive
agents capable of long-horizon
reasoning. In real deployments, MCP tool services can return noisy feedback and users may intervene to correct the
agent, but existing methods provide limited supervision for reflection learning and failure recovery. To bridge this gap, we propose
Agent-Reflex, a general training framework for incentivizing proactive reflection in
agents. Specifically,
Agent-Reflex comprises three stages. First, Environment Reflection Skill Discovery (RSD) injects grounded tool-feedback perturbations into environment scaling, samples a capability-diverse LLM pool, mines matched success-failure pairs, and summarizes reusable reflection meta-skills. Building on this skill library, we then apply Reflective Supervised Fine-Tuning (ReSFT) that converts each skill into supervision for self-reflection, skill recovery, and user-centric correction, strengthening complementary reflective behaviors. Finally, we propose On-Policy Reflective Policy Optimization (ORPO) to combine agentic reinforcement learning under noisy interactions with reflection-guided on-policy
distillation to further elicit proactive reflection. Built on Qwen3-8B,
Agent-Reflex reaches 58.6 overall on five long-horizon tool-use
benchmarks and 29.1 on AgentNoiseBench, surpassing strong environment-scaling and reflection baselines. Experiments on six challenging
agent benchmark suites demonstrate the effectiveness of
Agent-Reflex. Further analyses show that
Agent-Reflex improves
agents' robustness to noise while maintaining stable training dynamics, supporting scalable
agent training. Our code is available at https://github.com/RUC-NLPIR/
Agent-Reflex.
Read the full abstract ▾
All authors Guanting Dong, Xinyu Yang, Jiajie Jin, Yuyang Hu, Xiaoshuai Song, Yifei Chen, Xiaoxi Li, Jiejun Tan, Yutao Zhu, Tat-Seng Chua, Ji-Rong Wen, Zhicheng Dou
Cryptography and Security
Standing, Not Truth: Who May Say What About Whom in Agentic Selection
Yedidel Louck, Amit Dvir and Ariel Stulman
Software
agents increasingly choose on a user's behalf among competing offerings described by the parties who benefit. A lawful participant, publishing under its own identity, compromising no channel and issuing no instruction, can move that choice with a single false factual claim about a competing offering. Across twelve published defenses spanning the three placements a check can occupy, none separates it from marketing. Each accepts it for a reason correct on its own: its origin is a lawful channel, its influence is evidence meant to decide, its action serves the user's goal. None establishes that the publisher was entitled to speak about a competitor, each exclusion stated by the defenses' own authors. Disclosure does not replace enforcement: re-rendering every description as attributed
speech leaves the attack at 72/72, the
agent repeating the attribution and
reasoning from it. The missing relation is standing: whether a claimant's bound identity entitles it to assert about a claim's subject. A publisher may say what its own package does. It has no standing to say a competitor's package is frozen, and the difference is decidable without settling whether either is true. Deciding it needs the one fact prose extraction does not recover, who spoke, which a catalogue binds to every entry and then drops. The check is quiet on honest traffic, flagging 0.9% of natural pairs in two corpora. Used as a gate it stops 130 of 131 landed attacks and disturbs none of 348 honest selections. Applied everywhere it changes 0.9% and 2.6%, where deleting the whole description changes 12.7% and 21.0%. On thirteen further
agents the attack succeeds on 50.7% of decisions and sentence removal leaves 10.3% standing. Two published attacks stay outside: self-directed claims, which standing admits, and injected criteria, with no subject in the set.
Read the full abstract ▾
Computer Vision
FETALFusion: Resolution-Aware State-Space Modeling for Multi-Domain Fetal Head Segmentation
Ammar Bhilwarawala and Mainak Bandyopadhyay
Head circumference (HC) measured from 2D ultrasound is a routine marker of fetal growth, and automating it needs segmentations whose boundaries hold up on individual scans, not only on average. We present FETALFusion, a dual-path CNN-Mamba encoder-decoder for fetal head segmentation across acquisition types. It applies four-directional state-space scans only at the two highest-resolution stages, routes bottleneck features through domain-specific channel gates that are averaged at test time, and adds a weak landmark shape prior. We train jointly on transabdominal (HC-18) and transperineal (PSFHS) images and compare ten methods on a held-out test set of 471 images, each trained under one schedule and scored by surface distances at native resolution. FETALFusion reaches a Dice score of 0.963 and an HD95 of 2.10 mm without test-time augmentation or a domain label. It improves on U-Mamba on all five reported metrics (HD95 reduced by 0.31 mm; Holm-corrected ($p < 10^{-4}$), a lead that holds under test-time augmentation and across two independent training runs, and in the mean on U-Net,
Attention U-Net and TransUNet. Residual encoders close the gap: a ResNet-34 UNet++ exceeds FETALFusion, and an ImageNet initialised ResNet-34 U-Net is best overall (HD95 1.75 mm). The ablation agrees. Calibrated against run-to-run variation, it attributes FETALFusion's measurable gains to the landmark shape prior and, on transperineal images, to the domain gates, while removing the state-space branch does not measurably change accuracy. HC from the predicted masks agrees with the clinical reference at an intraclass correlation of 0.9986.
Read the full abstract ▾
Information Theory
Latency-Aware Uplink NOMA-MEC with PASS: A Feasibility-First Resource Allocation Framework
Sepehr Abolhasani, Saba Asaad, S. Mohammad Razavizadeh et al. (+1 more)
Meeting hard task-completion deadlines for many simultaneously offloading users is the binding challenge in mobile-edge computing (MEC). As the user count grows, the transmit power required to satisfy every deadline within per-user budgets rises until no feasible allocation exists. We take a feasibility-first view of this $K$-user problem in an uplink non-orthogonal multiple access (NOMA) MEC system served by a pinching-
antenna system (PASS), whose radiating points establish strong line-of-sight (LoS) links that lower the received-power requirement. We formulate a latency-constrained joint optimization of transmit powers, CPU frequencies, and
antenna configuration. We then derive a closed-form least-power feasibility test: the componentwise-least allocation meeting every deadline. It certifies feasibility with the largest attainable margin to the power budgets and defines a practical quality-of-service (QoS)-feasibility outage metric, the probability that no allocation meets all deadlines within budget. We solve the problem with a three-block alternating-optimization
algorithm that is provably monotone-convergent and has
polynomial complexity. Numerical results show that the proposed scheme sustains deadline feasibility at user loads where equal-power, orthogonal multiple access (OMA), and single-
antenna baselines fail or degrade sharply, each by a mechanism predicted directly from the system model, whereas the proposed design degrades gracefully. Stress tests further show that feasibility is sustained under order-of-magnitude budget reductions, and that the pinching-
antenna array itself enables constrained-budget operation. The result is a scalable, closed-form-initialized design for deadline-feasible offloading.
Read the full abstract ▾
All authors Sepehr Abolhasani, Saba Asaad, S. Mohammad Razavizadeh, Jiguang He
Machine Learning
HaloBlock: Faster and Better Decoding for Diffusion Large Language Models
Zhaohui Zheng, Chenhang He, Jinrui Zhang et al. (+2 more)
Diffusion large
language models (dLLMs) have attracted increasing research
attention due to their bidirectional
attention and arbitrary order decoding. However, there are two issues in dLLMs inference: the decoding difficulty is dominated by the
tokens on the right side of the block, and the block-wise decoding inherently suffers from boundary contextual discontinuity. To tackle these limitations, we propose HaloBlock, a difficulty-aware adaptive
halo mechanism for dLLM inference. We first leverage bidirectional cumulative
entropy to characterize block decoding difficulty. Then, based on the bidirectional decoding difficulty, we adaptively allocate bidirectional
halo regions on both sides of each block to mitigate boundary contextual discontinuity. The difficulty-aware design of HaloBlock smooths cross-block context propagation and lowers decoding difficulty for hard
tokens, yielding better generation quality and faster convergence. Evaluated on LLaDA-8B-Instruct, Dream-7B-Instruct and LLaDA-1.5 across mathematical
reasoning and code generation
benchmarks, HaloBlock demonstrates consistent accuracy improvements and higher inference efficiency. Source codes are publicly available at https://github.com/PolyU-VCLab/HaloBlock.
Read the full abstract ▾
All authors Zhaohui Zheng, Chenhang He, Jinrui Zhang, Ming-Ming Cheng, Lei Zhang
Computer Vision
AI-Enhanced Hyperspectral Imaging for Intraoperative Detection of Low-Grade Glioma: A Clinical Study
Siri Willems, Ishika Jain, Jens De Winne et al. (+9 more)
Current image-guided neuronavigation techniques, such as intraoperative MRI and ultrasound, are limited by high costs, limited sensitivity and operational complexity. There is a clear need for more efficient systems to enhance intra-operative tumor detection and improve patient outcomes for intrinsic
brain tumor resection. Whereas previous intraoperative
brain HSI studies have predominantly investigated high-grade gliomas, glioblastomas, or mixed-grade cohorts, this clinical study focuses specifically on low-grade gliomas (LGGs). LGGs strongly resemble normal
brain under white light conditions on the operative microscope. This study characterizes spectral differences between healthy and tumor tissue and provides a paired comparison of HSI- and RGB-based classification at matched tissue locations and under identical patient-level data splits. Tumor regions showed consistently lower reflectance, which may be associated with differences in hemoglobin concentration and oxygenation. A range of classification models was evaluated. The 3D CNN, which integrates spectral and spatial features, achieved the highest median ROC-AUC of 74.5%, compared with 67.9% for the spectral-only XGBoost model and 64.0% for the RGB-based model. These results support further investigation of HSI for low-grade glioma classification and quantify its performance relative to conventional RGB imaging in this cohort.
Read the full abstract ▾
All authors Siri Willems, Ishika Jain, Jens De Winne, Siri Luthman, Hamed Zivari Adab, Roeland Vandebriel, Anna Alperovich, Xiaohan Zhang, Ben Stoffelen, Tom De Schepper, Lien Solie, Steven De Vleeschouwer
Numerical Analysis
Space-Time Parallel Direct Numerical Simulation of Rayleigh-Bénard Convection
Thomas Saupe, Thibaut Lunet, Mathis Bode et al. (+3 more)
Rayleigh-Bénard convection (RBC) is a model for turbulent flow and challenging to simulate by direct numerical simulation (DNS). Adequate resolution of all relevant length scales requires very fine grids in space and stability restrictions can dictate small step sizes. In this paper, we investigate the use of parallel spectral deferred correction (SDC) as a high-order time-stepping method to reduce wall-clock times of direct numerical simulation of RBC. Performance results on JUSUF (CPUs) and JUPITER (GPUs) with two different codes show parallel SDC can offer some concurrency along the temporal axis plus larger maximum stable time steps. Taken together, this allows for a reduction of wall-clock time required for simulations over one free-fall time by having to compute fewer steps and being able to mitigate the higher cost per time step through temporal parallelization.
Read the full abstract ▾
All authors Thomas Saupe, Thibaut Lunet, Mathis Bode, Robert Speck, Sebastian Götschel, Daniel Ruprecht
Numerical Analysis
Block diagonal preconditioners for arrow-shaped multiple saddle-point linear systems
Luca Bergamaschi and Michele Bergamaschi
We consider multiple saddle-point linear systems with block-arrow structure. We analyze exact and inexact Schur complement based block diagonal preconditioner, by characterizing the
eigenvalues of the preconditioned
matrices in terms of the zeros of specific rational functions. Numerical results onto large tests coming from
liquid crystal modeling and PDE-constrained optimization validate the obtained
eigenvalue bounds
Read the full abstract ▾
Machine Learning
Sea-Net: A Small and Inherently Interpretable Neural Network for Time Series Classification
Ubaid Ur Rehman and Tanmoy Mondal
Traditional time-series classification methods often operate as black boxes, providing a class prediction without indicating which time point or time interval within the series led to that prediction. To improve temporal interpretability, MILLET (Multiple Instance Learning with Temporal Explanation), which combines an InceptionTime encoder with Conjunctive Pooling, provides both classification and temporal explanations. However, MILLET contains approximately 424 K parameters, making it unsuitable for deployment on resource-constrained micro-controllers, and it achieves an overall time-series accuracy of 0.888 and an explanation score of 0.681 NDCG@n. We therefore propose SEA-Net, a lightweight architecture using small multi-scale depthwise-separable convolutional TSC encoders and improved Multiple Instance Learning (MIL) pooling heads. Our SEA-Net bottleneck encoder with Top-k pooling achieves 0.931 accuracy and 0.765 NDCG@n with only 41 K parameters. Another variant, using a gated encoder with Top-k pooling, achieves 0.955 accuracy and 0.750 NDCG@n with 62 K parameters. These results demonstrate that lightweight architectures can maintain strong classification performance and temporal explanations while substantially reducing model size. The proposed variants address specific limitations of the pooling strategy used by MILLET, providing a practical direction for interpretable time-series classification on resource-constrained edge devices.
Read the full abstract ▾
Computer Vision
Haoyang Jiang, Zhuotong Fan, Mingyang Yi et al. (+3 more)
Table
reasoning with
language models typically assumes access to clean textual tables. In practice, tables are often serialized into text, which can corrupt
cell contents, distort structural relationships, and discard visual cues, leaving the model to reason over incomplete evidence. In contrast, table images retain this information, but using it requires both accurate perception and
reasoning grounded in the relevant
cells. To address this, we propose MERIT (
Multimodal Evidence
Reasoning over Image Tables), a three-stage framework for learning to reason over table images, with serialized tables serving as optional auxiliary inputs (if provided). Our analysis identifies visual evidence acquisition as a bottleneck, motivating table-specific encoder adaptation through reconstruction, localization, and color-conditioned supervision. Building on the adapted representations, supervised fine-tuning teaches explicit evidence selection and
reasoning using verified trajectories. Finally, reinforcement learning refines the policy with separate rewards for evidence correctness, calculation, final answers, and output format. By providing feedback on intermediate steps, the framework targets
retrieval and computational errors that final-answer supervision alone does not distinguish. We evaluate the approach on table question answering and fact verification, analyze the contributions of visual inputs and training components, and assess generalization to additional
datasets with different table structures and visual presentations.
Read the full abstract ▾
All authors Haoyang Jiang, Zhuotong Fan, Mingyang Yi, Ju Fan, Lanqing Hu, Xiao Zan
Computer Vision
PUGS: Physics-Guided Uncertainty Modeling for Underwater Dynamic 3D Gaussian Splatting
Tingjun Li, Yuxi Wang, Guoqiang Zhong et al. (+1 more)
Dynamic 3D Gaussian Splatting (3DGS) provides an efficient framework for dynamic scene reconstruction. Most existing approaches model scene dynamics with deterministic deformation fields, assuming each Gaussian follows a distinct
geometric trajectory over time. This assumption breaks down underwater, where light scattering, refraction, marine snow and low visibility create substantial physical ambiguity in captured images. We present PUGS, a physics-guided uncertainty model for underwater dynamic 3DGS. PUGS learns inherent uncertainty induced by underwater image formation and leverages it as a physical signal for dynamic scene modeling. Rather than estimating a single deterministic displacement, it parameterizes each Gaussian's motion as a probability distribution with expected deformation and physical uncertainty. We adopt
stochastic deformation optimization to sample Gaussian trajectories via local reparameterization, exploring multiple physically plausible solutions during training. We further propose uncertainty
stochastic annealing and a dual-path self-consistency
distillation objective, converting
stochastic exploration to deterministic reconstruction while preserving temporal coherence. Extensive experiments on underwater dynamic
datasets and physics-aware
benchmarks demonstrate superior rendering quality, temporal consistency and reconstruction robustness. Our method achieves 1.16 dB PSNR gain over the strongest baseline on UVEB and 3.99 dB on DRUVA.
Read the full abstract ▾
All authors Tingjun Li, Yuxi Wang, Guoqiang Zhong, Zhaoxiang Zhang
Cryptography and Security
Provenance and Authorization in Autobiographical Language Models
Faruk Alpay and Taylan Alpay
Autobiographical
language models may draw on archives containing observations, quotations, emotional reports, and earlier model outputs. Cryptographic authentication can preserve an archive while leaving these sources semantically conflated. We formulate this gap as a computer-security problem: narrative content must not silently become consent or alter an authorized decision rule. We define typed records, authenticated attestations, a separate policy channel, and admissible views. Under explicit assumptions, we give a standard integrity reduction and a noninterference argument, characterize the information required by exact decision-preserving summaries, and show why passive history and fixed-point convergence need not identify a preferred action. Alpay
Algebra supplies a comparative
language for iterative
memory without being a premise of the proofs. Sociology of religious affiliation, source-monitoring psychology, and self-determination theory motivate distinctions in a bounded Latter-day Saint vignette. A separate, reproducible pilot uses a frozen public
language model on 32 wholly synthetic cases across 576 paired conditions. It compares flattened records, source labels, and an explicit admission gate under contradictory summary repetition. The study concerns computational attribution and authorization, not the motives or psychology of the people in the vignette.
Read the full abstract ▾
Information Theory
Chordal Codes: Code Construction and Efficient Gaussian-Elimination Decoding
Yulin Chen, Laigang Guo, Tong Li et al. (+1 more)
Maximum-likelihood decoding of linear codes over erasure channels can be considered as solving a linear system of a column submatrix of the parity-check
matrix. In practice, Gaussian elimination is usually applied, and its computational cost depends on the structure of the
matrix, especially the sparsity and the fill-in generated during the elimination. The chordal graph, or triangulated graph, first introduced by C. Berge, has a so-called perfect elimination ordering, indicating that if the primal graph of a
matrix is a chordal graph, then there exists a perfect elimination ordering such that a special class of fill-in under Gaussian elimination following this ordering will be avoided. In this paper, we introduce chordal codes, i.e., codes equipped with parity-check
matrices such that the primal graphs of the parity-check
matrices are chordal. We prove that, for a chordal code, the decoding submatrix associated with any erasure pattern retains a chordal primal graph. So, the complexity of chordal elimination (Gaussian elimination following the perfect elimination ordering applied to the chordal code decoding) will be smaller than decoding a random code by Gaussian elimination. Also, we provide an upper bound on the complexity of chordal elimination.
Read the full abstract ▾
All authors Yulin Chen, Laigang Guo, Tong Li, Mingyang Zhu
Computer Vision
HierarchiRetina: A Diabetic Retinopathy Screening and Grading Cascade with Heterogeneous Mixture-of-Experts Lesion Segmentation
Md Asif Uddin, Niloy Farhan, Rafeed Rahman et al. (+1 more)
Clinical screening for diabetic retinopathy proceeds in stages, yet most automated systems grade fundus images with a single black-box network. Three gaps remain: (i) lesions differ widely in size and contrast, but segmenters typically apply the same blocks to all; (ii) ungradable images are usually excluded or treated as an extra class, and lesion-aware graders seldom test whether lesions drive the grade; (iii) staged systems often report each stage only on the images reaching it, leaving propagated errors unmeasured. HierarchiRetina, a screening, segmentation and grading cascade with inspectable stage outputs, addresses each gap. First, HSMoE-AUNet is a U-Net whose skip, bottleneck and decoder blocks are sparse mixtures of heterogeneous experts, with lesion-matched types, counts and losses; SwinHRUNetPP, a dual-encoder vessel segmenter, uses a field-of-view-restricted loss. Second, LG-DRG separates gradability from ordinal severity and lets lesion masks query the image through gated cross-
attention. Third, an end-to-end evaluation counts screening misses as errors and traces each error to its stage. Pooled Dice ranged from 0.184 (microaneurysms) to 0.579 (exudates); vessel Dice was 0.731. On 58,689 held-out images from six
datasets, end-to-end quadratic weighted kappa was 0.804, with referral sensitivity 0.832 at specificity 0.947, and the screening gate caused 66% of errors. In ablations, the grade ignored the masks, even with the cross-
attention gate started open. On all 4,105 official DDR test images, six-class accuracy was 85.6%, above the best published six-class result we found (83.8%). Staged screening systems should be evaluated end-to-end, with stage attribution and mask ablation, before clinical deployment.
Read the full abstract ▾
All authors Md Asif Uddin, Niloy Farhan, Rafeed Rahman, Md. Golam Rabiul Alam
Robotics
Locomotion with Online Awareness of Dynamics for Precision Footholds
Kunzhao Ren, Zhishuo Zhu and Xiaobin Xiong
Unknown payloads alter
robot dynamics and make precise contact execution difficult when foothold margins are small. We present LOAD, a perceptive locomotion framework that combines explicit inertial estimates with implicit dynamics features for narrow-beam traversal. Separate recurrent modules infer torso inertial changes and task-relevant history from proprioception, while a height-map teacher is distilled into a depth-based student. We extensively evaluate LOAD and its variants in simulation and on hardware across beam widths and payload configurations. The results show that implicit dynamics features accelerate training, while explicit inertial estimation further improves traversal success; combining both enables LOAD to approach the performance of a privileged policy supplied with ground-truth inertial parameters. Hardware experiments demonstrate traversal with unilateral payloads of 6 kg on a 10 cm beam and 9 kg on a 15 cm beam, and an evenly distributed 11 kg payload on a 15 cm beam. These results support combining physical estimates and history features for precision locomotion under unknown loads.
Read the full abstract ▾
Systems and Control
Enforcing a Strict Safety Margin in LLM Text Generation via Barrier Lyapunov Control
Anand Singh, Shubham Singh, Anjali Tiwari et al. (+1 more)
Large
language models are increasingly deployed without formal guarantees against toxic text generation. Existing control barrier function (CBF) based safety filters can keep the generation trajectory within a toxicity-free region, but do not enforce a positive distance from its boundary, allowing formally safe trajectories to approach the toxicity threshold arbitrarily closely and leaving little buffer against modelling errors or disturbances. We address this limitation with a Barrier Lyapunov Function (BLF) safety filter that enforces a prescribed clearance margin throughout generation while retaining the continuous-time
transformer dynamics, including feedforward layers. The resulting safe input set is a half-space defined by a constraint affine in the control input, and is non-empty under certified surjectivity and classifier-nondegeneracy conditions. For margin-compatible initial conditions we prove that the clearance margin is never violated and that the prescribed clearance is restored exponentially, yielding an explicit clearance floor, and show that, as the margin vanishes, the admissible trajectories satisfy the exponential second-order CBF condition. We further derive an explicitly computable sufficient disturbance budget under which the clearance guarantee degrades gracefully. Simulations on a small
transformer illustrate the resulting improvement in safety clearance.
Read the full abstract ▾
All authors Anand Singh, Shubham Singh, Anjali Tiwari, Katsuki Fujisawa
Artificial Intelligence
Learning How to Remember: Memory Modality Selection for GUI Agents
Taeyun Roh, Suhyeong Park, Gijin Kim et al. (+2 more)
Recent advances in
vision-
language models (VLMs) have substantially improved the capabilities of GUI
agents, while
memory augmentation has emerged as a promising approach for reusing knowledge from past interactions. However, existing
memory augmented GUI
agents typically adopt a fixed representation strategy, providing retrieved experience as a static modality. It remains unclear whether a single
memory modality is consistently optimal, or how modality preference changes across interaction steps. In this work, we conduct a systematic study of
memory modality in VLM based GUI
agents. Across GUI
benchmarks, we find that the preferred
memory representation is strongly step dependent. Motivated by the finding, we introduce SwitchMem, a routing framework that dynamically selects between textual and visual
memory representations at each step. Across three GUI
benchmarks, SwitchMem outperforms
memory augmented baselines that rely on static
memory representations. Our findings validate our claim that
memory modality is a step dependent decision rather than a fixed design choice. Code and project resources are available at https://txxnrd.github.io/switchmem
Read the full abstract ▾
All authors Taeyun Roh, Suhyeong Park, Gijin Kim, Wonjune Jang, Jaewoo Kang
Robotics
GLST: Global-Local Spatio-Temporal Memory Decomposition Framework for Online Chained-Goal Navigation
Yousef Liang, Ryan Ardalan, Yarden Goraly et al. (+6 more)
Autonomous navigation in real-world environments often requires long-horizon operation under partial observability and evolving goals. Existing mapless navigation approaches predominantly assume fixed goals throughout an episode, limiting applicability to practical scenarios where goals change online during execution. We study online chained-goal navigation, where goals evolve through existing-goal redirection or new-goal emergence without explicit transition signals. Under this setting, we find navigation may require either continued exploration or strategic revisitation, creating conflicting
memory requirements. We propose Global-Local Spatio-Temporal Belief Learning (GLST), a
memory-decomposition framework that separates latent beliefs into global-local spatial and long-short temporal representations for long-horizon
reasoning. We further introduce goal-conditioned rewards to balance exploration and exploitation under evolving goals. Extensive experiments in simulation across diverse terrains demonstrate improved chained-goal navigation performance over baselines. Real-
robot experiments using the Spot quadruped further validate our
memory decomposition framework.
Read the full abstract ▾
All authors Yousef Liang, Ryan Ardalan, Yarden Goraly, Chenhao Zhu, Yue Yin, Jonas Frey, Claire Tomlin, Marco Pavone, Shankar Sastry
Computer Vision
CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation
Xiaoxue Wu, Xinyu Gao, Fang Yu et al. (+2 more)
Autoregressive
video generation relies on
memory retrieval to model long-range dependencies. This capability becomes particularly critical for multi-shot generation, where models must reconcile substantial visual changes across shot transitions with persistent semantic continuity. Existing methods tend to perform
memory retrieval at the frame level and share the same historical context across all query
tokens, overlooking the heterogeneous information needs and leading to redundant
retrieval and inefficient use of historical
memory. To bridge this gap, we introduce CineMem, an
attention-aligned fine-grained
memory retrieval framework that combines online
memory organization with query-adaptive
retrieval for autoregressive multi-shot
video generation. Specifically, guided by intrinsic
memory-access patterns revealed through
attention analysis, we propose an online-clustered KV cache as a
memory organization strategy over all historical
tokens, enabling semantic-aware
memory grouping and more precise
retrieval. In addition, we introduce a query-level
retrieval mechanism that provides broader access to historical information under a fixed
retrieval budget, thereby improving long-term
memory utilization. Together, these designs enable the multi-shot
video generator to preserve long-range consistency across shot transitions, particularly in revisitation scenarios, while approximating full-
memory access under a constrained
memory budget. To facilitate evaluation, we further introduce a suite of task-specific, VLM-assisted metrics for faithful inter-shot consistency assessment. Extensive experiments demonstrate the effectiveness of our framework.
Read the full abstract ▾
All authors Xiaoxue Wu, Xinyu Gao, Fang Yu, Yu Qiao, Xinyuan Chen
Machine Learning
Stein Variational Distributional Reinforcement Learning: Score-Guided Particles for Multivariate Return Distributions
Manuel Haußmann and Melih Kandemir
Decisions that weigh several reward signals against each other require the joint distribution of the return vector. Categorical critics scale exponentially in the reward dimension, and
quantiles have no canonical multivariate analogue. Multivariate distributional critics therefore represent each return distribution by M equal-weight particles trained with a discrepancy loss. Beyond their atoms, the particles provide no sampler and cannot resolve events rarer than 1/M. We propose Stein variational distributional RL (SVDRL). Its critic outputs Stein particles, which Stein variational gradient descent transports along a learned score field of the distributional Bellman target. We learn this field by bootstrapped denoising score matching across noise levels and tie it across the Bellman recursion by a consistency loss, which we prove is a non-expansive temporal-difference scheme in score space. The same field certifies the particles. Its reverse-
diffusion sampler satisfies a supremal Wasserstein policy-evaluation bound that holds for bounded, possibly
multimodal returns. The Stein particles inherit this bound up to a gap that we measure without ground truth, and the sampler answers tail-risk queries below the particle resolution at any sample size. Empirically, SVDRL is more accurate on rare events than particle critics with the same number of particles, and on par on MuJoCo continuous control.
Read the full abstract ▾
Robotics
WoVR+: World Model as Reliable Simulator for Versatile VLA Policy Optimization with RL
Shangqing Zhou, Zhennan Jiang, Ning Ma et al. (+9 more)
Action-conditioned world models can reduce costly real-
robot interaction in reinforcement learning for
Vision-
Language-Action models (VLA-RL), but
hallucinations can mislead policy optimization. Extending them to richer VLA interfaces and long-horizon tasks raises challenges in spatiotemporal and cross-modal consistency, exploration-reliability balance in RL, and compounding rollout errors. We present WoVR+, extending WoVR's
hallucination-aware WM-RL framework by redesigning the learned environment and imagined interaction protocol: A VLA-interface-aligned world model provides multi-view prediction and proprioceptive updates while mitigating
hallucinations. Chunk-wise noise preserves flow-based policy exploration while limiting prediction-degrading action jitter. For long-horizon tasks, stage-local imagined training combines stage-entry resets, stage-specific rewards, local horizons, and controllable sampling to shorten generated prefixes and balance training across stages. WoVR+ improves success over SFT by 21.09% and 16.7% on RoboTwin and 6 real-
robot tasks. Long-horizon phone-packaging success rises from 30% to 75%.
Videos are available at https://youmo445.github.io/WoVR_Plus.github.io/.
Read the full abstract ▾
All authors Shangqing Zhou, Zhennan Jiang, Ning Ma, Xin Fu, Yupeng Zheng, Shuai Tian, Huangrui Li, Jiahao Liu, Chao Yu, Zhongpu Xia, Haoran Li, Dongbin Zhao
Computation and Language
Batch-Paced: Fixed-Budget Batch Decoding in Discrete Diffusion Language Models
Shuai Zhang, Zhanchao Zhou, Huachuan Qiu et al. (+2 more)
As generative
language models become more capable and widely used, inference demand grows, making efficient serving increasingly important. Discrete
diffusion language models (dLLMs) offer a promising path to more efficient inference through parallel
token generation. Prior dLLM decoding methods, however, focus on improving inference efficiency for individual sequences. We formulate fixed-budget dLLM batch decoding and introduce Batch-Paced, a training-free method that jointly optimizes the allocation of decoding compute across requests to improve overall batch quality. Across two dLLM backbones, five
benchmarks and their representative mixtures, Batch-Paced improves batch performance under matched budgets; gains generally grow with batch size and largely persist across decoding configurations. Analysis of requests' decoding trajectories suggests that these gains arise largely by raising the committed-
token confidence of lower-confidence requests. We further show that Batch-Paced's batch decode time remains competitive and that adding a decoding-depth allowance during Batch-Paced decoding can shorten it further at a modest performance cost.
Read the full abstract ▾
All authors Shuai Zhang, Zhanchao Zhou, Huachuan Qiu, Anqi Li, Zhenzhong Lan
Systems and Control
Safe Unicycle Navigation Among Multiple Obstacles Under Bounded Disturbances: A Learning-Augmented CLF-CBF Approach (Extended Version)
Shubham Singh, Anjali Tiwari, Anand Singh et al. (+1 more)
This paper presents a robust control framework for safe navigation of a unicycle
robot to a goal among multiple static obstacles under an unknown, time-varying disturbance. The controller solves a single real-time quadratic program (QP) that combines a goal-reaching term with one safety term per obstacle. The goal-reaching term is a cross-track control Lyapunov function built from body-frame tracking errors rather than a bearing angle, which keeps its Lie derivatives bounded everywhere, including the goal. Safety is encoded using robust control barrier functions, one per obstacle, each tightened by a closed-form, state-dependent disturbance bound. When stabilization and safety conflict, a slack variable relaxes only the convergence requirement, so that the safety constraints remain strictly enforced. Whenever the QP is feasible, the robust barrier constraints guarantee forward invariance of every obstacle's safe set under all admissible disturbances. Complementing this safety guarantee, a Lyapunov analysis yields an explicit ultimate bound on the distance to the goal. A learning-augmented variant replaces the fixed objective with a reinforcement-learning reference, which accelerates convergence when multiple constraints are simultaneously active. We further derive the obstacle separation below which the gap between two obstacles becomes too narrow to pass through under the robust constraints. For such gaps, a learned virtual goal for the Lyapunov function steers the
robot around the obstacles without compromising safety. Simulations, a Monte Carlo study, and a comparison against a sampled-data robust baseline support the theoretical results.
Read the full abstract ▾
All authors Shubham Singh, Anjali Tiwari, Anand Singh, Katsuki Fujisawa
Computer Vision
LinMorph: Learning to Morph Weights for Efficient Video DiT Linearization
Lingyi Long, Congyue Zhao, Xiaoou Li et al. (+2 more)
Post-hoc linearization is an attractive way to accelerate pretrained
Video Diffusion Transformers (
Video DiTs), yet existing methods largely treat the quality loss induced by
attention replacement as a recovery problem. We show that a more fundamental bottleneck lies upstream: initialization. Random initialization discards pretrained knowledge, whereas manual weight reuse transfers it through rigid and incomplete source–target correspondences. We introduce LinMorph, which recasts
Video DiT linearization as a learnable softmax-to-linear weight transformation problem. Instead of copying predefined counterparts, LinMorph learns a cross-parameter morphism that lets each target Gated DeltaNet (GDN) parameter draw jointly from pretrained query, key, value, and output projections, including for parameters with no direct softmax counterpart. A single morphism is shared across layers and learned through local teacher
alignment, while producing layer-specific initializations from their respective pretrained weights. The resulting weights are then materialized as independent GDN modules for progressive
distillation and joint recovery.Since the morphism operates in weight space rather than
token space, it can be learned on short, low-resolution clips and directly reused at larger
video scales. Across pretrained
Video DiTs, LinMorph enables markedly faster recovery and better final generation quality than random initialization and heuristic weight reuse. Results show that efficient linearization depends not only on how a converted model is recovered, but critically on how pretrained knowledge is transferred before recovery. Project page: https://lonelyling.github.io/LinMorph.
Read the full abstract ▾
All authors Lingyi Long, Congyue Zhao, Xiaoou Li, Yanmin Qian, Tao Huang
Machine Learning
NBCLT: Parameter-Agnostic Norm-Ball Clipped Local Training
Linxuan Pan, Shucheng Yang and Junchi Yang
Distributed learning with multiple local steps reduces communication but aggravates drift, and its practical performance often depends on carefully tuned hyperparameters under heterogeneous data and communication constraints. At the same time, recent
Muon-type optimizers suggest that constraining updates within suitable norm balls provides a simple way to encode
geometric priors into optimization. In this work, we propose NBCLT (Norm-Ball Clipped Local Training), a unified local-training framework for both
federated learning (FL) and decentralized learning (DL). NBCLT combines a predict-and-correct local update rule with Euclidean projections onto flexible norm balls, thereby performing norm-ball clipping under flexible update geometries while retaining a simple implementation. In FL, its problem-parameter-free regime achieves $\mathcal{O}(\epsilon^{-2})$ communication complexity and $\mathcal{O}(\epsilon^{-4})$ total
stochastic-gradient complexity without assuming bounded heterogeneity, when the per-round local-computation budget is scaled appropriately with the horizon. In DL, NBCLT is compatible with both static and time-varying mixing and preserves these accuracy exponents under the analogous computation scaling, up to fixed network constants and an additive initialization cost.
Read the full abstract ▾