跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+758新增论文
+578其中 AI 相关
+94已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-17 04:58 · 全站最近入库:2026-11-17 04:58各信源进度 →

统计口径与数据新鲜度

统计 2026-11-16 07:47 — 2026-11-17 07:47(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:2026-11-17 04:58最近发现新增版本:2026-11-17 04:58库内论文最新更新时间:2026-11-14 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。

24,106 已收录论文20,158 AI 相关7,049 有修订112 HF 社区发现

浏览论文库

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 20,158 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-17 04:57(北京时间)
新论文 · v1arXiv:2610.40305

Rimuru:通过弹性专家卸载实现现代LLM服务统一内存管理

Rimuru: Unified Memory Management for Modern LLM Serving via Elastic Expert Offloading

Zhiyuan Fang, Dingyang Li, Jianfeng Zhong, Bin Wang, Weixi Zhu, Cunshu Ni, Zicong Hong, Wuhui Chen 等 9 位作者

AI 速读 基于摘要

Rimuru 提出共享页池与内存视图机制,统一管理 LLM 服务中异构张量的内存,并通过弹性专家卸载提升吞吐、降低首 token 延迟。

cs.OS · cs.LG

查看原文摘要

Modern LLMs strain device memory through large model weights and attention states, particularly in resource-constrained scenarios. Existing systems separately provision memory for model weights and attention states, imposing fixed fixed boundaries that cannot adapt to the changing memory demands of workloads. Under heavy workloads, insufficient state capacity limits request concurrency and reduces throughput; under light workloads, idle memory in one region cannot be reallocated to another, wasting device memory. Meanwhile, modern LLM architectures introduce heterogeneous tensors with diverse layouts and lifetimes, further complicating memory management. These problems motivate unified memory management for heterogeneous tensors. However, a shared pool alone does not make memory directly reusable across tensors with different allocation granularities and execution layouts. This paper presents Rimuru, a modern LLM serving system that unifies memory management through elastic expert offloading. Rimuru establishes a shared page pool to enables elastic memory sharing across heterogeneous tensors. To accommodate different allocation granularities, Rimuru introduces memory views that allow each tensor type to interpret the shared memory space using its own page size and page table. Furthermore, Rimuru combines huge-page alignment with a multi-level page allocator that splits and merges pages, enabling cross-type capacity reuse. A page-table-aware fused MoE kernel directly accesses non-contiguous expert weights, avoiding copy overhead. Building on these mechanisms, Rimuru employs a workload-aware adjuster that dynamically reallocates pages across tensor types according to runtime demands. Implemented on top of vLLM, Rimuru remains compatible with modern LLMs. Evaluations show that Rimuru achieves up to 19.03x baseline throughput and reduces TTFT by 98.1% on average.

新论文 · v1arXiv:2610.40302

基于预对比帧减影的自训练用于X射线血管造影跨中心冠状动脉血管分割

Self-training for cross-centre coronary vessel segmentation in X-ray angiography using pre-contrast frame subtraction

Danial Moafi, Aida Moafi, Mostafa Aryafar, Ashkan Sami, Maryam Aryafar

AI 速读 基于摘要

作者报告,利用nnU-Net预测与预对比帧减影对比图生成伪标签进行自训练,可在不增加人工标注的情况下改善跨中心冠状动脉血管分割表现,但效果取决于初始伪标签模型的敏感性。

cs.CV · cs.AI

查看原文摘要

Deep learning models for coronary vessel segmentation in X-ray angiography often perform poorly on data from centres that were not represented in training. Apart from differences in equipment, the labels of the largest public dataset (ARCADE) are incomplete, as only the segments defined in the SYNTAX score are annotated. In this study, we evaluated whether self-training with pseudo-labels can improve performance on external data without additional manual annotation. Pseudo-labels were generated from two sources, namely the predictions of an nnU-Net model trained on ARCADE and a contrast map obtained by subtracting a pre-contrast frame from the same sequence. The nnU-Net predictions were extended along the contrast map, and pixels detected only in the subtraction image were assigned an ignore label and excluded from the loss. Six models were trained and tested on ARCADE and on two external datasets (XCAD and XACV). All first-round models initialised with the baseline predictions performed better than both the baseline and a control model fine-tuned for the same number of epochs. The model trained on the XCAD pool improved the macro-averaged Dice score by 2.7 points (95% CI 2.3-3.2), while the control decreased it by 0.6 points. A second round of self-training did not lead to further improvement. When an external model trained on 50 fully annotated images was used to generate the initial labels, the XCAD Dice score increased from 0.623 to 0.745 without any XCAD labels, although performance on XACV did not improve because large main vessels were missed. These results suggest that the benefit of self-training depends largely on the sensitivity of the model used to generate the initial pseudo-labels.

版本更新 · v2arXiv:2605.11999

LLM解码中功耗封顶的幻象:跨注意力架构的阶段感知能耗刻画

The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures

Bole Ma, Ayesha Afzal, Jan Eitzinger, Gerhard Wellein

AI 速读 基于摘要

作者报告在NVIDIA H200上,功耗封顶对以HBM等待为主的LLM自回归解码阶段几乎无效,而锁定SM时钟可在几乎不损失吞吐的情况下回收最高32%的解码能耗。

cs.DC · cs.AI · cs.LG · cs.PF

查看原文摘要

Power capping is a common GPU energy lever in LLM serving, and it appears to work: the cap is set, the GPU reports drawing less than it, and the energy budget is met. We show the cap does little for the phase that dominates LLM serving: autoregressive decode. Across four attention paradigms (GQA, MLA, Gated DeltaNet, and Mamba2) on an NVIDIA H200 under vLLM eager execution, decode kernels wait on HBM and the GPU idles between kernel launches, so decode draws less than half of the GPU's 700W rating and throughput stays within a few percent under every cap we set. The cap engages only when a large batch runs a long generation. Locking the SM clock instead lowers power without slowing memory-bound decode and recovers up to 32% of decode energy at minimal throughput loss. We identify three architecture-dependent frequency-scaling classes and find that, once prefill is measured without prefix caching, the recurrent architectures pay no prefill penalty: their linear-time mixing undercuts quadratic attention on long prompts, so their efficient decode adds to the prefill saving and lowers total request energy from the first output token at large batch.

版本更新 · v2arXiv:2510.26478

依赖缺失下基于矩阵补全的匹配决策统计推断

Statistical Inference for Matching Decisions via Matrix Completion under Dependent Missingness

Congyuan Duan, Wanteng Ma, Dong Xia, Kan Xu

AI 速读 基于摘要

针对匹配容量导致的观测条目依赖性问题,提出基于 Grassmannian 梯度下降的非凸矩阵补全方法,并构建去偏与投影框架,用于匹配决策的统计推断。

stat.ME · stat.ML

查看原文摘要

This paper studies decision-making and statistical inference for two-sided matching markets via matrix completion. In contrast to the independent sampling assumed in classical matrix completion literature, the observed entries, which arise from past matching data, are constrained by matching capacity. This matching-induced dependence poses new challenges for both estimation and inference in the matrix completion framework. We propose a non-convex algorithm based on Grassmannian gradient descent and establish near-optimal entrywise convergence rates for three canonical mechanisms, i.e., one-to-one matching, one-to-many matching with one-sided random arrival, and two-sided random arrival. To facilitate valid uncertainty quantification and hypothesis testing on matching decisions, we further develop a general debiasing and projection framework for arbitrary linear forms of the reward matrix, deriving asymptotic normality with finite-sample guarantees under matching-induced dependent sampling. Our empirical experiments demonstrate that the proposed approach provides accurate estimation, valid confidence intervals, and efficient evaluation of matching policies.

新论文 · v1arXiv:2610.40293

MAServeBench:面向分层协作工作负载的多智能体LLM服务系统基准测试

MAServeBench: Benchmarking Multi-Agent LLM Serving Systems with Hierarchical Collaboration Workloads

Shengxuan Qiu, Haochen Huang, Shuzhang Zhong, Zizhuo Fu, Zebin Yang, Jianming Tong, Meng Li

AI 速读 基于摘要

提出一个把多智能体协作规则作为可配置维度、用于评测LLM服务系统与GPU/NPU硬件行为的基准。

cs.MA

查看原文摘要

Large language model (LLM)-based multi-agent systems (MAS) coordinate specialized agents to solve complex tasks, turning each user request into interdependent model and tool operations. Unlike independent requests, these operations become ready at different times and consume evolving context as agents coordinate and exchange results. This creates changing patterns of concurrency, computation, and memory demand that can expose different bottlenecks in LLM serving hardware. Yet benchmarking these effects requires capturing the collaboration rules that generate serving workloads, beyond the requests observed during execution. We present MAServeBench, a benchmark that treats multi-agent collaboration as a configurable dimension of serving workloads for LLM serving and hardware evaluation. Its composable stages capture how agents coordinate and exchange context in documented MAS workflows, enabling native executions to generate different workloads even when task inputs and tools remain unchanged. Hierarchical Semantic Traces preserve realized operations and dependencies for reproducible comparisons of legal release constraints at fixed work. Task-linked measurements connect these workloads to serving execution and GPU/NPU hardware behavior, revealing why serving efficiency does not always translate into timely task completion. The benchmark code is available at https://github.com/ShengxuanQiu/MAServeBench.

新论文 · v1arXiv:2610.40292

DolphinRouting:面向解耦式LLM推理服务的集群级二元路由

DolphinRouting: Cluster-Level Binary Routing for Disaggregated LLM Inference Serving

Yishuo Yuan, Shaoyu Yang, Chunrong Fang

AI 速读 基于摘要

DolphinRouting 按请求特征聚类,并用离线策略搜索为每个簇学习一个二元路由决策,从而在 PD 解耦集群中选择本地或远程 prefill。

cs.LG

查看原文摘要

Prefill-decode (PD) disaggregation isolates the two phases of large language model serving, but request-level path selection must account for prefill work, cache reuse, and decode demand. We present DolphinRouting, which learns this choice from end-to-end SLO feedback under a given P/D resource allocation. Requests are clustered by raw prompt length, cache-adjusted input lengths on both worker pools, and output-length information. Offline policy search learns one binary action per cluster. Online feature extraction, cluster assignment, and table lookup select local or remote prefill. We evaluate DolphinRouting on a real PD-disaggregated cluster using three public benchmarks, a mixed workload, and real data. Across the mixed workload and real data, DolphinRouting with $k$-means reduces P90 TTFT by 5.7--7.9\% and P90 TPOT by 2.6--10.1\% relative to Dynamo.

版本更新 · v2arXiv:2610.24880

基于神经对偶评论家的一般效用强化学习样本高效方法

Sample-Efficient Reinforcement Learning with General Utilities via Neural Dual Critics

Ankur Naskar, Vaneet Aggarwal

AI 速读 基于摘要

作者提出一种自然演员-评论家方法,用神经评论家直接学习变分对偶伪奖励,以求解凹的一般效用强化学习(RLGU)问题,并给出样本复杂度分析。

cs.LG

查看原文摘要

Reinforcement learning with general utilities optimizes nonlinear functionals of policy-induced occupancy measures. We develop a natural actor-critic method for concave RLGU objectives using an exact variational dual representation, whose existence follows from concavity and differentiability, with explicit constructions for a broad class of separable occupancy utilities. Rather than estimating the occupancy measure and then forming the policy-gradient pseudo-reward, our method learns this pseudo-reward directly as a function of the state-action pair using a neural critic. The critic is trained by projected stochastic updates, while multilevel Monte Carlo combines outputs across training horizons to control its bias at logarithmic expected cost. Our analysis separates conditional actor bias from estimator second moments and accounts explicitly for dual optimization, critic approximation, and neural linearization errors. Under policy-transfer, dual-stability, and local critic-regularity conditions, the method achieves $\widetilde{O}(T^{-1/2})$ global convergence above policy, critic-class, and finite-width approximation errors using $\widetilde{O}(T)$ expected environment transitions and reference samples. For a fixed critic representation, this yields $\widetilde{O}(ε^{-2})$ sampling complexity above the approximation floor, covering infinite state-action spaces and occupancy utilities beyond fixed finite vectors of returns.

版本更新 · v3arXiv:2610.06729

提升大语言模型短篇小说生成的多样性

Improving Diversity in LLM Short Story Generation

Zahra Solati Dehkordi, Vasileios Lampos

AI 速读 基于摘要

提出 DivLM 两阶段后训练框架,通过继续预训练与复合奖励强化学习提升短篇小说在体裁、语气、风格和命名实体上的多样性。

cs.CL

查看原文摘要

Large language models (LLMs) can generate accurate responses, but these are void of diversity. We attempt to address this for the task of creative short story generation. Drawing on established writing conventions and known LLM limitations, we target variation in genre, tone, style, and named entities. To promote diversity across these dimensions, we introduce DivLM, an LLM post-training framework consisting of two phases. First, we perform continued pre-training on a creative writing corpus and restore instruction-following capabilities using weight residuals. We then apply reinforcement learning with a custom, composite reward function that jointly maximizes diversity across the targeted narrative dimensions while maintaining response quality. Our empirical results on two LLM families show that DivLM increases diversity metrics by more than 9% on average compared to alternative approaches, while preserving instruction following, overall response quality, and similarity to human outputs.

版本更新 · v2arXiv:2608.20084

证据门控的任务与运动规划:结合视觉语言模型

Evidence-Gated Task and Motion Planning with Vision-Language Models

Tsunehiko Tanaka, Matthew Stephenson, Alistair Macvicar, Edgar Simo-Serra

AI 速读 基于摘要

提出证据获取与可行性门控(EAFG)框架,让VLM生成子目标并由TAMP执行以获取视觉证据,再据此决定继续规划、补充证据或停止,从而提升长时程操作任务的可完成性与可行性判断。

cs.RO · cs.AI

查看原文摘要

Robots executing long-horizon manipulation tasks from natural-language instructions must reason about both semantic task structure and geometric feasibility. Hierarchical approaches combining Vision-Language Models (VLMs) with Task and Motion Planning (TAMP) offer a promising solution, but VLM-generated subgoals may rely on prior knowledge without sufficient observational support. This can lead to the omission of task-relevant subgoals or attempts to execute instructions whose requirements cannot be met in the environment. We propose Evidence Acquisition and Feasibility Gating (EAFG), a framework for evidence-gated task and motion planning that acquires visual evidence to specify appropriate task plans and assess whether given instructions can be fulfilled. EAFG first acquires evidence by having a VLM generate subgoals and a robot execute action sequences planned by TAMP for these subgoals. For feasibility gating, the acquired evidence is used to decide whether to proceed with task planning, acquire further evidence, or halt. When proceeding, the VLM generates task subgoals conditioned on the acquired evidence, and TAMP computes low-level actions. We evaluate EAFG in three cooking scenarios involving explicitly specified required objects, underspecified instructions, and instructions requiring an absent object. EAFG improves task completion over a VLM-TAMP baseline in the explicit and underspecified scenarios and enables appropriate halting when a required object is absent.

新论文 · v1arXiv:2610.40287

只有被接受的 token 才算数:延迟目标下投机解码的能量核算

Only Accepted Tokens Count: An Energy Accounting of Speculative Decoding Under Latency Targets

Bole Ma, Ayesha Afzal, Jan Eitzinger, Harald Koestler, Gerhard Wellein

AI 速读 基于摘要

在生产级服务条件下测量投机解码的能耗,发现其节能取决于被接受 token 的比例,且随批大小增大而缩小,甚至可能变为耗能。

cs.DC · cs.AI · cs.LG · cs.PF

查看原文摘要

Large language model serving is limited by facility power. Energy per token determines how many tokens a datacenter can serve, while a latency target bounds how quickly each user receives them. During decode, every weight is read from memory for every generated token. Batching amortizes this read across users but makes no individual user faster. Speculative decoding does: a drafter proposes several future tokens, and the target model verifies them in a single forward pass that reuses the same weight read. Because every drafted token must be verified whether or not it is accepted, the energy speculation saves depends on how many drafted tokens are accepted. This saving is hard to pin down. It varies across target models from different attention families and across drafting schemes, and it depends on the text being served. Every drafter we evaluate accepts fewer tokens on conversation than on code, and every trained drafter accepts fewer on Romansh, a low-resource language, than on English. We measure speculative decoding under production serving conditions (SGLang, CUDA graphs enabled) on H100 and H200 GPUs, at batch sizes up to 64 across 5 corpora. On dense models, verification, not drafting, dominates the energy cost. The saving shrinks as the batch grows, because batching has already shared the weight read that speculation would divide among the accepted tokens. At large batch sizes, block drafters push verification past the balance point between arithmetic and memory traffic into the compute-bound regime, where the saving becomes a loss, and a drafter with low acceptance raises energy per token. Meeting a tighter latency target with speculation then costs additional energy. Larger batches lower energy per token without speculation. Speculation adds to that saving only when acceptance is high, and on the model we tested it leaves little headroom for latency-preserving DVFS.

新论文 · v1arXiv:2610.40285

MUSBRIC:面向可重构肌肉骨骼机器人的乐高兼容气动肌肉积木

MUSBRIC: LEGO-Compatible Pneumatic Muscle Bricks for Reconfigurable Musculoskeletal Robots

Qiyao Wang, Yinglei Zhu, Liang Zhou, Wenzhe Gong, Xin-Jun Liu, Huichan Zhao

AI 速读 基于摘要

作者提出一种乐高兼容的气动人工肌肉模块及配套 MuJoCo 仿真器,用于快速搭建和探索可重构肌肉骨骼机器人。

cs.RO

查看原文摘要

Musculoskeletal robots combine compliant actuators with articulated skeletons, but exploring alternative configurations often requires repeated fabrication. We present MUSBRIC, a modular hardware platform and accompanying MuJoCo-based simulator for reconfigurable musculoskeletal robots. LEGO-compatible endcaps turn fiber-reinforced extensile pneumatic artificial muscles into reusable, plug-and-play muscle bricks that connect directly to standard LEGO components. Experimentally identified actuator behavior supports corresponding musculoskeletal simulations. An elbow-joint prototype validates load-dependent flexion and extension, showing that pulley-guided routing enables reversible motion and a mechanical stop stabilizes the straight posture. A robotic hand demonstrates compliant grasping and multi-joint construction. Matched hardware and simulation sweeps across 15 leg configurations demonstrate systematic exploration of attachment geometry, while a quadruped assembled from four legs demonstrates walking. Together, these demonstrations span mechanism analysis, configuration exploration, and functional robot construction within a single reconfigurable system. The hardware designs and simulation code will be released as open source soon to facilitate reproduction and further development.

新论文 · v1arXiv:2610.40284

LoRe-MIM:面向全身PET/CT自监督表征学习的丢失或替换掩码图像建模

LoRe-MIM: Lost-or-Replaced Masked Image Modeling for Self-Supervised Representation Learning in Whole-Body PET/CT

Amartya Bhattacharya, Bashirul Azam Biswas, Biratal Raj Wagle, Michael S. Leapman, Matthew E. Maeder, James B. Yu, Indrani Bhattacharya

AI 速读 基于摘要

作者提出LoRe-MIM自监督框架,通过将图像区域置零(Lost)或替换为互补模态(Replaced)进行掩码重建,在全身PET/CT多任务上报告优于基线。

cs.CV

查看原文摘要

Deep learning models for whole-body positron emission tomography/computed tomography (PET/CT) hold significant clinical potential for disease detection, treatment planning, and response assessment. However, the time and cost associated with expert annotations remain major bottlenecks in developing robust and generalizable models. Although self-supervised learning (SSL) has emerged as a promising approach to mitigating annotation scarcity, its application to whole-body PET/CT remains relatively underexplored due to the limited availability of large-scale datasets and the challenges associated with learning complementary cross-modal representations. To address these limitations, we curate a heterogeneous, multi-tracer, multi-institutional cohort comprising 6,531 whole-body PET/CT scans and propose LoRe-MIM (Lost-Or-Replaced Masked Image Modelling), a novel self-supervised framework designed to learn multimodal representations through masked image reconstruction. Specifically, LoRe-MIM introduces a masking strategy in which image regions are either replaced with zeros (Lost) or substituted with corresponding complementary imaging modality (Replaced), encouraging the model to capture both modality-specific characteristics and cross-modal relationships. We evaluate the learned representations across multiple downstream tasks, including multimodal PET/CT image reconstruction, patch-based classification into cancer vs. non-cancer, whole-body lesion segmentation, label-efficient training, and robustness assessment. Experimental results demonstrate that LoRe-MIM consistently outperforms the corresponding state-of-the-art baselines across these tasks, highlighting its potential as a scalable and generalizable self-supervised learning framework for whole-body PET/CT analysis.

版本更新 · v2arXiv:2605.19629

联邦线性随机逼近的高斯近似与乘子自助法

Gaussian Approximation and Multiplier Bootstrap for Federated Linear Stochastic Approximation

Ilya Levin, Maksim Shuklin, Eric Moulines, Paul Mangold, Sergey Samsonov

AI 速读 基于摘要

该论文为联邦线性随机逼近建立Berry-Esseen型界与联邦高斯近似,并据此提出一种无需显式估计渐近协方差矩阵的在线乘子自助推断方法。

stat.ML · cs.LG · math.OC

查看原文摘要

In this paper, we establish Berry-Esseen-type bounds for federated linear stochastic approximation (LSA). Our results provide the first federated Gaussian approximations for LSA that explicitly capture communication-computation trade-offs and heterogeneity-aware error terms, quantifying the effects of local step size, number of local updates, and heterogeneity on convergence rates. We present results for both (i) constant step size regime and (ii) decreasing step size with an increasing number of local iterations, recovering the recent rates of Bonnerjee et al. [2025] as a special case. As a primary application of our results, we develop an online multiplier bootstrap procedure for inference on the last iterate, which avoids explicit estimation of the asymptotic covariance matrix, and obtain non-asymptotic validity guarantees for this procedure.

新论文 · v1arXiv:2610.40283

通过潜力引导的子轨迹平衡进行潜在路径探索

Latent Path Exploration via Potential-Guided Subtrajectory Balance

Xiaoling Zeng, Qi Zhang

AI 速读 基于摘要

提出 SubLAT,用相对答案潜力与 Subtrajectory Balance 引导语言模型在连续潜在空间中的随机推理路径探索。

cs.CL · cs.LG

查看原文摘要

Continuous latent reasoning enables language models to perform intermediate computation without generating explicit reasoning traces. Advances in stochastic latent reasoning allow multiple paths to be sampled in continuous space, but stochasticity alone does not ensure effective exploration. A key challenge is guiding stochastic transitions between intermediate latent states toward useful reasoning paths. We introduce SubLAT, which couples a relative answer potential with Subtrajectory Balance to learn stochastic latent exploration. The relative potential evaluates the answer support of sampled states against replacement states, with a correctness signal at the terminal state. Subtrajectory Balance relates potential differences to forward and backward transition densities across subtrajectories of different lengths. The model is jointly trained with answer supervision, CoT supervision, and representation distillation. Experiments on arithmetic and deductive reasoning show increasing solution coverage with larger sampling budgets across in-domain and out-of-domain benchmarks, as well as improvements on several structural OOD benchmarks. Trajectory analyses reveal progressive divergence among sampled latent paths and higher mean relative potentials for correct trajectories across arithmetic benchmarks.

新论文 · v1arXiv:2610.40280

潜在预测在感觉诱发fMRI中产生跨被试可对齐的表征

Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI

Serwan Jassim, Victoria Bosch, Daniel Anthes, Elia Bruni, Tim Kietzmann

AI 速读 基于摘要

作者报告,仅用脑数据以自监督JEPA训练的被试专属编码器在下游脑描述与图像重建任务上表现有竞争力,且不同被试的编码器可完全无监督对齐并跨被试迁移解码头。

cs.LG · cs.AI · q-bio.NC

查看原文摘要

Decoding sensory-evoked functional magnetic resonance imaging (fMRI) data is a central analytical tool in cognitive neuroscience. Here we ask whether self-supervised learning (SSL), which has been scarcely explored in this domain, can yield representations that support strong downstream performance. To do so, we adapt a joint embedding predictive architecture (JEPA) to train participant-specific encoders on brain data alone. The encoders never see the stimulus images or any representation derived from them. Applied to the Natural Scenes Dataset (NSD), we evaluate our learned brain embeddings on the downstream tasks of brain captioning and image reconstruction, as well as cross-participant generalization. Our self-supervised approach achieves competitive performance with parameter-rich supervised pipelines that are trained end-to-end with access to image and language data. We further find that encoders trained independently for different participants can be aligned fully unsupervised, using neither images nor stimuli shared between them. After alignment, a neural decoding head trained on one participant can be applied to another without fine-tuning and retains most of its within-subject performance on image reconstruction and brain captioning. By removing the need for images and shared stimuli, our approach is a step towards pooling fMRI data across participants and, eventually, across datasets.

版本更新 · v2arXiv:2604.06167

Unsupervised Topological Characterization of Slug, Churn and Annular Flow in Small-Diameter Vertical Pipes Using Euler Characteristic Surfaces

Brady Koenig, Sushovan Majhi, Atish Mitra, Abigail Stein, Burt Todd

原文摘要

Regime transitions in vertical gas-liquid flow are read from mechanistic models or assigned by eye, and for churn flow neither route has produced a settled criterion. We ask how much an unsupervised topological description of flow video can establish about them. The description is the Euler characteristic surface, a count of the connected gas and liquid regions in each frame across morphological scales. Kernels derived from it are combined by unsupervised multiple kernel learning, and the trials are divided into contiguous groups along gas velocity. For 37 air-water trials in 2-in. tubing at one liquid rate, with three viewing stations averaged, four groups are separated at 4.33, 7.51 and 11.70 m/s. Each division falls at or within one trial of a change in the visual evaluation of the same videos; cuts placed at random would match as closely in 12% of cases. The divisions move between viewing stations and under resampling, a kernel built on gas velocity divides any sampled range into roughly equal parts and cannot locate a transition, and the data do not support a revised transition criterion. On independent images from an annulus, churn shows about three times the across-scale variance of slug. Within the band the published criteria assign to churn, the two upper cuts fall at graded changes in the rankings, consistent with a progression within churn; if confirmed by further data, they would subdivide the churn region.

cs.LG · math.AT

版本更新 · v2arXiv:2610.14617

Cointegrated Regressors: Where Folded Concave Penalties Go Beyond LASSO

Hongqi Chen, Chengwang Liao, Ziwei Mei, Zhentao Shi

原文摘要

LASSO is one of the most popular regularization methods for high-dimensional regression models. While cointegration is common in practical applications of predictive regressions with many regressors, the convex penalty of LASSO overly suppresses the coefficients of cointegrated regressors and therefore fails to deliver consistent parameter estimation. We employ folded concave penalties (FCP), including the well-known SCAD and MCP, to address this issue. Using FCP, we establish two asymptotic results: (i) a local oracle property for the penalized regression, and (ii) a global oracle property for regressions with a penalty-level constraint. In particular, the latter guarantees a global solution that consistently estimates the true coefficients and enjoys oracle prediction performance. Simulation studies and an application to predicting the euro area unemployment rate show that FCP improves variable selection and out-of-sample prediction relative to LASSO.

stat.ME · econ.EM · stat.ML

版本更新 · v2arXiv:2608.05430

Robust Context-Aware Detection of Malicious Instructions in Text

Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik

原文摘要

The remarkable instruction-following ability of modern LLMs has enabled their practical use in orchestrating workflows of tool-using agents. This, however, also exposes such agents to attacks which embed malicious instructions in text, such as indirect prompt injection (IPI). One class of approaches to defend against such attacks aims to detect malicious sentences within otherwise benign text. While a number of approaches for this have been proposed, all tend to be brittle under adaptive paraphrasing attacks, in part because they do not capture sufficient global context to effectively differentiate malicious text from benign. We address this gap by developing an approach for malicious sentence classification that is both context- and query-aware, which we then harden against paraphrasing through two adversarial training (AT) methods: feature-space robust learning and AT with simulated LLM-based paraphrasing. Moreover, we parametrize the AT variants to facilitate a smooth tradeoff between utility and attack robustness. In extensive experiments using IPI benchmarks we show that our approach outperforms state-of-the-art defense baselines under both static and adaptive paraphrasing attacks while preserving high utility. Our code is publicly available at https://github.com/tavia-liu/CAD.

cs.CR · cs.LG

新论文 · v1arXiv:2610.40278

Neighborhood Elites: Quality-Diversity Search for Uncertainty Quantification in Question Answering

Mesut Ceylan, Arda Baris Basaran, Elgar Fleisch, Filipe Barata

原文摘要

Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into downstream tasks. Perturbation-based uncertainty quantification (UQ) addresses this by probing a model over a set of input rewrites and reading uncertainty from how much its predictions vary. Yet this set is usually built generically, by free paraphrasing, token-level perturbation, or adversarial search. Such rewrites leave two things uncontrolled that matter in QA: what kind of change is made to the context, and how explicitly the context supports the answer. When neither is controlled, the composition of the set is determined by the generator rather than by design, and the estimate inherits whatever that generator happens to produce. Quality-diversity (QD) search is built to cover a predefined exploration space, so we recast input perturbation as a QD problem and propose \emph{neighborhood elites (NE)}, a neighborhood constructor that spreads answer-preserving rewrites across two axes, the kind of edit and the explicitness of support. We compare NE against three other neighborhood constructors, holding the editor, QA model, uncertainty measure and search objective fixed, and against three scores read from the original context. Across five extractive-QA datasets and five instruction-tuned LLMs, NE improves failure detection against every other constructor in at least 24 of the 25 dataset-model pairs, reaching 0.726 AUROC and 0.211 AUPRC lift over the base rate. Additionally, NE detects failure better than semantic entropy computed over decoder samples, by 0.074 AUROC and 0.062 AUPRC lift, and this advantage widens as the neighborhood grows.

cs.AI · cs.CL

新论文 · v1arXiv:2610.40276

TaskFrame: Connecting Task-Level Planning with Frame-Level Control for Game Agents

Guangzhi Wang, Junfu Pu, Yiran Wang, Xingyilang Yin, Honghao Chen, Cheng Cheng, Lingen Li, Yinan Zhou 等 13 位作者

原文摘要

Building general game agents requires both high-level task reasoning and low-latency action control in rapidly changing visual environments. These capabilities favor models with substantially different computational profiles, making them difficult to realize within a single model. In this work, we present TaskFrame, a hierarchical planner-controller framework that connects task-level planning with frame-level keyboard-and-mouse control. A vision-language task planner decomposes a high-level goal into an ordered sequence of atomic instructions and is optimized through supervised learning and dependency-aware GRPO. The hidden states of special goal tokens that terminate each atomic instruction provide continuous goal embeddings that are cached and reused across control steps. A causal Transformer controller combines the embedding of the active goal with recent observations to predict discrete keyboard and mouse-button actions and continuous camera motion at every game step. We train the system in three stages: planner training, controller pretraining, and joint alignment. Experiments in Minecraft show that TaskFrame is competitive with general-purpose vision-language models on instruction decomposition, and that in closed-loop evaluation the agent achieves a higher combat success rate than the evaluated baselines.

cs.CV · cs.AI

新论文 · v1arXiv:2610.40271

Gaussian Distillation of Flow Policies

Youssef Saied, Ziyad Sheebaelhamd, Claire Vernade, François Fleuret

原文摘要

Flow policies are among the strongest robot controllers and are well suited to modelling multimodal action distributions. Our analysis shows that the continuous-action distributions of the studied flow policies are well approximated by Gaussians. We propose the Gaussian Action Readout (GAR), which replaces a flow policy's final layer with a Gaussian readout trained on just 0.02% of eligible states, while keeping the rest of the network frozen. It samples with one action-network pass, gives closed-form likelihoods, and achieves near-teacher task success at up to twice the inference speed.

cs.RO

新论文 · v1arXiv:2610.40264

From MS/MS evidence to adaptive spectroscopic characterization: Reinforcement learning guided by candidate molecular structures

Bowen Gao, Lei Zhu, Yiying Wang, Wenjie Yu

原文摘要

Small-molecule identification from tandem mass spectrometry (MS/MS) may require complementary measurements. Herein, we propose a structure-informed deep Q-network (SI-DQN) that uses existing MS/MS evidence to decide whether further characterization is needed, which measurement to request, and when to stop. The policy combines spectral representations and candidate rankings with score-weighted descriptors of the candidates' chemical features and structural differences. The policy was evaluated on 79,462 held-out samples with simulated MS/MS, infrared (IR), and nuclear magnetic resonance (NMR) spectra from the Multimodal Spectroscopic Dataset. Evaluation used fixed hard candidate sets containing the correct structure and equal normalized acquisition costs. Averaged across three training runs, SI-DQN increased Top-1 accuracy from 80.10% to 93.78% for positive-ion MS/MS starts and from 70.44% to 93.31% for negative-ion starts. The corresponding mean additional measurement counts were only 0.227 and 0.340 per sample, respectively. Complete acquisition achieved 97.72% accuracy with four additions, whereas SI-DQN reduced the additional measurement count by 94.3% and 91.5%. Relative to a rule-based policy, SI-DQN reduced the composite loss combining terminal ranking error and acquisition cost by 19.3% and 25.5%. Adding structural information to DQN further improved accuracy while reducing requests across all three training runs. At comparable ranking uncertainty, SI-DQN increased request rates relative to DQN more strongly in groups with high structural disagreement, where larger reductions in composite loss were also observed. Together, these results support using the ambiguity among candidate structures after MS/MS analysis to guide further characterization, providing a quantitative basis for balancing identification performance against subsequent measurement effort.

cs.LG

版本更新 · v3arXiv:2603.26498

Rocks, Pebbles and Sand: Modality-aware Scheduling for Multimodal Large Language Model Inference

Konstantinos Papaioannou, Thaleia Dimitra Doudali

原文摘要

Multimodal Large Language Models (MLLMs) power platforms like ChatGPT, Gemini, and Copilot, enabling rich interactions across text, images, and videos. Unlike text-only workloads, multimodal requests are inherently heterogeneous, differing by orders of magnitude in latency and memory footprint. Existing LLM serving systems, designed for homogeneous text workloads, struggle under this heterogeneity: large image and video requests monopolize GPU resources, causing severe head-of-line blocking and degrading the responsiveness of lightweight, latency-critical text queries. Recent multimodal serving systems mitigate this interference through disaggregation, isolating encoding and inference stages across GPUs. While effective at large scale, such designs introduce severe GPU underutilization in more practical, moderate-scale deployments. In response, we build RPS-Serve a modality-aware scheduling framework that leverages the extreme heterogeneity in multimodal workloads and introduces a simple abstraction: videos behave like rocks, images like pebbles, and text like sand. Then, it lets sand flow quickly through pebbles and rocks, maximizing GPU utilization while ensuring fast responsiveness for lightweight requests and controlled execution for heavier ones. To achieve this, RPS-Serve estimates the GPU admission cost of each request, classifies requests into rocks, pebbles, and sand using lightweight clustering, and applies priority-based scheduling with aging to balance performance across modalities. Evaluation across state-of-the-art MLLMs shows that RPS-Serve increases GPU utilization by 65% and reduces TTFT by up to 9.3x, on average across models, compared to disaggregation-based multi-modal systems.

cs.DC · cs.AI

新论文 · v1arXiv:2610.40257

Learned Terminal Costs for Short-Horizon Model Predictive Control of Autonomous Trucks in Interactive Highway Traffic

Hooman Hamze, Benjamin Houshmand, Deepthi Pathare, Erik Börve, Morteza Haghir Chehreghani, Nikolce Murgovski

原文摘要

Autonomous highway driving for heavy-duty trucks is a challenging control problem. The greater mass, dimensions and intricate dynamics increase the requirements for cooperation from surrounding traffic in critical maneuvers, requiring a careful balance between safety constraints and efficient long-horizon decision making. Model Predictive Control (MPC) provides rigorous constraint satisfaction but relies on terminal cost which can limit its effectiveness at short, computationally affordable horizons. Reinforcement Learning (RL) captures long-term driving behavior but offers no constraint guarantees and tends toward overly conservative policies when trained under sparse collision penalties. In this paper, we propose a hybrid MPC and RL framework for highway driving in autonomous trucks, where a finite-horizon MPC, solved via dynamic programming, uses a pre-trained RL model for terminal cost estimation. We evaluate the framework in a simulation environment with reactive surrounding traffic and compare it against pure MPC with zero terminal cost, rollout with terminal cost estimation using a base policy, and pure RL. Results show that the hybrid approach achieves zero collisions with the lowest cost of any configuration.

cs.LG · cs.AI · cs.RO · eess.SY

版本更新 · v2arXiv:2610.14009

When Log Parsing Removes What Matters: Detecting Failures in Distributed GPU Workloads

Boyuan Cui, Yuyang Zeng, Yifang Tian, Hans-Arno Jacobsen

原文摘要

Large AI models increasingly rely on distributed GPU execution, yet it remains unclear whether established anomaly detection methods transfer effectively to this setting. We introduce GF-Bench, a PyTorch-based framework for generating controlled failures in distributed GPU workloads, and a dataset produced with it. The framework supports extensible workload and fault-injection logic; based on this design, the current release targets failures visible in multi-GPU communication logs and provides 220 labeled two-GPU runs covering normal behavior, CUDA out-of-memory fail-stop faults, and persistent-straggler fail-slow faults. Using GF-Bench, we evaluate three sequence-based methods (DeepLog, LogAnomaly, and LogBERT) and the large language model (LLM)-based LogPrompt with in-context learning (ICL) and chain-of-thought (CoT) prompting strategies on parsed logs, and additionally evaluate LogPrompt on raw logs. On parsed inputs, no method reliably detects both failure classes, and the highest overall F1 score is 0.667. Raw inputs raise the overall F1 score of ICL-LogPrompt to 0.983, at 9.0x its average input-token usage and 8.9x its per-run cost. These results reveal a trade-off between effectiveness and efficiency: parsed inputs reduce LLM token use and inference cost but can discard the distributed execution context required for accurate failure detection. GF-Bench provides a reproducible basis for studying cost-efficient anomaly detection methods and can be extended to additional GPU workloads and failure types.

cs.LG · cs.AI · cs.DC · cs.SE

新论文 · v1arXiv:2610.40256

When Requirements Interact: Scaling Long-Horizon Coding via Interdependent Specifications

Yishuo Cai, Minzheng Wang, Liang Zhao, Linghao Zhang, Lei Li, Shicheng Li, Xu Sun, Fuli Luo

原文摘要

To succeed in real-world long-horizon software development, coding agents must satisfy multi-dimensional task specifications, such as interface compatibility and error handling, and do so without breaking existing dependencies. However, current works lack specification in both quantity and diversity, often emphasizing primary goals while ignoring complex constraints. Synthesizing tasks to bridge this gap presents two challenges: naively adding specifications risks reducing tasks to trivial checklists rather than compelling joint reasoning, and verifying these subtle interactions risks overlooking hidden flaws or rejecting valid alternatives. To address these challenges, we introduce CodeSpecWeave, a framework for synthesizing tasks with rich, interdependent specifications. Grounded in real developer seeds, a synthesis agent iteratively develops both coupled task requirements and executable tests, while a review agent audits solution trajectories from multiple models to guarantee test reliability. Using this pipeline, we construct 4,670 training tasks across 2,865 repositories. Applying Reinforcement learning on these tasks significantly improves performance over the base model on DeepSWE-v1.1, largely outperforming existing baselines. Furthermore, we curate CodeSpecWeave-Bench, a rigorous benchmark comprising 100 tasks and 1,044 specifications, which clearly separates frontier models and reveals significant headroom in handling interdependent engineering constraints.

cs.SE · cs.CL

新论文 · v1arXiv:2610.40254

Statistical Analysis of Synthetic Data with Verification: A Linear Regression Framework

Heejune Sheen, Harrison H. Zhou

原文摘要

Synthetic data are widely used for training modern AI systems. However, their statistical understanding remains limited. It is well recognized in statistics that repeated self-training on synthetic data can amplify errors inherited from pre-trained models, leading to model collapse. Verification plays a crucial role in selecting high-quality synthetic data to help prevent model collapse and improve model performance. We study verified self-training in a linear regression framework, where a pre-trained estimator generates synthetic data with injected generation noise and a verifier selects samples according to a verification threshold. Post-training on the accepted samples updates either all coordinates (full fine-tuning) or only an active subset (partial fine-tuning). Our analysis reveals three potentially counterintuitive effects. We establish that tighter verification does not always lead to lower prediction risk. We also find that a suitable level of injected generation noise can reduce prediction risk, while excessive noise can increase it. Moreover, full and partial fine-tuning can respond differently to the same verification rule, since pre-training error in the frozen coordinates affects both sample selection and post-training risk. We analyze these effects by deriving finite sample risk bounds for four separate regimes determined by the relative scales of the verification threshold, generation noise, and pre-training error. The bounds precisely characterize how verification affects prediction risk across these regimes. In particular, we quantify how the generation noise, the effective accepted sample size, and the covariance of the accepted covariates affect prediction risk. The analysis extends to iterative verified full fine-tuning, where sufficiently tight verification reduces the initial error contribution at a geometric rate.

stat.ML · cs.LG · math.ST

新论文 · v1arXiv:2610.40253

Confidence-Aware Speed-over-Ground Estimation from Doppler Spectra via Reconstruction-Based Representation Learning

Malte Stelzer, Marvin Sach, Timo Bartels, Dinu Mihailescu-Stoica, Sören Kohnert, Florian Poprawa, Marc Zeller, Tim Fingscheidt

原文摘要

Reliable speed-over-ground estimation from ground-facing Doppler spectra is essential for mobile platforms such as railway systems. Classical signal-processing approaches can provide accurate estimates under favorable conditions, but often degrade in challenging conditions. We propose confidence-aware speed-over-ground estimation trained on rail-domain data that estimates speed over ground and frame-level confidence from Doppler spectra with several novel contributions: First, we transfer the idea of exploiting a reconstruction task by an autoencoder for performance estimation from previous work to Doppler RaDAR. Second, we append a speed-over-ground estimation head operating on the autoencoder's latent space features. Third, we omit the reconstruction decoder during inference but add a low-cost dedicated confidence head for frame-wise error-bound estimation. Fourth, we reveal how noise augmentation training can provide high robustness to the method. Experiments show that our approach improves speed estimation accuracy over classical baselines while providing informative confidence estimates that indicate the reliability of individual predictions, even under adverse signal conditions.

eess.SP · cs.LG

新论文 · v1arXiv:2610.40252

Conformal Annotation with Randomized Expert Review: Application to Online Cell-Type Labeling

Xuhe Zhang, Zhi Huang, Ying Jin

原文摘要

Artificial intelligence (AI) models can accelerate cell-type annotation in digital pathology, but safely scaling their use requires determining, with error control, which model-generated labels can be accepted without expert review. This is challenging in evolving workflows because cell morphology and type composition may change across tissue regions and slides, making one-time calibration unreliable. We propose Conformal Annotation with Randomized Expert review under Distribution shift (CARED), a distribution-free framework that leverages randomized expert audit to achieve long-run error control for AI-assisted annotation under distribution shift. For each incoming batch, CARED uniformly selects a subset of cases for expert review and uses the acquired labels to calibrate later decisions. Among unreviewed cases, CARED determines a subset of them to safely skip expert labeling, while suggesting candidate labels for the others for downstream resolution. We prove that this workflow provides long-run control of cumulative error over both the full stream and the cells outside of the audit sample, without stationarity or exchangeability assumptions. We further enhance the framework by introducing class-conditional guarantees to ensure error control within important but rare cell types, together with a utility module to target more automatic resolutions, smaller candidate sets, and greater biological coherence, without compromising validity. Experiments on pancreas, lung, and ovary annotation streams, together with a stream constructed from real expert annotations, show that CARED controls the cumulative errors while a substantial fraction of cells (up to 70%) bypass expert review.

stat.ME · cs.LG · stat.AP · stat.ML

新论文 · v1arXiv:2610.40250

Distributional Reward Calibration and Budget-Neutral Credit Assignment for Multimodal RLVR

Lang Chen, Zongxin Xu, Borui Wang, Anran Liu, Shitong Chen

原文摘要

We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that converts scalar verifier rewards into a comparable sequence-level signal, and a \emph{token-level credit assignment} step that distributes that signal over the trajectory. Existing estimators typically address only one of these stages: affine baselines preserve the shape of each task's reward law, so heavy tails and binary cliffs propagate into the gradient, while token-level credit rules tie the size of each token's update to raw confidence scales and need not conserve the total credit issued by the verifier. We propose \textbf{TACE} (Two-stage Advantage and Credit Estimation), a two-stage estimator that addresses both stages. At stage~(S1), we replace linear standardization with a one-dimensional optimal-transport map to a standard normal, which gives a common population reward law across tasks and caps finite-sample outliers deterministically. At stage~(S2), we rank-calibrate a stop-gradient evidence contrast within each trajectory and renormalize the clipped token weights to have mean one, so credit is redistributed across tokens while its total mass and sign are conserved. We prove population-level inter-task moment equity, a deterministic tail bound, and mass-conservation, boundedness, and sign-anchoring properties that affine baselines and unnormalized token weights do not satisfy. On a multimodal reasoning suite, TACE obtains the strongest results on a majority of the benchmarks but does not dominate every setting.

cs.AI