跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

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

统计口径与数据新鲜度

统计 2026-11-21 13:23 — 2026-11-22 13:23(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 08:44最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

每分钟刷新已保存的数据。空检查不代表采集异常;新收录可能包含历史论文。AI 导读按新增版本计数。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

时间范围跟随排序:版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常,查看状态 →

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 08:42(北京时间)
新论文 · v1arXiv:2611.25712

SkillLens: Action-Guided Dense Visual Dynamics for Proficiency Estimation

Deokhyun Ahn, Hyukjin Kim, Jae-Ho Han, Bumsub Ham, Heeseung Choi, Ig-Jae Kim, Haksub Kim

原文摘要

Human proficiency estimation is challenging because skill is a high-level and often subjective property that is not captured by action identity alone. Existing approaches leverage multimodal observations such as ego-exo video, gaze, pose, and inertial signals, but the gap between sensor-level evidence and abstract proficiency labels remains difficult to bridge. We present SkillLens, a proficiency estimation framework that uses atomic action descriptions as temporal guidance, rather than direct semantic supervision, to localize proficiency-relevant windows for dense visual-dynamics extraction. Each window is summarized into an action-dynamics feature and scored by a high-low prototype margin against higher- and lower-proficiency executions from the same activity-action category. Fusing these ego/exo PDM cues with a global ego-exo-gaze baseline through CORAL ordinal calibration, our method achieves 0.542 accuracy on Ego-Exo4D. Our project page is available at https://skill-lens.net/

cs.CV

新论文 · v1arXiv:2611.25711

Calibrate in Context: Efficient Data-Free Quantization from Small Synthetic Pools

Haowen Hua, Sen Lin, Yaokun Huang, Zeyi Shao, Hao Zhang, Wei Sui, John See, Zeyd Boukhers 等 9 位作者

原文摘要

We enable accurate low-bit recovery from small synthetic pools by improving both image synthesis and student preparation. A grid with lower local response error can incur greater error in the student's block context. Functional Grid Calibration (FGC) selects activation scales and integer offsets against full-precision responses constructed from the student's current block input. With weights fixed during calibration, FGC evaluates candidates only at their consuming operators, bringing block context to calibration at nearly local-scoring cost. For DeiT and ViT, progressive inversion updates the same images through increasingly deep teacher prefixes. With 1,000 images, the complete pipeline exceeds MimiQ's reported accuracy in all 18 W4A4/W5A5 settings across nine backbones. With 256 images, DeiT-S and ViT-S reach 68.20% and 66.90% ImageNet top-1 accuracy at W4A4 in 26-27 minutes on one RTX 5090. The pipeline outperforms strengthened 1K-image MimiQ by 13.03 and 24.36 percentage points at lower preparation cost and the same recovery-update count. The same low-budget checkpoints retain their advantage on ImageNetV2.

cs.CV

新论文 · v1arXiv:2611.25709

Distortion in Online Voting

MohammadHossein Ghasemi, Masoud Seddighin, Saeed Seddighin

原文摘要

We initiate the study of distortion in online voting, a framework that bridges computational social choice and online algorithms. In contrast to the classical offline setting, where the full election instance is known in advance, we consider a dynamic environment where a fixed set of voters is present from the beginning, but alternatives arrive sequentially over time. Upon each arrival, a mechanism must immediately and irrevocably decide whether to retain the currently selected candidate or switch to the newly arriving one, operating solely on the partial ordinal rankings induced by the underlying cardinal preferences. We provide upper and lower bounds for deterministic and randomized mechanisms under two standard cardinal preference frameworks. Utilitarian framework: For deterministic mechanisms under adversarial arrival order, we establish an $Ω(mn)$ lower bound and give an matching online algorithm with distortion at most $\frac{2}{3}m(n+\frac{1}{4})$. For randomized rules, we introduce regularity, which allows any regular, order-independent offline randomized rule to be converted into an online rule with the same expected distortion. The Harmonic voting rule satisfies this property, yielding online distortion $O(\sqrt{m\log m})$. Metric framework: For deterministic mechanisms, maintaining an alternative within a $\varphi$-weighted uncovered set guarantees distortion $2+\sqrt{5}$. We show that matching-based offline rules achieving distortion $3$ cannot be directly implemented online. We establish a lower bound of $\sqrt{13}$, even with three alternatives, and a matching upper bound for three alternatives and any number of voters. For randomized mechanisms, regularity gives an online distortion of $3-\frac{2}{n}$ via Random Dictatorship.

cs.GT

新论文 · v1arXiv:2611.25708

Slide2PPT: Native PowerPoint Reconstruction with Localization-Guided Refinement

Baoliang Chen, Xinlong Bu, Lingyu Zhu, Xiangjie Sui

原文摘要

Image-to-slide reconstruction must recover both visual appearance and native object structure for subsequent editing. Yet visually faithful charts and tables may lack editable series and cells, and direct code generation couples content prediction to rendering implementation. We present Slide2PPT, a model-agnostic, training-free framework that equips both open- and closed-source vision-language models with native PowerPoint reconstruction capabilities. Through a unified typed interface, the model predicts object records while a fixed renderer materializes their native properties, enabling integration with different backbones without task-specific training or architectural changes. Localization-guided refinement then connects visual discrepancies to object records for correction. Regional updates preserve unselected records, while whole-slide updates address cross-region relationships. Record refinement and targeted object editing support structural and attribute-level changes, with rendered feedback governing iterative acceptance. To evaluate this framework across diverse reconstruction demands, we introduce Slide2PPT-Bench, covering controlled elements, real slides, and scientific figures. Evaluation separately measures file production, rendered agreement, and native-object availability. Experiments across open- and closed-source backbones demonstrate substantially more reliable PPTX generation than direct code generation, improved layout and text recovery on scientific figures, and native chart and table interfaces beyond geometric primitives.

cs.CV

新论文 · v1arXiv:2611.25707

Safeguarded Learning-Assisted Nonlinear Conjugate Gradient Methods

Morteza Kimiaei, Saman Babaie--Kafaki

原文摘要

A learning-assisted framework for Nonlinear Conjugate Gradient (NCG) methods is developed in which lightweight online prediction is used to support, rather than replace, the classical optimization process. The proposed approach retains the standard two-term NCG structure and introduces two independent online extreme learning machine models. The first model predicts an NCG coefficient during restart recovery or when persistent stagnation is detected, whereas the second model is used only after a line-search failure in finite precision arithmetic to propose a bounded correction to the deterministic fallback step size. Neural predictions are accepted only when they satisfy deterministic numerical safeguards, including descent, scale, and out-of-distribution requirements; otherwise, the corresponding deterministic recovery or fallback mechanism is retained. Both learning models are updated online using quantities already generated along the optimization trajectory and therefore require no additional function or gradient evaluations for training. These learning frameworks are applied to six well-known classical NCG methods, producing corresponding low-storage learning-assisted variants with deterministic safeguards. Numerical experiments on 480 CUTEst test problems show improved robustness for all six variants at broadly comparable evaluation costs. A PDE-constrained conductivity-identification example further illustrates the potential of the proposed approach to reduce evaluation costs and computational time for problems with expensive function and gradient evaluations. These findings suggest that restricted online learning can improve the robustness and computational performance of classical NCG methods while preserving their low-storage structure and deterministic optimization safeguards, and is particularly promising when function or gradient evaluations are expensive.

math.OC · cs.LG

新论文 · v1arXiv:2611.25705

STARK: Moving towards Personalized Agents That Truly Learn and Remember

Aryan Jain, Abhishek Jha, Anish Nediyanchath, Promod Yenigalla

原文摘要

Long-term memory is essential for personalized agentic systems that interact with users over long time periods, yet current architectures only capture what happened while leaving the reasoning of why it happened to be derived later by underlying LLMs.%, and silo knowledge within individual users. These events can, however, convey not only what a user experienced but also how that experience shaped their behavioral patterns. We introduce STARK, a dual-graph memory architecture which treats these events not just as nodes but also as edges between behavioral insights. STARK maintains an Episodic Graph which records interactions as temporally, causally, and semantically linked episodes; and an Insight Graph which represents LLM-extracted behavioral signals scored by how many events support them, connected by the very events that led to them. At inference, behavioral knowledge is retrieved directly from insight nodes grounded by event-as-edges, eliminating repeated episodic traversal. The event-as-edge structure also naturally enables projecting the knowledge graph into a relational embedding space where cross-user transfer becomes possible under shared contextual circumstances, allowing the system to infer missing insights for cold-start users. Evaluations show that STARK improves by 1.48 judge score on LongMemEval information extraction and 0.93 on LoCoMo open domain questions over state of the art. On the public LongLaMP abstract-generation benchmark, cross-user transfer improves open-ended judge scores by 0.7 points and ROUGE-L by 3 at 5% graph sparsity.

cs.CL · cs.AI · cs.IR

版本更新 · v2arXiv:2609.35174

ProtoSeam: Lifting Classifier Training with Latent Gaussian Mixture Models

Robert Lampel, Timon Klein, Sebastian Sager

原文摘要

We propose a lifted reformulation of supervised classification that improves the final accuracy of standard classifiers without changing the architecture at inference time. A network $N=N_2\circ N_1$ is split at a single semantic interface and one learnable prototype per class is inserted there. Training combines a quadratic consensus penalty that pulls $N_1(x)$ toward the prototype of its class with a classification loss of $N_2$ evaluated on samples drawn around the prototypes, while no gradient crosses the interface. At inference the prototypes are discarded and the unmodified network $N_2\circ N_1$ is used. Across CIFAR-10, CIFAR-100, and TinyImageNet with ResNet and vision transformer backbones, lifted training improves test accuracy by up to six percentage points over variants without lifting under a shared tuning protocol. Moreover, we provide theoretical justification of those results.

cs.LG

版本更新 · v3arXiv:2606.12922

Polar: A Benchmark for Evaluating Political Bias in LLMs

Sangho Kim, Heejin Kim, Hyunggeun Jeon, Yoonhee Park, Jaejin Lee

原文摘要

Political bias in large language models (LLMs) is increasingly significant, but difficult to measure reproducibly across political and linguistic contexts. We introduce Polar, a 4,026-instance multiple-choice benchmark that measures political bias through option-level likelihoods rather than prompt-based generation. Polar covers two ideological axes and eight issue categories derived from the Manifesto Project, and evaluates models in parallel across U.S. and South Korean political contexts. Across 38 LLMs, measured bias varies systematically with political context, issue category, model group, and presentation language. All models lean left-progressive on U.S. political content, but show more centered and mixed patterns on South Korean content. Translation experiments further show that presentation language alone can shift measured bias. These findings highlight the need for multilingual and cross-contextual evaluation of political bias in LLMs. The code and dataset are publicly available on GitHub (https://github.com/mcrl/Polar) and Hugging Face (https://huggingface.co/datasets/thunder-research-group/Polar).

cs.CL · cs.CY

版本更新 · v2arXiv:2611.23615

Weight Space Programming for Vision Language Model Repair

Avinash Goutham Aluguvelly

原文摘要

In weight-space programming, a language model edits a network's weights directly, without gradients. We ask what a successful repair of this kind relies on. We plant faults in the weights of two vision-language models, SmolVLM-256M and LFM2-VL-450M, and check each edit made by a coding agent against the original weights. Without being told where to look, the agent finds rescaled projector rows and noise in the vision encoder, infers the unknown scale factors, and returns most or all of the rescaled weights to their exact original values and accuracy to near its original level. These repairs depend on a trace of how the faults were computed. The original weights have 16-bit precision, and faults computed in 32-bit arithmetic leave low bits that only the damaged weights carry, a cue that a real failure need not leave. When we round those bits away, each model answers our test questions as before, but the agent, unaided, no longer repairs either model: on LFM2-VL accuracy recovers by about 4 points, against 17 from the unrounded weights. Marking the damaged weights again in their low bits brings the edits back to them. Rounded weights still hold statistical evidence of the rescaling. On SmolVLM the agent uses it once a sentence in the prompt, which we wrote knowing the fault, names such a statistic; on LFM2-VL, whose scale factors are larger, most sessions find the rescaled rows unaided, but none finds the noise. Swapped rows or columns, which keep the set of stored values, are not found unaided on either model within our budgets. We recommend that studies of weight repair report the number format of the weights and include a rounded control.

cs.CV · cs.AI

版本更新 · v2arXiv:2608.11770

Achieving Near-Zero-Overhead Multi-Model Hierarchical Classification in Real-Time Detection Pipelines

Vaishnav Raju

原文摘要

Edge-deployed vision systems in target recognition, surveillance, autonomous vehicles, and drone domains require hierarchical inference pipelines where a detection model identifies objects of interest and downstream classifiers provide fine-grained attribute analysis. Running all models on the GPU creates a serial bottleneck that limits real-time throughput as pipeline stages grow. Modern edge SoCs pair GPUs with dedicated neural accelerators (NPUs, DLAs) capable of concurrent execution, yet deploying custom models on these accelerators remains impractical due to strict operator constraints, quantization incompatibilities, and an undocumented end-to-end pipeline. We target NVIDIA Jetson DLA cores as the representative platform. We present a five-step methodology for zero GPU fallback DLA INT8 deployment of classification backbones, comprising architecture adaptation, manual dynamic range workaround to rescue TensorRT's implicit quantization (recovering 94.0% accuracy from implicit quantization's 75%) for rapid pipeline validation before explicit quantization, quantization-aware training, ONNX graph surgery for DLA compilation, and a concurrent GPU-detection/DLA-classification inference pipeline. We document nine engineering constraints with root-cause analysis and generalizable solutions. Validation on a dual-head person attribute classifier running on DLA alongside a GPU object detector on a Jetson Orin NX demonstrates near-zero pipeline overhead (12.5 vs. 13.3~FPS detector-only at 1080p), with dual-DLA scaling at no additional cost. The methodology is backbone-agnostic and generalizes to any detection-classification edge pipeline.

cs.CV · cs.DC · cs.LG

新论文 · v1arXiv:2611.25696

LIFT: Lifting Language-Controlled Image Fusion to Free-Viewpoint 3D Scenes

Jingning Tian, Hao Zhang, Yumin Huang, Zizhuo Li, Xingyu Jiang, Erdun Zhao, Jiayi Ma

原文摘要

Multimodal image fusion traditionally generates a single fused image from paired observations at a specific viewpoint, limiting comprehensive scene perception and adaptability to diverse perceptual objectives. To overcome these limitations, we present LIFT, a novel framework for our proposed language-controlled 3D image fusion (L3D-IF) paradigm that extends multimodal image fusion from 2D images to free-viewpoint 3D scenes, enabling language-guided fusion tailored to diverse perceptual objectives. First, LIFT formulates Semantic Modality Binding (SMB), which interprets language instructions to identify semantic targets and their associated modality preferences and grounds these targets in corresponding regions of a shared Gaussian scene, establishing persistent semantic-to-spatial correspondences for consistent fusion control across viewpoints. Second, Language-Conditioned Gaussian Appearance (LCGA) is developed to achieve scene-wide multimodal appearance modeling by combining adaptive multimodal blending with language- and viewpoint-conditioned appearance refinement, enabling spatially adaptive realization of diverse fusion appearances while preserving source fidelity at pure-modality endpoints. Finally, we construct a Multi-View Language-Supervision (MVLS) dataset that associates language instructions and calibrated viewpoints with modulated fused images, providing effective supervision for learning instruction-dependent fusion from finite multi-view observations. Extensive experiments demonstrate that LIFT achieves coherent multimodal fusion across continuous viewpoints, accurate semantic target localization, and consistent regional fusion control under diverse language instructions.

cs.CV

版本更新 · v3arXiv:2606.07322

A Non-Nested Quantum Search for TSP: Explicit Oracle Construction Beyond the $2^n$ Barrier

Xujun Bai, Yun Shang, Honghong Lin

原文摘要

The traveling salesman problem (TSP) is a classic NP-hard problem. Held--Karp dynamic programming~\cite{held1962dynamic, bellman1962dynamic} solves it exactly in $O(n^2 2^n)$ time. Ambainis et al.~\cite{ambainis2019quantum}\ (SODA~2019) proposed a hybrid classical-quantum dynamic programming that improved the query complexity to $O^*(1.727^n)$. However, their algorithm uses nested quantum minimum finding, which complicates coherent circuit implementation, particularly the handling of threshold updates within nested subroutines. To address this difficulty, we design a quantum divide-and-conquer framework without any recursive process. We overcome the oracle-construction bottleneck by preparing a set partition state, requiring $O(n^2)$ gates and $O(n)$ depth. Under assumed QRAM model, the structured state preparation enables polynomial-depth oracle evaluation, yielding an overall running time of $O^*(1.866^n)$ for TSP. Qiskit simulations for $n=6$ and 7, using QFT-based data loading in place of QRAM, yield empirical optimal-solution probabilities of $98.9\%$ and $100\%$, respectively, in fixed-threshold amplitude-amplification tests.

quant-ph · cs.CC

新论文 · v1arXiv:2611.25695

DMT-Attack: Diffusion-Prior Texture Search for Closed-Loop Vision-Language-Action Policies

Jun Xia, Shangwen Wang, Jun Ma, Ruichao Ren, Zhouyang Jia, Xin Zhao, Huijun Liu, Jie Yu

原文摘要

Vision-language-action (VLA) policies rely on visual feedback throughout manipulation, making them vulnerable to persistent texture attacks. However, optimized patterns can stand out from their surroundings, making an attack easier to notice and its carrier more likely to be inspected or removed. To address this limitation, our key insight is to search the structured image distribution of a diffusion model for natural-looking textures while using closed-loop feedback to identify task-disruptive candidates. Based on this idea, we propose DMT-Attack, a gradient-free gray-box attack that generates textures for ordinary scene objects such as tablecloths. A frozen text-conditioned diffusion model defines the search space, and an eight-expert latent proposal network is initialized from evaluated teacher latents and refined using rollout feedback. We evaluate DMT-Attack against pi_0.5 and OpenVLA-OFT across four LIBERO suites. DMT-Attack achieves a macro clean-conditioned attack success rate (cASR) of 57.9%, compared with 44.7% for UPA-RFAS and 19.7% for random natural textures. It also attains higher scene similarity and a lower clean-calibrated detector flag rate (45% versus 97.5-100% for optimized patch baselines). These results demonstrate that natural-looking textures can disrupt VLA visual feedback and closed-loop decision-making, motivating defenses that jointly assess visual appearance and task behavior.

cs.AI

版本更新 · v2arXiv:2610.39454

Kairos: A Unified PDDL Planner for Robots: Plans in Milliseconds, with a Guarantee for Every Answer

Francisco Martín Rico, Esther Aguado González, Francisco Miguel Moreno Olivo, Rodrigo Pérez Rodríguez, José Miguel Guerrero Hernández, Francisco J. Rodríguez Lera

原文摘要

Robots that plan while they act need a task planner that reads the models their designers write, answers within milliseconds, and says what each answer means. Models are written in the Planning Domain Definition Language (PDDL), which has grown from classical planning to durative actions, numeric resources, time windows and continuous change, while planners cover one fragment each and differ in what their failures mean. The contribution in artificial intelligence is Kairos, a single planner, not a portfolio of existing planners, that covers the whole language and derives what each answer guarantees from the search that produced it. We prove when the exhaustion of a search shows that no plan exists, and give a relaxation of temporal tasks that proves unsolvability where temporal search cannot. For the compression of durative actions, we give a criterion on the values that actions read, prove that compression is sound, and show that it is not complete, so its failure is never reported as a proof. An independent validator checks every plan. The engineering application is on-line task planning for robots: Kairos is open source, packaged for the Robot Operating System, and the default planner of a widely used planning framework. On 1,756 public tasks from nine suites, Kairos solves more tasks than the strongest evaluated planner of each suite within 100 milliseconds, 1 second and 30 seconds; it proves ten of eleven unsolvable tasks, and handles each of the seventeen language features probed, where no other planner handles more than eight.

cs.AI · cs.RO

新论文 · v1arXiv:2611.25692

Measurable Does Not Imply Transportable: A Prospective Audit of Model Explanations in Multi-Year Field Trials

Rayhaneh Shabani Nia, Ali Karkehabadi

原文摘要

Model explanations are increasingly used as scientific evidence, yet it remains unclear what they license scientists to conclude beyond the data on which they were constructed. When a fine-grained explanation fails to replicate, the failure may be attributed to noisy measurement of its target, raising a fundamental question: does reliable measurement imply a reproducible explanation? We test this directly. We formalize prospective explanation transportability: the extent to which an explanation learned from past data is recovered in a genuinely future context. This property is distinct from feature importance and measurement reliability. Using multi-year Genomes-to-Fields maize trials, where each new year is a real future context rather than a random resample, we evaluate 16 agronomically interpretable environmental concepts across five forward splits and one prospectively locked test year. Coarse environment-level explanations transport reliably (median cosine 0.83); their locked 2024 value, 0.811, fell within a prespecified 80% bootstrap percentile interval. For grain yield, genotype-conditioned explanations have a historical median cosine of 0.30 and range from 0.006 to 0.822 across years. Reliability does not order these outcomes: the year with the highest split-half reliability had the lowest explanation transport. Within-context resampling showed that GxE explanations were reproducible within a fixed context (0.77-0.95) while exhibiting lower prospective alignment across the 2020-2023 transitions (0.01-0.36). A second phenotype transports strongly at both resolutions, and non-temporal validation inflates apparent interaction-level transport by +0.22. These results show that target reliability and within-context explanation reproducibility do not by themselves establish when a model explanation can support a reproducible scientific claim.

cs.LG

版本更新 · v3arXiv:2611.21258

ThinkWAM: Rethinking Latent Futures for Action Refinement

Haoyun Tang, Baqiao Deng, Enjin Zhou, Songwen Tian, Keyao Xu, Bowen Jing, Kun Wang, Ke Ma 等 10 位作者

原文摘要

World-action models (WAMs) couple action generation with predictions of future states. An initial action chunk may be flawed. A future prediction that is not conditioned on the chunk is identical for every proposal and thus carries no proposal-specific signal, limiting its usefulness for refinement before execution. We introduce ThinkWAM, a latent WAM that establishes bidirectional feedback before execution through a proposal-rethink-refine loop: the policy first proposes a complete action chunk, the proposal corrects multi-horizon future latents through a learned residual, and the corrected latents are injected into a second pass of the same action head, which generates the executable chunk. An affordance-guided observation-action memory and a near-fine, far-coarse multi-horizon prediction scheme, both motivated by predictive coding, support this loop, and all prediction stays in latent space. ThinkWAM achieves 98.70% success on LIBERO, 84.76% on LIBERO-Plus without OOD fine-tuning, 85.75%/65.85% on RoboTwin 2.0 Clean/Random, and 65.17% on RoboCasa24. ThinkWAM achieves 64.4% mean success across three real-world OOD conditions. The mean two-pass inference latency per action chunk is 153.48 ms on LIBERO, 164.61 ms on RoboTwin, and 101.2 ms on the Galaxea A1Z. Ablations show complementary gains from rethinking and affordance guidance. Diagnostics indicate that proposal-conditioned corrections change both predicted futures and action trajectories, showing that the corrected future representations improve the final action.

cs.RO

新论文 · v1arXiv:2611.25691

Exploring Semantic Table Search in Data Lakes

Martin Pekár Christensen, Matteo Lissandrini, Katja Hose

原文摘要

Discovery of relevant datasets within data lakes remains a key challenge. Union and join search are effective techniques for discovering data when augmenting an existing table. In exploratory search, instead, keyword search is commonly adopted to find a relatively small set of highly relevant tables matching some search terms. In this context, semantic search is a new technique that exploits the presence of named entities in exemplar tuples used as queries and in target tables. Hence, keyword search and entity search are able to find a diverse set of tables. In this work, we propose \texttt{Thetis++}, which combines keyword and semantic table search to discover relevant tables that combine the semantic signal with the presence of exact keyword matches. Incorporating multiple paradigms and sources of information allow us to combine the best of multiple worlds. Therefore, we study many alternative techniques for combining rankings and evaluate these for the table search task in data lakes. We explore both unsupervised and supervised techniques, including TOPSIS. Finally, alternative to Thetis++ combining keyword and semantic relevance signals, we study a variant of learning-to-rank for the table search task in data lakes. Our evaluation highlights both the limitations of many standard approaches along with some promising directions offered by learned approaches. Furthermore, while indexes for keyword search are quite efficient, here we provide insights into how to improve the scalability of prefiltering techniques for semantic search, comparing LSH indexes with Hierarchical Navigable Small Worlds. Our experiments show that HNSW drastically improves the runtime of semantic table search by 4.7X on average whilst retaining the high-quality tables. Together, our findings plot the line for effective and efficient data discovery techniques for semantic data lakes.

cs.IR

新论文 · v1arXiv:2611.25689

D3-Cache: Accelerating Diffusion Models with Dynamic Mode Decomposition

Yanbo Li, An Xiang, Xiaoxin Hu, Feng Wang, Cheng-zhong Xu, Kejiang Ye, Xitong Gao

原文摘要

Diffusion Transformers generate high-quality images and videos, but every sampling step requires a full network evaluation. Training-free caching reduces this cost by reusing or forecasting network outputs across steps, but common approaches use per-model calibrated skip criteria or maintain per-layer prediction histories. We present D3-Cache, which applies Dynamic Mode Decomposition (DMD) to Diffusion sampling: it fits DMD to a short history of exact velocities and forecasts only the velocity that the scheduler consumes. A horizon-aware gate decides when to skip: whenever the network is evaluated, its output is compared with the forecast for that step, and the larger the error, the sooner the network is evaluated again, up to a cap on consecutive skipped steps. D3-Cache requires no training or per-model offline calibration curve and adds negligible memory. It shares one history length and risk tolerance across the four evaluated models. On four state-of-the-art image and video models, D3-Cache achieves speedups of 2.6-3.8x with high fidelity to the base model output.

cs.CV

版本更新 · v3arXiv:2607.17117

Persistent Sparse Autoencoders: Learning Feature-Specific Timescales in Language Model Representations

Haoyan Luo, Mateo Espinosa Zarlenga, Mateja Jamnik

原文摘要

Sparse autoencoders (SAEs) decompose language model activations into sparse features, yet these models traditionally encode each token independently, failing to expose information that persists across a sequence. We first show that temporal persistence can naturally emerge in standard SAE features: after a feature activates, the hidden state remains aligned with its direction, and past activations reduce the reconstruction error of later hidden states. How long this lasts varies widely across features. We therefore introduce Persistent Sparse Autoencoders (Persistent SAEs), an extension of standard SAEs that learns a persistence coefficient for each feature, allowing feature-specific timescales to emerge from reconstruction. Our experiments show that Persistent SAEs retain competitive reconstruction quality while learning a spectrum of timescales: short-timescale (fast) features remain locally interpretable, whereas long-timescale (slow) features accumulate higher-level contextual information. Moreover, we show in a prompt-injection monitoring case study that slow features retain injection signals over long contexts and causally affect monitor judgements. These results suggest that Persistent SAEs offer new opportunities for interpreting and monitoring language models via persistent features.

cs.LG · cs.CL

版本更新 · v2arXiv:2604.02930

BEVPredFormer: Spatio-temporal Attention for BEV Instance Prediction in Autonomous Driving

Miguel Antunes-García, Santiago Montiel-Marín, Fabio Sánchez-García, Rodrigo Gutiérrez-Moreno, Rafael Barea, Luis M. Bergasa

原文摘要

A robust awareness of how dynamic scenes evolve is essential for Autonomous Driving systems, as they must accurately detect, track, and predict the behaviour of surrounding obstacles. Traditional perception pipelines that rely on modular architectures tend to suffer from cumulative errors and latency. Instance Prediction models provide a unified solution, performing Bird's-Eye-View segmentation and motion estimation across current and future frames using information directly obtained from different sensors. However, a key challenge in these models lies in the effective processing of the dense spatial and temporal information inherent in dynamic driving environments. This level of complexity demands architectures capable of capturing fine-grained motion patterns and long-range dependencies. We introduce BEVPredFormer, a novel multi-camera architecture for Bird's-Eye-View Instance Prediction that uses attention-based temporal processing to improve temporal and spatial comprehension of the scene and relies on an attention-based 3D projection of the camera information. BEVPredFormer employs a recurrent-free design that incorporates gated transformer layers, divided spatio-temporal attention mechanisms, and multi-scale prediction heads. Additionally, we incorporate a difference-guided feature extraction module that enhances temporal representations. Extensive ablation studies validate the design of the temporal module, including the configuration of the spatio-temporal attention blocks and the difference module, as well as the choice of feature extractor and view transform, the training strategy and the input resolution. When evaluated on the nuScenes dataset, BEVPredFormer performs on par with or surpasses state-of-the-art methods, particularly in long-range scenarios, at a moderate computational cost. Code is available at https://github.com/miguelag99/BEVPredFormer.

cs.CV

新论文 · v1arXiv:2611.25683

TipDex-VTLA: Learning When to Refine Actions with Touch for Dexterous Manipulation

Xudi Ge, Yepeng Liu, Haifeng Liu, Enze Shi, Liangqi Zhang, Yongchao Xu

原文摘要

Changes in illumination can induce action drift in dexterous manipulation even when the physical state remains unchanged. Although existing vision--tactile--language--action (VTLA) policies incorporate tactile feedback, when and how touch refines actions under changing visual conditions remains challenging. We introduce \textbf{TipDex-VTLA}, a VTLA policy that combines estimated visual action reliability and tactile forecast verification to regulate execution-time refinement. Specifically, Visual Action Sensitivity Estimation (VASE) learns visual reliability from a frozen reference policy's action sensitivity to illumination perturbations. Tactile Anticipation and Correction during Execution (TACE) compares predicted and measured touch at matched times and combines the resulting discrepancy with visual reliability to gate bounded feature corrections for unexecuted actions. This effectively helps to refine actions under challenging unseen visual conditions. We evaluate TipDex-VTLA on four real-world dexterous manipulation tasks and the UniVTAC simulation benchmark. TipDex-VTLA trained on data collected under normal visual conditions, achieves average full-task success rates of 87.5% (resp. 73.8%) under normal (resp. challenging unseen) lighting in real-world tasks, significantly outperforming some state-of-the-art methods. We will release the collected data and source code.

cs.RO · cs.AI

新论文 · v1arXiv:2611.25681

Explainability of genotype embedding models through observed cohort paths

Amashi Niwarthana, Aloysius Tan, Jagath C. Rajapakse

原文摘要

Deep learning models that combine genotypes with neuroimaging predict neurological diseases more accurately than either modality alone. Their clinical use, however, requires identifying which genetic variants a prediction is based on. Path-based attribution methods like Integrated Gradients address this by integrating the model's gradient from a baseline to the input. These methods assume the model accepts any point along that path as a valid input. Genotype models violate this assumption. They map the three discrete allele dosages \{0,1,2\} to vectors through a learned embedding defined only at those values, so a straight line passes through fractional genotypes at which no embedding, and therefore no gradient, exists. Attribution must therefore proceed in embedding space where the choice of path can affect the resulting attribution. We show that the commonly used per-variant estimator does not generally satisfy completeness. Additive separability guarantees completeness for this estimator, but interactions between variants generally break that property. Instead, we integrate along piecewise-linear embedding-space paths connecting genotype waypoints observed in the training cohort. Each path satisfies completeness in the continuum although the interiors of its segments are not necessarily observed. Our method improves faithfulness over Integrated Gradients and discretized Integrated Gradients under both perturbation protocols, achieves the strongest results for Parkinson's disease classification under support-preserving perturbations, and is competitive with a support-background Shapley baseline under per-variant perturbations. It also shows higher seed stability and better recovery of planted non-additive effects in a synthetic benchmark.

cs.LG

版本更新 · v2arXiv:2603.09185

DEO: Training-Free Direct Embedding Optimization for Negation-Aware Retrieval

Taegyeong Lee, Jiwon Park, Seunghyun Hwang, JooYoung Jang

原文摘要

Recent advances in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) have enabled diverse retrieval methods. However, existing retrieval methods often fail to accurately retrieve results for negation and exclusion queries. To address this limitation, prior approaches rely on embedding adaptation or fine-tuning, which introduce additional computational cost and deployment complexity. We propose Direct Embedding Optimization (DEO), a training-free method for negation-aware text and multimodal retrieval. DEO decomposes queries into positive and negative components and optimizes the query embedding with a contrastive objective. Without additional training data or model updates, DEO outperforms baselines on NegConstraint, with gains of +0.0738 nDCG@10 and +0.1028 MAP@100, while improving Recall@5 by +6\% over OpenAI CLIP in multimodal retrieval. These results demonstrate the practicality of DEO for negation- and exclusion-aware retrieval in real-world settings.

cs.CL

版本更新 · v2arXiv:2609.16811

Hyper-RED: Scalable Event Pre-training via Semantic Hypergraph Distillation

Meisen Wang, Zhiqiang Tian, Wei Bao, Chengjie Wang, Shaoyi Du, Siqi Li

原文摘要

Event cameras have shown great potential for robust visual perception, yet scaling event representation learning remains challenging due to the scarcity of large-scale annotated event data. Pretrained image models provide scalable semantic supervision, but existing image-to-event methods rely on rigid pixel-wise or token-wise alignment that overlooks modality discrepancies in texture, density, and appearance, potentially causing semantic collapse and limiting transferability. To address this issue, we propose Hyper-RED, a simple, painless, and scalable image-to-event pretraining framework that transfers high-order semantic structures from images to events. Hyper-RED uses hypergraphs to model and align high-order semantic associations among multiple image and event tokens, enabling cross-modal knowledge transfer while accommodating modality-specific differences rather than enforcing rigid one-to-one correspondence. Specifically, given a paired event--image sample, Hyper-RED leverages DINOv3 to extract spatial token representations and constructs image, event, and cross-modal semantic hypergraphs, where each hyperedge connects multiple semantically correlated tokens. We further introduce a hypergraph relational distillation loss that imposes complementary intra- and cross-modal constraints, enabling the event encoder to inherit image-derived semantic organization while preserving local relational consistency and event-specific characteristics. Experiments on three tasks across five event datasets demonstrate consistent scaling from ViT-S to ViT-L and state-of-the-art performance (Fig.1). The code is available at: https://github.com/meisenwang/Hyper--RED.

cs.CV

新论文 · v1arXiv:2611.25680

Beyond Entity Recognition: Vision-Centric Knowledge Visual Question Answering

Jiatong Ma, Yuchen Liu, Longteng Guo, Yichen Yuan, Yuze Wu, Dongze Hao, Ru Zhen, Yanhao Zhang 等 10 位作者

原文摘要

We propose VC-VQA, a large-scale benchmark for vision-centric knowledge reasoning, aiming to systematically evaluate the capabilities of Multimodal Large Language Models (MLLMs) in fine-grained visual knowledge acquisition and complex multi-stage reasoning. Unlike existing benchmarks that primarily treat visual information as entity recognition and rely on text-based external knowledge, VC-VQA explicitly models the role of visual information by considering both its source (internal vs. external images) and stage of involvement (pre-retrieval vs. post-retrieval). Specifically, VC-VQA requires models to retrieve external visual evidence, identify visual clues before retrieval, and localize, verify, or match retrieved knowledge against the internal image. We further construct a controlled multimodal knowledge base with traceable textual and visual evidence for each sample. We evaluate 21 representative MLLMs under four settings: no external knowledge, with provided evidence, knowledge base retrieval, and open-web search. Experimental results lead to three key findings: current models still struggle with vision-centric knowledge reasoning; fine-grained visual knowledge acquisition remains the primary bottleneck; and agentic retrieval highlights the value of multi-step planning and cross-modal knowledge integration. Overall, VC-VQA provides a more challenging benchmark for evaluating vision-centric knowledge reasoning in MLLMs. Our code and dataset are available at https://github.com/CASIA-IVA-Lab/VC-VQA.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25679

LeCompass: Task-Level Execution through State-Indexed Interfaces

Kai Shi, Shiqi Zhao, Zimo Li, Hairong Qu, Hongyu Ma, Yongsong Yang, Jiahao Ai, Ziran Yin 等 9 位作者

原文摘要

Action-conditioned joint-embedding predictive architectures (JEPAs) offer a foundation for predictive decision-making by modeling the consequences of actions in representation space. Yet evaluating local reachability in latent space does not by itself provide a task-level execution interface: intermediate targets must be generated, local inference has finite budgets, and execution requires spatial feedback and persistent interaction state. We introduce LeCompass, a state-indexed execution framework built around a frozen LeWorldModel (LeWM). A proposer supplies intermediate latent targets, while CompassFlow searches the source space of a learned trajectory prior to obtain effective action candidates under limited predictive-evaluation budgets. Patch-token readouts provide spatial feedback, while observation-based memory supports phase transitions and bounded recovery. State-indexed targets support cross-episode context-goal composition. On 1,000 official TEST full-episode Cube trials, the complete LeCompass execution system achieves 86.9% native 4-cm reach. Separate matched analyses show that predictive ranking raises success from 4.7% to 44.9% on TEST PushT and from 33.8% to 77.7% on TEST TwoRoom. These results demonstrate task-level execution with task-dependent roles for latent target proposal, predictive search, and observation-grounded control.

cs.RO

版本更新 · v2arXiv:2609.17488

LimiX-2: A Contextual Mechanism Network Towards General Structured-Data Intelligence

Xingxuan Zhang, Gang Ren, Hao Yuan, Hao Zou, Hongze Tan, Hui Wang, Jianhao Song, Jiansheng Li 等 60 位作者

原文摘要

We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws. LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM). CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling. Rather than centering the network on the $p(y \mid x, D_{\mathrm{context}})$ objective of conventional tabular PFNs, it is designed around learning $p(x, y \mid D_{\mathrm{context}})$, a context-dependent representation of the joint structure underlying data generation. Pretraining uses synthetic datasets generated by structural causal models (SCMs) spanning diverse graph structures, functional mechanisms, and observation processes. Evaluations on TabArena, TALENT, and BCCO show that LimiX-2 outperforms current dataset-specific models and tabular foundation models. Beyond predictive performance, the CMN paradigm also promotes causal awareness in LimiX-2: its feature attention encodes direct causal relationships, enabling accurate causal skeleton recovery.

cs.AI

新论文 · v1arXiv:2611.25678

Lightweight Low-Frequency Non-Intrusive Load Monitoring via Karhunen-Loève Feature Distillation and Temporal Convolutional Networks

Sanka Peeris, Pandula Thennakoon, Praveen Sumanasekara, Roshan Godaliyadda, Parakrama Ekanayake, Janaka Ekanayake

原文摘要

Non-Intrusive Load Monitoring (NILM) is a critical enabler for demand-side management which allows for smart grid optimization. A deployment-ready NILM solution necessitates three key features: accurate disaggregation, low-frequency sampling, and low computational cost. This paper proposes a lightweight, edge-oriented NILM framework that combines activity-boundary-aware synthetic data augmentation with Karhunen-Loève Transform (KLT) feature extraction and a Temporal Convolutional Network (TCN). The augmentation stage extracts and recombines complete or near-complete appliance activation segments so that the model can be trained without new fully labeled household aggregates. The KLT filter bank extracts decorrelated, appliance-informed temporal features which are then fed into a compact TCN along with the original aggregate for energy disaggregation. Evaluations on two standard NILM datasets, UK-DALE and REDD, at 10-s sampling and with leave-one-house-out testing, demonstrate that the proposed architecture achieves comparable or superior disaggregation accuracy relative to NILMFormer, BERT4NILM, BiLSTM, and BiGRU. The computational footprint of the framework is 31,009 parameters, the fewest of the five models compared, and on a single CPU thread it needs 2.78 ms per 1000 samples, 84-95% less than the baselines. These results demonstrate a favorable accuracy-efficiency tradeoff for low-frequency smart-meter NILM.

eess.SP · cs.LG · eess.SY

新论文 · v1arXiv:2611.25675

Minimal Memory for Correctable Visual Continuation

Xiyang Zhang, Yuanhe Tian, Hongzhi Wang, Yan Song

原文摘要

Given past images and known actions, visual continuation generates future frames from one evolving scene state. Keeping this state revisable matters when an object reappears or a later view changes an earlier interpretation. Once past images cannot be replayed, a summary sufficient for current rendering can lose candidates needed after correction. We establish matching sparse and dense bounds on the bits needed for later correction under stable observations and bounded disagreement. For static streams at the stated smoothness and margin scales, correction incurs at least logarithmic overhead in one dimension and polynomial overhead in higher dimensions. Coherent Archive Memory (CAM) stores geometric summaries with exact updates under clipped expansion and coordinate assignments, then uses historical existence constraints to select one state for all requested frames. Exhaustive photographic tests show strict worst-truth image-risk gains from joint witnesses, while controlled neural continuations recover positions hidden in the current view.

cs.CV

新论文 · v1arXiv:2611.25673

CompAct-Bench: A Benchmark for Working-Context Compaction in Long-Horizon Agent Tasks

Jiayi Chen, Lizhe Chen, Yujia Chen, Shihan Dou, Ming Zhang, Chendi Ge, Shiguang Ni, Tao Gui 等 11 位作者

原文摘要

As language-model agents are applied to increasingly extended tasks, their working context continuously accumulates interaction history, tool observations, intermediate decisions, and task progress. Context compaction offers a practical way to reduce this growing history while allowing execution to continue, yet the compaction ability of modern LLMs remains insufficiently understood. We introduce CompAct-Bench, a benchmark for evaluating working-context compaction through its downstream effect on agent task completion. Starting from successful agent trajectories, we insert compaction boundaries at different stages of execution, compress the preceding working context with the model under evaluation, and let the same executor continue the original task. To enable fair comparison across compactors, we evaluate them under controlled retention ratios using a lightweight iterative ratio-adjustment procedure. CompAct-Bench covers information-seeking, software-engineering, and workspace-oriented tasks through BrowseComp, SWE-bench, and an internal CompanyBench evaluation. Our experiments show that working-context compaction remains highly lossy even for frontier models: Claude- and GPT-family models perform strongest overall, yet substantial degradation in downstream task accuracy persists under aggressive compaction. Further analysis reveals that failures are often caused not only by omitted information, but also by distorted task state, such as turning unresolved issues into apparent conclusions or forgetting previously established results, which can lead to incorrect decisions or redundant execution. These findings highlight working-context compaction as a distinct and still challenging ability for LLMs operating in extended agent tasks.

cs.AI