Peer Revenue Play credits. Real papers.

Papers

Fresh from arXiv, typeset properly. Highlighted words trade on the market.

Computer Science

cs Watch Computer Science

Thursday 17 September

Machine Learning · Cross-listed from quant-ph

Quantum Graph Convolutional Networks: Implementation and Trainability Analysis

Paul San Sebastian Sein, Theodor Iosif, Tilen G. Limbäck-Stokin et al. (+2 more)

Graph Neural Networks (GNNs) achieve state-of-the-art performance on graph-structured data, but training and inference on large graphs are often bottlenecked by memory constraints and sparse linear-algebra workloads. Quantum computing offers an alternative set of primitives that may improve scalability for graph learning. Building on the quantum graph neural network (QGNN) framework of Liao et al., this work implements two representative architectures — the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models — and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation. We compare predictive performance and optimization behavior against classical baselines, showing that the quantum models achieve competitive performance with fewer parameters. Finally, we present a cost gradient analysis that identifies the tasks for which the models showcased are trainable. This is followed by a classical simulability study to find regimes in which the proposed circuits remain robust during training.
Read the full abstract

All authors Paul San Sebastian Sein, Theodor Iosif, Tilen G. Limbäck-Stokin, Kin Ian Lo, Yidong Liao

Cryptography and Security

JANUS: Denial-of-Service Attack Against Beam Hopping in LEO Satellite Networks

Yuval Aviv, Roee Idan, Roy Peled et al. (+2 more)

Low Earth orbit (LEO) satellite networks are increasingly used to provide global connectivity. However, each satellite has limited resources that need to be allocated according to demand, which varies geographically and over time. Beam hopping addresses this challenge by dividing a satellite's service area into geographic cells. Rather than illuminating every cell simultaneously, it dynamically assigns available beams to a selected subset based on demand. This reliance on observed traffic demand as an input to beam-selection decisions creates a new attack surface whose security implications have received little attention. In this paper, we present JANUS, a novel targeted denial-of-service attack against beam-hopping systems in LEO networks. We show that a small botnet of compromised terminals can inject legitimate user traffic into carefully selected non-victim cells to manipulate the beam-hopping scheduler's view of demand. This manipulation alters beam-allocation decisions and redirects service away from the targeted victim area. We evaluate JANUS across different system configurations, schedulers, attack horizons, and attacker-knowledge settings to characterize the attack's effectiveness, required resources, and resulting service disruption over time. Against a rank-based KMAX scheduler, JANUS achieves complete service denial for up to approximately 95% of evaluated victims. Against DRL, JANUS can exclude the victim from approximately 92% of scheduling decisions. Finally, we evaluate mitigation strategies that reduce the attack effectiveness.
Read the full abstract

All authors Yuval Aviv, Roee Idan, Roy Peled, Asaf Shabtai, Yuval Elovici

Robotics

Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation

Harsha Guda, Adrià Colomé and Carme Torras

Vision-language-action models tell a robot where to move, but not how hard to push. Contact-rich tasks depend on that second quantity, compliance, yet no widely used demonstration interface records it. The obstacle is identifiability as realized pose and measured force cannot separate the operator's intended equilibrium from their stiffness, so VR controllers, SpaceMouse and handheld grippers cannot supply compliance supervision even in principle. Prior compliance-output policies work around this with hand-specified task structure, privileged simulation contact state, or dedicated force and tactile hardware. Four-channel bilateral teleoperation removes the ambiguity directly by using the leader arm as a separate measurement of the intended equilibrium, making per-axis stiffness identifiable by regression using only the joint-torque sensing already on the manipulator. This yields per-timestep, direction-dependent compliance labels at zero annotation cost, which we use to fine-tune a VLA to emit stiffness alongside pose. On a Franka Research 3 wiping task, ours is the only policy of five whose contact force changes when the instruction asks for a firm wipe rather than a normal one (6.4N (normal) to 9.1N (firm) RMS, Cohen's d = 0.89, p = 0.023
Read the full abstract

Robotics

MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation

Zitai Huang, Taiyi Su, Jian Zhu et al. (+6 more)

Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout execution. This challenge becomes particularly critical when multiple objects share identical appearances and must be manipulated in a prescribed order. In such scenarios, relying solely on a limited-horizon manipulation policy is often insufficient to determine which instance should be operated on and when the task should transition to the next stage. To address this challenge, we propose MaskHarness-WAM, an instance-grounded harness for long-horizon manipulation. The proposed system connects high-level task planning with low-level manipulation policies through target masks, while leveraging visual feedback for subtask scheduling and continuous execution. Since each subtask corresponds to a different target instance, the low-level policy requires a newly established initial target mask under the updated scene at each subtask transition. The harness continuously re-observes the environment, generates, and verifies the target mask at subtask boundaries, thereby updating the instance-level spatial condition provided to the low-level policy. Furthermore, the system advances the manipulation process by switching target instances according to the verified completion status of each subtask. Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.
Read the full abstract

All authors Zitai Huang, Taiyi Su, Jian Zhu, Jianjun Zhang, Chong Ma, Tianbin Liu, Weiyi Lu, Yi Xu, Hanli Wang

Computer Vision

An Event Preserving Velocity Invariant Representation for Event Cameras

Mikihiro Ikura, Luna Gava, Jiahang Wu et al. (+2 more)

Event cameras provide low-latency, high temporal resolution perception for real-time vision tasks such as robotics.The novel circuitry (i.e. asynchronous, independent pixels) that enables these advantages also introduces new algorithmic challenges. Velocity-invariant representations alleviate missing observations under slow motion and motion blur under fast motion, but most discard temporal information by converting events into image-like representations. We propose Set of Centre Active Receptive Fields (SCARF), a real-time velocity-invariant representation that preserves raw events while consistently handling fast motion, stationary scenes, and independently moving objects. SCARF achieves state-of-the-art performance in both computational efficiency and representation quality.
Read the full abstract

All authors Mikihiro Ikura, Luna Gava, Jiahang Wu, Chiara Bartolozzi, Arren Glover

2609.19973 · 17 Sep · @inproceedings{ikura2026event, title={An Event Preserving Velocity Invariant Representation for Event Cameras}, author={Ikura, Mikihiro and Gava, Luna and Wu, Jiahang and Glover, Arren and Bartolozzi, Chiara}, year={2026}, booktitle={ECCV 2026 Workshop-Event-Based Multimodal Vision: From Imaging to Perception and Understanding} }

Abstract PDF $VISN ×1

Performance

Efficiently Distributed Federated Learning

Gianluca Mittone, Robert Birke and Marco Aldinucci

Federated Learning (FL) is experiencing a substantial research interest, with many frameworks being developed to allow practitioners to build federations easily and quickly. Most of these efforts do not consider two main aspects that are key to Machine Learning (ML) software: customizability and performance. This research addresses these issues by implementing an open-source FL framework named FastFederatedLearning (FFL). FFL is implemented in C/C++, focusing on code performance, and allows the user to specify any communication graph between clients and servers involved in the federation, ensuring customizability. FFL is tested against Intel OpenFL, achieving consistent speedups over different computational platforms (x86-64, ARM-v8, RISC-V), ranging from 2.5x and 3.69x. We aim to wrap FFL with a Python interface to ease its use and implement a middleware for different communication backends to be used. We aim to build dynamic federations in which relations between clients and servers are not static, giving life to an environment where federations can be seen as long-time evolving structures and exploited as services.
Read the full abstract

Machine Learning

CellRFT: Reinforcement Fine-Tuning for Single-Cell Perturbation Modeling

Jie Yan, Li Liu, Hanze Guo et al. (+7 more)

Predicting cellular responses to perturbations supports the study of gene function, disease mechanisms, and therapeutic strategies. Despite advances in single-cell perturbation modeling, existing models typically optimize surrogate losses that do not directly reflect the biological criteria used for evaluation, so better data fitting need not yield better biological predictions. To address this mismatch, we introduce CellRFT, a reinforcement fine-tuning framework that uses biological evaluation as direct training feedback. CellRFT uses policy-gradient optimization to learn from non-differentiable evaluations of generated cell populations and integrates multiple biological rewards through hierarchical reward aggregation. Comprehensive experiments demonstrate CellRFT's applicability across different pretrained models and effectiveness in improving perturbation prediction, reveal that optimizing one biological criterion can help or hinder others, and show that complementary rewards can improve criteria beyond those directly optimized, offering a way to probe how biological metrics shape model behavior, with the potential to inform evaluation design. Code will be made available.
Read the full abstract

All authors Jie Yan, Li Liu, Hanze Guo, Jiaxin Hu, Houxin He, Xiaoning Qi, Haoran Wang, Cong Li, Zhong-Yuan Zhang, Yong Wang

Computation and Language

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

DeepSeek-AI: Anyi Xu, B. Li, Bangcai Lin et al. (+588 more)

The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work has substantially reduced the cost of long-context computation, prefill remains computationally expensive, and large KV caches continue to strain HBM and SSD capacity and data-transfer bandwidth. Together, these compute, storage, and bandwidth demands constitute the primary bottleneck to further lowering deployment costs. To address this challenge, we introduce DeepSeek-V4.1-Flash, a multimodal Mixture-of-Experts (MoE) model with 552B backbone parameters and support for contexts of up to one million tokens. With its Causal Encoder-Decoder (CED) architecture, the model activates 16B parameters per token during decode but only 8B parameters during prefill, substantially improving cost efficiency for agentic workloads. To push the limits of KV cache compression, DeepSeek-V4.1-Flash combines cross-layer KV cache reuse in Compressed Sparse Attention 2 (CSA2) with FP4 KV caching. These designs reduce its global KV cache footprint (always in HBM) to 890 bytes per token, roughly 1/4 of the corresponding footprint of DeepSeek-V4-Flash. Further, through a dedicated deployment optimization known as SWA Bounded Replay, DeepSeek-V4.1-Flash reduces its persistent KV cache footprint (always on SSD or in host memory) to roughly 1/8 of that of DeepSeek-V4-Flash. Despite its much smaller KV cache footprint, the model delivers substantially better performance than the baseline. In addition, we streamline the DeepSeek-V4 architecture and introduce several efficient architectural extensions. We pretrain DeepSeek-V4.1-Flash on a multimodal corpus comprising 45T tokens and conduct comprehensive post-training, yielding strong performance across diverse text-based and multimodal agentic scenarios. Model checkpoints are available at https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash.
Read the full abstract

All authors DeepSeek-AI: Anyi Xu, B. Li, Bangcai Lin, Bing Xue, BingCheng Xian, Bingzheng Xu, Bochao Wu, Bowei Zhang, Boyi Deng, C.C. Yu, Chao Jin, Chaofan Lin, Chen Dong, Chenbing Wang, Chenfan Feng, Chengda Lu, Chenggang Zhao, Chengqi Deng, Chengyuan Zhang, Chenhao Xu, Chenqi Zhao, Chenze Shao, Chuhao Wang, Chuqi Zhang, Damai Dai, Dejian Yang, Deli Chen, Di Huang, Di Wu, Donghao Li, Erhang Li, Eric Fu, F. Zhou, Fangwei Zhou, Fangyun Lin, Fangzhou Yuan, Feiyu Xia, Fucong Dai, Guangbo Hao, Guanglin Li, Guanting Chen, Guoai Cao, Guofan Fan, Guolai Meng, Guowei Li, Haichuan Zhang, Haiyang Ma, Haiyang Shen, Han Li, Han Yu, Han Zhang, Hangyuan Deng, Hanwei Xu, Hanxiang Xu, Hanxun Zhong, Hao Guo, Hao Jiang, Hao Li, Hao Qin, Haodong Wen, Haofen Liang, Haofeng Huang, Haohua Liu, Haoling Zhang, Haoming Luo, Haoran Yang, Haotian Xu, Haotian Yuan, Haoting Huang, Haowen Luo, Haoyang Cai, Haoyu Chen, Haozhe Ji, Hengran Zhang, Hengrui Wang, Hengxu Wu, Honghui Ding, Hongxuan Tang, Huadong Wang, Huanqi Cao, Huazuo Gao, Hui Qu, Hui Zeng, J. Yang, J.H. Jin, J.H. Zhang, J.X. Zou, Jia Yu, Jiahui Zhou, Jiajun Chen, Jialiang Huang, Jialin Zhao, Jiamin Tang, Jian Zhou, Jianan Tong, Jianwen Li, Jiaqi Zhu, Jiarui Wang, Jiasheng Ye, Jiashi Li, Jiaxin Xu, Jiaying Ding, Jibai Lu, Jiewen Hu, Jin Yan, Jincheng Zhai, Jingchang Chen, Jingcheng Hu, Jingli Zhou, Jingsheng Xu, Jingting Xiang, Jingyan Yun, Jingyang Yuan, Jingyuan Cheng, Jinhua Zhu, Jinpeng Wang, Jinyi Chen, Jinyi Hu, Jiping Yu, Jueliang Guo, Junbo Pei, Junbo Sun, Junguang Jiang, Junjie Qiu, Junkang Zhou, Junqi Liu, Junren Li, Junxian Li, Junxiao Song, Junyi Guo, Kai Dong, Kaifeng Chen, Kaige Gao, Kang Guan, Kangdong Yuan, Ke Hong, Ke Xu, Kefan Zhao, Kexin Ji, Kexin Zhang, Kexing Zhou, Kuai Yu, Lan Zhang, Lean Wang, Lecong Zhang, Lei Wang, Letian Gao, Liang Zhao, Liansheng Xu, Lihua Guo, Lingxiao Luo, Lingyue Fu, Litao Deng, Litong Wang, Liyue Zhang, Longhao Chen, Lu Chen, Luotian Huang, Luyao Ma, Luyao Wang, M.S. Di, Max Mei, Menghao Ye, Miao Cui, Mingchuan Zhang, Minghua Zhang, Minghui Tang, Mingjing Zhang, Mingqi Wei, Mingshu Chen, Mingxing Liu, Mingxu Zhou, Mingyu Xu, Mingyu Yang, Mingze Wang, Muyang Chen, Ni Shentu, Ning Wang, Niufang Ning, Panpan Huang, Peixin Cong, Peiyi Wang, Peiyuan Xin, Pengfei Ren, Pengfei Yan, Pengle Zhang, Qi Kang, Qi Tang, Qiancheng Wang, Qiang Li, Qihao Zhu, Qingyang Li, Qinyu Chen, Qiushi Du, Qizhou Guo, Rongxian Xu, Rui Ding, Rui Hu, Rui Tian, Rui Yu, Ruidong Zhu, Ruifan Xu, Ruihan Yang, Ruihang Xia, Ruijie Lu, Ruilin Geng, Ruipeng Hong, Ruiqi Ge, Ruisong Zhang, Ruize Sun, Ruizhe Pan, Runji Wang, Runqian Chen, Runxin Xu, Ruohong Tian, Ruomeng Shen, Ruoyu Zhang, Ryan X., S.H. Liu, Shanghao Lu, Shangyan Zhou, Shanhuang Chen, Shaofei Cai, Shaoheng Nie, Shaoyuan Chen, Shengding Hu, Shengkai Lin, Shengwen Ran, Shengyu Liu, Shengyuan Jia, Shi Bai, Shi Feng, Shicheng Xu, Shichun Liu, Shiqiang Hu, Shirong Ma, Shiyu Wang, Shiyuan Feng, Shufan Gong, Shuhan Lin, Shuiping Yu, Shunfeng Zhou, Shuo Yang, Shuomeng Wang, Shuting Guo, Shuting Pan, Shuying Yu, Sinuo Cao, Siyi Lin, Sizhe Chen, Songyang Chen, Songyang Zhou, Tao Ni, Tao Yun, Tian Jin, Tian Pei, Tian Ye, Tianle Lin, Tianran Ji, Tianyi Cui, Tianyuan Yue, Tingting Yu, Tongrui Xiong, Wangding Zeng, Wei Liu, Wei Zhang, Weibin Xu, Weihao Zeng, Weilin Zhao, Wen Liu, Wenfeng Liang, Wenjie Pang, Wenjing Luo, Wenjing Yao, Wenjun Gao, Wenkai Shao, Wenkai Yang, Wenli Zhang, Wenlu Wang, Wenlve Huang, Wenqian Yan, Wentao Zhang, Xi Gao, Xiang He, Xiang Li, Xiangli Li, Xiangwen Wang, Xiangying Zhang, Xiankui Wei, Xiao Bi, Xiaodong Liu, Xiaohan Wang, Xiaojian Qu, Xiaokang Chen, Xiaokang Zhang, Xiaotao Nie, Xiaoyao Zou, Xiaoyuan Li, Xicheng Guo, Xieting Chu, Xin Cheng, Xin Liu, Xin Xie, Xinbo Xu, Xingchao Liu, Xingchen Liu, Xingkai Yu, Xingyou Li, Xintong Yao, Xinyang Chen, Xinyong Jiang, Xinyu Yang, Xinyu Yang, Xu Chen, Xuanyu Wang, Xubei Zhong, Xuecheng Su, Xuejie Liu, Xuheng Lin, Xujie Fan, Xuncheng Zhao, Xuwei Fu, Y.C. Yan, Y.H. Jiang, Y.T. Wu, Y.W. M., Y.Z. Wang, Yafei Gao, Yang Yang, Yang Zhang, Yanru Ma, Yanwen Huang, Yao Li, Yao Li, Yao Meng, Yao Zhao, Yaofeng Sun, Yaohui Wang, Yaoyang Ye, Yehang Yin, Yexinrui Wu, Yi Qian, Yi Tao, Yi Yu, Yichao Zhang, Yichen Jiang, Yicheng Wang, Yifan Ding, Yifan Shi, Yifeng Peng, Yifeng Zhai, Yijia Wu, Yiliang Xiong, Yilun Wang, Ying He, Ying Zhou, Yingjia Luo, Yinmin Zhong, Yiping Wang, Yisong Wang, Yixiang Zhang, Yixiao Chen, Yixuan Tan, Yixuan Wei, Yiyang Ma, Yiyao Yang, Yiyuan Liu, Yizai Cai, Yizhen Wei, Yizhi Wang, Yonglun Yang, Yongqi Zhuo, Yongqiang Guo, Yongtong Wu, Yu Wu, Yu Zhang, Yuan Bian, Yuan Cheng, Yuan Ou, Yuan Sun, Yuanfan Xu, Yuanhang Sun, Yuanhao Li, Yuchen Liu, Yuchen Yao, Yudong Han, Yuduan Wang, Yuhan Wu, Yuhao Meng, Yuheng Zou, YuKun Li, Yunchuan Wang, Yunfan Xiao, Yunfan Xiong, Yupeng Chen, Yuqian Cao, Yuqian Wang, Yuqing Chen, Yushun Zhang, Yutong Lin, Yuwei Xiao, Yuxian Gu, Yuxiang Chen, Yuxiang Huang, Yuxiang Luo, Yuxiang You, Yuxin Chen, Yuxin Xiang, Yuxuan Liu, Yuxuan Zhou, Yuyang Zhou, Yuzhe Guo, Yuzhen Huang, Yuzhuo Bai, Z.Y. Z., Zanlin Ni, Zehao Wang, Zehua Zhao, Zehui Ren, Zejun Zhao, Zhangli Sha, Zhanying Wang, Zhaochen Zhang, Zhaoshuai Du, Zhe Fu, Zhean Xu, Zhenda Xie, Zheng Liu, Zhengyan Zhang, Zhenhua Dong, Zhewen Hao, Zhibang Wang, Zhibin Gou, Zhicheng Ma, Zhihao Li, Zhihong Shao, Zhihuan Huang, Zhijie Li, Zhirui Lu, Zhixian Huang, Zhixuan Chen, Zhixuan Chen, Zhixuan Pan, Zhiyu Wu, Zhizhou Ren, Zhu He, Zhuoshu Li, Zhuping Zhang, Zian Xu, Zihao Wang, Zihui Gu, Zijia Zhu, Zili Zhang, Zilin Li, Zilong Hou, Zilong Lyu, Ziqiao Wang, Ziwei Xie, Ziya Zhang, Ziyi Gao, Zizheng Pan, Zonglin Li, Zongqing Yao, Zui Chen, Zuofan Wu, Chenchen Ling, Chengyu Hou, Chong Chen, D. Li, Di Qi, Dongjie Ji, Fang Wei, Fanyi Xia, Fei Xie, Feiyi Tan, Hailong Guo, Haiyan Zhai, Hui Zhou, Huihui Tan, Huijie Li, Jia Luo, Jia Song, Jialu Cai, Jian Liang, Jiangting Zhou, Jiaqi Gao, Jiayi Shao, Jie Chen, Jieyu Yang, Jin Chen, Jingde Zhang, Jingzi Zhou, Jinqian Wang, Jinyang Liu, JinZhao Sun, Junhua Ling, Junmin Zheng, Kaicheng Yang, Ke Xu, Le Su, Leyi Xia, Liangfeng Ding, Lin Zhuo, Linwang Ma, Linyan Zhu, Liyu Cai, Luqi Yao, M.K. Zhang, Meng Li, Miao Lin, Miaojun Wang, Min Zhang, Mingming Li, Mingming Wang, Mingze Yin, Minmin Han, Nan Cao, Ning Wang, Ningxin Ma, Panpan Wang, Peihan Lin, Peng Sun, Peng Zhang, Qian Ying, Qiang Xiang, Qiao Wang, Qingmiao Mao, Qiwei Jiang, Rongli Jin, Ruyi Chen, Sha Tao, Shangmian Sun, Shaoqing Wu, Shichao Zou, Si Lei, Tianyang Zhang, Tianyu Sun, Tingting Yin, W.L. Xiao, Wei An, Wei Li, Wei Wang, Weiwei Lin, Wenqing Hou, X. Lin, Xiangfei Meng, Xianzhu Huang, Xiao Peng, Xiaoqian Li, Xiaoting Zhang, Xiaowen Sun, Xiaoxiang Wang, Xiaoyu Ye, Xinrou Zhang, Xinyu Zhang, Xue Cao, Xueyin Chen, Yanan Zhou, Yanhong Xu, Yao Xia, Yao Xu, Yi Shao, Yihong Zhang, Yiling Ma, Ying Tang, Yining Lou, Yiru Chen, Yishi Piao, Yixuan Chen, Yong Xiong, Yuchen Xuan, Yuehan Yang, Yuer Xu, Yukun Zha, Yunxian Ma, Yuping Lin, Yuting Yan, Yutong Xie, Yuwen Sheng, Yuxuan Zhu, Zekai Zhang, Zhe Ju, Zhenzhen Lin, Zheren Gao, Zheyang Sun, Zhigang Yan, Zhongyu Wu, Zi Wang, Zihua Qu, Ziling Yan, Ziyi Wan

Discrete Mathematics

Integrality gap preserving reductions

Koppány István Encz, Monaldo Mastrolilli and Eleonora Vercesi

We propose a framework for the systematic study of integrality gaps of combinatorial optimization problems with respect to a fixed linear programming formulation. The method, called integrality gap preserving reduction, consists of iteratively shrinking the input universe of the problem while guaranteeing that gap-maximizing instances remain selected. When the subset of remaining instances becomes specific enough, we calculate the integrality gap explicitly. Besides applying integrality gap preserving reductions to three well-known optimization problems via their standard linear programming formulations (weighted vertex cover problem, multiple knapsack problem, and unrelated machine scheduling problem), we analyse the restricted assignment problem via its configuration LP relaxation. We prove that the integrality gap is equal to $1$ for three “easy” subclasses of the problem that are either solvable in polynomial time or admit a PTAS (e.g., the all-one processing time case). For some remaining cases, we improve the current lower bound using our technique.
Read the full abstract

Computer Vision

Beyond the Foreground: FOV-Aware Polyp Image Synthesis via Lesion-Guided Adaptive Mucosal Context Propagation

Tong Wang, Yuting He, Bin Ren et al. (+2 more)

Synthetic image and mask pairs can alleviate scarce colonoscopy annotations, but realistic synthesis requires preserving the supplied lesion while generating compatible mucosa. Existing foreground-guided methods treat all non-foreground pixels as background and rely mainly on local integration. Directly applying them to colonoscopy causes two problems: non-mucosal black regions contaminate generated tissue, and local reasoning produces inconsistent mucosal texture and illumination. We propose LAMP, the first foreground-guided framework for polyp image synthesis based on lesion-guided adaptive mucosal context propagation. LAMP explicitly separates the lesion, valid mucosa, and camera exterior using a field-of-view (FOV) mask. Lesion-to-Mucosa cross-attention extracts lesion appearance conditions for valid-mucosa locations, while FOV-constrained multidirectional Vision Receptance Weighted Key Value propagates them over legal tissue support. An adaptive gate then controls their residual fusion into the diffusion U-Net. Extensive experiments on five polyp datasets demonstrate that LAMP substantially outperforms existing methods in overall generation quality and consistently improves five downstream segmentation models. Our code will be released at https://github.com/wangtong627/LAMP.
Read the full abstract

All authors Tong Wang, Yuting He, Bin Ren, Yutong Xie, Guanyu Yang

Computation and Language

Before the Arrest: Benchmarking LLMs on Criminal Profiling from Incomplete Evidence

Yutong Yao, Yanjie Cao, Guanhua Chen et al. (+5 more)

Large Language Models (LLMs) are increasingly applied to legal and criminal justice tasks, yet existing work focuses almost exclusively on post-arrest scenarios where the suspect's identity is already known, leaving the critical pre-arrest challenge of inferring suspect characteristics from incomplete evidence largely unexplored. To fill this gap, we introduce the Profiling, Investigation, and Judgment (PIJ), comprising 2,500 real homicide cases from five countries. PIJ evaluates LLMs across three tasks that span the entire criminal investigation pipeline: criminal profiling, which requires abductive reasoning to infer suspect attributes from fragmentary scene evidence, crime process reconstruction, which tests structured information extraction, and sentence prediction, which demands legal deductive reasoning. We evaluate 9 powerful LLMs and find that performance degrades systematically as tasks shift from explicit fact extraction to implicit reasoning over unknown suspect profiles. Categories requiring inferential reasoning, such as motivation and victim-offender relationships, remain the primary bottlenecks. Further analysis reveals substantial gaps between LLMs and human experts, along with pervasive biases in gender, age, and motive attribution. Our findings indicate that pre-arrest inference from incomplete evidence remains an open challenge.
Read the full abstract

All authors Yutong Yao, Yanjie Cao, Guanhua Chen, Xu Yang, Junchao Wu, Zeyu Wu, Lidia S. Chao, Derek F. Wong

Computer Vision

Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement

Yitong Xing, Yuhao Cheng, Yanping Li et al. (+1 more)

Detection Transformers (DETRs) achieve strong performance in object detection but remain challenging to deploy on edge devices due to their high computational cost. Existing DETR distillation methods mainly focus on aligning distillation points, while largely overlooking the quality of the teacher's supervision itself. We observe that due to stage-wise non-monotonic prediction behavior in DETRs, well-localized or correctly classified predictions from earlier stages may degrade in later ones, and some negative predictions become increasingly overconfident. As a result, relying solely on the current stage's predictions yields inaccurate and inconsistent supervision. To address this issue, we propose Teacher Prediction Refinement Distillation (TPRD), a plug-and-play module that refines teacher predictions before distillation by exploiting stage-wise prediction information. TPRD improves supervision quality through Positive Prediction Correction (PPC), which corrects degraded positive predictions by restoring more accurate ones from earlier stages, ensuring reliable localization and classification signals, and Negative Prediction Suppression (NPS) suppresses the influence of overconfident negatives, preventing them from providing misleading supervision to the student. To preserve informative dark knowledge, we further introduce Maximum Dark Knowledge Preservation (MDKP), which selectively refines target-class logits while retaining non-target relations. Extensive experiments on MS COCO and PASCAL VOC demonstrate the effectiveness and robustness of the proposed method. Our code is available at https://github.com/xingyitong1/TPRD.
Read the full abstract

All authors Yitong Xing, Yuhao Cheng, Yanping Li, Yichao Yan

Game Theory

Exact Regret Frontiers and Externality Scheduling in Centralized Serial-Dictatorship Bandits

Lishang Xu, Guodong Ma, Pengcheng Weng et al. (+1 more)

Exploration in centralized serial-dictatorship matching bandits must use complete matchings, so learning one player-arm pair can impose regret on others. We study this externality under a known common priority order and Gaussian rewards with unit variance. We show that the matching-level Graves-Lai constraints reduce to finitely many pairwise exploration quotas and, at top-choice-separated instances, yield a polynomial-size marginal linear program. At these instances, the exact attainable set of expected logarithmic regret coefficients is $G(\theta)\mathcal{X}(\theta)$, where $\mathcal{X}$ is the feasible matching-allocation set and $G$ maps allocations to player regret. The usual upper-closed Graves-Lai region can be strictly larger despite having the same Pareto-minimal boundary. We further show that identical exploration quotas can induce very different regret through their scheduling. Finally, we construct estimate-solve-track policies, uniformly good on the full row-strict class, that attain every fixed positively weighted optimum without assuming optimizer uniqueness. Every Pareto-minimal point is pointwise attainable, possibly through an instance-calibrated target.
Read the full abstract

All authors Lishang Xu, Guodong Ma, Pengcheng Weng, Zixuan Xia

2609.19963 · 17 Sep · v3: exposition clarified; a sentence in Section 5.3 that was inaccurate for K > N removed, and the K = N condition stated in the introduction; comparison with Cuvelier et al. made precise; two statements in Appendix B corrected; computational cost stated; experiments rerun with 50 seeds (was 10), KL-UCB baseline added to Figure 2; references updated. Main results unchanged

Abstract PDF $PLYN ×1

Robotics

Hybrid Residual Reinforcement Learning for Contact-Rich Robotic Book Insertion

Tianyuan Liu, Rutherford Agbeshi Patamia, Benjamin Champion et al. (+2 more)

Placing a grasped book into a tight shelf is a compact but difficult contact-rich control problem: millimetre-scale pose error can turn a geometrically valid approach into jamming, failed release, or incomplete seating. We study this final phase after grasp acquisition and global approach, and ask how control authority should be divided between known geometry and learned behaviour. Our method retains a nominal task-space controller for structured insertion and seating, while residual PPO supplies bounded local corrections and decides when to release. Only the brief open-retreat-reclose transition is scripted. For the final policy used on hardware, a deployment-matched simulation evaluation over 512 fixed conditions yields 98.50 percent mean success (0.23 percentage-point sample SD) across three independent training runs, compared with 37.89 percent for nominal control. On the physical xArm7, 60 trials over 30 matched conditions show the same qualitative advantage: residual control raises success from 26.7 percent to 63.3 percent, reduces failures from 22 to 11, and wins 13 of the 15 matched conditions in which the two controllers differ. Robustness tests show that performance remains above 87 percent under initialization perturbations up to 1.5x, while very tight clearances expose the geometric limit of local correction. These results support a hybrid design in which geometry preserves reliable task structure and learning is concentrated on the contact-sensitive behaviour that fixed rules handle poorly.
Read the full abstract

All authors Tianyuan Liu, Rutherford Agbeshi Patamia, Benjamin Champion, Akansel Cosgun, Richard Dazeley

Artificial Intelligence

Neuro-Symbolic Agentic AI for Networked Low-Altitude UAVs

Yuqi Ping, Tianhao Liang, Nanchi Su et al. (+4 more)

Networked low-altitude unmanned aerial vehicles (UAVs) need reliable and adaptive decision-making capabilities to operate under uncertain observations, dynamic environments, and intermittent connectivity, while many existing agentic systems remain limited by hallucination risks, data dependence, and weak generalization. This article investigates neuro-symbolic agentic AI (NSAAI) as a framework for combining neural grounding, symbolic reasoning, and closed-loop agentic interaction to support more reliable and adaptive UAV autonomy. We first examine its capability foundations in data efficiency, compositional generalization, continual learning, and zero-shot transfer, and then develop a reference architecture integrating task and goal management, neuro-symbolic planning, verification and metacognition, skill execution and network interaction, and shared knowledge and memory. An urban fire-inspection case implemented in LAESim illustrates how a UAV can coordinate sensing and cloud access under intermittent connectivity, reuse a verified image-delivery skill, and satisfy explicit evidence conditions before completing the mission. The results illustrate the potential of NSAAI to support reusable skills, evidence-grounded decision-making, and adaptive mission execution in networked UAV systems. We further discuss key research directions in uncertainty-aware reasoning, knowledge and skill expansion, adaptive self-monitoring, and standardized evaluation.
Read the full abstract

All authors Yuqi Ping, Tianhao Liang, Nanchi Su, Guangyu Lei, Junwei Wu, Qinyu Zhang, Tingting Zhang

Data Structures and Algorithms

Exact Greedy Influence Maximization in Linear Time on Bounded-Treewidth Graphs

Matic Požar

Computing influence spread under the Independent Cascade (IC) model is #P-hard, and influence maximization is commonly approached using Monte Carlo or reverse-reachable-set sampling. We study IC diffusion on bounded-treewidth graphs. Using probability distributions over separator reachability relations, we obtain exact influence evaluation in $O(n2^{O(w^2)}\operatorname{poly}(w))$ time for a graph with $n$ nodes and treewidth $w$. Our main contribution is an exact all-marginal-gains algorithm. We introduce variable artificial source edges and show that, at a deterministic seed set, the derivative with respect to each source-edge probability equals the corresponding greedy marginal gain. Reverse-mode differentiation therefore computes all marginal gains simultaneously with the same asymptotic complexity as one exact influence evaluation. This yields an exact implementation of classical greedy influence maximization in $O(Kn2^{O(w^2)}\operatorname{poly}(w))$ time, linear in graph size for fixed $w$ and seed budget $K$. We also show that the separator-relation representation has tight $2^{\Theta(w^2)}$ state complexity within exact context-independent compositional separator summaries. This contrasts with the NP-hardness of globally optimal IC influence maximization already on graphs of treewidth one and pathwidth two. Experiments on synthetic bounded-treewidth networks are consistent with linear scaling for fixed width and show that runtime is largely insensitive to propagation and seed-activation probabilities. In demanding diffusion regimes, the method substantially outperforms reverse-reachable-set and optimized Monte Carlo greedy baselines while computing greedy marginal gains exactly.
Read the full abstract

Machine Learning

Graph-Based Stochastic Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation

Tung Tran, Viet Bao Mai, Hoang Ta et al. (+1 more)

Tree-based Monte-Carlo Tree Search (MCTS) duplicates the same state when it is reached through different trajectories, which can waste simulations in stochastic MDPs. We introduce Graph-Based Stochastic-Power-UCT (GS-Power-UCT), which shares states reached at the same planning depth while keeping separate values for states reached at different depths. This design applies to general stochastic MDPs, including problems with cycles. We prove that for a fixed planning horizon, the root estimate converges to the finite-horizon value at rate $O(n^{-1/2})$, matching tree-based Stochastic-Power-UCT while reusing samples across shared states. We also study two full-state variants: GS-Power-UCT-F, which stores one node per physical state to increase sample sharing but may mix values from different remaining horizons, and GS-Power-UCT-F$^+$, which uses an adaptive horizon to control this bias. The latter converges to $V^{\star}(s_0)$, the optimal infinite-horizon discounted value at the root state $s_0$, when the remaining cross-depth gap vanishes. Experiments on stochastic planning benchmarks show improved sample efficiency over tree-based and graph-based baselines.
Read the full abstract

All authors Tung Tran, Viet Bao Mai, Hoang Ta, Tuan Dam

Machine Learning

One Intervention per Component is Enough: Towards Identifiability in Linear Stochastic Dynamics from Steady State

Saber Salehkaleybar

We study the problem of recovering the parameters of a multivariate Ornstein-Uhlenbeck (OU) process from steady-state observational and interventional data. In many applications, such as large-scale gene perturbation experiments, only stationary "snapshot" measurements are available, making standard stochastic differential equation estimation methods that rely on time-series trajectories inapplicable. We first establish an identifiability result: one intervention per strongly connected component (SCC) of the drift graph suffices to recover all OU process parameters generically up to a global scaling factor. This holds provided that the SCC condensation graph is connected with a single root and certain spectral nondegeneracy assumptions hold. We propose a recursive learning algorithm that orders SCCs topologically and, for each component, isolates its marginal dynamics and solves a linear system derived from the steady-state moment equations, leveraging parameters recovered for upstream components. Building on this theoretical foundation, we propose a regularized least-squares estimator that jointly minimizes residuals of the steady-state mean and covariance equations across observational and interventional data. Experimental results validate our theoretical findings in recovering parameters of the underlying OU process.
Read the full abstract

Robotics

LapaTrack-3D: 6 DoF pre-operative shape tracking for laparoscopic surgery

Jingwei Song, Javid Hussain Jakir, Ray Zhang et al. (+4 more)

This work proposes a real-time 6 Degree-of-Freedom (6 DoF) tracking algorithm for monocular laparoscopic surgery. It provides alignment between intra-operative video and pre-operative data (e.g., CT). The 6 DoF tracking offers a solution for accurately locating the internal anatomy of the target organ despite the lack of tactile feedback and transparency. The ORB-SLAM2 framework is adopted and modified for prior-based 3D tracking with four major modifications. First, the primitive 3D shape is used for fast initialization of the ORB-SLAM2 monocular mode. Second, a pseudo-segmentation strategy is employed to separate the target organ from the background for tracking. Third, the 3D shape is incorporated as a geometric prior in its pose graph optimization. Fourth, the Multi-Scale Retinex with Chromaticity Preservation (MSRCP) algorithm is leveraged and modified for image enhancement in challenging illumination scenarios. In-vivo and ex-vivo experiments validate that LapaTrack-3D provides robust 3D tracking and effectively handles typical challenges such as poor illumination, fast motion, out-of-field-of-view scenarios, partial visibility, and “organ-background” relative motion. LapaTrack-3D achieves a processing rate of 13 Hz for 1280*720 pixel video.
Read the full abstract

All authors Jingwei Song, Javid Hussain Jakir, Ray Zhang, Wenwei Zhang, Hao Zhou, Xiaomeng Xian, Maani Ghaffari

Numerical Analysis · Cross-listed from math.DS

Dynamics of Stochastic Hamiltonian systems I - Wong-Zakai Variational integrators

Jacky Cresson and Rouba SAfI

We construct variational integrators to study the dynamics of stochastic Hamiltonian systems using their Wong-Zakai approximation. This approach can be used to interpret and justify previous work of Wang et al (L. Wang, J. Hong, R. Scherer, F. Bai. Dynamics and variational Integrators of stochastic Hamiltonian systems. International Journal of Numerical Analysis and Modeling, 6(4), 2009) on stochastic variational integrators. Numerical examples are provided.
Read the full abstract

Artificial Intelligence

Not All AI Agents Are Equal: Characterizing Resource and Performance Dynamics

Wonmi Choi, Minuk Park, Zhixiong Niu et al. (+3 more)

LLM-based AI agents process user requests through iterative reasoning and tool execution, often involving the invocation of remote LLM APIs with local tool containers. This execution model can make the optimization of agent serving difficult because latency, local resource demand, and container bottlenecks inter-mix across requests. However, the current agent ecosystem runs without much consideration of resource dynamics, which results in significant waste of the precious resources. This paper analyzes the resource inter-mix of AI agents for three representative tasks: retrieval-augmented question answering, web search, and software coding. To this end, we characterize the latency with respect to the resource dynamics of processing multiple requests and tasks concurrently. Our measurements show that agents have a wide range of behaviors depending on tasks, so that even the same tool can differ substantially in resource dynamics. We also find that running multiple requests concurrently exposes task-dependent bottlenecks in resource dynamics such as CPU, disk I/O, and memory. Furthermore, we uncover that faster LLM responses or more CPU cores do not always accelerate agents. Based on these observations, we demonstrate new optimization opportunities that exploit the resource dynamics of tasks: CPU-aware tool admission and task-aware CPU allocation. Our results show that the latency of CPU-sensitive agent tasks improves $\sim$5.4$\times$, and the average latency across multiple tasks is reduced $\sim$32% compared to native agents.
Read the full abstract

All authors Wonmi Choi, Minuk Park, Zhixiong Niu, Yongqiang Xiong, Chuck Yoo, Gyeongsik Yang

Robotics

Execution-Aware Pre-Execution Ranking for Grasp-Conditioned Robotic Placement

Tianyuan Liu, Rutherford Agbeshi Patamia, Benjamin Champion et al. (+2 more)

A geometrically valid placement can still be difficult to execute because the selected grasp changes the required end-effector pose, collision geometry, and transport motion. Placement is formulated as a pre-execution ranking problem in which supplied grasp-placement candidates are scored before planning. The model combines a typed target-conditioned point cloud with three pose descriptors and hierarchical heads for planning success and execution success conditioned on planning. On a 30-object, 1,235-scene dataset with scene-group-held-out splits, three-seed top-1 success on covered test groups reaches 85.63 +/- 1.08% for joint selection and 79.84 +/- 0.16% for fixed-target ranking. For the designated frozen seed-42 checkpoint, top-1 success improves from 72.84% to 85.78% over full-pool cuMotion for joint ranking and from 59.65% to 79.67% for fixed-target ranking. Frozen transfer to xArm7/MoveIt requires no xArm-specific retraining. Across 27 locked cases, 13 complete end to end (48.15%). Of the 16 cases that pass Top-5 preflight and begin execution, 13 succeed (81.25%). Candidate-level deployment-feasibility prediction reaches 81.25% recall, 85.20% specificity, and 83.23% balanced accuracy.
Read the full abstract

All authors Tianyuan Liu, Rutherford Agbeshi Patamia, Benjamin Champion, Richard Dazeley, Akansel Cosgun

Artificial Intelligence

MaSCoD: A Multi-Agent Framework for Structural-Context-Guided Candidate Causal Graph Generation

Yudai Nakada, Yuichiro Nishiura and Jin Michael Splichal

Large language models (LLMs) have been applied to causal discovery, but candidate-graph generation rarely treats premature omission of potentially relevant causal relations as an explicit design objective. We propose MaSCoD, a multi-agent framework that organizes candidate third variables and local structural patterns before direct-edge judgment. We evaluate MaSCoD on Auto-MPG, DWD, and Sachs using GPT-5.4 as the primary backbone and GPT-4o for replication. MaSCoD exhibits a dataset- and backbone-dependent retention-selectivity profile rather than uniform superiority. Across all six dataset-backbone settings, Full, which supplies structural hypotheses before direct-edge judgment, achieved higher mean Recall and F1 than No Phase 1, which instead constructs them within the judgment procedure, while also increasing false-positive rates. Additional reference-edge retention over all evaluated baselines was observed on DWD with GPT-5.4 and on Sachs with GPT-4o, rather than uniformly across settings. Partial ablations showed that supplying both information components did not always outperform supplying only one. For GPT-5.4, stage-wise analysis showed that the Full-No Phase 1 retention gap was already present after direct-edge judgment, while reconciliation introduced additional reference-edge loss for Full on Sachs. These findings support structural pre-organization as an explicit design and evaluation target for omission control and motivate evaluating context construction jointly with its utilization in judgment.
Read the full abstract

Data Structures and Algorithms

Counting Triangles in Graph Streams with Repeatable and Forgettable Edges

Sourav Chakraborty, Debarshi Chanda, Arijit Ghosh et al. (+3 more)

Most existing graph streaming algorithms assume the ideal scenario where each edge arrives only once. Real-world graph streams, such as communication or transaction logs, often contain many repeated occurrences of the same edge. In general, the algorithms developed for the single-edge arrival case can fail when edges can arrive multiple times. Motivated by this, we study the repeated-edge arrival graph streaming model where an edge is allowed to arrive multiple times. In this work, we study the triangle counting problem in the repeated-edge arrival model: approximate the number of triangles in the underlying simple graph despite arbitrary edge repetitions. We design the first algorithms for triangle counting with optimal space complexity. In particular, we present a single-pass algorithm that computes an $(\varepsilon,\delta)$-approximation of the number of triangles with optimal space complexity. We introduce right-to-be-forgotten graph streaming (RFGS) model, where a forget operation can cause all previous occurrences of an edge to disappear. We show that our single-pass algorithm can be extended to the RFGS model with optimal space complexity. Finally, we present optimal constant-pass algorithms that compute an $(\varepsilon,\delta)$-approximation of the number of triangles and cliques for the repeated-edge arrival graph streams.
Read the full abstract

All authors Sourav Chakraborty, Debarshi Chanda, Arijit Ghosh, A. Pavan, Chhaya Trehan, N. V. Vinodchandran

Computation and Language

Intrinsic Sequence-Likelihood Confidence in Retrieval-Dominated Extractive QA: Two Pre-Specified Negatives, and What They Do and Do Not Attribute

Gunwoo Lee, Changmin Sung, Sang-Hwan Gwak et al. (+3 more)

In extractive document question answering whose questions were generated from the passages that contain their answers – so that retrieval recovers 92-99.8% of what any mode combination could reach, whatever its absolute accuracy – confidence-driven mechanisms have little to gain. Fine-tuning an open language model on a specialized domain corpus yields a model whose own confidence is a tempting control signal: it could decide which queries warrant further adaptation, and which answers to trust. We evaluate both uses under criteria fixed before the runs were executed, across four 7-9B model families whose adaptation moved closed-book F1 by at most +0.03, and both fail: a distillation trigger on all four families, under its pre-specified three-step transfer budget, and a routing-and-abstention policy in its single-model pilot. Retrieval alone recovers 92-99.8% of best-case combined accuracy under every correctness criterion we test, leaving routers no meaningful gain. The sequence-likelihood signal is insufficient relative to that mode – area under the receiver operating characteristic curve 0.65-0.81 under the registered criterion – before adaptation as well as after, unchanged by scalar recalibration and not consistently improved by token-level temperature rescaling. And the finer diagnostics depend on the correctness criterion and on answer length; on the three adapted combinations where we could test it, selector ablations show no statistically detectable downstream benefit from the confidence term on any seed; on Gemma, removing it changes the selector from failing to passing both registered criteria. The usable product is a set of pre-specified negatives with their dependencies made explicit.
Read the full abstract

All authors Gunwoo Lee, Changmin Sung, Sang-Hwan Gwak, InA Kim, Ji-Young Choi, Kyong-Ha Lee

Formal Languages and Automata

Stringological sequence prediction III: layered ziplines and a tradeoff between efficiency and expressivity

Vanessa Kosoy

In previous papers, we began the study of sequence prediction algorithms adapted to stringological word complexity measures. In particular, we defined a complexity measure called Arithmetic Repetition Complexity (ARC) which admits a polynomial-time prediction algorithm with a mistake bound quasilinear in the complexity. Here, we show a weaker complexity measure related to ARC that admits an especially efficient prediction algorithm: an algorithm that runs in quasilinear time and polylog space for appropriate highly-structured sequences. The complexity measure is defined via a restricted class of "zipline programs" (a variant of straight-line programs), which we call layered. We thus get a less expressive measure with a more efficient algorithm (compared to our results for ARC), demonstrating a possible tradeoff.
Read the full abstract

Computers and Society

Who Decides? Agency and Legitimacy in Digital Educational Systems

Eriam Schaffter and Ahmed Bounekkar

Digital Educational Systems (DES) enable millions of individuals to learn or to acquire new skills. Their promises vary from one platform to another: some grant genuine degrees, others pledge rapid progress, drawing for this purpose on a range of techniques, from the recommendation of learning resources through complex models to a plain course textbook uploaded onto a learning management system. In this article, we argue that categorizing DES along two dimensions allows to map differences in the way these DES structurally conceptualise the learning process. These underlying dimensions are at once dimensions of the student model and mechanisms built in the DES's designs; we identify them as agency and legitimacy. Indeed, DES are, on the one hand, anchored in an institutionalised regime that grants them legitimacy and, in turn, legitimises the learning undertaken on these platforms; on the other hand, they make design choices as to the share of decision left to the learner in the learning process. We map a curated sample of common DES onto a plane composed of these two dimensions translated into indicators. This allows us to highlight underpopulated regions of the plane and to envisage how a DES might regulate these two dimensions algorithmically, in the interest of learning.
Read the full abstract

Machine Learning · Cross-listed from stat.ML

Error bounds in Sobolev norms for approximations with norm constrained ReLU neural networks

Xianjun Li and Yunfei Yang

Recent studies have shown that smooth functions can be well approximated by ReLU neural networks with path norm constraint on the weights. We extend these results from uniform approximation to approximation in Sobolev norm. Specifically, we analyze how well Sobolev functions in $W^{n,p}$ can be approximated by neural networks with width $W$, depth $L$ and path norm bounded by $K$, when the approximation error is measured in the $W^{1,p}$-norm. For shallow networks with depth $L=1$, we derive the approximation error bound $\mathcal{O}(\max\{W^{-(n-1)/d}, K^{-(n-1)/(s-n)}\})$, when the smoothness index satisfies $n<s=(d+3)/2$ and the input is $d$-dimensional. For deep networks, we remove the restriction on the smoothness by showing that the approximation bound $\mathcal{O}(K^{-(n-1)/(d+d/p+1)})$ holds if the width $W$ and depth $L$ are sufficiently large.
Read the full abstract

Distributed Computing

VERA: Reinforcement Learning for Dynamic Memory Scaling of HPC Workloads in Kubernetes

Ade Pramono, Jie Ren and Ivy Peng

Memory over-provisioning results in resource underutilization when HPC workloads run on Kubernetes. The default Vertical Pod Autoscaler (VPA) cannot anticipate phase-driven memory spikes for first-run HPC jobs. In this work, we present a reinforcement learning (RL) recommender VERA that formulates vertical memory scaling as a Markov Decision Process and trains an agent on 3353 real Prometheus traces. Evaluated on a live Google Kubernetes Engine cluster using LAMMPS, graph analytics, in-memory analytics, and MLPerf 3D-UNet, the RL agent reclaims 31.6% of the available memory headroom and incurs at most one OOM event while VPA reclaims -7.9% over the same runs, raising memory provisioning, and its recommendation would have been insufficient to avoid OOM in 30 runs. The results demonstrate that an observation-driven RL recommender could outperform retrospective heuristics for dynamic memory scaling.
Read the full abstract

Artificial Intelligence

Beyond Depth Truncation: Controlled Evaluation of Depth Utilization in Recursive Language Models

Ha Van Dau, Thanh Tung Khuat and Nguyen Thanh Dung

Depth-recurrent language models iteratively apply a small layer stack, decoupling per-token compute from distinct parameter count. To determine whether such a model genuinely utilizes its depth, both recurrence and layer-pruning literatures rely on a shared evaluation: truncating depth at inference time, plotting quality against retained depth fraction, and reading off the slope. While cheap and training-free, this metric suffers from an unexamined flaw: it extracts a single scalar from an intervention that alters multiple model properties simultaneously. Depth truncation concurrently reduces the number of block applications, decreases the volume of distinct computation performed, and pushes the readout head onto an out-of-distribution residual stream. The observed slope conflates all three factors, yet is conventionally interpreted as reflecting solely the second. We propose the Depth Control Protocol (DCP), a diagnostic suite that disentangles these three quantities. DCP comprises three positive controls that isolate each factor while varying the others, a negative control applying the identical interventions to dense transformers to ensure the effect is not an artifact of the measurement protocol, and a controlled training intervention to verify causality. The linchpin control, running the full budget of block applications while executing only a single distinct iteration, is strictly realizable only in depth-wise weight-sharing architectures, since in a dense network repeating a layer yields an entirely different model rather than the same model in an alternative configuration.
Read the full abstract