跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 15:23 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 15:44 — 2026-11-10 15:44（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-10 15:23最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

20,643 已收录论文17,531 AI 相关5,643 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 15,443 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 15:22（北京时间）
新论文 · v1arXiv:2611.09280

An Empirical Study of Issues in GPU Kernel Libraries for LLM Systems

Yanjie Gao, Jiayi Bi, Haoxiang Lin, Ling Feng

原文摘要

Behind the expanding use of large language models (LLMs) across application domains lies a growing dependence on specialized GPU kernel libraries. These libraries underpin the correctness and efficiency of training and inference across diverse GPU platforms, implementing attention, GEMM, quantization, and low-precision operators while managing tensor shapes, memory layouts, code generation, and hardware-specific dispatch. Problems at this layer can silently corrupt outputs, hang GPUs, prevent compilation, introduce deployment incompatibilities, or degrade performance, thereby reducing developer productivity and wasting expensive GPU resources. We present the first comprehensive empirical study of issues in GPU kernel libraries for LLM systems. We manually analyzed 300 high-quality GitHub issue reports, their discussions, and available fixes from seven representative libraries: FlashInfer, FlashAttention, Triton, CUTLASS, DeepGEMM, xFormers, and bitsandbytes. The analysis characterizes symptoms, root causes, fixes, and testing and debugging practices. Our main findings are: (1) 60.33% of the sampled issues originate in the Compiler and Build System or Runtime Environment dimensions, so validation must cover the deployment and execution stack, not just kernel code. (2) Kernel specialization imposes implicit correctness constraints on tensor shapes, metadata layouts, memory aliasing, and hardware resources. Violations can produce incorrect outputs or launch failures even for supported operations, highlighting the need for explicit contract validation and boundary-case testing. (3) Current testing and debugging practices are often insufficient for identifying low-precision numerical problems and hardware-specific execution failures. We outline research opportunities and tooling directions to support future LLM GPU kernel development.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.14837

Modular magnetic soft robotic catheter enables visualized intervention in the pancreatobiliary tree

B. Calmé, N. J. Greenidge, A. Metcalf, A. Bacchetti, G. Loza, D. Kpeglo, P. Lloyd, V. Pensabene 等 10 位作者

原文摘要

Diagnosis and therapy in the pancreatobiliary tree are limited by access. Guidewires reach deep into the ducts but are blind, whereas cholangioscopes provide vision but are too large to readily enter the pancreatic body and tail, the cystic duct, or the gallbladder. At the millimeter scale of these ducts, every function added to a steerable catheter competes with steering for cross-section and adds bending stiffness. We present a 1.47-mm modular magnetic soft robotic catheter in which each function is built into the magnetic body, onto its surface, or onto the footprint of the camera, and we measured what each function costs in bending under bedside fields. Imaging and fiber Bragg grating (FBG) shape sensing accounted for most of this cost, whereas a compliant gripper, magnetic anchoring balloons, and a micrometer-thick ultrasound-triggered release shell together reduced the tip angle at 8 mT only from 70° to 64°. The anchoring balloon increased the gripping force about threefold without stiffening the catheter during navigation. In live pigs, the robotic catheter performed operator-initiated task-autonomous cannulation of the native papilla without sphincterotomy and was teleoperated under onboard vision 75 mm into the pancreatic duct and, without a guidewire, through the cystic duct into the gallbladder, whose lumen it imaged. Anchoring, grasping, and payload release were each demonstrated in vivo. Adding each function at a measured cost to steering allows a soft robot small enough for these ducts to intervene as well as navigate.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2510.16822

ReefNet: A Large-Scale Dataset and Benchmark for Fine-Grained Coral Reef Recognition

Abdulwahab Felemban, Yahia Battach, Faizan Farooq Khan, Yuqian Fu, Xuhui Liu, Yesmeen M. Khattab, Yousef A. Radwan, Xiang Li 等 22 位作者

原文摘要

Coral reef monitoring requires scalable recognition of visually similar taxa across heterogeneous underwater surveys. We introduce ReefNet, a public dataset that aligns approximately 925K hard-coral point annotations from 76 CoralNet sources and an independently collected Al-Wajh dataset with the World Register of Marine Species taxonomy. A stratified expert audit of 8,962 patches guides filtering to a 479,027-annotation benchmark with 39 labels: 38 genera and the family Fungiidae. Expert agreement is 92% on the retained audit subset, rather than an exhaustive accuracy estimate. We evaluate pretrained models through zero-shot recognition, few-shot adaptation, and full fine-tuning, each on within-source ReefNet and held-out-source Al-Wajh tests. Biological vision-language pretraining provides the strongest zero-shot results; supervised adaptation substantially improves recognition, with DINOv2 reaching 65.79% macro recall on Al-Wajh. Matched text-description experiments improve all four evaluated MLLMs on Al-Wajh, while a GPT-5.4 reasoning ablation does not improve over direct classification. Long-tail recognition, label uncertainty, and geographic imbalance remain challenges. ReefNet provides a taxonomically grounded resource for studying these challenges; the Al-Wajh test is a regional stress test rather than evidence of global robustness. Public data and resource links are documented in the supplement.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09279

AnomSep: Bridging Optimization-Based Separation and Deep Neural Refinement for Anomaly Detection with Listenable Explanations

Koki Shoda, Jun Younes Louhi Kasahara, Qi An, Atsushi Yamashita

原文摘要

We propose AnomSep, which combines optimiza-tion-based separation with deep neural refinement to achieve accurate anomaly detection with listenable explanations. Anomaly detection requires no predefined anomalous categories, and understanding the basis for each detection helps security personnel assess the validity of each detection. End-to-end anomaly detectors can achieve high detection accuracy but output only scalar scores, and existing anomalous sound separation methods provide listenable explanations with limited detection accuracy. AnomSep first obtains preliminary normal-sound and anomalous-sound estimates through optimization-based separation using a dictionary learned from normal sounds in the target environment. Deep neural refinement then improves the preliminary estimates in a pretrained audio latent space. The separated anomalous sound serves as the listenable explanation, and its energy determines the anomaly score. Experiments on synthetic mixtures and real mixtures show improved separation quality over baseline separators. AnomSep achieves detection performance competitive with the end-to-end baseline and provides listenable explanations directly linked to each detection decision.

cs.SD · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09275

AudioSphere: Towards Self-Supervised Spatial Audio Representation Models

Goksenin Yuksel, Marcel van Gerven, Kiki van der Heijden

原文摘要

Recent audio embedding models learn representations that transfer across clip- and frame-level tasks, yet they operate almost exclusively on single-channel signals and are blind to spatial structure. Spatial audio models capture that structure but rely on clip-level supervision or contrastive objectives, yielding embeddings unsuitable for frame-level tasks like sound event detection and localization (SELD). We argue this dichotomy is not fundamental: patch-level spatial self-supervision can jointly learn acoustic and spatial features at both temporal granularities. We introduce AudioSphere, a multi-channel masked autoencoder trained on Ambisonics recordings that reconstructs both spectral content and directional cues via a joint spatiotemporal masking strategy that masks both time-frequency patches and intensity vectors. AudioSphere supports frame-level predictions while producing strong clip-level representations via aggregation. Alongside the model, we release RealSELD, a standardized benchmark for evaluating frozen backbones on real-world multi-channel SELD. AudioSphere enables, for the first time, SELD with a frozen self-supervised backbone, while matching or exceeding prior self-supervised audio embedding models on clip-level classification tasks spanning environmental sound, speech, and music, and on frame-level sound event detection. All code and data are available at https://github.com/labhamlet/AudioSphere and https://huggingface.co/labhamlet.

cs.SD · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.10070

Frequency-consistent synthesis and selective transfer for medical image analysis

Zhuhui Wang, Jianwei Zuo, Xin Peng, Kai Zhong, Xuliang Deng, Jiajia Luo

原文摘要

Complementary imaging is not always available, and realistic synthesis does not necessarily improve downstream analysis. Here we introduce a training framework linking medical image synthesis to task learning through adaptive frequency consistency and selective feature transfer. Image-specific frequency constraints encourage consistency of structure and detail. Features are transferred only when a teacher using synthetic images achieves a lower task-error score than the student by a task-specific margin on a labelled training sample. Evaluations across five datasets show improved translation fidelity with three adversarial and diffusion-based translators trained without paired supervision, alongside gains in brain-tumour segmentation on tumour-containing slices and lesion centre-point detection. All 105 reported paired comparisons yielded point estimates favouring the proposed methods, including 36 external translation comparisons on post?treatment MRI without retraining. These findings support synthetic modalities as task-oriented complements to acquired scans when complementary imaging is unavailable.

eess.IV · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09270

EGT: Execution-Grounded Traversability through Learned Closed-Loop Trajectory Distributions

Chinmay Mundane, Amith Manoharan, Arun Kumar Singh

原文摘要

Rough terrain traversability is often estimated through point-wise roll, pitch, or force-angle margins along a planned path. However, these metrics are often inaccurate and overly conservative because they ignore how terrain disturbances and low-level controller corrections can affect the vehicle's motions. To overcome these limitations, we introduce Execution-Grounded Traversability (EGT), defined as the probability that a vehicle-controller pair can execute a candidate path while meeting trajectory-level tracking and progress requirements. We estimate EGT by predicting the distribution of closed-loop trajectories using a latent-space flow matching (FM) model conditioned on multi-resolution terrain features and 3D vehicle attitude and wheel-ground contact points prior. Across 650 simulated trials on unseen terrains, EGT reduces safe-path rejection to 2.2% (versus 11.4%-39.5% for pose-margin and force-angle baselines) and unsafe acceptance to 7.7%. Integrated into a receding-horizon sampling-based planner, EGT reduces navigation failure rates by 24-42 and 30-44 percentage points over [1] and [2], respectively, while cutting goal-reaching time by up to 20.5% and 45%. Finally, we demonstrate zero-shot transfer of our simulation-trained model to real-world outdoor experiments.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.34590

Sparse Sum-of-Squares Layers for Certified Learning

Ege Gursoy, Nicolas Mansard

原文摘要

A central limitation of modern machine learning systems is the lack of formal certificates guaranteeing their behavior beyond empirical, sample-based evaluation. Sum-of-squares (SOS) methods provide such guarantees by certifying polynomial inequalities over continuous domains via semidefinite programming (SDP). While prior work has introduced SDP layers as differentiable components in neural networks, repeated learning calls can lose the computational benefit of the forward program's sparse representation. We propose Sparse SOS Layers, differentiable value layers whose backward passes reuse the local coordinates of the forward solve. Under a fixed template and learned objective coefficients, each layer avoids building dense certificates and reuses its sparse structure across training steps. Compared with existing methods, our approach achieves up to 2.7 times speedup in total warm-call time, with nearly 100 times lower memory usage (1.7 vs. 160 GiB) for relatively large problem sizes for the tested dense parameterization. Experiments cover sparse polynomial certification, pendulum control, combinatorial relaxations, robotics projection, oscillator chains, and pose graph synchronization. A design study achieves zero certified violations across unseen problem instances and sizes, while requiring roughly 7 times fewer optimization solves than estimating gradients by perturbing the objective coefficients and re-solving the problem (finite differences). These results show that sparse certificate values can be effectively integrated into learning pipelines when the backward pass respects the verifier's structure.

cs.LG · math.OC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2602.23903

SegMate: Asymmetric Attention-Based Lightweight Architecture for Efficient Multi-Organ Segmentation

Andrei-Alexandru Bunea, Dan-Matei Popovici, Radu Tudor Ionescu

原文摘要

State-of-the-art models for medical image segmentation achieve excellent accuracy, but require substantial computational resources, limiting deployment in typical resource-constrained clinical settings. We present SegMate, an efficient 2.5D framework that achieves state-of-the-art accuracy, while considerably reducing computational requirements. Our efficient design is the result of meticulously integrating asymmetric architectures, attention mechanisms, multi-scale feature fusion, slice-based positional conditioning, and multi-task optimization. We demonstrate the efficiency-accuracy trade-off of our framework across three modern backbones (EfficientNetV2-M, MambaOut-Tiny, FastViT-T12). We perform experiments on three datasets: TotalSegmentator, SegTHOR and AMOS22. Compared with the vanilla models, SegMate reduces computation (GFLOPs) by up to 2.5x and memory footprint (VRAM) by up to 2.1x, while generally registering performance gains of around 1%. On TotalSegmentator, we achieve a Dice score of 93.51% with only 295 MB peak GPU memory. Zero-shot cross-dataset evaluations on SegTHOR and AMOS22 demonstrate strong generalization, with Dice scores of up to 86.85% and 89.35%, respectively. SegMate variants in this study empower single GPU setups to process up to 10,000 volumes per hour with just 74 J per volume using batch inference, enabling population-scale CT processing on commodity hardware. We release our open-source code at https://github.com/andreibunea99/SegMate.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.00722

From Points to Targets: Online Foreground Affinity and Background Learning for Infrared Small Target Detection

Qiancheng Zhou, Xiaodong Yue, Wenhua Zhang

原文摘要

Infrared small-target detection must identify a few faint target pixels in extensive background clutter while keeping false alarms low. Under single-point supervision, each target has only one labeled foreground pixel with unknown spatial extent during training, whereas the detector must recover complete targets from the infrared image without any point guidance at inference. Existing methods typically reconstruct regional pseudo-labels from local cues or intermediate predictions, which can introduce boundary noise around blurry target edges. Instead of turning uncertain boundaries into dense pseudo-masks, we propose Online Foreground Affinity and Background Learning (OABL), a single-stage framework that learns target structure directly from sparse points. First, for online foreground affinity learning, each annotated target point serves as a feature anchor, and local spatial proximity and intensity similarity weight the feature alignment between the point and surrounding pixels, guiding target-related representations without hard boundary labels. Second, for online background learning, we exclude the ambiguous neighborhood around each target point and select high-response false alarms outside this region as active negatives. Averaging the background loss over this active set keeps sparse target-like clutter influential as easy background pixels are suppressed. Jointly optimizing these objectives in a single stage updates the detector directly without generating or refreshing persistent pseudo-masks. Across three public datasets and the combined SIRST3 benchmark, OABL improves detection probability by 1.06--7.82 percentage points over matched PAL training at a false-alarm area rate of $2 \times 10^{-5}$ and avoids PAL's multi-stage full-pool label updates.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09267

Load Balancing with Item Fragmentation and More Bins than Items: Linear-Time and Exact

Ben Bals, Tomáš Flouri, Kassian Kobert, Solon P. Pissis, Leen Stougie

原文摘要

We study a fundamental load-balancing problem in which $N$ items of strictly positive integer sizes with total size $W$ must be assigned to $B$ bins, with items allowed to be divided into integer-size fragments across bins. Each bin must receive a load of either $\lfloor W/B \rfloor$ or $\lceil W/B \rceil$, ensuring that the loads of any two bins differ by at most one unit. Under this constraint, the objective is to minimize the maximum number of distinct item fragments placed into any single bin. This problem is NP-hard and there exists an $(\mathrm{OPT}+1)$-approximation algorithm that runs in $O(N \log N + B)$ time [Kobert et al., 2014]. The existing algorithm is employed by several widely used production codes for phylogenetic reconstruction. Here, we focus on the case $B \ge N$, that is, bins are at least as numerous as items. This setting arises pervasively in modern parallel and distributed systems, as well as in iterative algorithms that rebalance their workload at every step. In this context, bins are machines or machine cores, and items represent computational tasks (jobs). Our central contribution is a remarkably simple $O(N)$-time algorithm that computes an optimal assignment in this setting; this assignment is encoded using $O(N)$ space. In particular, we prove that an optimum always exists in which every bin receives at most two fragments and provide a characterization of when one fragment per bin suffices. Our result strictly improves the $(\mathrm{OPT}+1)$-approximation of Kobert et al. in the many-bins setting and, together with it, yields a strongly polynomial-time $(\mathrm{OPT}+1)$-approximation algorithm for the general setting, as it removes the dependency on the number $B$ of bins.

cs.DS · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09266

SUGARv2: Learning Diverse Visual Humanoid Loco-Manipulation Skills from Synthesized Interaction References

Tianshu Wu, Tianxiang Gui, Yue Chen, Tingxu Liu, Ziye Peng, Guangjie Yang, Xiangqi Kong, Ye Shi 等 10 位作者

原文摘要

Scaling up visual humanoid loco-manipulation skill acquisition requires reducing the human effort needed as tasks and spatial configurations expand, particularly in demonstration collection and task-specific training design. We present SUGARv2, a unified framework for learning diverse visual humanoid loco-manipulation skills through interaction reference synthesis and a shared training pipeline. To obtain diverse references at low cost, we adapt reusable task templates to different spatial configurations, synthesizing coordinated robot and object motions. To reduce task-specific reward design and training effort, we use reference-based imitation as a common learning objective across tasks. We first train privileged teachers to execute these references, then train visual policies through teacher distillation and reinforcement learning with the same reference-based mimic rewards, using diverse object instances and visual domain randomization to support visual generalization and sim-to-real transfer. Across five humanoid loco-manipulation tasks, SUGARv2 achieves a mean success rate of 91.0% in simulation. Deployment on a real humanoid robot further demonstrates successful sim-to-real transfer for whole-body manipulation. These results demonstrate the framework's potential for learning diverse visual humanoid loco-manipulation skills.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09265

Reconciling European Electricity Data with Diffusion Priors Learned from Observations Alone

Matthias Pirlet, Adrien Bolland, Gilles Louppe, Damien Ernst

原文摘要

The ENTSO-E Transparency Platform publishes generation, load, and cross-border power flows for European bidding zones. The values carry undocumented errors and violate energy conservation, and data reconciliation consists in correcting them to satisfy that balance. In this work, we formulate data reconciliation as Bayesian inference. Classical methods implicitly take a uniform prior, which we replace with a diffusion model estimated from the observations alone by empirical-Bayes expectation-maximization. The resulting posterior is sampled with a guided process whose projection step makes every sample satisfy the balance exactly. On synthetic systems of six to thirty-five bidding zones, built from ENTSO-E resource-adequacy data, the diffusion prior gives the most accurate reconciliation, increasingly so as the system grows. Its credible intervals are calibrated or conservative, and it remains the most accurate under a misspecified noise covariance. Finally, when the generation of entire zones goes unreported, the classical methods fail while the learned prior recovers it from cross-zone structure.

eess.SY · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09264

Nudging Decision Models: Do Digital Nudges Steer Fast, Generation-Free AI Agents?

Sascha Kaltenpoth, Haya Halimeh, Kevin Bösch, Oliver Müller

原文摘要

LLM-based agents increasingly automate business and consumer tasks but are slow and expensive. Decision models, a new class that chooses among options without generating text, are far faster and less costly. Developers call them "System One models," referencing dual process theory. We ask whether such models can be steered by digital nudges online and whether, as the theory predicts, automatic nudges affect them more than reflective ones. We adapted an online shopping experiment, previously run with humans and LLM agents, to three decision models (Jev, Decision-1, d1). Across 600 runs per model, they chose a preselected default in 97.5-99.9% and a product with social influence information in 75-96% of choices, versus 47-49% in the control. All responded more strongly to the automatic nudge, the opposite of what has been reported for reasoning-capable LLM agents. We provide first evidence that non-generative decision models are susceptible to digital nudges in a System 1 pattern, implying agent-type-specific nudge effects.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09263

Model-based learning for DoA estimation and array calibration via continuous sparse recovery

Baptiste Chatelier, José Miguel Mateos-Ramos, Vincent Corlay, Matthieu Crussière, Christian Häger, Henk Wymeersch, Nir Shlezinger, Luc Le Magoarou

原文摘要

Direction of arrival (DoA) estimation, a classical signal processing problem, has experienced renewed interest with the advent of integrated sensing and communication (ISAC). While decades of research have yielded highly accurate DoA estimators, hardware impairments have frequently been neglected, despite degrading both DoA estimation accuracy and downstream communication performance in ISAC systems. This work introduces a joint array calibration and DoA estimation method based on the simultaneous orthogonal matching pursuit (SOMP) algorithm, following the model-based machine learning paradigm. The proposed method enables the calibration of antenna arrays subject to severe gain-phase and antenna location impairments through projected gradient descent (PGD), with either supervised or unsupervised objectives. Additionally, DoA estimation is enhanced by extending SOMP to continuous dictionaries via PGD refinement steps. Simulation results demonstrate that the proposed method enables efficient hardware impairment compensation, even without labeled samples, while outperforming conventional sparse recovery and subspace-based DoA estimation baselines.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09260

Navigating Complexity: A User-Centered Evaluation of Project Management Tools

Yasin Ghadimi Zaker, Hamid Reza Ghaeini

原文摘要

In the age of digital transformation, companies are increasingly relying on specialized software to manage the complexity of projects. However, when selecting tools, features and costs often take precedence over user experience (UX), leading to low adoption rates, user frustration, and project delays. This study empirically evaluates the user experience of leading project management tools (Jira, Trello, Monday.com, Asana, and Microsoft Project) across various project scales using a mixed methods approach. The System Usability Scale (SUS) was used as the primary quantitative instrument, with data collected from 141 experienced professionals via online questionnaires. The results reveal a significant trade-off between functionality and usability. Trello achieved the highest SUS score (77.5), indicating a superior user experience for small projects and agile teams, while Microsoft Project scored the lowest (51.2), suggesting significant usability challenges despite its robust features. Jira demonstrated a balanced profile, offering powerful features with manageable complexity. Statistical analyses confirmed that the choice of the optimal tool is highly context dependent, with team size and project complexity influencing UX outcomes. The findings underscore that UX is not a secondary feature but a critical success factor for software acceptance and project effectiveness. This study provides an evidence-based framework for aligning tool selection with the project context, offers practitioners actionable insights, and identifies design opportunities for software developers.

cs.SE · cs.HC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09259

Forecasting cumulative intraoperative hypotension burden: patient-disjoint evaluation of quantile boosting and alert policies

Yunfan Zhao

原文摘要

Background: Binary hypotension forecasts do not describe the depth and duration of future low pressure. Burden forecasts may support graded early warning, but better forecast scores need not yield more useful alerts. Objective: To evaluate conditional quantiles of the next 15-minute mean arterial pressure (MAP) deficit below 65 mmHg and distinguish forecasting performance from episode-warning performance. Methods: Public VitalDB numeric arterial MAP was reduced to 10-second medians without forward filling. Subject-disjoint training, validation and test splits included 70,402, 14,270 and 15,575 labeled windows. We compared climatology, calibrated persistence, last-MAP-only boosting, and direct and residual quantile boosting, with and without additional MAP-history features. Patient-weighted pinball loss and subject-bootstrap intervals evaluated forecasting. Validation selected alert thresholds before a hash-recorded test evaluation. Results: In the test split, the prespecified residual-versus-persistence comparison at the 90th percentile yielded losses of 2.256 and 2.900 mmHg-min, respectively (difference -0.644; 95% interval -0.814 to -0.487). Direct prediction achieved 2.196, and direct prediction with additional MAP features achieved 2.193. Episode-warning results were sensitive to the alert rule and operating threshold. Conclusions: This retrospective benchmark separates burden-forecast skill from warning-policy performance. Findings support further study of direct burden estimation; they do not establish patient benefit, prospective reliability or transportability beyond the source hospital.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09256

Zero-Query Transferable Pretend Benign Attacks with Amortized Online Generation for Cooperative Perception

Hongwei Lin, Xun Huang, Chenglu Wen, Cheng Wang

原文摘要

Cooperative perception enables an ego agent to acquire information from collaborators beyond its own sensors' reach. Yet, the most beneficial messages are often the hardest to verify from local observations. Pretend Benign (PB) exploits this asymmetry by targeting regions with weak local verifiability and applying multi-objective perturbations, making harmful feature changes appear to be benign assistance. However, PB is victim-dependent: selecting regions and optimizing perturbations require the victim model's architecture, parameters, and gradients, limiting transfer to unseen victims. A transferable attack must capture properties shared across cooperative detection models rather than those specific to one network. We address this by building a victim-agnostic attack from a heterogeneous ensemble of surrogate models and encoding its capabilities in a reusable dictionary to reduce per-message generation cost. Specifically, Transferable Pretend Benign (TrPB) transfers PB's region selection criterion and multi-objective perturbation strategy across heterogeneous surrogates to construct an offline attack. We further propose RT-TrPB, which encodes transferable regions and perturbation patterns into a region predictor and reusable perturbation dictionary, amortizing per-message attack generation. Experiments on widely used cooperative perception benchmarks show that RT-TrPB bypasses the consensus-based defenses ROBOSAC and FLD with success rates approaching 100% and generates each perturbation in under 56 ms. To counter PB-style attacks masquerading as benign collaboration, we also propose STTrust, which verifies received messages using spatial and temporal consistency and incorporates identity-level trust. STTrust detects over 90% of PB-style attacks and restores perception performance to near the attack-free level.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.22133

Approximate Total Weighted Completion Time with Convex Controllable Processing Times

Klaus Heeger, Danny Hermelin, Dvir Shabtay

原文摘要

We study the single-machine scheduling problem with controllable processing times to minimize the total weighted completion time, focusing on the setting where a job's processing time is a convex function of its allocated continuous resource. The computational complexity of this problem represents a long-standing open question, as it is currently neither known to be polynomial-time solvable nor NP-hard. While we do not fully resolve this complexity question, we provide several insights into the problem's approximability. On the positive side, we present a polynomial-time $e \le 2.719$-approximation algorithm, alongside a quasi-polynomial approximation scheme for instances where the largest parameter value is polynomially bounded by the instance size. On the negative side, we demonstrate that simple sorting rules, which are optimal for certain special cases in the literature, cannot guarantee a constant-factor approximation for the general case.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09254

TwinHash: Two-Sided Object Identity Management for Time- and Energy-Efficient Agentic Workflows

Sangbu Yun, Jung Gyu Min, Jin Hyun, Jeonghwan Ahn, Youngjoo Lee

原文摘要

Agentic artificial intelligence (AI) services interleave large language model (LLM) generation with external tool execution, and increasingly rely on search-based workflows that repeatedly revisit shared reasoning states and computations. These patterns create substantial redundancy across tool outputs, LLM responses, and key-value (KV) prefixes, yet existing serving systems primarily optimize shared prompt prefixes, while naive input-keyed caching is unsafe when identical requests produce different outputs. We present TwinHash, a unified object management architecture that assigns each object an input-side hash key to recognize repeated requests and an output-side content fingerprint to validate and locate stored state, complemented by type-specific reuse guards that preserve correctness and response diversity. A software object identity table maintains reusable objects across requests and trajectories, while a hardware object placement table tracks their residency across hierarchical memory tiers so that evicted state can be retrieved rather than recomputed. Across seven agent frameworks and five benchmark suites, reuse follows workflow structure more than benchmark identity. TwinHash serves up to 81% of tool outputs wherever deterministic tool reads recur, and up to 92% of LLM responses in search-based frameworks. Retrieving an evicted KV-prefix from DRAM reduces TTFT by up to 5.6x on Qwen3-32B, with greater gains projected for larger dense models. Under search-based frameworks, TwinHash reduces end-to-end wall-clock time by up to 87% and measured task energy by up to 81% over a prefix-cached baseline, while a per-key serving cap controls the quality-reuse trade-off in adaptive search. These results demonstrate that unified identity, safety, and placement management can convert structural redundancy in emerging agentic workflows into substantial serving-efficiency gains.

cs.AR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09251

Green500: Adventure in Qualifying a Cluster

Nicolas Richart, Xavier Ouvrard, Julia Paolini, Manuel Cubero-Castan, Gilles Fourestey

原文摘要

Energy effciency has become a key metric for evaluating High Performance Computing (HPC) systems, as reflected by the Green500 ranking. However, energy effciency alone does not capture the full environmental impact of an HPC cluster. Using the Kuma cluster at EPFL, we report on two Green500 measurement campaigns at Level 2 and Level 3, and extend this analysis to a full carbon footprint assessment using the MITSI life-cycle based methodology. GPU power capping experiments show that energy effciency peaks at 450 W, achieving an 11% performance loss offset by a 20% reduction in energy consumption. When embodied emissions are accounted for, the optimal power cap for carbon effciency shifts to 500 W under Switzerland's low-carbon electrical grid, revealing a tension between minimizing usage and embodied contributions. We discuss the challenges of generalizing this approach into a broader carbon-based HPC ranking, and argue that moving beyond energy effciency is both necessary and feasible.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.25508

Dyna-Style Safety Augmented Reinforcement Learning: Staying Safe in the Face of Uncertainty

Artur Eisele, Bernd Frauenknecht, Friedrich Solowjow, Sebastian Trimpe

原文摘要

Safety is a key problem in reinforcement learning, especially during exploration. While safety filters are promising to address this issue, they are ill-suited for high- dimensional systems with unknown dynamics. We propose Dyna-style Safety Augmented Reinforcement Learning (Dyna-SAuR), a novel algorithm that learns a control policy as well as a safety filter requiring minimal domain knowledge by leveraging a learned uncertainty-aware dynamics model. A novel filter learning formulation requires the filter to avoid failures and areas of high model uncertainty. As joint deployment of the control policy and filter allows to safely collect data and improve the dynamics model, certain areas grow and filter conservatism decreases over time. Dyna-SAuR reduces failures compared to established safe RL baselines by two orders of magnitude on goal-reaching CartPole and MuJoCo Walker.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09248

Topology as a Design Variable: Joint Architecture-Sizing Optimization for SRAM

Can Wang, Junhao Ma, Yikai Wang, Shan Shen, Wei W. Xing

原文摘要

SRAM's power-performance-area-stability trade-off depends on bitcell topology, a discrete architectural choice that interacts non-separably with continuous transistor sizing. However, no open-source SRAM tool treats topology as an optimizable variable. OpenRAM generates SRAM layouts but performs no optimization, while OpenYield supports high-fidelity evaluation but restricts optimization to scalar sizing of a fixed 6T cell. OpenYieldV2 closes this gap through three integrated contributions. First, a fully parameterized compiler generates complete 6T and 10T SRAM macros with peripheral circuits and replica-bitline self-timing, enabling topology comparison under identical simulation conditions. Second, a few-shot TabPFN surrogate learns topology-dependent PPA responses with limited full-macro SPICE samples. Third, a coarse-to-refined multi-objective optimizer combines global exploration of discrete architectural choices with local refinement of continuous transistor sizes. Experiments across varying design conditions reveal a topology decision boundary that shifts with operating constraints rather than following a fixed design rule. Jointly optimizing across this boundary improves hypervolume by up to 17.3\% over the strongest single-topology baseline. OpenYieldV2 is open-source to support reproducible SRAM design research.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09247

Practical Non-Stationary Graph Gaussian Processes

K. S. Sesh Kumar, Viacheslav Borovitskiy

原文摘要

Gaussian processes on graphs provide a principled framework for prediction and uncertainty estimation, but modelling heterogeneous networks often requires balancing flexibility against parameter complexity. Variability at a node may reflect useful signal that should propagate through the network, unreliable measurements whose influence should be suppressed, or a mixture of both. We introduce Variance-Coupled Gaussian Processes (VCGPs), which use a positive auxiliary signal to modulate graph interactions through a single learned coupling exponent. The exponent controls how strongly high-variability nodes propagate or attenuate information, while a cluster-wise extension accommodates different regimes within the same graph. Under stated structural assumptions, we characterize the unique stationary-rescaling point of the basic family, where correlations match those of a stationary graph kernel while node-dependent variances remain. Experiments on traffic, air-quality and weather datasets show competitive prediction and uncertainty estimation relative to stationary and per-node non-stationary baselines, with the largest gains on networks requiring multiple coupling regimes. Stationary correlations after variance rescaling remain sufficient on some data, and performance depends on the auxiliary signal and model selection.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.18413

Adamas: Hadamard Sparse Attention for Efficient Long-Context Inference

Siyuan Yan, Guo-Qing Jiang, Yuchen Zhang, Xiaoxing Ma, Ran Zhu, Chun Cao, Jingwei Xu

原文摘要

Large language models (LLMs) now support context windows of hundreds of thousands to millions of tokens, enabling applications such as long-document summarization, large-scale code synthesis, multi-document question answering and persistent multi-turn dialogue. However, such extended contexts exacerbate the quadratic cost of self-attention, leading to severe latency in autoregressive decoding. Existing sparse attention methods reduce these costs by attending to only a subset of key-value (KV) tokens, but fixed or coarse-grained selection strategies can miss important tokens or retain substantial redundancy under constrained token budgets. We introduce \textbf{Adamas}, an accurate and efficient token-level sparse attention mechanism for long-context inference. Adamas applies the Hadamard transform, bucketization and 2-bit compression to produce compact representations, and uses lightweight distance-based estimation for efficient top-$k$ candidate selection. The selected positions are then used to gather the corresponding original KV states for sparse attention. Comprehensive evaluations show that Adamas maintains near-lossless performance within the effective context length of Llama-3.1-8B-Instruct. In efficiency evaluations, Adamas achieves up to $6.5\times$ self-attention speedup and $1.7\times$ end-to-end decoding speedup at a 32K context length. Adamas also maintains performance comparable to full attention on challenging long-form reasoning benchmarks, including AIME 2024 and AIME 2025.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09240

MM-DyGraph: A Dataset, Benchmark, and Model for Multimodal Dynamic Graphs

Zongyuan Wu, Pengjie Wang, Lingshan Chen, Tianhang Wan, Yuan Meng, Xin Wang, Ling Feng, Wenwu Zhu

原文摘要

Multimodal dynamic graphs are pervasive in real-world applications, where nodes and edges are accompanied by multimodal signals, including text and images. Despite their practical importance, benchmarks and methods that explicitly study multimodal learning in dynamic graphs remain scarce, hindering the full understanding and effective utilization of multimodal information for downstream tasks. To address this gap, we introduce MM-DyGraph, to the best of our knowledge, the first benchmark for multimodal dynamic graph learning, consisting of diverse real-world datasets with fine-grained temporal graph evolution and rich multimodal attributes. MM-DyGraph provides three evaluation tasks to comprehensively assess model performance in dynamic settings. We benchmark representative state-of-the-art dynamic graph methods and reveal that naive feature concatenation yields target-level inconsistencies: multimodal inputs benefit certain prediction targets while harming others. This observation indicates that the modality informativeness depends on the specific prediction target over time. Building on these observations, we propose a Target-aware Spatial-Temporal Multimodal Fusion (TST-MF) framework, which jointly conditions multimodal fusion on the prediction target and spatial-temporal relations, enabling context-adaptive cross-modal interplay for target-specific representations. Extensive experiments over diverse datasets and tasks show that TST-MF delivers robust and competitive performance, achieving clear gains in multimodal settings.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.31061

STEP: Learning STructured Embeddings for Progressive Time Series

Lucas Thil, Jesse Read, Rim Kaddah, Guillaume Doquet

原文摘要

We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised contrastive objective to learn a low-dimensional latent space whose geometry is itself the interpretation: each observation becomes a point on a manifold anchored between two fixed orthogonal prototype vectors, and a trajectory becomes a path across that manifold. From this structure we read a latent compass, the polar coordinates (θ, r) of the latent vector, in which θ tracks the progression of the underlying state (e.g., from healthy to failed) and r identifies the active mode (e.g., the operating condition), without any proxy labels. We evaluate the approach against the state of the art on diverse domains, including industrial degradation, robotic tasks, and neural activity, validating three key capabilities: (1) end-state prediction, (2) multi-step forecasting, and (3) interpretable phase separation. Our method matches or improves over black-box counterparts on all of these while providing transparency about the underlying mechanisms. A simple linear regressor on top of the latent compass coordinates is competitive with deep architectures, direct quantitative evidence that the underlying state is encoded in a geometrically accessible form.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.07976

VLD: Visual Learned Distance as an Interface for Reinforcement Learning Navigation

Lazar Milikic, Manthan Patel, Jonas Frey

原文摘要

Training end-to-end policies from image data to directly predict navigation actions for robotic systems has proven inherently difficult. Existing approaches often suffer from either the sim-to-real gap during policy transfer or limited action-labeled training data. To address this problem, we introduce Visual Learned Distance (VLD), a scalable framework for image-goal navigation that decouples perception learning from policy learning. We first train a self-supervised distance-to-goal predictor on about 3,000 hours of internet-scale and simulated video, providing a distance signal that a reinforcement learning (RL) policy can minimize. The RL policy is trained separately in simulation using privileged geometric distances perturbed by GeoNoise, a learned noise model that reproduces the viewpoint- and overlap-dependent errors of the trained distance predictor. At deployment, the policy consumes VLD predictions zero-shot, without retraining, inheriting ``where to go'' from large-scale visual training while retaining the robust navigation behaviors learned in simulation. This error modeling is key to the transfer: with VLD inputs, GeoNoise-trained policies reach $58.7\%$ success on HM3D and $76.2\%$ on Gibson, whereas policies trained with generic temporally correlated noise collapse to $4.9\%$ and $11.5\%$. On a physical robot, the VLD-driven policy succeeds in $88\%$ of trials, compared with $60\%$ for a strong end-to-end image-goal baseline that outperforms it in simulation. Our decoupled design thus provides an alternative and scalable path toward reliable navigation policies that transfer from simulation to the real world.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09235

Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective

Zhuoran Li, Xu Sun, Chang Wen Chen, Wanyu Lin

原文摘要

Controllable molecule generation is crucial for diverse scientific applications, such as drug discovery and materials design. While large language models (LLMs) show great promise, their dense and entangled representations impede precise control over the generation of molecules with bespoke substructures or properties. To address this, we propose Sparse Representation Editing (SpaRE), an interpretability-driven framework for fine-grained and precise control in LLM-based molecule generation. The crux of SpaRE is to learn an overcomplete sparse feature space that disentangles LLM representations into a compact set of latent features corresponding to chemically meaningful concepts. Within this space, we can directly manipulate these concept-aligned latent features to achieve (1) local control, by generating target atoms and functional groups at specified positions; and (2) global control, by customizing the overall structural and physicochemical properties within defined ranges. In this way, our framework advances interpretability from post-hoc analysis to actionable generative control. Experiments show that SpaRE can generate chemically desirable molecules under complex constraints in real-world scenarios, while offering mechanistic insights for quantitative structure-property analysis. The code and demo are available at https://github.com/WanyuGroup/ICML2026_SpaRE.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09233

Cross-Layer TopK: Dynamically Allocating Sparsity Across Layers in Transcoders

Anyuan Zhuo, Shaohua Zhang, Tianle Li, Yuan Lin, Diandian Gu, Jun Wang, Pinyan Lu

原文摘要

Cross-Layer Transcoders (CLTs) decompose the activations of large language models into human-interpretable features and trace how these features interact across layers to form circuits, making them a key tool for mechanistic interpretability. However, training CLTs effectively and efficiently is hard. Beyond the usual trade-off between sparsity and reconstruction quality, a CLT has to model all layers at once, which adds a further challenge. The common JumpReLU recipe controls sparsity only indirectly through a penalty, while the direct extension of TopK selects a fixed number of latents in every layer. Yet reconstruction difficulty differs widely across layers, and intermediate layers are much harder than others, so giving every layer the same budget is suboptimal. We propose Cross-Layer TopK, which sets a single L0 budget for the whole model and dynamically allocates it across layers during training. In a comparison with JumpReLU and other TopK variants on Qwen3-8B-Base, this gives lower FVU while using 20% fewer active latents than JumpReLU. The better reconstruction carries over to circuit tracing, yielding more complete circuits with higher replacement and completeness scores. The fixed per-token budget of Cross-Layer TopK also makes it easy to pair with sparse decoding, which cuts both computation and communication and gives a 2.9x speedup per training step. We further show that Cross-Layer TopK follows scaling laws in both latent size and sparsity. We have open-sourced the weights of our CLT at https://huggingface.co/ByteDance-Seed/Cross-Layer-TopK-CLT.

cs.LG

查看论文
arXiv ↗PDF ↗