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

+0新增论文
+0其中 AI 相关
+0已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-22 08:44 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 13:08 — 2026-11-22 13:08(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:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 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 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.25761

AdaptReg: Skip-level FiLM Adapter for Task-Specific Adaptation of a Frozen Registration Foundation Model

Shuyue Shi, Rong Yuan, Lin Tian

原文摘要

Longitudinal PSMA-PET/CT registration is a key step in assessing treatment response in prostate cancer, and it requires more than generic alignment accuracy: the deformation must preserve lesion volume, so that measured changes in metabolic tumor volume (MTV) and total lesion glycolysis (TLG) reflect treatment response rather than registration artifacts. We propose AdaptReg, which adapts a frozen registration foundation model to such task-specific requirements through a lightweight trainable adapter branch with identity-preserving initialization. Keeping uniGradICON fully frozen, we apply FiLM-style per-voxel affine modulation ($γ$, $β$) to its decoder skip connections; the modulation is generated from anatomical semantic features of a frozen TotalSegmentator encoder and supervised by a lesion volume-preservation loss. On the official Codabench validation set (20 pairs), AdaptReg achieves DSC 0.7585, HD95 6.33 mm, MTV/TLG errors of 1.68%/2.11%, and 0.0022% non-diffeomorphic voxels, improving on the uniGradICON + instance optimization baseline by $+0.05$ DSC and reducing the MTV/TLG errors by 70.9%/67.7%. On the hidden official test set (160 pairs), AdaptReg achieves CT DSC 0.816, PET DSC 0.598, and MTV/TLG errors of 4.02%/3.46%, ranking fourth among 16 teams in the final PSMAReg evaluation. Code: https://github.com/shishuyue/AdaptReg

cs.CV · cs.LG

新论文 · v1arXiv:2611.25760

Characterizing and Detecting Unfaithful Work Reports by Coding Agents

Wenhao Yang, Runzhi He, Minghui Zhou, Pengfei Gao, Dayi Lin, Qingwei Lin, Dongmei Zhang

原文摘要

Coding agents increasingly carry out long-horizon development tasks, autonomously planning and executing multi-step actions that span files, tools, and sessions. Because developers rarely follow each action, and agents resuming the work depend on records of what was done, the agent's work report often becomes the primary account of what was changed and established. When the report contains false or unsupported claims, it gives recipients false assurance: incomplete work may be accepted without verification, incorrect assumptions about the current state can propagate to later steps and agents, and evaluators that credit stated success may reward the report rather than the work. Yet little is known about what unfaithful reporting looks like in real development work, or how developers and agents handle it once it surfaces. Starting from real developer--agent conversations in SWE-chat, we conduct a systematic mixed-methods analysis of self-admitted unfaithful reports. We identify eleven subtypes in four categories: misreported observations, misattributed evidence, overstated task success, and faulty technical explanations, with overstated task success the most common. Handling these problems involves on average 4.3 further user turns and 12.71 minutes of recorded response and execution time, and users express dissatisfaction more often. Among 435 work reports that we separately sample and annotate, \NaturalPositiveShare{}\% contain at least one unfaithful claim. We also develop FaithDetector, a detector for unfaithful reporting informed by the observed patterns. On naturally sampled reports, FaithDetector attains \NaturalDetectorMacro{}\% macro-F1, about 13 percentage points above the baseline. Together, our findings and FaithDetector provide empirical evidence and an automated method for checking reporting faithfulness, informing agent evaluation and training feedback.

cs.SE · cs.AI

新论文 · v1arXiv:2611.25757

Uniqueness, Proximity, and Scaling in Atomic Splittable Polymatroid Congestion Games

Tobias Harks

原文摘要

We give a polynomial-time algorithm for exact equilibrium computation in atomic splittable polymatroid congestion games with integral ranks and rational player-specific affine latencies with positive slopes. The algorithm first computes equilibria of associated integer-splittable games, in which demands are allocated in multiples of a common packet size. For arbitrary polymatroid bases, no polynomial-time algorithm for these discrete equilibria was previously known. We provide such an algorithm and use progressively finer packets to recover the continuous equilibrium exactly. Our proof uses the multiple-exchange theorem of Oki and Schwarcz (2025) to obtain two exchange matchings that yield equilibrium proximity under changes of packet sizes and ranks, independently of cost coefficients. We then bound the matching deficiency caused by rank changes and construct compatible submodular rank roundings. Together these give a polynomial-time packet-halving algorithm using polynomially many submodular-function minimizations and exact rational arithmetic. The analysis rests on a uniqueness theorem of independent interest: for arbitrary real polymatroid ranks and continuously differentiable, strictly increasing, convex latencies, we prove uniqueness of equilibria, resolving a previously open problem.

cs.GT

新论文 · v1arXiv:2611.25756

Self-Supervised Operator Learning for Channel Estimation in Fluid Antenna Systems

Erqiang Tang, Zixin Wang, Wei Guo, Shenghui Song, Jun Zhang, Khaled B. Letaief

原文摘要

Fluid antenna systems (FAS) have emerged as a promising technology for enhancing wireless communications through adaptive antenna repositioning. Recently, Fourier neural operators (FNOs) have shown strong potential for FAS channel estimation owing to their ability to learn resolution-invariant mappings and generalize across different port densities. However, existing operator learning approaches require densely sampled channel realizations as training labels, whereas a practical receiver only collects noisy pilot observations from a small subset of ports. This mismatch between training requirements and practical channel acquisition poses a major obstacle to deployment. To address this challenge, we develop a self-supervised framework that trains the FNO-based estimator directly from noisy sub-sampled pilots without any labeled channel fields. The proposed objective combines a pilot splitting strategy, which creates supervision at ports hidden from the model input, with a correction based on Stein's unbiased risk estimate (SURE) that eliminates the measurement noise bias. We prove that this objective admits the same minimum mean square error (MMSE) solution as the ideal supervised criterion. Since the loss relies solely on received pilots, the estimator can be continually adapted online on the live pilot stream. Simulation results show that the self-supervised FNO achieves accuracy comparable to supervised training, generalizes zero-shot to unseen port resolutions, and rapidly recovers from distribution shift via online adaptation.

cs.IT · eess.SP

新论文 · v1arXiv:2611.25754

ADAPT: Adaptive Decision and Abstention with Pool-Size-Aware Thresholds for Service Routing

Manile Srun, Muntasir Adnan, Arslan Shaukat, Carlos C. N. Kuhn

原文摘要

Retrieval-based classifiers efficiently route queries to specialised services, but they typically select a candidate even when no suitable service exists. We introduce Adaptive Decision and Abstention with Pool-Size-Aware Thresholds for Service Routing (ADAPT), a lightweight routing architecture with an explicit fallback option that enables queries to abstain from specialist selection. ADAPT uses the separation between the highest relevance score and the candidate score distribution as routing confidence. Experiments across retrieval models and increasing numbers of services reveal a consistent empirical behaviour: the confidence distribution changes systematically with candidate-pool size K, making fixed abstention thresholds increasingly miscalibrated. ADAPT addresses this effect with a K-aware threshold that adapts as services are added without classifier retraining. Evaluation across two specialist datasets shows that this simple mechanism provides an effective accuracy-cost trade-off compared with generative LLM routing, supporting lightweight and dynamically extensible service-routing architectures.

cs.AI

版本更新 · v3arXiv:2611.22897

Born for the Task: Rethinking Quantum Chemistry with Foresighted Agentic Computing

Haozhi Han, Junjie Yang, Ruge Zhang, Zihe Huang, Pengyi Xu, Bo Zhang, Xianyi Zhang, Yunquan Zhang 等 12 位作者

原文摘要

Quantum chemistry relies on general-purpose software, whose generality leaves many large-scale calculations beyond practical resource budgets. Coding agents make task-specific programs cheap to write, but not efficient ones easy to find: whether a computational strategy is accurate and fast enough becomes clear only after it actually runs at the target scale. We introduce MakoBORN, a foresighted agentic computing framework that synthesizes high performance quantum chemistry programs on demand. MakoBORN anticipates the behavior of each strategy before execution, extrapolating its error from representative small systems and predicting its runtime from the target-scale workload and measured hardware throughputs. Building on these predictions, MakoBORN unfolds the preset schemes of existing packages into independently configurable algorithmic components, selects the fastest strategy within the error tolerance from the predicted accuracy-runtime Pareto frontier, and guides coding agents to compile it with component-level performance predictions. For a Hartree-Fock calculation with 50,024 basis functions, MakoBORN finishes in 1.41 h on a single CPU node, 77$\times$ faster than the estimated runtime of a general-purpose baseline and still 9.8$\times$ faster with development time included. On a single GPU, MakoBORN completes the ubiquitin calculation in 2.1 h, the same order of runtime as the GPU-accelerated package Mako on 64 GPUs, and shortens the B-DNA duplex calculation from an estimated two months to 8.1 h (173$\times$).

cs.AI · physics.chem-ph

新论文 · v1arXiv:2611.25752

Beyond Error Mitigation: Using Boosting for Noisy Quantum Machine Learning

Anastasiia Lukianenko, Yash J. Patel, Nurbolat Kenbayev, Vedran Dunjko

原文摘要

Quantum error mitigation (QEM) can recover information about ideal quantum computations from noisy circuit executions, but may require a large sampling overhead. Fundamental lower bounds show that recovering noiseless observables without problem-specific information can require superpolynomially many samples, with exponential overhead for broad classes of noisy circuits. However, problem-specific information can reduce the number of samples needed to obtain the required answer. We investigate this possibility in supervised quantum machine learning, where labeled examples provide information about the function to be learned. Binary classification provides such a setting, since correct prediction depends on the sign and margin of the classifier output rather than on accurate reconstruction of every noiseless expectation value. We develop a theoretical and empirical framework for comparing boosting of noisy parameterized quantum circuits with probabilistic error cancellation (PEC), requiring both methods to reach the same learning target. For the specified circuit architectures under Pauli noise, we establish a common hypothesis-class complexity bound: matching empirical margin loss gives the same upper bound on expected classification risk. We derive resource criteria and evaluate AdaBoostR and Real AdaBoost in finite-shot teacher-student simulations across circuit depth and physical noise strength. Under the same classification-accuracy target, boosting requires fewer circuit executions as depth and noise increase. Boosting also achieves higher test accuracy than the corresponding reference. For the supervised-learning problems studied, these results demonstrate a task-dependent resource advantage: exploiting information retained in noisy outputs can avoid the cost of ideal-output reconstruction without sacrificing observed classification performance.

quant-ph · cs.LG

版本更新 · v3arXiv:2602.07045

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

Zhiming Luo, Hebaixu Wang, Haonan Guo, Jing Zhang, Bo Du

原文摘要

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,000 question-answer pairs with an average question length of 129.87 words, spanning 14 tasks and up to eight temporal phases. VLRS-Bench is constructed via a specialized pipeline that integrates RS-specific priors and expert knowledge to ensure geospatial realism and reasoning complexity. Experimental results reveal significant bottlenecks in existing state-of-the-art MLLMs, providing critical insights for advancing multimodal reasoning within the remote sensing community.

cs.CV · cs.AI

版本更新 · v2arXiv:2606.05263

Learning Which Evidence-Seeking Decisions Matter: Calibrated Counterfactual Replay for Language Agents

Renwei Meng, Chengyi Sun, Hongyi Zhang, Xiaoyi Hou

原文摘要

Language agents answer questions by searching, reading, and checking claims. A reward on the final answer says little about which of those decisions earned it, since an agent can reach the right string after redundant searches or with half the evidence missing. We treat the question as an experiment. At a saved decision point, PCCC-RL, for prefix-conditioned counterfactual credit, restores the tool state, runs the action the agent chose alongside a feasible alternative, and lets the same frozen policy finish both branches. The difference in final score then samples what the decision was worth. Replaying everything is too expensive, so the method predicts each action's credit up front, checks a random subset, and uses the recorded selection probabilities to correct the errors of that prediction, spending the budget where a further check can still move the training signal. Alternatives are drawn from the prefix alone, which keeps the comparison a usable gradient baseline. On HotpotQA and MuSiQue, joint exact match, requiring a correct answer together with complete supporting evidence, reaches 56.71% and 36.82%, gains of 4.19 and 3.86 points over a baseline with the same replay access. The gain concentrates in complete evidence chains and accumulates over many updates. Single-update effects stay uncertain, and citation coverage and scope distinctions such as "none" versus "not all" remain open.

cs.LG · cs.AI

版本更新 · v4arXiv:2509.22050

BrainPro: Process-conditioned Pretraining with Topographic Retrieval for Large EEG Models

Yi Ding, Muyun Jiang, Weibang Jiang, Shuailei Zhang, Xinliang Zhou, Chenyu Liu, Shanglin Li, Yong Li 等 9 位作者

原文摘要

EEG foundation models are pretrained on heterogeneous corpora, but two challenges remain underexplored: (1) experimental protocols provide mental-process cues that are rarely used in masked pretraining, and (2) electrode montages vary across datasets, making spatial representations montage-dependent. Existing methods typically learn a single general-purpose representation and model spatial structure implicitly, limiting their ability to exploit process-related information under montage heterogeneity. We introduce BrainPro, a process-conditioned self-supervised pretraining framework that couples topographic retrieval with shared and process-associated representation learning. BrainPro maps dataset-specific montages to a universal channel-region template and retrieves channel- and region-level spatial filters to form a topographically aligned spatial basis. Over this basis, BrainPro learns a shared encoder for general EEG structure and additional affective, motor-related, and auxiliary residual branches for process-associated variation. Protocol-derived mental-process cues condition branch activation and region-weighted masked reconstruction, incorporating topographic spatial priors and process information. Across nine public BCI benchmarks, BrainPro achieves strong performance among evaluated baselines. Ablations, channel-drop analysis, encoder-configuration studies, and spatial-filter visualizations suggest that topographic retrieval and process-conditioned representation learning jointly improve EEG decoding. Our code is available at https://github.com/yi-ding-cs/BrainPro.

cs.LG

新论文 · v1arXiv:2611.25744

Embodied Human-Data Interaction

Niklas Elmqvist

原文摘要

We propose the concept of human-data interaction (HDI) as the human manipulation, analysis, and sensemaking of large, unstructured, and complex datasets. We then proceed to suggest an embodied approach to HDI to build physical reasoning environments for these difficult and polymorphic tasks. We illustrate our approach with two examples: tangible lenses for visual exploration, and an educational computer game with tangible bricks.

cs.HC

新论文 · v1arXiv:2611.25741

Beyond geometric lattices: pseudo-atoms and redundant join representations in the face lattice of the permutohedron

Giovanni Rossi

原文摘要

We study the lattice obtained from the poset of ordered set partitions (the Fubini poset), ordered by merging adjacent blocks, by adjoining a bottom element of rank -1. It is the face lattice of the permutohedron. We look at it from the point of view of geometric lattices: it is graded, atomic and coatomic in the strong sense that every element is a meet of coatoms, but it is not semimodular. Its atoms are the $n!$ permutations, and its elements of rank one, which we call pseudo-atoms, are the edges of the permutohedron. Describing ordered set partitions by chains of subsets, the cuts, we show that the rank is modular whenever the meet is above $\bot$, while the join of two distant atoms can have large rank, so that the rank of the join is a metric on permutations. An element has a unique representation as a join of atoms only up to rank one; above it, irredundant representations have sizes ranging from two to the rank, and the redundancy of an element is its number of atoms minus two. The Möbius function is that of an Eulerian lattice, the Whitney numbers are the face numbers of the permutohedron, and the characteristic polynomial has the alternating coefficients of the geometric case, but only $\bot$ and $\top$ are left-modular, so the lattice is not supersolvable. We show that it is CL-shellable, we exhibit EL-labelings for $n\le5$, and we compare the independent sets of Raz arXiv:2307.05005 (v3, Jan. 2026) with irredundant families and with the matroid of the vertices of the permutohedron. Replacing ordered set partitions by partial flags of subspaces of $\mathbb F_q^n$ gives a $q$-analogue, whose Möbius function is $(-1)^{\mathrm{rk}+1}q^κ$, with $κ$ the number of pairs of elements in a common block at $q=1$, and whose characteristic polynomial and Betti numbers are polynomials in $q$.

math.CO · cs.DM

新论文 · v1arXiv:2611.25738

CACO: Coverage-Aware Coordinated Optimization for Continuous Generative Retrieval

Pan Zhang, Nan Zhuang, Yongkang Zhang, Kun Xú, Zhongtao Jiang, Zhiwei Wang, Kun Xǔ, Youhuan Li

原文摘要

Continuous generative retrievers powered by flow matching and diffusion sample multiple queries in item embedding space for parallel approximate nearest-neighbor (ANN) search under fixed retrieval budgets. However, optimizing distribution diversity or target-level interest separation ignores set-level retrieval geometry: sampled queries collapse onto overlapping ANN neighborhoods, while discrete top-K lookup and single-target supervision block end-to-end coverage optimization. We introduce CACO (Coverage-Aware Coordinated Optimization), a lightweight self-supervised post-training framework that coordinates queries from frozen flow-matching and diffusion retrievers toward complementary item coverage with negligible additional inference latency. CACO uses empirical retrieval frequencies across sampled reference queries as a relevance proxy, formulating a label-free coverage objective that improves recall across all 30 backbone-dataset settings in offline greedy selection experiments. To avoid the inference overhead of generating a large query pool, CACO employs a coordinated query adjustment network that combines inter-query bidirectional attention with gated relative directions, finally updating queries by bounded tangent-space projection and spherical retraction. During training, CACO applies tangential antithetic perturbations and measures each query's marginal gain via counterfactual single-query replacement, yielding an unbiased gradient estimator of smoothed set coverage across non-differentiable ANN search. On eight public benchmarks and an in-house 24-partition streaming industrial dataset, CACO improves Recall@100 by up to 23.7% and Recall@400 by up to 23.9% over the strongest baseline, cuts inter-query overlap by 53.3%-64.9%, and adds only 0.5%-3.0% inference latency.

cs.IR

新论文 · v1arXiv:2611.25736

An LLM-Driven Traffic-Control xApp for Dynamic 5G RAN Intents

Valerio Triolo, Luca Valcarenghi, Emilio Paolini

原文摘要

Programmable Radio Access Networks (RANs) enable runtime deployment of traffic-control functions, but selecting the appropriate configuration remains challenging as network conditions and service requirements change over time. Conventional solutions often rely on static rules or learning-based controllers with predefined state and action spaces, limiting their ability to accommodate changing intents. This paper introduces an LLM-driven xApp for traffic control in programmable RANs. The proposed architecture combines operator-defined service intents, runtime E2 interface telemetry, and the currently deployed configuration to generate traffic-management policies without blocking packet forwarding or the processing of incoming E2 measurements during LLM inference. Experiments on an OpenAirInterface 5G environment show that the proposed controller dynamically adapts the traffic-control pipeline to runtime intent changes, achieving an average intent satisfaction ratio of 0.91, compared with 0.52 for a static TC-RAN configuration. When channel conditions degrade, the controller maintains an intent satisfaction ratio of approx. 0.88, compared with approx. 0.4 for the static baseline.

cs.NI · cs.AI

版本更新 · v2arXiv:2605.07274

Structured Role-Aware Policy Optimization for Multimodal Reasoning

Bingqing Jiang, Guoxi Zhang, Jasper Wang, Bingning Wang, Difan Zou

原文摘要

Reinforcement learning from verifiable rewards (RLVR), especially with Group Relative Policy Optimization (GRPO), has shown strong potential for improving the reasoning capabilities of large vision-language models (LVLMs). However, in multimodal reasoning, final-answer rewards are typically assigned at the sequence level and do not distinguish the functional roles of different tokens, making it difficult to determine whether a correct answer is supported by task-relevant visual evidence. In this paper, we revisit multimodal RLVR from the perspective of role-aware token-level credit assignment, where structured responses are decomposed into perception tokens for extracting visual evidence and reasoning tokens for deriving answers from that evidence. Based on this perspective, we propose Structured Role-aware Policy Optimization (SRPO), which refines the sequence-level GRPO advantage into role-aware token-level advantages without changing the reward function. Specifically, SRPO assigns role-specific credit by using self-distilled on-policy contrasts: perception tokens are emphasized according to their visual dependency under original versus corrupted visual inputs, while reasoning tokens are emphasized according to their consistency with the generated perception. These role-specific signals are further unified through a shared trajectory-level baseline, yielding positive token weights that adjust relative update magnitudes while preserving the original GRPO reward and advantage signs, without requiring external reward models or separate teachers. Experiments across diverse multimodal reasoning benchmarks show that SRPO improves evidence-grounded reasoning, highlighting the importance of moving beyond uniform sequence-level credit toward role-aware optimization for reliable multimodal reasoning.

cs.AI · cs.LG

新论文 · v1arXiv:2611.25734

From Reliance to Overreliance: Taxonomizing and Detecting Relational Risks in AI Companionship

Viet Cuong Nguyen, Fiona Li, Chang Wan, Sheyril Agarwal, Nhi Nguyen, Angel Hsing-Chi Hwang, Munmun De Choudhury

原文摘要

Companion AIs are increasingly used for emotional support, yet distinguishing meaningful engagement from harmful reliance remains difficult. We introduce the Taxonomy of Relational Risks (TRR), which operationalizes users' emotional overreliance (EO) as observable conversational behaviors and separately identifies evidence of relational harm (RH), enabling empirical examination of when reliance behaviors co-occur with adverse consequences. Using naturalistic Character.AI and Replika conversations from 110 adults, we found EO-related behaviors in 63.2% of non-roleplay conversations, while observable relational harms appeared in 10.5%. Although EO did not necessarily lead to harm, recurring patterns often co-occurred with harmful outcomes, suggesting value as risk indicators. Open-source LLMs satisfactorily detected 12 of 14 EO behaviors in at least one configuration. Qualitative analysis revealed expectations of care, repeated support seeking, dependency, distress, and reduced confidence in personal judgment. We argue for graduated safety interventions tailored to patterns and trajectories of EO-related behavior.

cs.HC · cs.AI

新论文 · v1arXiv:2611.25733

Can LLMs Resolve Entity Conflicts in Domain Specific NLU Pipelines?

Akansha Bhardwaj, Mingbo Cui, Victor Guimaraes, Dominik Kohler, Diana Nicoleta Popa, Meghana M. Reddy, Paolo Rosso

原文摘要

Resolving entity conflicts is a critical step in Pipeline-based NLU architectures, especially when multiple extractors provide overlapping or conflicting outputs. Traditional rule-based entity conflict resolution methods often lack flexibility and are unscalable. In this work, we aim to study if the broad knowledge of LLMs can be leveraged to resolve entity conflicts in domain specific NLU pipelines. We present an experimental comparison between a traditional rule-based conflict resolution method, and two LLM-based approaches: a multi-shot prompting method using the Llama3.1-8B-Instruct model and a LoRA fine-tuned Llama3.1-8B-Instruct model. The evaluation was conducted under two setups: (1) a broad assessment of LLM's capability to match existing NLU pipeline output, and (2) a more controlled scenario assessing the LLM accuracy on human-labeled data. Results show that while multi-shot prompting offers ease of adaptation and rapid behavioral changes, the fine-tuned model delivers superior performance on complex, ambiguous cases. Ultimately, the best approach appears to be a combination of both strategies, leveraging multi-shot prompting's flexibility alongside the broad accuracy gains of LoRA fine-tuning for a more comprehensive performance.

cs.IR · cs.LG

版本更新 · v4arXiv:2604.25322

Simulation of temporomandibular joint space changes based on rigid-body transformation using virtual and semi-virtual models: a proof-of-concept study

Agnieszka Anna Tomaka, Krzysztof Domino, Michał Tarnawski, Emil Kalinowski, Małgorzata Domino, Dariusz Pojda

原文摘要

The integration of multimodal data within a common coordinate system is essential for spatial analysis of the stomatognathic system. This proof-of-concept study aims to use a multimodal data integration methodology for digital modeling of spatial changes in the temporomandibular joint (TMJ) across various mandible positions. As two digital models were investigated, the study also aimed to investigate inter-model differences in the simulated TMJ joint spaces. A transformation tree framework was proposed to integrate cone-beam computed tomography (CBCT), facial, and dental representation images into a common coordinate system and to simulate seven mandible positions using rigid-body transformations. Data were collected from a single participant. Spatial changes in mandible positions were propagated to TMJ articular surface positions using both models, although the results were model-related. The model-based uncertainty was quantified using two metrics - the consistency error and the model disagreement. The consistency error presented anisotropy in the latero-lateral direction. The model disagreement were not uniform across mandible positions and were higher (p<0.0156) at the TMJ level (1.46 mm) than at the dental level (0.47 mm). The proposed methodology may prove useful in future research investigating the geometric relationships between mandible position and the TMJ. However, given the proof-of-concept nature of this study, the numerical findings should not be generalized to broader clinical populations.

cs.CV

新论文 · v1arXiv:2611.25729

A generic construction of complex codebooks from functions over Abelian groups

Ziling Heng, Chenkun Xie, Jiantao Hu, Xiaoyan Jing

原文摘要

Codebooks with small inner-product correlation play a central role in direct spread code division multiple access communications, space-time coding, compressed sensing, and related areas because they improve system performance. This paper presents a generic construction and a modified construction of complex codebooks from functions on finite Abelian groups. By choosing perfect nonlinear functions, we systematically obtain several families of optimal or asymptotically optimal codebooks with respect to the Welch or Levenshtein bounds. These constructions recover a number of known optimal codebooks and also yield new codebooks with previously unreported parameters.

cs.IT

新论文 · v1arXiv:2611.25728

What's in the box? Revealing Object Layouts Inside Opaque Boxes via Contactless Vibration Excitation and Sensing

Ethan Turok, Matan Kichler, Shai Bagon, Mark Sheinin

原文摘要

Can we reveal what is inside an opaque box by observing its surface vibrations? Objects inside a box alter its mechanical response, providing cues about their hidden locations. We introduce a method that uses these cues to predict a box's 2D occupancy layout entirely remotely. A nearby speaker excites vibrations, which we measure on one visible wall using a grid of laser points and a camera measuring each point's speckle-pattern shifts. Our model, WhisperBox, learns to encode these vibrations into a latent representation and decode it into an occupancy map of the box's contents. The method requires no physical contact to excite or sense vibrations. We demonstrate layout recovery across various boxes and single- and multiple-object scenes, with generalization to unseen object instances, positions, orientations, and weights, as well as changes in laser placement and excitation source. Our analysis reveals that informative frequency bands need not coincide with the box's resonances and that the learned latent space captures object placement and supports arithmetic operations. These results demonstrate the potential of remote vibration sensing to infer spatial layouts hidden from view.

cs.CV

新论文 · v1arXiv:2611.25725

On the Hamel Coefficients and the Boltzmann-Hamel Equations for the Rigid Body

Andreas Müller

原文摘要

The Boltzmann-Hamel (BH) equations are central in the dynamics and control of nonholonomic systems described in terms of quasi-velocities. The rigid body is a classical example of such systems, and it is well-known that the BH-equations are the Newton-Euler (NE) equations when described in terms of rigid body twists as quasi-velocities. It is further known that the NE-equations are the Euler-Poincare, respectively, the reduced Euler-Lagrange equations on SE(3) when using body-fixed or spatial representation of rigid body twists. The connection between these equations are the Hamel coefficients, which are immediately identified as the structure constants of SE(3). However, an explicit coordinate-free derivation has not been presented in the literature. In this paper the Hamel coefficients for the rigid body are derived in a coordinate-free way without resorting to local coordinates describing the rigid body motion. The three most relevant choices of quasi-velocities (body-fixed, spatial, and hybrid representation of rigid body twists) are considered. The corresponding BH-equations are derived explicitly for the rotating and free floating body. Further, the Hamel equations for nonholonomically constrained rigid bodies are discussed, and demonstrated for the inhomogenous ball rolling on a plane.

cs.RO

新论文 · v1arXiv:2611.25724

Verifying Before Enhancing: Target Evidence Chain Verification for Infrared Small Target Detection

Jiayi Zuo, Songwei Pei, Shuhuai Wang, Yifei Wu, Shangguang Wang

原文摘要

Infrared small target detection is essential for early warning, surveillance, remote sensing, and space-based target perception. However, infrared small targets are typically tiny, weakly textured, and boundary-blurred, making them difficult to distinguish from complex backgrounds. Moreover, target-like background structures can produce salient responses across multiple scales, making response strength alone insufficient for reliable target discrimination. To address this challenge, we propose VBE-UNet, a Target Evidence Chain Verification Network that assesses candidate reliability beyond response magnitude through complementary evidence cues. Specifically, counterfactual background explanation models local target evidence, while joint evidence verification integrates cross-scale support and perturbation-based contribution verification to guide feature recomposition. The resulting reliability estimates guide selective feature refinement, promoting target-relevant responses while reducing unsupported background activations. Extensive experiments on IRSTD-1K, NUDT-SIRST, and NUAA-SIRST demonstrate that VBE-UNet achieves superior detection accuracy and lower false-alarm rates compared with state-of-the-art methods. Ablation studies and evidence reliability analysis further validate the effectiveness of the proposed verification framework.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.04910

Fast Gauss Sums via Flash Attention

Nicolaj Rux, Sebastian Neumayer

原文摘要

Gauss kernel sums are the computational core of maximum mean discrepancies (MMDs), kernel gradient flows, Stein variational gradient descent (SVGD), and many other kernel methods. At the same time, softmax attention has received an extraordinary amount of hardware-aware code engineering, culminating in FLASH attention. We show that Gauss kernel sums with arbitrary, signed weights can be evaluated via FLASH attention: two small input augmentations turn the normalized softmax reduction into the unnormalized Gauss sum, without writing a single line of custom GPU code. For feature dimension $D>8$ in fp16, this approach beats compiled PyTorch code in speed and memory, and PyKeOps kernels in speed and accuracy at comparable or lower memory. Its memory scaling remains linear.

cs.LG · math.NA

版本更新 · v2arXiv:2611.13481

Euclidean Hulls of Double Cyclic Codes of Arbitrary Block Lengths

Awadhesh Kumar Shukla, Om Prakash Pandey, Sachin Pathak, Ashish Upadhyay

原文摘要

A $\mathbb{Z}_2$-double cyclic code of block length $(r,s)$ can be viewed as a $\mathbb{Z}_2[x]$-submodule of $\mathbb{Z}_2[x]/\langle x^r - 1 \rangle \times \mathbb{Z}_2[x]/\langle x^s - 1 \rangle$. In 2023, Gao et al. \cite{GWF23} investigated the Euclidean hulls of double cyclic codes over $\mathbb{Z}_2$ for both separable and non-separable cases. In the non-separable setting, they determined the hull generators under the assumption that the block lengths are coprime (i.e., $\gcd(r,s)=1$) and left the non-coprime case ($\gcd(r,s) > 1$) as an open problem. In this paper, we resolve this open problem by deriving the explicit hull generators for arbitrary block lengths $(r,s)$, recovering the coprime setting as a special case of our framework. Furthermore, we establish the necessary and sufficient conditions for non-separable double cyclic codes to be linear complementary dual (LCD) and provide several numerical examples to validate our theoretical findings.

cs.IT

新论文 · v1arXiv:2611.25722

DACA: Dual-Anchor Collaborative Agent for Zero-Shot 3D Visual Grounding

Jiaming Liu, Linghe Kong, Guixu Zhang, Huaxi Huang

原文摘要

3D visual grounding (3D-VG) is a task that bridges the natural language and 3D space, serving as a foundational capability for embodied intelligence and human-computer interaction. Although recent 3D-VG agents overcome the reliance on pre-processed 3D point clouds, they essentially employ a unidirectional, pipeline-style tool-calling architecture. This architecture separates semantic understanding from geometric reconstruction, leading to error accumulation and an inability to autonomously recover from failures. To address this flaw, this paper proposes the Dual-Anchor Collaborative Agent (DACA), which reinterprets 3D-VG as a semantic-geometric dual-anchor collaborative reasoning paradigm. DACA comprises two complementary specialized tools: the semantic anchor tool holds the visual semantic features of the target and achieves efficient target tracking via optical flow and VLM local verification; the geometric anchor tool holds the 3D spatial geometric features of the target and performs global spatial reasoning via voxelization and multi-keypoint projection. The two components exchange information bidirectionally via a standardized tool call protocol, autonomously deciding on the next perception-action step to form a closed-loop optimization. Experiments on the ScanRefer and Nr3D benchmarks demonstrate that zero-shot DACA achieves an overall Acc@0.25 of 73.6\% on ScanRefer and 70.4\% overall accuracy on Nr3D, far surpassing the latest zero-shot 3D-VG methods. The code and models are available at https://github.com/liujia99/DACA

cs.CV

新论文 · v1arXiv:2611.25721

MemMend: A Selective Revision Framework for Memory Question Answering

Sheng Shi, Geng Li

原文摘要

Revising every answer from a long-term memory can consume substantial inference budget and damage facts that were already correct. We introduce MemMend, a modular selective revision framework that routes potentially incomplete answers to an editor, represents corrections as bounded exact-text replacements, and accepts only edits with resolvable source coordinates and valid edit operations. The editor preserves the current answer when no legal repair is proposed; accepted edits require no additional semantic-verification call. On 1,986 LoCoMo development questions, MemMend achieves 67.17 conversation-macro F1 and 88.35 mean Judge score, improving over a verified revision chain by 0.82 and 1.24 points while using 62.37% fewer revision calls. Routing uses 54.15% fewer revision calls than ungated local review, with similar F1 but a 0.67-point lower Judge score. Applied directly to native PropMem, Mem0, and SimpleMem answers, the editing interface raises F1 by 3.79, 6.44, and 0.42 points. It outperforms same-gate rewriting and saves 49.85-83.72% of editing calls relative to ungated editing, which retains higher F1 in this adaptation. A source-by-editing factorial supports local editing for F1 but leaves an independent quality benefit from source obligations unresolved. Transfer to 451 LongMemEval-V2 Small questions also favors revision efficiency, while an external PerLTQA dialogue subset reveals a completeness gap. These results support selective editing as a reusable quality-cost operating point.

cs.AI

版本更新 · v2arXiv:2605.08963

Survey-aware Machine Learning: A Guideline for Valid Population Health Inference based on Scoping Review

YongKyung Oh, Henry W. Zheng, Jeffrey Feng, Alex A. T. Bui

原文摘要

Machine Learning (ML) models trained on complex health surveys such as the National Health and Nutrition Examination Survey (NHANES) often ignore primary sampling units, stratification variables, and sampling weights. This practice violates the independence assumptions of standard evaluation methods. As a result, estimates become biased, uncertainty is underestimated, and fairness assessments fail to reflect population-level disparities. We propose Survey-aware Machine Learning (SaML), a nine-step guideline that incorporates survey design metadata across the ML lifecycle. Through a scoping review of 16 methodological papers, we summarize existing work on weighted model training, design-based cross-validation, and survey-adjusted performance evaluation. We also identify gaps in hyperparameter tuning and deployment. We provide task-specific guidance that clarifies which steps are required for different analytical objectives. SaML provides a checklist for valid population inference from survey data.

stat.ML · cs.LG

新论文 · v1arXiv:2611.25717

VR-SparseQuant: Accurate FP4 Quantization with 2:4 Sparsity on Vera Rubin

Samir Khaki, Wei-Chen Wang, Song Han, Ryan Hanrui Wang

原文摘要

In recent years, GPUs have incorporated increasingly specialized support for low-precision computation, from Hopper's FP8 to Blackwell's FP4 Tensor Cores. Precision formats have evolved alongside this hardware, from MXFP4 and NVFP4 on Blackwell to E2M1 FP4 with direct UE5M3 block scaling on Vera Rubin, which we term as $\boldsymbol{VRFP4}$. These advances help serve larger language models at lower cost, but four-bit activation quantization can substantially degrade model quality. We introduce VR-SparseQuant, which uses Vera Rubin's elementwise 2:4 sparsity to recover accuracy while retaining native FP4 execution. By allowing two sparse streams to overlap, we use the same FP4 value budget as dense quantization to refine activations with larger errors. Offline scale-ratio calibration avoids runtime search, while a shared-weight GEMM accumulates both streams efficiently. On Nemotron-3-Nano-30B-A3B, VR-SparseQuant reduces WikiText-2 perplexity from $\boldsymbol{6.85}$ to $\boldsymbol{5.57}$ versus dense RTN W4A4. Including activation preparation, our native Rubin kernels for VRFP4 achieve up to $\boldsymbol{3.1\times}$ GEMM and $\boldsymbol{2.7\times}$ MoE speedup over BF16. To the best of our knowledge, this is the first study of adaptive activation quantization using Vera Rubin's elementwise 2:4 structured sparse FP4 instructions.

cs.CL

版本更新 · v2arXiv:2611.19247

GameWM: Toward Next-Generation Video Games with Interaction-Centric World Models

Bing He, Runze Wang, Fei Zha, Zhongyuan Wu, Ke Xu, Tao Zhuang, Yuxuan Xie, Zhongyuan Liu

原文摘要

For more than half a century, video games have pursued better graphics, more natural interaction, and more engaging gameplay. Generative video models (VMs) now bear on all three. Neural networks already draw most of the pixels in shipped games, and recent world models let a lightweight game engine keep the world state while a VM turns the engine's coarse proxy video into final frames. These systems, however, treat the VM as a renderer that only restyles motion the engine has already authored, which leaves most of its generative capacity unused and limits the diversity a game can offer. We present GameWM, a design for next-generation games built on a clear division of labor. The GameWM-engine keeps what must be exact: rules, state, camera, and the layout of the world, which also spares the video model from having to remember it. The GameWM-VM generates what is expensive to author by hand: the look of the world and the detail of the player's interactions. One game mechanic can then be realized in many visually and physically distinct ways, while its outcome stays exactly as the engine computed it. To realize this division of labor, we build GameWM as a complete system: a data engine centered on interactions rather than exploration, an interface through which authored character sheets, scene art, and skill descriptions enter the model, and a model family from 5B to 33B parameters with a real-time causal variant for play. Together they give every player a fresh version of the same game: each player's own character, world, and skills turn the same engine mechanics into a new experience, while every event keeps the timing and outcome the GameWM-engine computed.

cs.CV

新论文 · v1arXiv:2611.25713

Interpreting DeepStack-Style Vision-Language Models: Do Input or Deeper-Layer Visual Tokens Drive Answers?

Yucheng Du, Yi Nian, Ruixue Lian, Yue Zhao, Xiyang Hu

原文摘要

DeepStack-style vision-language models feed visual tokens to the language model at its input, and again at deeper layers. We call these the main entry and the later entries. What do the later entries add when the model already has the image? We give the entries versions that differ in one object's color and see which one the answer follows. On photographs, the original DeepStack follows the later entries, while Qwen3-VL-8B/32B follow the main entry. Does weakening the main entry give the later features more influence? On synthetic images, we keep this conflict and reduce color saturation at the main entry only. The unchanged later features gain a stronger effect on the relative scores of the two colors, in all four models, including Granite Vision. This holds even under mild desaturation, when accuracy without the conflict stays at 100%. To test whether later features can also correct errors, we degrade both entries and restore only the later ones. The same blur costs both Qwen models 50 percentage points of accuracy on stripe orientation. The 32B model recovers 48 points and the 8B model only 8. Accuracy with one clean entry predicted which entry each model can lose, and five of six tested predictions held on new GQA attribute questions. With the other entry zeroed, Qwen3-VL-8B loses only 0.3 points on its main entry alone, and DeepStack at most 3.45 points on either entry alone. In split inference on these questions, DeepStack can then send only its main-entry features at higher precision. This takes 49% fewer bytes than all entries at a shared precision, at similar accuracy.

cs.CV