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 10:29 — 2026-11-17 10:29(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 17,909 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)
版本更新 · v2arXiv:2610.21779

FuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing Modalities

Xin Zhang, Robby T. Tan

原文摘要

Multi-modal semantic segmentation benefits from complementary sensors, but this benefit is fragile when some modalities are degraded or missing at test time. Many existing methods rely on dedicated fusion modules or multi-branch cross-modal encoders, and the fusion often becomes unreliable when modalities are absent, leading to substantial performance drops. We propose FuseAdapt, a parameter-efficient framework that performs fusion within the adaptation space of a frozen vision foundation model (VFM), exploring whether VFM priors can serve as an effective shared backbone for multi-modal segmentation. Instead of attaching a standalone fusion network, FuseAdapt assigns each modality a lightweight adaptation branch and performs adaptation-space fusion by keeping Q/V low-rank adaptation private to each modality and routing only FFN low-rank residual activations across modalities inside the frozen backbone. The pretrained VFM remains fixed while modality-specific corrections and explicit cross-modal interaction are learned through the adaptation paths. To handle missing modalities, we further introduce Predictive Modality Modeling (PMM), a direct representation-level objective for cross-modal redundancy. During training, PMM masks a target modality and predicts its embedding from the visible ones, supervised by a teacher target computed under full-modality input. PMM is used only during training and adds no inference-time overhead. Across three multi-modal segmentation benchmarks (MCubeS, DELIVER, MUSES), FuseAdapt consistently improves both modality-complete and modality-incomplete segmentation with a small trainable budget, yielding up to +3.01 mIoU under full modalities and +11.25 mIoU under missing modalities over prior state-of-the-art. Project page: https://devinxzhang.github.io/FuseAdapt-Page/

cs.CV

新论文 · v1arXiv:2611.04894

VisSearch-Bench: Evaluating Long Horizon Visual Search in Multimodal Agents

ZhengXian Wu, Qianhao Nie, Zhuohong Chen, Junjie Gao, Yuyao Zhang, Yunyao Yu, Hangrui Xu, Cheng Cheng 等 13 位作者

原文摘要

Multimodal agents use web and image tools to answer questions beyond their internal knowledge. Some search tasks use images mainly to identify an initial entity, then rely on text retrieval. These tasks offer limited insight into how agents connect information across images, objects, and search steps. We therefore focus on visual context management. This involves organizing and using visual information and linking it to other findings during search. Visually intensive tasks require agents to combine object appearance, local details, or spatial relations with external information. We introduce VisSearch-Bench, with 204 human-written tasks across 7 main domains and 25 subdomains. It covers Set-wise Visual Search, Sequential Visual Search, Hybrid Wide-Deep Search, Competitive Visual Disambiguation, and Visual-Structure-Guided Search. Each task provides a reference answer, traceable evidence, and scoring rules. Accuracy measures complete task success, while Process Score measures the correctness and completeness of individual results and subquestion answers. Across 16 multimodal models, the best system fully solves only 26.47% of tasks, even with search tools. These results highlight the challenge of linking visual evidence with search results to produce complete answers.

cs.CV · cs.AI

新论文 · v1arXiv:2611.04893

Fault-tolerant shallow recurrent decoders for sparse sensing with missing sensor measurements

Matteo Romilio Pasqual, Matteo Tomasetto, J. Nathan Kutz, Andrea Manzoni

原文摘要

Real-world sensing systems are inherently imperfect: sensors may fail, intermittently disconnect, operate with asynchronous sampling rates, and be subject to noise, leading to measurement streams that are irregular, incomplete, and heterogeneous. Nevertheless, sensing strategies for real-time state reconstruction typically assume synchronous and continuously active sensors, a constraint that substantially limits their applicability in operational environments. In this work, we introduce fault-tolerant sparse sensing strategies in the context of shallow recurrent decoders (SHRED) to enable high-dimensional state estimation from sparse, asynchronous, and missing sensor measurements. Specifically, we consider naive imputation strategies, fault-tolerant recurrent temporal encoders, and we introduce four different transformer-based masking mechanisms to make SHRED explicitly aware of sensor availability through the binary data-availability mask. Moreover, we further introduce a multi-step decoding training objective for SHRED, resulting in smoother latent trajectories and more robust predictions. Throughout a synthetic benchmark and three real-world problems in hydrodynamic and ocean modeling, we show that (i) transformer-based masking mechanisms outperform standard imputation techniques and fault-tolerant recurrent architectures, (ii) the multi-step decoding training objective enhances reconstruction fidelity and robustness in the presence of heterogeneous missing-data patterns, while (iii) the computational efficiency of SHRED is preserved, with no additional inference-time overhead.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.41970

When Does Test-Time Search Help World Action Models? An Empirical Audit of Candidate Selection and Simulator Integrity

Jun Liu, Dajie Sun, Zhenglun Kong, Zhenjiang Fan, Peiyan Dong, Fan Yang, Wenbin Zhang, Geng Yuan 等 11 位作者

原文摘要

World-action models increasingly apply test-time scaling, spending extra inference computation on candidate selection and adaptive allocation to improve control. Such gains are credible only when candidates carry exploitable signal, nominal compute savings become real speedup, and evaluation stays reliable. We audit all three on Cosmos Policy and RoboCasa with a premise-first, pre-registered methodology. On clean data, a learned value selector is 1.66 pp worse than random; a hindsight oracle gains only 1.40 pp, with an episode-level interval spanning zero; and 82% of states show identical candidate outcomes, leaving little selection headroom. Token pruning cuts per-forward FLOPs by up to 47% but yields at most a measured 1.15$\times$ end-to-end speedup on the deployed path (1.25$\times$ on a decode-excluded path), short of a 1.5$\times$ target, and our adaptive-allocation experiment is inconclusive under a power gate. We further identify and fix a silent rendering corruption whose rate rises sharply along compute-heavy planning paths while leaving the official direct-policy result unaffected, and release a detector, fix, and scripts. These findings show why test-time scaling should be audited as a chain of premises (decision signal, realized efficiency, evaluationintegrity) rather than by success rate alone. Conclusions are scoped to the tested configuration.

cs.AI

新论文 · v1arXiv:2611.04889

NP-Hardness and a PTAS for Maximum Interval Multicover, with Applications to Dense Subgraphs

Morteza Alimi, Tobias Mömke, Alexandru Popa, Michael Ruderer

原文摘要

Given intervals and points on a line, each point with a demand, and a budget $K$, Maximum Interval Multicover asks for at most $K$ intervals that satisfy as many points as possible, a point being satisfied if it lies in at least as many chosen intervals as its demand. One application is committee elections in which each candidate is approved by consecutive voters and voters have individual demands. Xu, Ran and Zhang introduced the problem and gave a $1/2$-approximation; the objective is not submodular when demands exceed one. Li, Tu, Zhang and Cao gave a polynomial-time approximation scheme (PTAS) for the minimization counterpart, unweighted partial interval multicover, and asked for its complexity. We prove that both problems are NP-hard, even for intervals of equal length; as their optima are integers bounded by the input size, neither has a fully polynomial-time approximation scheme unless $\mathrm{P}=\mathrm{NP}$. We then give a PTAS for Maximum Interval Multicover, also for arbitrary nonnegative nondecreasing rewards for the coverage of each point. Building on a decomposition from Nonner's PTAS for Densest $k$-Subgraph on interval graphs, our scheme cuts the line into pieces at a small loss and solves every piece exactly. The key dynamic program handles intervals crossing a common point by choosing an interleaving of their left and right endpoints rather than sweeping along the line; it needs only two counters to track these intervals. The same algorithm yields PTASes on convex bipartite graphs for Bipartite Dense Subgraph, improving on the ratio $2/3$ of Backer and Keil for the subclass of bipartite permutation graphs, and on interval graphs for Maximum $k$-Vertex Cover and weighted clique counts.

cs.DS

新论文 · v1arXiv:2611.04886

Modelling lock-in of AI adoption through skill erosion

Renaud Lambiotte

原文摘要

Generative AI can improve immediate performance but may erode the human skills required for future work. We study a model in which individuals tend to imitate successful peers, while their independent skills grow with practice and erode with reliance on AI. Because each agent's skill reflects their history, non-users and AI users develop different skill distributions, which we derive exactly. Skill erosion can produce bistability and hysteresis between a low-adoption, high-skill state and a high-adoption, low-skill state. When agents rarely change behaviour at random, the two transitions are asymmetric. A single AI user spreads through a population of experts only if AI-assisted work earns more than expert work, whatever the timescale of skill adaptation. A single non-user, by contrast, can lead an AI-dependent population back to independent work only if they regain enough skill before returning to AI, which becomes easier the more persistent behaviours are. As AI improves, adoption can jump abruptly, and a sufficiently long increase in its benefit, such as a period of low prices, can leave a population relying on AI after the benefit has returned to its initial value. Skill erosion thus creates a history-dependent switching cost that can make widespread AI adoption difficult to reverse.

cs.AI · physics.soc-ph

版本更新 · v2arXiv:2610.17613

MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

Hehai Lin, Zixuan Wang, Ming Yan, Peidong Wang, Shilei Cao, Minzhi Li, Bosheng Ding, Juepeng Zheng 等 9 位作者

原文摘要

Large language model (LLM)-based multi-agent systems (MAS) can solve complex problems beyond the reach of a single agent by decomposing tasks and coordinating complementary capabilities. Despite extensive research on MAS, existing work largely focuses on specific aspects or individual phases of their development and operation, resulting in fragmented perspectives with objectives and signals that are difficult to reconcile across these different settings. To bridge these disconnected perspectives, we conceptualize MAS development and operation as a three-phase lifecycle spanning design-time orchestration before execution, runtime intervention during execution, and post-hoc attribution after execution, and introduce MAS-Gate, a unified node-centric quantification applicable across these phases. Modeling each execution as a directed acyclic graph, MAS-Gate combines within-node utility, which estimates a node's contribution through changes in reference-answer likelihood, with inter-node strength, which approximates semantic uptake and potential downstream reach. We adapt this shared quantification to three objectives: providing a structure-aware dense reward for Orchestrator training, training an Editor to act on execution prefixes using paired rewards from completed edited and unedited trajectories, and supplying risk-ranked nodes as auxiliary evidence for LLM-based post-hoc attribution. Experiments spanning interaction environments, knowledge-intensive multi-hop question answering, general reasoning, and post-hoc attribution demonstrate that MAS-Gate improves workflow construction, targeted runtime editing, and LLM-assisted error localization over corresponding phase-specific baselines. Together, these results establish MAS-Gate as a unified structural interface for improving MAS generation, dynamic editing, and error attribution throughout the lifecycle.

cs.AI · cs.MA

新论文 · v1arXiv:2611.04885

DLER: Dual-Logit Experience Replay for Online Continual Learning

Huiwei Lin, Shanshan Feng, Kong Aik Lee

原文摘要

Online continual learning aims to continuously train neural networks on a non-stationary data stream in a single pass. Rehearsal-based methods alleviate catastrophic forgetting by replaying stored samples, but the imbalance between current and previous data often leads to predictions biased toward current classes. Many approaches have been proposed to overcome the forgetting problem by correcting the bias; however, they still need to be improved in an online fashion. By decomposing the dot-product logits into an angle factor and a norm factor, our analysis reveals that the angle factor efficiently captures novel knowledge but is particularly susceptible to prediction bias, whereas the norm factor helps preserve historical knowledge. Based on these observations, we propose Dual-Logit Experience Replay (DLER), which exploits dual-logits for both model optimization and memory management. Specifically, DLER learns current samples using cosine logits and incorporates additional dot-product logits when replaying previous samples to mitigate prediction bias. To strengthen dual-logit learning under limited replay memory, an auxiliary supervised contrastive objective promotes angular compactness within each class, extending corrections learned from limited replay samples to other samples of the same class. Meanwhile, we introduce a memory update strategy that preferentially retains samples for which dot-product prediction assigns a higher probability to the correct class than cosine prediction, aligning sample selection with dual-logit training. Extensive experiments on three datasets demonstrate the effectiveness of DLER, particularly under limited memory budgets.

cs.LG

新论文 · v1arXiv:2611.04884

Best-of-Many-Worlds MMS Allocation for Chores with Sublinear Disposals

Zehan Lin, Xiaowei Wu, Shengwei Zhou

原文摘要

We study randomized allocations (lotteries) of indivisible chores under additive costs and introduce the notion of MMS1, which requires each agent's bundle to satisfy the maximin share (MMS) bound after the removal of at most one chore. Our main result establishes that every instance admits an ex-ante proportional lottery in whose support every allocation is MMS1 and all but $o(n)$ agents satisfy MMS. Consequently, every realized allocation can be made MMS by disposing of at most $o(n)$ chores. The proposed framework further achieves ex-ante proportionality alongside ex-post $4/3$-MMS, $o(n)$-AMMS, or $1$-out-of-$d$ MMS for $d=(1-o(1))n$. These guarantees substantially improve upon state-of-the-art bounds for MMS allocation for chores with disposal or subsidy, best-of-both-worlds fairness, approximate AMMS, and ordinal MMS approximations.

cs.GT · cs.DS

版本更新 · v2arXiv:2609.23015

An exponential lower bound for the bit pigeonhole principle in resolution over parities

Kamil Braun

原文摘要

Resolution over parities, $\mathrm{Res}(\oplus)$, is the characteristic-two version of resolution over linear equations: clauses are disjunctions of affine equations over $\mathbb F_2$. Superpolynomial size lower bounds were previously known only for restricted refutations: tree-like, regular, or of bounded depth. We prove that every DAG-like $\mathrm{Res} (\oplus)$ refutation of the bit pigeonhole principle with $n+1$ pigeons and $n=2^\ell$ holes has more than $\exp(n/(32768\ell^2))=2^{Ω(n/\log^2 n)}$ clauses, for every $\ell\ge32$, with no restriction on regularity or depth. The proof translates an arbitrary refutation with $S$ clauses into a polynomial calculus refutation of degree $O(\log n)$ over $O(S+n^2)$ groups of extension variables in the style of Buss, Impagliazzo, Krajicek, Pudlak, Razborov, and Sgall. One substitution then removes all extension variables at once and leaves a nonzero low-degree polynomial derived from the pigeonhole axioms alone at degree at most $n/2$; a degree lower bound in the style of Razborov, proved through the homology of chessboard complexes, shows that no such derivation exists. The argument also yields a general sufficient condition for $\mathrm{Res}(\oplus)$ size lower bounds. The main theorem, this condition, and all their dependencies are formalized in Lean 4, and every statement links to its formal proof. The proof was developed with substantial AI assistance within an open research framework described in the final section.

cs.CC · cs.LO

版本更新 · v2arXiv:2610.38946

MAS-Loop: Beyond One-Shot Orchestration towards Self-Evolving Multi-Agent Systems

Hehai Lin, Qi Yang, Chengwei Qin

原文摘要

Training-time multi-agent system (MAS) design seeks to learn reusable orchestration policies, yet prevailing approaches remain largely one-shot: an Orchestrator generates a system but only observes and learns from its terminal outcome. This paradigm discards execution trajectories that expose system-level failures and contain fine-grained information beyond the terminal outcome, leaving no direct basis for revising the source MAS, evaluating the updated MAS, or learning from the resulting contrast. To this end, we introduce MAS-Loop, an execution-grounded framework that closes this feedback loop by coupling an Orchestrator with a trajectory-conditioned Refiner. For each task, the Orchestrator constructs and executes a source MAS to obtain an outcome score and an intermediate trajectory. Conditioned on the trajectory, the Refiner localizes an actionable failure, formulates a trajectory-grounded diagnosis, and proposes a bounded patch to the agents, information flow, or execution configuration. The executable updated MAS is re-executed on the same task to measure its realized outcome under stochastic execution. This pair-MAS comparison provides complementary learning signals: the Orchestrator learns to generate strong systems with fewer recoverable failures, whereas the Refiner learns to expose and repair observed weaknesses, thereby driving policy-level co-evolution across training iterations. Experiments show that MAS-Loop achieves the strongest overall performance among the evaluated baselines, with consistent gains from refinement across all evaluated benchmarks. The co-evolution process also yields MAS-JudgeCorpus, a dataset of execution-grounded source-updated pairs with orchestration- and trajectory-level supervision, which can provide the community with support for MAS reward modeling and trajectory-aware investigation.

cs.MA · cs.AI

版本更新 · v2arXiv:2607.12135

LQG solution for POMDP without estimating states: A minimum variance approach

Ranjan Sarkar, Prabhat K. Mishra

原文摘要

This paper investigates the control of discrete-time linear time-invariant (LTI) systems subject to incomplete and corrupted measurements. Specifically, we focus on designing a Linear Quadratic Gaussian (LQG) controller without relying on explicit state estimation. By leveraging minimum variance duality, our approach allows the current control input to be represented as a linear function of available measurements and previously applied inputs, successfully reducing the task to a tractable deterministic optimization problem. We provide theoretical justification for this framework and demonstrate its practical effectiveness through numerical experiments.

math.OC · cs.RO · eess.SY

版本更新 · v2arXiv:2609.02542

World-Model-Augmented Visual Locomotion for Humanoids on Foothold-Constrained Terrain

Yuxi Liu, Lijun Han, Ziming Wang, Ao Zhang, Cong Yang, Wei Sui

原文摘要

Foothold-constrained terrain limits feasible footholds to sparse, discontinuous, or narrow support regions, as in gaps, stepping stones, stairs, and balance beams. In such settings, a single misplaced step can cause a fall. Reliable traversal therefore requires precise foot placement and anticipation of upcoming terrain. To address this challenge, we present World-Model-Augmented Visual Locomotion (WM-LOCO), which augments a visual locomotion policy with predictive context from a jointly trained world model. Given onboard depth observations and proprioception, a recurrent state-space model (RSSM) learns action-conditioned latent dynamics that predict future proprioceptive states, egocentric observations, and task rewards. The resulting recurrent feature is then fed into the proximal policy optimization (PPO) actor-critic, providing predictive context for anticipatory foot placement on foothold-constrained terrain. WM-LOCO achieves average success rates of 96.0% on gaps, 96.9% on stepping stones, 94.0% on stairs, and 92.1% on balance beams, outperforming the evaluated baselines while improving gait efficiency and smoothness. Furthermore, WM-LOCO achieves zero-shot sim-to-real transfer to a Unitree G1, with 92.5% success across these four terrain classes.

cs.RO

新论文 · v1arXiv:2611.04873

Trusting Imagined Futures: Auditing Imagined Rewards for VLA Post-Training

Zicheng Kong, Zhenbo Xu, Haoyan Zhang, Jinghan Yang, Zhenzhen Li, Yiwei Ru, Liuyu Xiang, WanTing Xu 等 10 位作者

原文摘要

Video world models enable candidate actions to be evaluated through imagined outcomes, but high predicted rewards can favor trajectories with poor execution quality. We introduce Trusting Imagined Futures (TIF), an offline supervision selection method for vision-language-action (VLA) post-training that audits predicted rewards using execution feedback. A multidimensional reward model predicts a utility score for candidate ranking and five dimensions of execution quality. An auditor uses reward predictions and uncertainty to identify overestimation patterns learned from paired imagined videos and real executions. TIF accepts the candidate with the highest predicted utility when its advantage over the existing trajectory exceeds a margin and its audit risk passes a threshold; otherwise, it retains the existing supervision. The retained real trajectories then supervise behavior cloning. Across four LIBERO suites and three training seeds, TIF achieves a mean success rate of 76.25%, improving over training on the existing trajectories by 3.00 percentage points with the same trajectory count and training budget. Adding audit gating yields 1.47 percentage points with the reward model and advantage margin held fixed. The gains persist against advantage ranking and logistic regression risk selection at matched replacement counts. On recorded videos from three real robot tasks, TIF increases clean completion among selected trajectories from 58.33% to 70.00% across 60 candidate pools.

cs.RO · cs.CV

新论文 · v1arXiv:2611.04871

Physics-Based Plausibility Assessment of AI-Predicted Vehicle Parameters for Automotive Radar in Pre-Crash Scenarios

Rainer Engert, Patrick Zaumseil, Thomas Brandmeier

原文摘要

Automotive radar is a key sensing modality for safety-critical vehicle functions due to its robustness under adverse weather and lighting conditions. Recent advances in AI-based radar perception enable the direct estimation of object parameters from a single radar measurement cycle. However, the internal decision process of data-driven models is typically not explicitly linked to the underlying radar sensing physics. Consequently, object estimates may achieve high statistical accuracy while remaining physically inconsistent with the measured radar signature, particularly in previously unseen scenarios. Such inconsistencies are especially critical for heading estimation, as they directly affect trajectory prediction and collision assessment in pre-crash scenarios. This paper presents a physics-based consistency assessment framework for validating AI-derived vehicle hypotheses in automotive radar perception. The proposed approach generates an expected radar signature from AI-estimated object parameters using a physics-based reference model that incorporates occlusion-dependent edge visibility, aspect- and angle-dependent RCS modeling, and characteristic wheel-induced MD signatures. The expected signature is compared with the observed radar point cloud using a Wasserstein-distance-based consistency metric computed from three complementary features: the spatial distribution of detections along object edges, the local detection count, and the radar reflection intensity. In this way, physically implausible object hypotheses can be identified and corrected independently of the underlying neural network architecture and without model retraining or architectural modifications. The proposed consistency module is integrated as a cascaded post-processing stage for vehicle heading estimation.

cs.RO

新论文 · v1arXiv:2611.04870

PrimeSim: A Generalist World Model Simulator from Large-Scale Cross-Embodiment Demonstrations

Travis Davies, Wentao Ma, Lihao Guo, Tengfei Ma, Xiaowen Chang, Jiafeng Xu, Shilong Wang, Yiqi Deng 等 13 位作者

原文摘要

A robot world model that serves as a simulator must do more than generate plausible videos: it must faithfully follow commanded actions, maintain consistency across camera views, and sustain coherent long-horizon rollouts. We present PrimeSim, an action-conditioned, multiview world model simulator that addresses these challenges through progressive midtraining and posttraining. Starting from a pretrained video generator, we midtrain on 30,110 hours of robot demonstrations spanning 22 platforms. To improve action following, we introduce a unified cross-embodiment action representation and frame-aligned dual-path conditioning to strengthen action-frame correspondence. To maintain multiview consistency, we develop view-aware interleaved attention with explicit camera identities, enabling cross-view information exchange while preserving view-specific representations. We further introduce a fast-video, slow-memory posttraining framework that transforms the bidirectional video generator into an efficient autoregressive simulator. By combining fast causal generation, self-rollout training, and hierarchical temporal memory, PrimeSim mitigates error accumulation from self-generated histories and supports coherent long-horizon simulation. PrimeSim runs at 10.1 FPS, remains stable over long-horizon rollouts on rigid and deformable manipulation tasks, and transfers to held-out platforms within 100 to 200 gradient steps where the pretrained backbone does not. Against five open-source action-conditioned world models it leads four of the five WorldSimProbe suites and posts the best overall EWMBench score, while fine-grained local calibration still trails the field; its rollouts are faithful enough to support GRPO-based policy optimization. We release the model weights, inference code, and training code.

cs.RO

新论文 · v1arXiv:2611.04863

Geometric Obstructions and Sharp Genus Dependence in LCD Scalings

Rahim Rahmati-Asghar

原文摘要

We study the least pole order of a rational function whose nonzero evaluations scale a prescribed code to a Euclidean LCD code. A residue-one differential yields an obstruction for odd-dimensional one-point AG codes in characteristic two: for $C=C_L(D,aQ)$ with $0\le a<n$ and odd dimension, the threshold is at least $n+2g-a-1$. The obstruction uses alternating Gram matrices and does not require the scaled code to be self-orthogonal. For the dimension-three codes $C_L(D,(r+1)Q)$ on Hermitian curves over $\F_{r^2}$, $r=2^e\ge4$, we obtain \[ n+2g-r-2\leτ_D(C;Q)\le n+2g-3. \] Consequently the leading genus contribution is asymptotically sharp even in dimension three. On the elliptic curve $y^2+y=x^3$ over $\F_4$, we prove the exact dimension-three threshold $6$ by an explicit multiplier. For repetition codes on the Hermitian family, the threshold equals the general interpolation bound $n+2g-1$. The upper bounds use information sets and hold for $q>3k$, and for $q>2k$ in characteristic two.

math.AG · cs.IT

新论文 · v1arXiv:2611.04860

Robust Aggregation of Quantile Statistics: from Median to Interval

Mingyu Song, Yizhou Wang, Yuqing Kong

原文摘要

Quantile-based summaries, such as prediction intervals and medians, are commonly used in economic forecasting, climate science, and public health. For highly skewed samples, experimental evidence suggests that estimates of the mean can be biased toward the median, whereas estimates of the median are relatively accurate. This motivates aggregating explicitly elicited quantiles rather than reported means. We study robust aggregation of quantile reports for bounded outcomes under squared loss, minimizing worst-case regret relative to an omniscient Bayesian aggregator who knows the information structure and observes all private signals. Without restrictions on the information structure, no rule improves on the constant forecast at the range midpoint in worst-case regret. We therefore consider weak substitutes, a diminishing-returns condition on the value of information, and characterize optimal aggregation rules under this condition. For central prediction intervals with common nominal coverage $α$, the optimal rule, which we call regularized simple average for prediction intervals, shrinks the average reported interval midpoint toward the range midpoint, with a weight determined by $α$ and the number $n$ of experts. This optimal rule strictly improves on the constant baseline in worst-case regret when $α<1/\sqrt{n}$; at or above this threshold, the constant rule is optimal. The optimal worst-case regret is minimized at a unique interior coverage level, revealing a nonmonotonic relationship between coverage and aggregation performance. For median reports, regularized simple average for medians similarly shrinks the average reported median toward the range midpoint, assigning weight $1/n$ to the reported average and strictly improving on the constant baseline in worst-case regret for every finite $n\ge2$.

cs.GT

版本更新 · v2arXiv:2610.25837

Exact minimum Birkhoff decompositions of doubly stochastic matrices with finite precision

András Czégel

原文摘要

The minimum Birkhoff decomposition problem asks for a representation of a doubly stochastic matrix as a convex combination of as few permutation matrices as possible. This NP-hard problem arises in the scheduling of switches in data centers and satellite systems, in random assignments in economics and in the statistics of rankings. We consider doubly stochastic matrices whose entries are given with a fixed number of decimal digits and look for exact decompositions whose weights have the same precision. We propose a parallel method with three parts. For matrices built from few permutation matrices, the first part reads the weights from the frequencies of the entries and places them on the matrix positions by a rule that, given the correct weights, never fixes a position wrongly. The second part computes lower bounds from pairs of rows or columns, which remain valid for real weights, and from certificates of a satisfiability solver. For matrices built from many permutation matrices, the third part runs a beam search over steps that each make at least one entry zero. On 375 test instances with up to 100 rows, the method proves optimality for 208 instances, and 197 of these proofs also hold for real weights. Of the 190 instances built from few permutation matrices, 187 are solved to proven optimality, 180 of them within one second. Compared with the best exact decompositions known before, the new decompositions are shorter for 278 instances and never longer.

cs.DS

版本更新 · v5arXiv:2609.31328

A Constructive FPT Algorithm for Integer Cone Optimization with Convex Costs

Klaus Jansen, Felix Ohnesorge, Björn Schumacher

原文摘要

We give a deterministic fixed-parameter algorithm for integer cone optimization with convex costs. Given $τ$ rational polytopes in $\R^{d+k}$, we combine generators whose first $d$ coordinates are integral and whose remaining $k$ coordinates may be fractional. Each generator has a convex cost depending only on its integer coordinates. We minimize the total cost of nonnegative integer combinations subject to arbitrary rational linear constraints on the full typewise aggregates and generator counts. Our algorithm runs in time \[ 2^{τ\log(τ+1)\,2^{O(d)}}\cdot |I|^{O(1)}, \] where $|I|$ is the total binary input length. It constructs an optimal representation using at most $2^{2d+1}$ distinct generators per type. The number $k$ of continuous coordinates contributes only to the polynomial input factor. For a single generator type, the running time becomes $2^{2^{O(d)}}\cdot |I|^{O(1)}$. Applications include constructive FPT algorithms for Cone and Polytope Intersection, high-multiplicity bin packing, vector bin packing, and makespan minimization on uniform and unrelated machines. The double-exponential dependence on $d$ is tight for Point-in-Cone and both bin-packing problems assuming $\mathrm{NP}\nsubseteq\mathrm{SUBEXP}$. The mixed-integer formulation also yields additive EPTASs for makespan minimization, machine covering, and envy minimization on identical machines, and additive schemes fixed-parameter tractable in $1/\varepsilon+τ$ on uniform machines.

cs.DS

版本更新 · v2arXiv:2611.02476

GigaSpeech 3: Scaling Multi-Dialect Arabic Speech Recognition with Weakly Labeled Data

Junzhe Liu, Yujie Tu, Yifan Yang, Peng Wang, Haoran Wang, Guodong Lin, Leyan Liao, Chengquan Zhang 等 16 位作者

原文摘要

Dialectal Arabic speech recognition remains constrained by the scarcity of dialect-resolved transcribed speech despite the abundance of web audio. We introduce GigaSpeech 3, a corpus of 39,000 hours and 10 million weakly transcribed speech segments covering Algerian, Egyptian, Iraqi, Saudi, and Syrian Arabic. Starting from 60 hours of manual transcription per dialect, we train labeling models using speech-recognition-biased self-supervised learning and apply them to dialect-matched web audio. Data selection and four rounds of noisy-student refinement for Saudi and Syrian Arabic yield the final corpus. We validate its utility through dialect-specific and multi-dialect speech recognition training and cross-domain evaluation. On GigaSpeechBench, the final dialect-specific models outperform their labeling models across all five dialects and achieve a macro-average word error rate of 23.86%, a 16.6% relative reduction from the strongest third-party system covering all five dialects, while outperforming the best third-party result on three dialects. A multi-dialect model using self-predicted dialect identities achieves a macro-average word error rate of 25.51% while also supporting Modern Standard Arabic. Across eight conditions from three external corpora, a GigaSpeech 3-trained Zipformer achieves the lowest word error rate among six evaluated models in every condition, while adapting the Qwen3 speech recognizer on GigaSpeech 3 improves performance across all eight conditions. We release the corpus and recipes as a foundation for dialect-aware Arabic speech processing.

cs.CL

版本更新 · v2arXiv:2610.34534

Multimodal Socially Aware Framework for Human-Robot Interaction in Virtual Reality

Richard Xu, Dakarai Crowder, Alexis E. Block, Wenzhen Yuan

原文摘要

Social robots must coordinate speech and movement while interpreting multimodal human input. We present a multimodal framework that integrates speech, vision, and touch to generate contextually appropriate robot speech and movement. We evaluated the framework in virtual reality with 18 participants across five social interaction scenarios, comparing its performance against a human-teleoperated baseline. Although participants rated the autonomous system above the neutral midpoint for both naturalness and social appropriateness, the teleoperated baseline received significantly higher ratings on both measures. Behavioral coding and qualitative feedback revealed that conversational timing, clarification of ambiguous requests, and spatial coordination were important factors contributing to this performance gap. These findings highlight key challenges in developing autonomous robots capable of natural, multimodal social interaction.

cs.RO

新论文 · v1arXiv:2611.04848

Amortized Nonlinear Variable Selection with Prior-Data Fitted Networks

Jin Zhu, Junxian Zhu

原文摘要

Variable selection is an important task for interpreting potentially complex systems in fields such as biology, business, and sociology. The importance of variable selection has attracted considerable attention in statistics and machine learning. In this paper, we are mainly interested in model-agnostic variable selection for identifying variables that have general nonlinear dependence on the response. We propose MambaPFN, short for Model-Agnostic Markov BlAnket selection with Prior-data Fitted Networks, which is built upon the Transformer, a building block of many popular large language models. Specifically, we consider a functional-mapping perspective on variable-selection learning, in which the Transformer is treated as a learnable mapping from a dataset to its relevant variables. To learn this mapping, MambaPFN introduces three new components: (i) a faithful, rich, and scalable scheme for generating pretraining data, (ii) an objective that targets each variable's posterior inclusion probability, and (iii) a modified Transformer architecture tailored to variable selection. Once pretrained, MambaPFN is applied to new datasets without parameter updates. Empirically, MambaPFN achieves desirable variable-selection performance in simulation studies and exhibits a scaling law---more pretraining datasets and larger models can continuously improve its performance. Applied to a Facebook comments dataset, MambaPFN selects the fewest variables and achieves the highest computational efficiency and predictive performance, improving upon the best baselines by about 20%.

cs.AI · stat.ME · stat.ML

版本更新 · v3arXiv:2609.03628

Random Garbage Creates Exponential Quantum Query Separations

Khaled Elbassioni, Rishikesh Gajjala, Saurabh Ray

原文摘要

We prove an exponential separation between standard (XOR) quantum queries and forward-erasing queries for a Boolean property of injective functions, answering a question of Aaronson~\cite{Aaronson2021Open}. We also obtain an exponential separation for a Boolean promise problem on permutations, where forward in-place queries are unitary but inverse queries are not supplied. Our construction follows Aaronson's suggestion of appending fixed random garbage to a Simon function. Let $X=\{0,1\}^n$ and $N=2^n$. We use the injection $f_{h,r}(x)=(h(x),x,r_x)$, where $h:X\to X$ is promised to be either a permutation or a Simon function, and $r:X\to X$ is an arbitrary tag table that is reused on every query. The resulting problem is solvable with at most $n+2$ standard queries, but requires $Θ(\sqrt N)$ forward-erasing queries, matching classical collision sampling. Embedding these instances into permutations, with the copy of $x$ replaced by a single bit that keeps the embedding injective, gives a promise problem on permutations of $L=4N^2$ elements that requires $O(\log L)$ standard queries versus $Θ(L^{1/4})$ forward in-place queries. The lower bounds use the recording method. We replace each query by a nearby contraction that records cells of a purified tag table. After $T$ queries, tracing out the purified tag table yields a sum of positive-semidefinite contributions, each depending on $h$ at no more than $T$ addresses. A query-by-query hybrid bounds the trace-norm difference between the actual and auxiliary final operators by $O(T/\sqrt N)$. Random permutations and random Simon functions have the same restriction distribution on such a set unless it contains a hidden Simon pair, an event of probability $O(T^2/N)$. Consequently, the actual final states in the two cases remain close unless $T=Ω(\sqrt N)$, giving the required lower bounds.

cs.CC · quant-ph

新论文 · v1arXiv:2611.04847

Real-to-Integer Reduction for All-Pairs Shortest Paths

Nick Fischer, Adam Polak, Jonas Schmidt

原文摘要

Efficient graph algorithms often use techniques that are specific to integer-valued inputs and do not work for real-valued versions of the problems. Is it a limitation of current techniques, or are the real-valued variants inherently harder? One way to study this question is through real-to-integer reductions. We give (randomized, combinatorial) subcubic real-to-integer reductions for two central graph problems in fine-grained complexity: All-Pairs Shortest Paths and Exact Triangle. That is, we show that if the integer variants of these problems can be solved in truly subcubic time, then the real variants can also be solved in truly subcubic time. Our work extends and combines techniques from three previous works: (1) our real-to-integer reduction for the 3SUM problem (Fischer, Polak, Schmidt, FOCS 2026), which itself combines the Frank--Tardos theorem from optimization with Freiman's theorem from additive combinatorics; (2) universe reduction for APSP (Fischer, STOC 2026), which we generalize to reals and use to reduce the doubling of the set of edge weights; and (3) the ``Fredman's trick meets dominance product'' technique (Chan, Vassilevska Williams, Xu, STOC 2023), which is needed to adapt the prior real-to-integer framework from equality constraints to inequalities. As a corollary, our reduction combined with Yuval's fast Integer APSP algorithm in the real RAM model with multiplication (IPL 1976) shows that the Real APSP Hypothesis is false in this model, which also follows from the very recent breakthrough by Alman and Vassilevska Williams using a very different approach.

cs.DS

版本更新 · v2arXiv:2609.20267

CleanVideo: Adaptive Concept Erasure for Text-to-Video Diffusion Models

Junchi Liao, Hongji Li, Wenrui Zhou, Lijie Hu

原文摘要

Concept erasure aims to selectively eliminate undesired visual semantics from pre-trained generative models without compromising their general utility. Extending concept erasure from images to video is nontrivial. Target concepts emerge gradually and vary across frames and denoising steps. As a result, fixed interventions may miss the target or introduce blurring, jitter, and content distortion. We propose CleanVideo, a selective erasure framework that performs low-dimensional subspace intervention controlled by a tri-modal gating mechanism. By jointly processing spatiotemporal visual features, timestep signals, and textual semantics, CleanVideo determines where, when, and whether to intervene, steering erased content toward natural surrogate concepts when such surrogates can be clearly defined while preserving non-target content. Experiments on three video diffusion models show that CleanVideo effectively erases target concepts while maintaining visual fidelity and temporal coherence, outperforming existing baselines under frame-level and video-level evaluations and under concept-recovery attacks when the protected pipeline remains intact.

cs.CV · cs.AI

版本更新 · v3arXiv:2609.07974

A $(3+ε)$-Approximation for Fair $k$-Means and a Matching Lower Bound

Kangke Cheng, Guanlin Mo, Shihong Song, Hu Ding

原文摘要

Fair clustering aims to prevent algorithmic bias against protected groups. We study Euclidean fair $k$-means, in which the proportion of each protected group in every cluster lies between prescribed lower and upper bounds. Because these constraints violate the nearest-center assignment property, center selection is coupled with point assignment. We introduce the drift-regularized relaxation, a new convex relaxation solved by a modified Frank-Wolfe method with linear-programming iterations, whose optimality condition controls the cost of converting its solution into $k$ fair clusters. Combined with any $ρ$-approximation algorithm for weighted $k$-means, the relaxation yields an exactly fair fractional solution of cost at most $2ρ+1+ε$ times the fractional optimum, improving the previous ratio $1+4ρ+ε$. In fixed dimension, this improves the best known ratio from $5+O(ε)$ to $3+O(ε)$. The fractional solution can be rounded to an integral one without changing the centers or increasing the cost, at a bounded additive violation of the fairness bounds. We also show that a $(3-δ)$-approximation is NP-hard for every fixed $δ>0$, even on the line with fractional assignments, so $3$ is the exact approximation threshold for fractional fair $k$-means in fixed dimension. The same guarantees hold for $k$-sparse Wasserstein barycenters, a special case of fractional fair $k$-means. More generally, they hold whenever every cluster must satisfy given homogeneous linear inequalities in the fractions of its points, such as a bound on the ratio between two groups or on the average of a numerical attribute in every cluster.

cs.CG · cs.LG

新论文 · v1arXiv:2611.04841

DGC-Net: Cross-Modal Dynamic Routing with Global-Guided Compensation in Multimodal Sentiment Analysis

Linan Zhu, Huaijing Wu, Xiao Han, Yuhao Wang

原文摘要

User-generated videos, including opinion vlogs and video reviews, provide a rich source of people's attitudes toward products, services, and social topics. Understanding the sentiment expressed by speakers is important for analyzing online opinions, as transcripts alone may not capture the attitude and intensity conveyed through vocal tone and facial expressions. Multimodal sentiment analysis (MSA) addresses this need by integrating textual, acoustic, and visual cues. However, these cues are often subtle, noisy, and inconsistent across modalities. Existing local affective cue modeling methods typically operate within individual modalities and overlook global contexts from other modalities. This may cause cross-modal affective cue inconsistency. Hierarchical global-local fusion methods integrate global semantics with fine-grained local affective cues. However, they commonly determine the relative contributions of the two representations implicitly, preventing the global-local contributions from adapting to the sample-dependent reliability of local cues and resulting in either insufficient use of informative local cues or excessive interference from unreliable ones. To address these issues, we propose DGC-Net, a Dynamic Gating and Global-Guided Compensation Network for MSA. DGC-Net mitigates cross-modal affective cue inconsistency through cross-modal contribution-aware dynamic expert routing. This mechanism uses auxiliary global contexts to guide local expert selection. Moreover, global-guided dynamic compensation fusion alleviates sample-dependent global-local contribution imbalance while preserving global semantic as the primary anchor and adaptively incorporating expert-refined local cues. Experiments on five multimodal benchmark datasets demonstrate the effectiveness and general applicability of DGC-Net, and ablation studies verify the contribution of each proposed component.

cs.AI · cs.MM

版本更新 · v2arXiv:2606.03994

SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image

Inhee Lee, Sangwon Baik, Sungjoo Kim, Hyeonwoo Kim, Hyunsoo Cha, Hanbyul Joo

原文摘要

Reconstructing interactive, simulation-ready 3D scenes from a single image is a critical bottleneck for robotic manipulation. While recent single-image lifters recover plausible per-object shapes, composing them yields scenes that collapse under physical simulation due to interpenetrating, hovering, or sinking objects. Existing physics-aware compositional reconstruction methods mainly address this as a post-hoc layout correction, leaving the underlying geometric errors unresolved. To address this, we introduce SimuScene, a compositional 3D reconstruction pipeline that puts physics in the loop of shape and layout estimation. Rather than using physics merely for layout cleanup, we utilize the physics engine as a diagnostic measurement tool during the generative process itself. By diagnostically simulating reconstructed objects under gravity, we convert penetration and support failures into quantitative correction signals that drive amodal shape resampling, with gravity-axis stretching as a lightweight correction for minor errors. This physics-informed feedback loop mitigates accumulated reconstruction errors and produces a stable, simulation-ready compositional 3D scene. Extensive experiments demonstrate state-of-the-art performance on physical stability and geometric alignment benchmarks. We further highlight SimuScene's utility by deploying reconstructed environments in humanoid control and robot-arm manipulation tasks.

cs.CV · cs.RO

版本更新 · v2arXiv:2610.39004

How Architecture, Typology, and Adaptation Strategies Shape ASR for Low-Resource African Languages: A Controlled Empirical Study

Mercy Muchai, Kevin Chege, Nick Mumero Mwangi, Samuel Chege Maina, Felermino Ali, Elizabeth Ankrah, Ignatius Ezeani

原文摘要

Despite recent advancements in ASR, identifying effective architectures, fine-tuning approaches, and data adaptation strategies for low-resource languages remains challenging. We present a systematic comparison across five low-resource African languages and Swahili as a mid-resource contrast, fine-tuning three models from distinct architectures: Phi-4-multimodal-instruct, Whisper-large-v3-turbo, and MMS-1B-all. We analyze data sufficiency, monolingual versus multilingual adaptation, domain fine-tuning, and language-adapter transfer. Phi-4 achieves the best overall accuracy, MMS shows comparable CER, while Whisper exhibits high CER, consistent with known hallucinations and repetition loops. Performance saturates at different data scales, offering practical data-efficiency targets, while typological complexity consistently shapes error rates. Domain fine-tuning benefits Phi-4 and Whisper but degrades MMS, revealing limitations of adapter-based adaptation. Proxy language adapters outperform training MMS adapters from scratch.

cs.CL · cs.SD · eess.AS