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
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-22 21:02 · 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 2026-11-22 00:32 — 2026-11-23 00:32(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 21:02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 21:00(北京时间)
版本更新 · v2arXiv:2512.02460

UniCom: A Unified Framework for Community Search and Detection via Transfer Learning

Yifan Zhu, Hanchen Wang, Wenjie Zhang, Alexander Zhou, Ying Zhang

原文摘要

Searching and detecting communities in real-world graphs underpins a wide range of applications. Specifically, community search identifies a community for a given query, whereas community detection partitions the entire graph into multiple communities. Although they target different community analysis objectives, both tasks aim to uncover cohesive community structures and are complementary in real-world applications. Despite this connection, current learning-based solutions generally regard them as separate problems, necessitating task- and dataset-specific retraining. This separated learning paradigm limits the applicability and generalization ability of the existing models. To mitigate this limitation, we propose UniCom, a unified framework to solve both community search and detection tasks. UniCom centers on a Universal Graph Learning (UGL) stage that distills local and global community-aware knowledge from multiple source domains. Following UGL, the Domain-aware Specialization (DAS) stage supports on-the-fly adaptation to unseen graphs and tasks through transfer learning, avoiding costly retraining while keeping the model compact. Extensive experiments on both tasks across 16 datasets and 22 baselines have been conducted to ensure a comprehensive, rigorous, and fair evaluation. UniCom consistently outperforms all state-of-the-art baselines across all tasks while maintaining runtime efficiency.

cs.SI · cs.DB

版本更新 · v3arXiv:2610.18088

ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch

Peng Jiang, Dongyang Li, Quanying Liu, Xiaoxuan Jia

原文摘要

Autoresearch systems increasingly undertake entire research projects. In practice, scientific research requires systems to pursue multiple interdependent claims through a continuous, multi-stage workflow and revise experiments as evidence accumulates. Existing evaluations of autoresearch systems, however, typically score isolated tasks or final artifacts, leaving these process-level capabilities largely unmeasured. We therefore introduce ResearchFlow-Eval, a fine-grained framework for assessing continuous scientific execution and iteration at both the stage and claim levels. Each evaluation is grounded in a published anchor paper, from which we derive stage-specific rubrics that decompose each research stage into dimensions and separately scored rubric items. Using these rubrics, we score each research stage and examine experimental execution in detail, focusing on multi-claim completion and revisions across attempts. We apply the evaluation framework to general-purpose agent harnesses, skill-augmented harnesses, and systems with research-specific orchestration. Averaged over two runs per system, each scored by two LLM judges, experimental execution lags behind design and planning for every evaluated system. Within execution, systems struggle to produce high-quality results and meet claim requirements, and repeated attempts rarely yield measurable improvements. Moreover, neither skill augmentation nor research-specific orchestration reliably yields higher scores. ResearchFlow-Eval thus extends autoresearch evaluation beyond isolated, single-objective runs to continuous workflows in which systems pursue multiple claims and refine their work across iterations.

cs.AI · cs.LG

版本更新 · v2arXiv:2602.18224

SimVLA: Attributing Gains in VLA Models Through Controlled Ablation

Yuankai Luo, Woping Chen, Tong Liang, Zhenguo Li

原文摘要

Vision-Language-Action (VLA) models often bundle architectural changes with different pretraining data, backbone scales, and optimization recipes, obscuring what actually drives progress. We introduce SimVLA, a deliberately minimal VLA, a standard vision-language backbone with a lightweight continuous-action head, as a controlled testbed for this attribution problem; our contribution is methodological and empirical (a controlled attribution study and a minimal-baseline calibration), not a new technique. Across LIBERO, CALVIN, WidowX, and Google Robot, one-knob-at-a-time ablations show that training dynamics are the largest measured driver, producing performance swings of $Δ$$\approx$54--94\%, while task configuration and architecture have smaller effects under matched settings. Despite using a small backbone and no additional large-scale robot-data VLA pretraining before benchmark-specific training, SimVLA reaches 98.6\% average success on LIBERO, remains competitive across the other benchmarks, and transfers to held-out real-robot scenes. These results suggest that simple, carefully controlled VLA baselines remain underexplored and provide a calibration point for future architectural claims within the VLM-encoder plus lightweight-head family. Website: https://frontierrobo.github.io/SimVLA

cs.RO · cs.LG

版本更新 · v3arXiv:2509.17955

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

Fan Xu, Hao Wu, Nan Wang, Lilan Peng, Kun Wang, Wei Gong, Xibin Zhao

原文摘要

The modeling of complicated time-evolving physical dynamics from partial observations is a long-standing challenge. Particularly, observations can be sparsely distributed in a seemingly random or unstructured manner, making it difficult to capture highly nonlinear features in a variety of scientific and engineering problems. However, existing data-driven approaches are often constrained by fixed spatial and temporal discretization. While some researchers attempt to achieve spatio-temporal continuity by designing novel strategies, they either overly rely on traditional numerical methods or fail to truly overcome the limitations imposed by discretization. To address these, we propose CoPS, a purely data-driven methods, to effectively model continuous physics simulation from partial observations. Specifically, we employ multiplicative filter network to fuse and encode spatial information with the corresponding observations. Then we customize geometric grids and use message-passing mechanism to map features from original spatial domain to the customized grids. Subsequently, CoPS models continuous-time dynamics by designing multi-scale graph ODEs, while introducing a Markov-based neural auto-correction module to assist and constrain the continuous extrapolations. Comprehensive experiments demonstrate that CoPS advances the state-of-the-art methods in space-time continuous modeling across various scenarios.

cs.CV

版本更新 · v2arXiv:2609.36805

UpliftMem: Learning Set-Level Uplift for Agent Memory Retrieval

Mengkun Liang, Haoran Qiang, Guannan Liu, Junjie Wu

原文摘要

Large language model (LLM) agents draw on external memory to guide new tasks, raising the question of which memories to retrieve together to improve execution. Learning set values requires outcome feedback, but evaluating each untested alternative costs an additional rollout. We introduce \textsc{UpliftMem}, which learns set-level execution uplift relative to the same executor without memory. Our analysis of how retrieval preferences limit feedback coverage motivates targeted probes. Under a correlated Gaussian surrogate, we derive a closed-form expected value of sample information (EVSI) criterion that prioritizes probes by their expected benefit to local retrieval decisions. The feedback trains a shared scorer with the executor frozen, and inference requires no probing. Across ALFWorld, WebShop, and BigCodeBench, \textsc{UpliftMem} achieves best or joint-best success rates among evaluated methods. On fixed-store MemSyco-Bench evaluations, decision accuracy increases from 41.7\% to 66.5\% with Qwen3-4B and from 44.4\% to 68.8\% with Qwen3-8B. At matched probe budgets, EVSI improves decision accuracy over random probing by 10.6 and 13.9 percentage points, respectively.

cs.AI

版本更新 · v2arXiv:2611.22132

DailyBrick: Language-Guided Synthesis of Brick Assembly Instructions

Hang Zhang, Qijian Tian, Yuan Xie, Xuhong Wang, Xin Tan

原文摘要

Generating a LEGO model from a user request is more than a plausible 3D shape generation. LEGO models require physical support per brick, and each brick should be placed unblocked. Current methods address this issue by training an expert large language model. We reduce the problem of generating extremely long context on all brick connections to that of writing a program that builds LEGO models like a human, considering each intermediate step could be executed. We introduce DailyBrick , a multi-stage agentic system that produces a LEGO model together with a brick-by-brick assembly instruction for human building and robot assembly. We design a multi-stage harness with roles to help LLMs generate more effectively. A versioned construction SDK compiles multi-level decisions, from semantic subparts to individual bricks, into canonical operations. An external Meta-Reviewer agent replays and inspects the generated package, verifies the model and its construction process, identifies failures, traces them to the responsible stage, and routes them to bounded repairs or to editable candidates for later skill or tool updates. Extensive experiments demonstrate that DailyBrick generates LEGO models based on simple user requests better than recent agentic systems, and show its utility in downstream applications such as robot manipulations on model assembly from instructions and brick sets (https://spatialagentlab.github.io/DailyBrick.github.io/).

cs.RO · cs.CV

新论文 · v1arXiv:2611.25543

Efficient Multimodal Agents for Auditing 3D Worlds

Jingbo Yang, Ziyan Jiang, Li An, Jiabao Ji, Yujian Liu, Tommi Jaakkola, Yang Zhang, Shiyu Chang

原文摘要

Multimodal agents can now build interactive 3D worlds and games, yet these worlds, like those built by people, often contain glitches such as floating objects, walls that can be walked through, or objects that change when no one is looking. An automatic auditor could check such worlds at scale and provide rewards for agents that build them, but only if it is both accurate and cheap. Auditing requires three abilities, namely navigating to the objects that may contain a glitch, triggering glitches that appear only after a specific behavior, and recognizing what is wrong. Current auditors are either accurate but slow and expensive or cheap but unreliable. We study how much of the audit small models can take on. A 4B vision language model fine-tuned end to end on verified trajectories of a frontier teacher guided by Bayesian search learns to navigate and trigger, and six such explorers together match a frontier model on both, but recognition stays far behind. We therefore build an auditor in which a swarm of small explorers navigates and triggers, and a frontier model reviews what they record and report. On WorldAuditBench, our auditor succeeds on 55.9% of 213 tasks in Unreal Engine 5 and Three.js worlds, 13.6 points above the strongest auditor reported, at less than a quarter of its cost. It matches the frontier reviewer exploring on its own at 4.6 times lower cost and about half the latency. Without further training, it also answers embodied questions about real-world scans, matching the frontier reviewer exploring on its own and surpassing four other frontier models by 6.4 to 16.6 points.

cs.AI

版本更新 · v3arXiv:2605.12088

UniCustom: Unified Visual Conditioning for Multi-Reference Image Generation

Yiyan Xu, Qiulin Wang, Wenjie Wang, Yunyao Mao, Xintao Wang, Pengfei Wan, Kun Gai, Fuli Feng

原文摘要

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual conditioning: semantic ViT features are processed by the VLM for instruction understanding, whereas appearance-rich VAE features are injected later into the diffusion backbone. Despite its intuitive design, this separation makes it difficult for the model to associate each semantically grounded subject with visual details from the correct reference image. As a result, the model may recognize which subject is being referred to, but fail to preserve its identity and fine-grained appearance, leading to attribute leakage and cross-reference confusion in complex multi-reference settings. To address this issue, we propose UniCustom, a unified visual conditioning framework that fuses ViT and VAE features before VLM encoding. This early fusion exposes the VLM to both semantic cues and appearance-rich details, enabling its hidden states to jointly encode the referred subject and corresponding visual appearance with only a lightweight linear fusion layer. To learn such unified representations, we adopt a two-stage training strategy: reconstruction-oriented pretraining that preserves reference-specific appearance details in the fused hidden states, followed by supervised finetuning on single- and multi-reference generation tasks. We further introduce a slot-wise binding regularization that encourages each image slot to preserve low-level details of its corresponding reference, thereby reducing cross-reference entanglement. Experiments on two multi-reference generation benchmarks demonstrate that UniCustom consistently improves subject consistency, instruction following, and compositional fidelity over strong baselines.

cs.CV

新论文 · v1arXiv:2611.25542

Technology-Enabled Fuel Supply Chain Resilience: An Integrated Information System for Real-Time Monitoring and Decision Support

Mohamed Loutis, Esma Aïmeur

原文摘要

This study evaluates and extends the transactional information system described in an earlier fuel logistics study, focusing on data reliability, monitoring, and decision support. An author-led re-evaluation examined available Delphi and SQL code and compared a reconstructed source-derived baseline (R0) with a revised SQL Server system (R1) across twelve evaluation scenarios. Synthetic transactions and public US energy data were used for technical assessment, while organizational processes and supply delays were simulated. R1 improved data integration and reporting accuracy in controlled SQL Server tests and introduced stock-movement records, automated alerts, and recovery controls. On comparable data feeds, integration defect rates decreased from 2.90 to 3.46 percent in R0 to 0.14 to 0.49 percent in R1. For national weekly demand forecasting, selected methods did not significantly outperform the previous-year mean. Process and disruption simulations suggested improvements in manual workload and replenishment delays, although these outcomes depended on modelling assumptions and were not observed in operational settings. The study presents a revised transactional architecture for fuel logistics and distinguishes experimentally measured information-system performance from simulated organizational outcomes. Its findings highlight the potential of traceable inventory records, early exception detection, and recoverable information systems to support supply chain resilience.

cs.SE

新论文 · v1arXiv:2611.25541

Dynamics of Protected State Evolution

Qinyou Wang

原文摘要

States with identical protected observations can admit different future interventions. Each transition specifies its successor, response increment, required initial reserve and net consumption. Composing these records in execution order distinguishes protocols with equal net consumption and different initial reserve requirements. At a fixed state, a weighted Gram operator determines the linear response ellipsoid and a quotient identifies directions attainable only through cooperation between blocks. Nonlinear systems with identical complete affine data can have incomparable finite-budget response sets. In regular charts, the first correction to quadratic minimum cost is a covariant cubic form involving the third derivative of cost and the Hessians of protection and response. At singular gates, sequential feasibility depends on the peak reserve along the path. A history-weighted operator detects responses outside the old channel's range closure. Controlled congruence characterizes exact reductions of deterministic labelled dynamics, and a two-cut value identity separates the effect of paid verification from that of subsequent action selection. On Qwen2.5-7B Base, two projected policies preserved 2,048 reference top tokens under a per-position KL ceiling of $2\times10^{-5}$. Over 200 arrivals they recovered 391 of 396 initial rejections. Each yielded over 1,200 times the held-out cross-entropy reduction of historical-channel-only AdamW. Under an expanded 2,560-position contract, fixed continuation and neutral renewal began on the same protected logit fiber in distinct structural strata. Both admitted all 200 subsequent writes. Fixed continuation yielded 1.74 times the held-out loss reduction per unit squared write cost. Renewal had a smaller KL excess on the first candidate tested at every arrival and used fewer full verification scans.

math.OC · cs.LG

版本更新 · v2arXiv:2609.30981

RevisitQA: Short Videos Are Not Easy under Dense Revisits

Siru Zhong, Shenghan Tan, Rihong Yan, Xiaohui Lv, Yuzheng Zhuang, Shuai Tao, Wulong Liu, Haohuan Fu 等 9 位作者

原文摘要

Video question answering benchmarks have increasingly focused on longer recordings, yet short videos can also be challenging when scenes are revisited frequently. As a camera repeatedly leaves and returns to the same workspace, objects may change out of view, making earlier observations outdated or misleading. Understanding such videos requires models to track evolving states across repeated visits rather than simply retrieve past observations. To study this challenge, we introduce RevisitQA, a benchmark containing 2,577 questions across 622 episodes with a median duration of 44.8 seconds, drawn from five real-world egocentric domains and two simulated environments. RevisitQA covers six question types and evaluates models at specific query times, requiring them to answer from the observed history or abstain when it is insufficient. Across 15 offline and seven streaming video LLMs, the median model correctly answers only 55.5% of answerable questions and abstains on just 30.3% of unanswerable ones. Removing earlier frames further reveals that historical observations help answer questions but can also make models less likely to abstain when answers remain unresolved. These findings highlight dense episodic revisits as an important and unresolved challenge for video question answering. Code is available at https://github.com/siruzhong/RevisitQA.

cs.CV

版本更新 · v3arXiv:2609.22226

Swiss-Knife: A Framework for Reconfigurable Externalised Multi-Objective Alignment at Decode Time

Agnibh Karmakar, Mayur Parvatikar, Shreyash Dhoot, Amit Dhanda, Aman Chadha, Kapil Wanaskar, Vinija Jain, Amitava Das

原文摘要

Decode-time alignment methods steer a frozen language model by scoring candidate continuations with an external reward and selecting the maximiser. We argue that this shared design is a single degenerate point in a much larger space. We introduce Swiss-Knife, a framework for externalised multi-objective alignment in which the alignment specification is a first-class runtime object: hot-swappable scoring blades, a batch normaliser, a pairwise aggregation operator, and a selection rule. Six axioms characterise the admissible aggregation operators, and we prove a representation theorem: every operator satisfying them has the form $R_i = \sum_{j \neq i} g((μ_i - μ_j)/s(σ_i,σ_j))$, a two-parameter family containing probit and logistic comparison rules and pointwise argmax as named coordinates. Within it, pairwise aggregation is Lipschitz-stable under adversarial reward contamination while argmax is not, and Candidate-Batch Normalization (CBN) makes the weight simplex invariant to the rescalings under which reward models are only ever identified. Our reference instantiation pairs DPO-LoRA blades with an uncertainty-aware pairwise tournament. Sweeping the helpfulness/honesty/harmlessness simplex, it attains the best balanced frontier of six decode-time methods (harmonic $F_1$ 0.797 vs. 0.750 for the strongest baseline, $p < 10^{-14}$) with the lowest refusal rate and highest helpfulness of any arm, and reconfigures its objectives in 0.05 ms with no gradient computation.

cs.CL · cs.LG · stat.ML

新论文 · v1arXiv:2611.25539

COVERAGE-TRACE: Source-Side Counterfactual Tracing for Detecting Omissions in LLM Summaries

Ali Karkehabadi, Jamshid Hassanpour, Rafael E. Banchs

原文摘要

Omissions are difficult to verify because missing information leaves no output span to inspect: a summary may be factually supported while still excluding a decision, qualification, quantity, or condition needed to preserve the source's meaning. We introduce COVERAGE-TRACE, a source-side counterfactual framework that evaluates omission as dependence on a designated atomic source fact. It replaces only the target fact with type-matched alternatives, holds the candidate summary fixed, and measures the resulting change in its teacher-forced, length-normalized likelihood. A summary covering the target should respond more strongly than one omitting it, while aggregation across multiple counterfactuals reduces sensitivity to replacement choice. We evaluate COVERAGE-TRACE on 80 matched covered--omitted QMSum pairs spanning several fact types and four open-weight models. Multi-CF achieves 0.764--0.825 AUROC, compared with 0.640 for the strongest evaluated text-only baseline. On Falcon-7B, targeted interventions achieve 0.779 AUROC, whereas shuffling counterfactual assignments reduces performance to 0.533; target deletion is effective while unrelated deletion is not. However, adjustment for meaning-preserving paraphrases reduces AUROC to 0.591--0.624. COVERAGE-TRACE therefore provides a practical, complementary signal of target-specific source--summary dependence, but not a wording-invariant semantic coverage probability. These results establish source-side intervention as a promising approach to omission detection while identifying semantic invariance as the central remaining challenge.

cs.AI · cs.CL

版本更新 · v2arXiv:2611.16217

WorldDraft: If Code Builds the World, Can Video Models Just Render It?

Zhiyu Hou, Wen-Jie Shu, Harold Haodong Chen, Weilin Ruan, Chenfei Liao, Liuzhou Zhang, Disen Lan, Xiaogang Xu 等 10 位作者

原文摘要

Multimodal coding agents decouple 4D world construction from visual generation, repurposing video models from world generators toward generative renderers. This division of labor raises a fundamental question: if code builds the world, can video models just render it? A reliable generative renderer hinges on two complementary criteria: (i) world preservation, retaining prescribed 4D kinematics and camera paths; and (ii) visual realization, persistently binding text-specified target attributes over time. To evaluate this capability, we introduce WorldDraft, a benchmark of $432$ strictly paired test cases across $48$ executable 4D world families spanning six dynamic challenge categories. Under a $3 \times 3$ factorial design, WorldDraft orthogonally crosses draft granularity (abstract proxy to previs) and appearance alignment (neutral to conflicting) under identical dynamics. Extensive evaluations across $12$ representative models reveal that: (I) world preservation and visual realization remain in stark operational tension; (II) richer draft scaffolding anchors structure but paradoxically impairs appearance fidelity; and (III) conflicting source cues trigger severe source leakage (up to $64\%$), exposing fragile cross-modal disentanglement. To mitigate these bottlenecks, we propose WorldDraft-Primer, a plug-and-play visual prompting strategy that consistently improves both objectives across frozen video renderers. Together, WorldDraft and WorldDraft-Primer lay a foundation for bridging programmatic 4D simulation with video generation, advancing physically grounded generative rendering.

cs.CV

版本更新 · v3arXiv:2609.15677

Beyond 1/3-Approximation: Random Greedy for Constrained \(\boldsymbol{k}\)-Submodular Maximization

Siyuan Chen, Shengminjie Chen, Suixiang Gao, Zheyu Jiang, Chenhao Wang, Wenguo Yang

原文摘要

\(k\)-submodularity generalizes submodularity by allowing each selected element to be assigned one of \(k\) labels. We study the maximization of a non-monotone \(k\)-submodular function, where \(k\ge2\), under matroid and knapsack constraints. We develop a proportional Top-2 randomized framework that achieves an approximation ratio of \(\sqrt2-1\approx0.4142\) under either constraint, breaking the previous \(1/3\) barrier. Once an element is selected, its label is chosen from the two labels with the largest marginal gains, with probabilities proportional to their positive parts. We further improve the approximation guarantees to $1/2$ under cardinality and knapsack constraints, through a Bellman-style backward induction analysis using the same proportional Top-2 rule. Our $1/2$ guarantees for cardinality and knapsack constraints are asymptotically tight as $k\to\infty$. They are also tight for $k=2$. The value-oracle complexities are \(O(Bnk)\) for cardinality, where \(B\) is the cardinality bound, \(O(n^2k)\) for matroid, and \(O(n^3k^2)\) for knapsack.

cs.DS

新论文 · v1arXiv:2611.25537

Query-Aware vs. Query-Agnostic Training-Free Video Token Pruning in Multimodal LLMs

Divya Kothandaraman, Timo Kumkel, Jaclyn Pytlarz

原文摘要

Video Large Language Models process large numbers of visual tokens, making token pruning important for efficient inference. Training-free pruning methods differ in whether and how they use the user query, and the value of query conditioning remains unclear. We present a controlled study of training-free, pre-LLM video token selection. Using a shared Qwen-3-VL backbone, token budgets, and decoding settings, we compare 21 pruning principles spanning query-agnostic, shallow query-conditioned, structured query-conditioned, and holistic strategies. To instantiate the last two categories, we introduce Structured Query Pruning, which decomposes the question into semantic anchors, and a Pareto variant, which combines anchor relevance with query-agnostic visual diversity. Across Video-MME, MVBench, and LongVideoBench, relevance computed from the raw question embedding is unreliable (8--16 points below the best methods), whereas anchors derived from query decomposition avoid this failure. However, query access is not inherently advantageous: strong query-agnostic coverage methods remain competitive or superior in the full-field comparison. Relative to a redundancy-only baseline, structured selection helps most on evidence-specific and long-context tasks at tight budgets; on broad tasks, the holistic selector improves over either relevance or redundancy alone. Further, pruning reduces cost and memory. These results support a practical design rule: preserve visual coverage by default, and add structured relevance when the task and token budget demand selective evidence retrieval.

cs.CV

版本更新 · v4arXiv:2503.15854

Persistent Stiefel-Whitney Classes of Tangent Bundles

Dongwoo Gang

原文摘要

Stiefel--Whitney classes are invariants of the tangent bundle of a smooth manifold, represented as cohomology classes of the base manifold. These classes are essential in obstruction theory, embedding problems, and cobordism theory. In this work, we propose a concrete algorithm to compute persistent cohomology classes representing these characteristic classes. Given a point cloud, we construct a Čech or alpha filtration and apply the Wu formula using the cup product and Steenrod squares. The algorithm runs in polynomial time in the number of simplices without estimating tangent spaces or constructing a classifying map. Under suitable hypotheses on the filtration, the resulting classes represent those of a closed smooth manifold even when the filtration contains additional wedge summands on whose reduced cohomology all positive Steenrod squares vanish. For sufficiently large samples drawn independently and uniformly from the manifold, recovery holds with high probability over an interval of scales. We present experiments on triangulated four-manifolds and on point clouds from image patches and a molecular conformation space.

math.AT · cs.CG

新论文 · v1arXiv:2611.25536

Differentially Private Score Estimation with Applications to Score-Based Generative Models

Mengxiao Gao, Elly K. H. Hung, Yuchen Wu, Yi Yu

原文摘要

Estimating the score function of a distribution plays a central role in statistics and machine learning, with applications in distribution estimation, sampling, and score-based generative modeling. However, learning scores from sensitive data raises privacy concerns. These concerns are particularly pronounced in score-based generative modeling, where trained models may memorize individual training examples and expose sensitive information through membership inference and data extraction attacks. Although non-private score estimation has been extensively studied, the statistical limits of its private counterpart remain less understood. In this work, we study score estimation under $(α,β)$-differential privacy for $d$-dimensional sub-Gaussian distributions with locally $γ$-Hölder-continuous scores. We develop a sampling-based private score estimator using quadratic B-splines and the exponential mechanism, and we implement our proposal through projected Langevin Monte Carlo with runtime polynomial in the sample size $n$. The proposed estimator satisfies $(α,β)$-differential privacy, and achieves expected density-weighted squared error $\mbox{polylog}(n) \max(n^{-2γ/(d+2γ+2)},\,(nα)^{-2γ/(d+γ+1)})$. We also establish a nearly matching private minimax lower bound, thereby characterizing the privacy-accuracy trade-off for score estimation. As an application, we construct a differentially private diffusion model whose privacy guarantee is independent of the number of denoising steps. We show that, with an appropriate discretization scheme, the resulting diffusion model attains nearly minimax optimal expected total variation error among all private distribution estimators. We validate our theoretical findings through experiments on both synthetic and real-world datasets.

stat.ML · cs.LG · math.ST · stat.ME

新论文 · v1arXiv:2611.25535

Support-Guided Triadic Decoding for Hallucination Mitigation in Multimodal Dialogue with LVLMs

Yiheng Li, Wenhao Wang, Xingyi Li, Zhilin Tang, Zichang Tan, Zhen Lei, Yang Yang

原文摘要

In multimodal multi-turn dialogue, dialogue history plays a dual role: reliable responses provide useful context for subsequent turns, whereas hallucinated responses can propagate errors across turns. Existing training-free methods globally adjust the effect of dialogue history on generation, making it difficult to suppress misleading information without weakening useful context. To address this trade-off, we introduce Support-Guided Triadic Decoding (SGTD), a training-free framework that selectively controls the influence of unreliable history and fuses complementary predictions during decoding. Specifically, Historical Answer Support Estimation measures the visual support of historical responses against type-matched alternatives and identifies low-support content that may mislead later generation. Support-Targeted Attention Intervention then weakens the influence of this content while preserving the surrounding dialogue, producing a support-refined prediction. Triadic Decoding combines this prediction with the full-history prediction and answer-free visual evidence, while the Support-Adaptive Plausibility Constraint filters implausible tokens using visual agreement and historical support. Experiments on MMHalSnowball and VisDiaHalBench across representative LVLMs show that SGTD consistently achieves the highest accuracy under hallucinated histories while preserving the benefits of factual context.

cs.CV

版本更新 · v2arXiv:2407.08743

Genomic Bottleneck, Neural Scaling, and the Emergence of Intelligence: A Theoretical Perspective on Biological and Artificial Neural Systems

Arifa Khan, Venkatesan S. K

原文摘要

We study the biological evolution of low-latency natural neural networks for short-term survival, and its parallels in the development of low latency high-performance Central Processing Unit in computer design and architecture. The necessity of accurate high-quality display of motion picture led to the special processing units known as the GPU, just as how special visual cortex regions of animals produced such low-latency computational capacity. The human brain, especially considered as nothing but a scaled-up version of a primate brain evolved in response to genomic bottleneck, producing a brain that is trainable and prunable by society, and as a further extension, invents language, writing and storage of narratives displaced in time and space. We conclude that this modern digital invention of social media and the archived collective common corpus has further evolved from just simple CPU-based low-latency fast retrieval to high-throughput parallel processing of data using GPUs to train Attention based Deep Learning Neural Networks producing Generative AI with aspects like toxicity, bias, memorization, hallucination, with intriguing close parallels in humans and their society. We show how this paves the way for constructive approaches to eliminating such drawbacks from human society and its proxy and collective large-scale mirror, the Generative AI of the LLMs.

cs.OH

新论文 · v1arXiv:2611.25531

LM-based Personalized Travel Planner

Amandi Nimasha, Oshadha Wijerathne, Dushan Fernando, Nisansa de Silva, Srinath Perera

原文摘要

Effective travel planning requires handling multiple information sources, managing constraints, and tailoring recommendations to user preferences. While LLMs have introduced dynamic, context-aware decision-making, single-agent models often struggle with complex multi-step reasoning, constraint adherence, and modular execution. To overcome these limitations, we propose a hierarchical multi-agent framework where a supervising chatbot agent coordinates specialized agents for schedule validation, user query formulation, real-time data retrieval, and constraint-aware itinerary generation. By integrating LLM reasoning, external APIs, and iterative refinement mechanisms based on a deterministic, multi-dimensional scoring framework, our approach ensures adaptability, efficiency, and personalization. Evaluations on the well-known TravelPlanner benchmark demonstrate improvements in Budget Constraint planning by 10\%, wider constraints set-based planning by 25\%, and personalized planning results by 45\%. compared to the ReAct baseline. Our code is available at https://github.com/nimashaklaa/TravelPlanner_Research

cs.AI · cs.CL

版本更新 · v2arXiv:2611.18690

Perceptual Weight Space Programming for Diffusion Super-Resolution

Chenzhi Zheng, Zhuoran Zheng

原文摘要

Diffusion models for image super-resolution can recover scene content while producing distracting artifacts or unbalanced colors. We study whether a large language model (LLM) can improve perceptual quality by editing a small subset of existing U-Net weights without a clean reference image. The proposed framework provides the editor with architecture code, selected weights, activation summaries, and sampling previews. It permits up to 1,020 candidate trials while limiting accepted changes to three layers and fewer than 0.1\% of model parameters. The evaluation protocol uses ResShift, SinSR, and SUPIR and compares GPT-6 Astra with a specified Qwen3-VL model under matched access. Feedback metrics guide editing, while separate quality metrics and blinded human comparisons evaluate the final weights. We also report an executed color calibration experiment using real photographs and two small residual networks. This experiment demonstrates correction of a fixed color shift and reveals that an improving feedback score can accompany worse performance on unseen scenes. A separate lightweight super-resolution experiment isolates modest changes in luminance detail while preserving color. The findings motivate restricted updates and independent evaluation of perceptual weight editing.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25527

Learning Generative Ranking Policies for Whole-Page Optimization

Chen Qiu, Zhigang Hua, Qi Xu, Jizhe Zhang, Sha Hua, Ren Mao, Luke Simon

原文摘要

A recommendation page is consumed as a whole: the items on it compete for attention and complement one another, so the best page is not simply the individually best items placed side by side. We study whole-page optimization, which selects and orders the items on a page jointly to maximize the score of the page. The number of possible pages grows combinatorially, so good pages must be generated rather than enumerated. Some generative re-ranking methods use the same page-level training signal for every choice in a sampled page. Others imitate target pages built before training, which remain largely fixed as the generator improves. We address both limitations with one local page-level objective, which repeatedly moves the current generator toward pages with higher score. This objective splits exactly into one training target per position, and each target compares candidates at the same partial page by the scores of the complete pages they lead to. Every position therefore learns to choose the item that is better for the whole page, rather than the item that looks best on its own. We call this procedure whole-page policy improvement. On two public datasets, KuaiRand-1K and RL4RS-SeqSlate, which cover multi-objective item selection and constrained ordering, and on an industrial dataset of logged pages, our method outperforms the evaluated generative re-ranking baselines. On a synthetic benchmark with a known optimal page, it also comes closest to the optimum, showing that its improvements come from better whole-page decisions.

cs.IR · cs.AI · cs.LG

新论文 · v1arXiv:2611.25526

MATE: Mobile Agent Trustworthy Execution for Safe and Efficient Mobile Control

Minsuk Jang, Hee-Seon Kim, Hui-Cheol Yu, Changick Kim

原文摘要

Mobile agents on personal smartphones can affect private data, payments, settings, and the foreground screen. We present MATE (Mobile Agent Trustworthy Execution), an execution-layer system that controls the boundary between agent action proposals and device effects without modifying the underlying model. MATE represents each UI primitive as a structured action record that combines the instruction, target app, screen context, primitive, and action fields. Runtime Guardrail (RG) maps this record to an allow, block, or user-approval decision; Predefined Task Routing (PTR) serves recurring requests through verified routes with post-execution screen checks; and a floating interface keeps execution in a compact overlay. On MobileSafetyBench, MATE raises high-risk blocking from 29.7% to 97.0% under GPT-4o. On AndroidWorld, it reduces LLM calls by up to 6x and raises recurring-use task success to 95.7%.

cs.CL · cs.AI

新论文 · v1arXiv:2611.25524

Contrast Where It Matters: Visual Evidence-Guided Decoding for Mitigating Hallucinations in LVLMs

Yiheng Li, Wenhao Wang, Xingyi Li, Mingda Jia, Zichang Tan, Yinhang Tang, Zhen Lei, Yang Yang

原文摘要

Despite strong multimodal capabilities, large vision-language models (LVLMs) often hallucinate when linguistic priors outweigh visual evidence or when predictions are grounded in irrelevant or misleading image regions. Training-free contrastive decoding mitigates hallucinations by contrasting the original prediction with an auxiliary one that exposes linguistic priors. Yet existing methods focus on altering the auxiliary input or computation and do not ensure that either branch uses query-relevant visual evidence during decoding. We propose Visual Evidence-Guided Decoding (VEGD), a training-free framework that identifies query-relevant visual evidence and guides its use throughout contrastive decoding. VEGD locates this evidence by aggregating localization heads with strong visual responses and coherent spatial structure, then selectively weakens it in the auxiliary image. During generation, VEGD directs visual-carrier heads in both branches toward the same evidence location, strengthening access to intact evidence in the main branch while anchoring the auxiliary branch to its weakened counterpart. An adaptive distribution fusion strategy then combines or contrasts their predictions according to distribution divergence. Experiments across diverse LVLMs and benchmarks demonstrate that VEGD consistently reduces hallucinations.

cs.CV

版本更新 · v2arXiv:2611.24650

Self-Rewarded Reinforcement Learning for Better-Structured Medical Explanations in Small Language Models

Prakhar Mishra, Bhavya Yajush Awasthi, Tanuja, Nishant

原文摘要

Small language models (SLMs) can run on commodity hardware and support privacy-preserving, on-premises clinical deployment, but their medical explanations are often short and poorly structured compared with large language models. Recent supervised approaches such as Meerkat transfer chain-of-thought reasoning into 7B-8B backbones, yet their training objective does not directly target the style or organization of the generated rationales. Building on the instruction-tuned Mistral-7B backbone, we investigate whether a lightweight reinforcement learning (RL) step can improve explanation structure without human preference labels. We apply Proximal Policy Optimization (PPO) with LoRA adaptation to 2000 Meerkat-derived medical prompts, guided by a simple self-supervised reward that favors longer, lexically diverse, and well-punctuated responses while penalizing very short ones. Training for about 170 PPO steps on a single NVIDIA A100 GPU yields a stable increase in the average reward. Quantitative and qualitative comparisons show that the RL-tuned model produces longer, more organized, multi-point explanations while preserving the underlying medical content. We discuss the promise and the limitations of self-rewarded RL for shaping the style of medical explanations.

cs.AI · cs.CL

版本更新 · v2arXiv:2607.14821

Blurring Modal Boundaries: A Unified Survey from Single- to Multi-Modal Person Re-ldentification

Xiao Wang, Bing Wang, Bin Yang, Cuiqun Chen, Xin Xu, Mang Ye

原文摘要

Person re-identification (ReID) serves as a critical component in intelligent surveillance systems, aiming to match identities across disjoint camera networks. While traditional methods primarily rely on single-modal RGB imagery, they are often constrained by environmental challenges such as low illumination and occlusion. To overcome these limitations, the field is rapidly evolving toward cross-modal and multi-modal paradigms. This survey presents a comprehensive overview of this transition, systematically reviewing key cross-modal tasks including visible-infrared (VI-ReID), text-image (TI-ReID), sketch-based (Sketch-ReID), and the emerging Non-Line-of-Sight (NLOS) ReID, which extends perception beyond direct visibility. Furthermore, we examine tri-spectral and multi-modal fusion ReID, discussing how complementary information from diverse sensors enhances robustness. Beyond summarizing datasets, challenges, and methodologies, we propose a Transformer-based baseline framework for visible-infrared ReID, designed to effectively capture modality-invariant features. Finally, based on the current landscape, we outline several promising directions for future research.

cs.CV

版本更新 · v3arXiv:2605.05895

Detecting AI-Generated Videos with Spiking Neural Networks

Minsuk Jang, Yujin Yang, Hee-Seon Kim, Minseok Son, Younghun Kim, Changick Kim

原文摘要

Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection. Existing detectors typically handle this temporal evidence in three ways: feeding the full frame sequence to a generic temporal backbone, reducing one dominant temporal cue to fixed video-level descriptors, or comparing temporal features to real-video statistics through a detection metric. These strategies degrade sharply under cross-generator evaluation, where artifact type and timescale vary across generators. On caption-paired benchmark, GenVidBench, we identify two signatures that prior detectors do not jointly exploit: AI-generated videos exhibit smoother frame-to-frame temporal residuals at the pixel level, and more compact trajectories in the semantic feature space, indicating a temporal smoothness gap at both levels. We further observe that, when raw video is fed into a Spiking Neural Networks (SNNs), fake clips elicit firing predominantly at object and motion boundaries, unlike real clips, suggesting that the SNN responds to temporal artifacts localized at edges. These cues are sparse, asynchronous, and concentrated at moments of change, which makes SNNs a natural choice for this task: their event-driven, sparsely-activated dynamics align with the structure of the residual signal in a way that dense ANN backbones do not. Building on this observation, we propose MAST, a detector that processes multi-channel temporal residuals with a spike-driven temporal branch alongside a frozen semantic encoder for cross-generator generalization. On the GenVideo benchmark, MAST achieves 93.14\% mean accuracy across 10 unseen generators under strict cross-generator evaluation, matching or surpassing the strongest ANN-based detectors and demonstrating the practical applicability of SNNs to AI-generated video detection.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25521

DRVEXO-4B-Unified: Design and Evaluation of a Modular Speech-Vision System

Zeyuan Li

原文摘要

We present DRVEXO-4B-Unified, a modular multimodal assistant built around a 4B language backbone. A self-contained checkpoint combines text, image, and speech inputs with reference-conditioned speech output and structured interaction. A temporal residual connector adapts acoustic sequences to the language interface; explicit text boundaries support incremental speech synthesis; and three task-conditioned scoring heads rank supplied action candidates alongside generative tool calls. These interfaces connect conversation to application-defined choices while leaving action authorization to the application. The system obtains 74.22% on all 900 MMMU validation questions, exceeding the published validation scores of Gemma 3 4B IT and InternVL3.5-4B without test-time scaling. Strict prompt-level IFEval accuracy is 82.26% and MATH-500 accuracy is 89.40%, above the original Qwen3-4B non-thinking report's 81.2% and 84.8%, respectively. On NVIDIA GB10, the model achieves a speech-synthesis first-chunk latency of 390 ms. For concurrent text generation, a growth-aware admission policy completes a 128-answer batch at 594.41 output tokens/s, including filling and draining, without preemptions. We plan to release the model weights and accompanying code under Apache License 2.0, retaining applicable third-party terms.

cs.CL

新论文 · v1arXiv:2611.25519

The computational complexity of bosonic Lindbladian fixed points

En-Jui Kuo, Arsalan Motamedi, Mohammad Hafezi, Saeed Mehraban

原文摘要

We study the computational complexity of estimating observables and sampling from stationary states, or fixed points, of bosonic Lindbladian dynamics with bounded-degree polynomial interactions. While the complexity of transient bosonic dynamics has been investigated, understanding the computational power of bosonic fixed points requires addressing subtleties of infinite-dimensional systems, including the existence, uniqueness, and convergence of stationary states. We establish a broad complexity landscape spanning universal quantum computation, efficient classical simulation, sampling hardness, and undecidability. First, we show that universal quantum computation can be embedded into observable estimation at the unique fixed point of a bosonic Lindbladian with a Hamiltonian of degree at most twelve and only linear photon loss. Moreover, this fixed point can be prepared from vacuum in polynomial time. On the classical side, we identify Gaussian regimes with incoherent pumping that admit efficient photon-number sampling and establish stability of classical approximability under sufficiently weak non-Gaussian Kerr perturbations. Conversely, for Gaussian fixed points without incoherent pumping, we establish hardness of exact sampling under constant-rate linear loss and hardness of approximate sampling at inverse-polynomial loss rates under standard boson-sampling conjectures. We also relate sampling from non-Gaussian fixed points to variants of boson sampling. Finally, we prove that deciding the existence of a stationary density operator is $\mathsf{RE}$-hard, even for purely dissipative Lindbladians with degree-five jump operators acting on at most four modes.

quant-ph · cs.CC