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
+2已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-15 07:45 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-14 07:59 — 2026-11-15 07:59（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：2026-11-15 07:45最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 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。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

浏览论文库

研究日报 / 周报 →按信源浏览 →

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 5,643 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-15 07:44（北京时间）
版本更新 · v3arXiv:2605.14201

MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving

Rajeev Yasarla, Deepti Hegde, Hsin-Pai Cheng, Shizhong Han, Yunxiao Shi, Meysam Sadeghigooghari, Hanno Ackermann, Litian Liu 等 12 位作者

原文摘要

Vision-language-action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings due to being trained under traditional imitation learning framework. Existing closed-loop supervision approaches lack scalability and fail to completely model a reactive environment. We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model. The ego vehicle and nearby traffic agents are independently controlled over multi-step horizons, while being reactive to other agents in the scene, enabling closed-loop training. MAPLE consists of two training stages: (1) supervised fine-tuning on the latent rollouts based on ground-truth trajectories, followed by (2) reinforcement learning with global and agent -specific rewards that encourage safety, progress, and interaction realism. We further propose diversity rewards that encourage the model to generate planning behaviors that may not be present in logged driving data. Notably, our closed-loop training framework is scalable and does not require external simulators, which can be computationally expensive to run and have limited visual fidelity to the real-world. MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13504

Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction

Donghoon Cha, Bomseok Park, Hansl von Kwon, Ku DoHyung, Hanwool Sul

原文摘要

SDR-to-HDR reconstruction is an ill-posed problem in which clipped highlights, crushed shadows, and quantization artifacts must be recovered while preserving the original content. Latent diffusion models provide powerful generative priors for restoring missing detail, but their effectiveness is constrained by how HDR signals pass through the pretrained VAE. We find that common log-like encodings suppress low-luminance chromatic differences before generation, producing a dark-side collapse in the frozen-VAE latent. We introduce EquivFlow, a compact, invertible exposure-equivariant encoding that maps exposure changes to additive shifts while retaining a scale-independent chromatic component, without modifying the VAE. Encoding-level tests across pretrained image and video VAEs show that its exposure structure and deep-dark chroma transport persist across the tested hosts. Integrated into SDR-to-HDR video diffusion, EquivFlow delivers consistent chromatic-fidelity gains across the tested settings while retaining competitive reconstruction fidelity.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13503

FaiSonic MMD: A popular music dataset with temporally aligned multidimensional annotations for multitask music analysis

Tieyao Zhang, Yuke Liu, Jiaxing Yu, Xinda Wu, Genfang Chen

原文摘要

Temporal analysis in music information retrieval concerns the positions of musical events and structures within recordings. Joint modeling has demonstrated the value of combining musical descriptions, but existing resources differ in joint coverage and expert verification across dimensions, constraining detailed joint supervision and the analysis of relationships on the same recordings. To support multitask modeling and the study of relationships among musical dimensions in popular music, we introduce FaiSonic Multidimensional Music Dataset (FaiSonic MMD), containing 500 songs totaling approximately 32.86 hours, comprising 250 Chinese-language and 250 English-language songs. Professional musicians annotate phrases, sections, chords, and rhythm in real recordings, followed by independent review. Events and intervals across dimensions share a recording-based time reference while retaining their respective musical granularity and boundaries, allowing direct comparison across musical descriptions. We describe the annotations, collection procedure, and statistics, and establish a comprehensive multitask baseline for phrase boundaries, section boundaries, section functions, chords, beats, and downbeats. We report reference performance for all prediction targets. FaiSonic MMD provides shared expert annotations and accompanying benchmarks for temporal music analysis.

cs.SD

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13499

DeRep: Learning Depth Representations for End-to-End Navigation in Cluttered Environments

Hanyu Jin, Kenji Shimada

原文摘要

End-to-end navigation in cluttered environments relies on compact visual representations to support collision avoidance and goal-directed motion. Existing methods typically learn these representations jointly with the policy or through observation reconstruction, which does not explicitly specify what information the representation should preserve. Moreover, they are usually evaluated with a single downstream policy learner, although the benefit of a representation may depend on how the policy is learned. It therefore remains unclear how different representation-learning objectives affect downstream navigation performance and robustness. This work proposes DeRep, a navigation-oriented representation-learning method that combines local bird's-eye-view reachability supervision with depth reconstruction. To compare representation objectives under controlled conditions, we pretrain encoders with a common architecture and freeze them during downstream learning. We evaluate the representations using a linear policy probe, flow-matching imitation learning, and reinforcement learning with PPO. DeRep achieves the lowest linear policy probe prediction error and outperforms reconstruction alone across all six tested PPO conditions. In imitation learning, both reachability-based objectives achieve higher mean success rates than reconstruction alone, with similar mean success rates between the reachability-only and joint objectives. These results demonstrate consistent benefits of incorporating reachability supervision into depth representation pretraining across different downstream learning methods and evaluation conditions. We further deploy the PPO policy with the frozen DeRep encoder in Gazebo and on a physical quadrotor without fine-tuning, demonstrating its capability for zero-shot sim-to-sim and sim-to-real transfer.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13496

Reasoning-Aware Relational Representation Learning for Open-Vocabulary Scene Graph Generation

Jiawei Xiao, Boya Wang, Longtian Qiu, Shan Ning, Xuming He

原文摘要

Open-Vocabulary Scene Graph Generation (OV-SGG) requires models to recognize visual relationships beyond the training vocabulary, yet existing methods often rely on dataset-specific object--predicate co-occurrence patterns. Under long-tailed distributions and noisy object localization, such reliance leads to biased, entangled relation representations, limiting both rare-relation recognition and generalization to unseen predicates. To address these challenges, we propose RaRe, a reasoning-aware relational representation learning framework that transforms MLLM-generated chain-of-thought (CoT) rationales into structured relation embeddings. Rather than using CoT only as an intermediate reasoning trace for final prediction, RaRe directly optimizes the rationale-derived representation space to improve inter-relation discriminability. Specifically, RaRe first aligns rationale embeddings with textualized relation descriptions through self-supervised contrastive learning, and then refines rationale generation with a specificity-oriented reinforcement learning objective that encourages semantically object-pair-specific relational evidence. Experiments on VG150 and PSG demonstrate improved category-balanced recognition over existing baselines, while the additional gains from learning vary across datasets and proposal settings. Code available at: https://artanic30.github.io/project_pages/RaRe.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.11475

Generative Scenario Rollouts for End-to-End Autonomous Driving

Rajeev Yasarla, Deepti Hegde, Shizhong Han, Hsin-Pai Cheng, Yunxiao Shi, Meysam Sadeghigooghari, Shweta Mahajan, Apratim Bhattacharyya 等 14 位作者

原文摘要

Vision-Language-Action (VLA) models are emerging as highly effective planning models for end-to-end autonomous driving systems. However, current works mostly rely on imitation learning from sparse trajectory annotations and underutilize their potential as generative models. We propose Generative Scenario Rollouts (GeRo), a plug-and-play framework for VLA models that jointly performs planning and generation of language-grounded future traffic scenes through an autoregressive rollout strategy. First, a VLA model is trained to encode ego vehicle and agent dynamics into latent tokens under supervision from planning, motion, and language tasks, facilitating text-aligned generation. Next, GeRo performs language-conditioned autoregressive generation. Given multi-view images, a scenario description, and ego-action questions, it generates future latent tokens and textual responses to guide long-horizon rollouts. A rollout-consistency loss stabilizes predictions using ground truth or pseudo-labels, mitigating drift and preserving text-action alignment. This design enables GeRo to perform temporally consistent, language-grounded rollouts that support long-horizon reasoning and multi-agent planning. On Bench2Drive, GeRo improves driving score and success rate by +15.7 and +26.2, respectively. By integrating reinforcement learning with generative rollouts, GeRo achieves state-of-the-art closed-loop and open-loop performance, demonstrating strong zero-shot robustness. These results highlight the promise of generative, language-conditioned reasoning as a foundation for safer and more interpretable end-to-end autonomous driving.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.10864

Multi-View Relational Distillation for Spatial Reasoning with Vision-Language Models

Kiet T. Nguyen, Hanbo Shim, Jinwoo Kim, Seunghoon Hong

原文摘要

Vision-language models (VLMs) have achieved strong image and video understanding, yet their visual-spatial representations remain geometrically fragile, leading to failures in spatial reasoning needed for embodied AI, robotics, and autonomous driving. Prior approaches to geometry grounding either fine-tune VLMs on spatial question answering, which can perpetuate spurious visual representations, or fuse features from large geometry-grounded vision models, which substantially increases model size at inference. Knowledge distillation from geometry-grounded vision models offers an alternative, but directly matching multi-view teacher features can disrupt the pretrained alignment between visual and textual representations, degrading object- and language-semantic capabilities. We propose multi-view relational distillation (MVRD), which distills patch-wise cosine similarities across views instead of the teacher features themselves. These relations encode geometric correspondences adequate for spatial understanding, while leaving the student representation underdetermined, allowing it to remain close to its pretrained vision- language space. Across representative VLMs, MVRD improves visual-spatial reasoning, outperforming supervised fine-tuning and feature distillation while approaching feature fusion methods with considerably fewer added parameters and lower latency. We show that MVRD makes visual representations more geometric while retaining language alignment, and generalizes to 3D scene understanding tasks such as object grounding, dense captioning, and question answering. Code is available at https://github.com/kietngt00/MVRD

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.14578

Designing Collaborative Virtual Environments for Software Engineering Education

Filipe Fernandes, Cláudia Werner

原文摘要

Collaborative virtual environments offer opportunities to make software models available for shared inspection, but educational design and usability need to be examined separately from claims of learning effectiveness. This article presents MetaSEE, an approach connecting requirements guidance, a Web XR feature model, a reusable UML component, and a browser-based multiuser platform. We synthesize documented formative evaluations of the framework (16 participations), feature model (15), UML component (9), and platform (14). These counts represent evaluation participations; the same 12 developers took part in the first two evaluations. The principal platform study involved six teachers working individually and eight students working in four pairs through desktop or notebook computers, keyboard, and mouse. The documentary synthesis traces educational intentions to implemented features and reported difficulties. Participants identified potential value in shared modeling and simulation, alongside navigation, interaction, visualization, and distraction concerns. A numerical audit reconstructs a student System Usability Scale mean of 67.50 from published item frequencies, conflicting with the reported 79.38; an incomplete teacher item distribution prevents recovery of that group's overall mean. The contribution is a traceable account of educational design and formative limitations, with practical implications for onboarding, model readability, collaboration, and evaluation reporting. The evidence supports bounded feasibility and perceived usefulness, without establishing learning gains, sustained engagement, or adoption.

cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2609.19548

A generalization of the map $χ$

Xiutao Feng, Qiang Wang, Jingyi Yu, Anpeng Zhang

原文摘要

The mapping $ χ_n:\mathbb{F}_2^n \to \mathbb{F}_2^n$ defined by $y=χ_n(x)$ with $y_i = x_i + x_{i+1}x_{i+2} + x_{i+2}$, where the indices are computed modulo $n$, has been widely studied for its application in lightweight cryptography. In this paper, we generalize this mapping and completely characterize all these shift-invariant permutations of the form $y_i=x_{i+u}+x_{i+v}(x_{i+w}+a_i)$, where $0\le u, v, w<n$ and $a_i\in \mathbb{F}_2$, $1\le i\le n$. We also determine their compositional inverses explicitly.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2510.08590

Evolutionary Computation: A Paradigm of Natural Generative AI and Creative Synthesis

Abhishek Gupta, Yaxin Shi, Ying Wu, Melvin Wong, Ivor Tsang, Thiago Rios, Stefan Menzel, Bernhard Sendhoff 等 10 位作者

原文摘要

Generative AI relies on statistical learning and local gradient-based guidance, often resulting in artifacts that may be more emulative than genuinely creative. This position paper advances a perspective on Evolutionary Computation (EC) as a paradigm of Natural Generative AI (NGAI), in which stochastic variation, diversification, and natural selection present an alternative foundation for generative exploration and creative synthesis. EC provides an array of variation operators with varied generative capabilities: parent-centric operators induce population distributions analogous to conventional generative models, while disruptive operators can produce structured evolutionary leaps to out-of-distribution artifacts (e.g., programs, designs, or AI agents themselves). This lens reveals a unique theoretical association between certain disruptive variations in multitask EC and a product-of-distributions population structure. A mathematical result derived herein shows that a product structure also occurs under a local second-order approximation of an established generative adversarial program for creative extrapolation, inspired by Martindale's cognitive theory of artistic creation. The simultaneous existence of multiple fitness landscapes in multitask EC inherently moderates selection pressure, allowing these novel artifacts to survive and seed further innovation. Structured disruption and selection moderation are thus argued to be key elements to support creative synthesis. Agnostic to any specific algorithmic realization, the perspective positions NGAI as an emerging engine for open-ended scientific exploration.

cs.NE · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13485

Differentially Private Statistical Inference for Rankings from Pairwise Comparisons

Xintao Xia, Jia Gu

原文摘要

Reliable inference for rankings of large language models based on human pairwise comparisons must preserve the privacy of individual preference records. To meet this need, we develop methods for score and rank inference under the Bradley-Terry model with edge differential privacy. For an objective-perturbed estimator, a new leave-one-out analysis establishes finite-sample bounds on Euclidean and entrywise estimation errors. For sufficiently dense comparison graphs, the error bounds extend to smaller privacy budgets, including regimes in which its privacy term dominates its statistical term. A uniform asymptotic expansion yields asymptotically valid confidence intervals for individual scores and pairwise score differences. To improve finite-sample performance, we account for both regularization bias and privacy-induced randomness by combining a plug-in ridge-bias correction with Gaussian-Laplace calibration. We further establish a bootstrap procedure for simultaneous rank inference, providing asymptotically valid confidence sets for individual ranks and tests of top-$K$ membership. When the comparison probability is public and known, all proposed inferential procedures require no additional privacy budget. We evaluate finite-sample performance through simulations and apply the proposed methods to rank large language models for creative writing.

stat.ML · cs.LG · stat.ME

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13482

ExRL: Sample-Efficient Online Adaptation of Long-Chunk Policies via Execution Length Control

Xu Luo, Jiaying Yang, Hao Wu, Junlin Xie, Zijin Hong, Ji Zhang, Lianli Gao, Jingkuan Song

原文摘要

Predicting long action chunks, often spanning dozens of timesteps, has become a key ingredient in increasingly capable robot policies. In this paper, we find that adapting these long-chunk policies with existing reinforcement learning (RL) methods can require many online samples due to the high dimensionality of the action chunks being optimized, making such adaptation impractical in real-world scenarios where interaction data are costly to collect. Our key insight is to shift adaptation from optimizing actions to optimizing how long to execute each predicted action chunk. This keeps the adaptation space low-dimensional while its expressivity grows with the chunk size. We thus introduce Execution at the Right Length (ExRL), a simple approach which augments the base policy with a lightweight adapter that predicts the execution length of each chunk and is trained using off-policy RL algorithms. Across simulation benchmarks and real-world robotic tasks, ExRL enables sample-efficient adaptation of a diverse range of long-chunk policies with minimal task-specific hyperparameter tuning.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13481

Euclidean Hulls of Double Cyclic Codes of Arbitrary Block Lengths

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

原文摘要

Gao et al. \cite{GWF23} recently explored the Euclidean hulls of double cyclic codes over $\mathbb{Z}_2$. While they found answers for non-separable codes with coprime lengths ($\gcd(r, s) = 1$), the non-coprime case ($\gcd(r, s) > 1$) remained an open question. This paper completely solves that problem for all possible block lengths. We calculate the exact generator polynomials for the hull and show the precise conditions needed for a non-separable code to turn into a separable one. Using this, we show how to construct non-separable LCD codes. We also include several numerical examples to confirm our findings.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2511.13502

SnapAudit: Active Auditing of Differentially Private In-Context Learning via Snapshot-Based Simulation

Yuyang Xia, Ruixuan Liu, Li Xiong

原文摘要

In-context learning (ICL) enables LLMs to adapt to tasks using demonstrations that may contain sensitive data. Differentially private (DP) ICL mechanisms mitigate this risk by adding noise during aggregation. However, verifying their claimed privacy bounds through repeated end-to-end membership-inference attacks is costly and yields unstable estimates. We propose SnapAudit, an active auditing framework that decomposes a DP-ICL pipeline into a deterministic clean-inference stage and a stochastic DP-noise stage, and audits the full pipeline by combining a small snapshot of the former with bootstrap simulation of the latter. Because clean LLM outputs are near-deterministic at low temperature, tens of thousands of clean LLM calls suffice to approximate the snapshot distribution; SnapAudit then bootstraps hundreds of thousands of noisy trials at negligible additional cost, controlling finite-sample uncertainty via an empirical Bernstein correction. For embedding-based mechanisms, a multi-sweep search constructs maximally separable audit signals. Compared with passive auditing, SnapAudit yields tighter, more stable privacy estimates that closely match theoretical guarantees. Across privacy budgets, SnapAudit reuses snapshots across noise configurations, whereas passive auditing requires fresh end-to-end trials. Across four DP-ICL pipelines and five privacy budgets, this reduces total wall-clock auditing time by $4.3$--$5.5\times$. SnapAudit also uncovers two flaws in existing DP-ICL designs: (i) classical Gaussian noise calibrations underestimate leakage at large privacy budgets, allowing empirical leakage to exceed the theoretical bound; (ii) an embedding-aggregation mechanism's sensitivity analysis is incorrect when the number of partitions equals one, leading to undersized noise and a privacy violation.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13471

Context Types: Bunched Modalities for Unifying Safety and Reachability

Zhe Zhou, Benjamin Delaware, Suresh Jagannathan

原文摘要

Most type systems are designed to verify safety properties: the judgement $e : τ$ holds if $e$ may evaluate to any value contained in the denotation of $τ$, but nothing more. More recent type systems have considered the complementary class of reachability properties: in these systems, the typing judgment holds if $e$ must be able to evaluate to every value denoted by $τ$, and possibly more. This paper introduces a refinement type system for higher-order functional programs where types can capture both safety and reachability properties. Simultaneously supporting both is challenging because each imposes different constraints on how variable bindings in a typing context are interpreted. We address this challenge by treating typing contexts as a kind of resource that mediates which capabilities are available when typing a program. We formalize this notion by developing a resource algebra of contextual capabilities and a bunched modal context logic over this algebra. We then interpret our type system in this logic, establishing soundness with respect to a denotational semantics that unifies safety and reachability guarantees within a single typing judgement.

cs.PL · cs.LO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.09288

MC$^2$: Monte Carlo Correction for Fast Elliptic PDE Solving

Ethan Hsu, Hong Meng Yam, Ivan Ge

原文摘要

Partial differential equation (PDE) solvers underpin modern computer graphics, geometry processing, and scientific computing. Classical Monte Carlo PDE solvers such as Walk-on-Spheres (WoS) provide mesh-free estimations that are unbiased, but with accuracy limited by sampling and numerical approximation. Learned solvers are fast but biased and brittle under distribution shift. We therefore present MC$^2$, a hybrid Neural Network-Monte Carlo PDE solver that treats a low-budget Monte Carlo solution as a structured estimator of the true field and learns a single-pass neural correction to recover a high-fidelity solution. MC$^2$ matches the accuracy of solutions using over $1000\times$ more Monte Carlo samples, outperforming all evaluated mesh-free classical, denoising, and neural-operator baselines. To enable reproducible study of finite-compute PDE solving, we additionally release PDEZoo, the largest standardized elliptic PDE benchmark to date: 2 million PDEs spanning 5 elliptic families and unlimited geometric compositions, with analytic ground truth and multi-budget Monte Carlo trajectories. Together, MC$^2$ and PDEZoo (1) empirically establish that finite-sample Monte Carlo error is structured, learnable, and correctable in a single forward pass, (2) show that we can solve PDEs $\sim$218$\times$ faster than WoS at matched accuracy and achieve a $\sim$171$\times$ reduction in inference time relative to state-of-the-art diffusion methods while attaining higher accuracy, and (3) provide the reproducible evaluation infrastructure the field has so far lacked. Code & Data: https://mc-error-correction.github.io

cs.LG · cs.AI · cs.CE · cs.CV · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2404.00613

On $(θ, Θ)$-cyclic codes and their applications in constructing QECCs

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

原文摘要

Let $\mathbb F_q$ be a finite field, where $q$ is an odd prime power. Let $R=\mathbb{F}_q+u\mathbb{F}_q+v\mathbb{F}_q+uv\mathbb F_q$ with $u^2=u,v^2=v,uv=vu$. In this paper, we study the algebraic structure of $(θ, Θ)$-cyclic codes of block length $(r,s )$ over $\mathbb{F}_qR.$ Specifically, we analyze the structure of these codes as left $R[x:Θ]$-submodules of $\mathfrak{R}_{r,s} = \frac{\mathbb{F}_q[x:θ]}{\langle x^r-1\rangle} \times \frac{R[x:Θ]}{\langle x^s-1\rangle}$. Our investigation involves determining generator polynomials and minimal generating sets for this family of codes. Further, we discuss the algebraic structure of separable codes. A relationship between the generator polynomials of $(θ, Θ)$-cyclic codes over $\mathbb F_qR$ and their duals is established. Moreover, we calculate the generator polynomials of dual of $(θ, Θ)$-cyclic codes. As an application of our study, we provide a construction of quantum error-correcting codes (QECCs) from $(θ, Θ)$-cyclic codes of block length $(r,s)$ over $\mathbb{F}_qR$. We support our theoretical results with illustrative examples.

cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.15507

Federated Learning of Binary Neural Networks: Enabling Low-Cost Inference

Nitin Priyadarshini Shankar, Soham Lahiri, Sheetal Kalyani, Saurav Prakash

原文摘要

Federated Learning (FL) enables distributed clients to jointly train a global model without sharing their raw data. However, deploying the resulting deep neural networks on resource-constrained edge devices remains challenging due to their inference-time computational and memory requirements. Binary Neural Networks (BNNs) offer substantial efficiency gains by representing weights and activations using a single bit, but achieving competitive accuracy under such aggressive quantization remains difficult. Rotation-aware binarization reduces quantization errors by aligning real-valued weights with their binary representations. Despite its effectiveness in centralized learning, applying rotation-aware binarization in FL is non-trivial due to discrepancies between local and global models, particularly under heterogeneous client data distributions. To address this challenge, we propose FedBNN, a federated rotation-aware binarization framework that leverages global model information to guide local binarization while incorporating locally learned rotation information into server-side construction of the global binary model. Experiments across multiple benchmark datasets, model architectures, and degrees of data heterogeneity demonstrate that the proposed integrated methodology achieves accuracy competitive with full-precision federated models while generally outperforming existing federated binary learning approaches. Overall, FedBNN enables accurate binary inference in heterogeneous federated settings, with savings of up to $58\times$ in FLOPs and $32\times$ in memory over full-precision models, offering a practical balance between predictive performance and deployment efficiency on resource-constrained edge devices.

cs.LG · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.37431

Query Complexity of Testing Structured Parenthesis Languages

Tim Jackman, Diptaksho Palit, Sofya Raskhodnikova

原文摘要

We study the query complexity of testing membership in structured string languages, focusing on Dyck languages and natural generalizations. A tester receives query access to a word and must distinguish valid inputs from words that are far in Hamming distance, while inspecting only a sublinear number of positions. Our results sharpen the boundary between constant-query testability and polynomial query complexity. First, we prove an $Ω(n^{2/5})$ lower bound for testing Dyck languages $D_m$ with any fixed number $m\ge2$ of parenthesis types, improving the previous $Ω(n^{1/5})$ lower bound of Fischer, Magniez, and Starikovskaya (SODA `18) and nearly matching their upper bound of $O(n^{2/5+o(1)})$. Furthermore, we show that all nonadaptive algorithms for these problems require $Ω(n^{1/2})$ queries. Our lower bounds use a Pólya-urn process to construct the hard distribution; Second, we identify a broad class of weighted-parenthesis languages, which we call {\em excursion languages,} that remain constant-query testable. These languages encode bounded-step walks that stay nonnegative and return to zero. For every fixed excursion language, we give a nonadaptive tester with query complexity $O(1/\varepsilon^2)$, and we prove this dependence on $\varepsilon$ is optimal, even for adaptive algorithms. As a special case, we obtain the tight $Θ(1/\varepsilon^2)$ query complexity of testing $D_1$, improving the previous $O(\log(1/\varepsilon)/\varepsilon^2)$ upper bound and giving the first matching two-sided-error lower bound. Third, we construct a simple hard language, Hidden String, that is generated by a deterministic linear grammar but nevertheless requires $Ω(n^{2/5})$ adaptive queries and $Ω(n^{1/2})$ nonadaptive queries to test. This shows that polynomial query complexity appears even for highly restricted string languages.

cs.DS · cs.CC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.06044

Art2Song: Enhancing Visual Art Appreciation with Contextual Music Generation

Sungeun Jo, Myung Jin Kim, Chi Yoon Jeong

原文摘要

Art2Song is a conceptual framework that expresses artworks as sound by separating Non-Visual Context, which is difficult to perceive from the image alone, from Visual Evidence. Visual Evidence, such as objects, colors, and spatial composition, is transformed into Lyrics, while the Contextual Mood derived from the historical and art-historical context in the museum's artwork description is reflected in the background soundtrack. Rather than describing artworks textually, Art2Song aims to explore the possibility of a new mode of art appreciation in which viewers experience hidden stories and emotional context through music. As future interaction directions, we plan an Emotional Layer Blending Slider interface and a structured, traceable song-generation scenario, presenting the possibility that users can explore the relationship between Visual Evidence and Contextual Mood.

cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.09183

On derandomizing the line-point low-degree test

Prahladh Harsha, Swastik Kopparty, Mrinal Kumar, Ramprasad Saptharishi, Madhu Sudan

原文摘要

We investigate the derandomized version of the classical line-point low-degree test in the high-error regime in the bivariate setting and reveal some unexpected behavior. The classical line-point low-degree test takes an $m$-variate function $f$ over a finite field $\mathbb{F}_q$, queries it along a random line and accepts if the restriction of the function to this line is a low-degree polynomial. The high-error version of (the analysis of) this test asserts that if $f$ has at least $ε$ expected local agreement with a degree-$k$ univariate polynomial on a random line, then in fact $f$ is non-trivially close to some degree-$k$ $m$-variate polynomial even as $ε$ approaches $0$ (provided $q$ is sufficiently large compared to $k$ and $1/ε$). The derandomized version of the problem asks if the same holds when the line is not chosen uniformly over all possible lines but rather from a small set. In this paper we explore the bivariate case ($m=2$). We show, somewhat surprisingly, that there exists a function $f\colon \mathbb{F}_q^2 \to \mathbb{F}_q$ and a set of lines $\mathcal{L}$ in $\mathbb{F}_q^2$ of size nearly $q^{3/2}$ such that on every line in $\mathcal{L}$, $f$ has agreement $\approx 1/2$ on average with some univariate polynomial of degree $k=\sqrt{q}/2$ and yet $f$ is $1 - O(q^{-1/2})$ far from every polynomial of degree $O(k)$. On the positive side, we show that once the field size $q$ is at least $k^2/(ε)^{O(1)}$ such examples disappear and we can get sets of lines of size $O(q/ε^{O(1)})$ on which the low-degree test has a high-error analysis. On the way to our positive result, we show a new high-degree version of the classical two-direction Polishchuk--Spielman divisibility lemma.

cs.CC · cs.IT

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.40658

Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint

Haichao Zhang, Chong Zhang, Wen Wang, Shi Qiu, Peiyu Hu, Jia Wang

原文摘要

Recommendation unlearning aims to remove the influence of specific historical interactions that should no longer affect future recommendations, such as noisy clicks or outdated user preferences. However, performing recommendation unlearning becomes much harder in modern Machine-Learning-as-a-Service (MLaaS) architectures, where the recommendation model is remotely hosted by a model provider (MP) and accessed by service operators (SO) only through APIs. In this setting, a service operator serves end users but cannot access or modify internal model parameters. As a result, existing unlearning methods are difficult to apply because they require access to model internals for retraining, fine-tuning, or other parameter updates. To address these challenges, we propose Causal Explanation-based Unlearning (CEU), a novel unlearning framework tailored for MLaaS environments. Instead of modifying internal model weights, CEU operates through a two-step output-level score intervention. First, it estimates how the forgotten interaction causally contributes to the current recommendation. Second, guided by this causal signal, the system removes the influence of the forgotten interaction by adjusting the final ranking scores of affected items. Because CEU leaves model parameters untouched, it naturally supports continuous unlearning requests while avoiding the error accumulation that can result from repeated parameter updates. Extensive experiments on three public datasets show that CEU achieves unlearning effectiveness comparable to full retraining while preserving recommendation utility and significantly reducing computational cost. The source code is available at: https://github.com/zhang-haichao/Explain-and-Forget.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13425

Prompt2Echo (P2Echo): Text-Prompted Multi-View Echocardiography Segmentation with One Model

Moein Heidari, Alvin Kimbowa, Mahdi Tabatabaei, Afshin Bozorgpour, Sina Ghorbani Kolahi, River Jiang, Wenjin Chen, David J. Foran 等 11 位作者

原文摘要

Automated segmentation in multi-view echocardiography is essential for comprehensive cardiac assessment, yet remains challenging due to substantial anatomical and appearance variability across standard acoustic windows. In this paper, we present P2Echo, a unified framework capable of segmenting diverse cardiac structures across multiple standard echocardiographic views using a single model controlled by structured view-aware text prompts. Unlike recent foundation model adaptations that rely on implicit latent priors, P2Echo explicitly conditions the segmentation process via a novel Dynamic Image-Text Alignment (DyITA) module. DyITA integrates a differentiable routing mechanism and token differential operators to dynamically modulate decoder features according to the requested view and target structure. This allows the network to adaptively switch its processing pathways for different views without architectural changes. Extensive experiments on a large-scale internal dataset (seen during training) and held-out evaluation on three external datasets demonstrate that P2Echo matches or exceeds both view-specific specialists and state-of-the-art universal models at a fraction of their computational cost, offering an efficient, controllable solution for multi-plane cardiac analysis. Code is available at: https://github.com/moeinheidari7829/P2Echo.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.09841

ORCA: Hunting Compositional Failures in Text-to-Image Diffusion

Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani, Mohammad Vali Sanian, Hesam Asadollahzadeh, Aryan Yazdan Parast, Mohammad Lotfollahi

原文摘要

Text-to-image diffusion models fail predictably on compositional prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent architectures already augment CLIP with a T5 encoder precisely because CLIP's contrastive embedding loses compositional structure, yet these failures persist. We argue the binding problem is therefore not one of missing information but of misaligned information: a text encoder preserves compositional structure, but in a representation space shaped by language modelling rather than vision, and the denoising objective does not directly reward aligning the two. We show this correspondence can be supplied as an explicit training signal, that the relevant cross-modal information is concentrated in a low-rank subspace of self-supervised visual features, and that supplying it can be folded into diffusion training as a single auxiliary loss. Our method, ORCA (Orthogonal Residual Compositional Alignment), aligns the latent of a diffusion transformer with a low-rank target derived from a frozen visual encoder, through a predictor whose orthogonal basis is parameterised by a learned residual between T5 and CLIP embeddings, which provides a prompt-dependent signal for selecting the visual readout subspace. We prove that the cross-modal information recoverable at a given rank is bounded by the spectral mass of the visual encoder's covariance in the top components. Across three diffusion-transformer backbones (DiT-B/2, DiT-L/2, U-ViT-L), ORCA improves FID and GenEval over both vanilla and REPA baselines at zero inference-time cost; on DiT-L/2 it reaches FID 16.65 and GenEval 0.291 at 200K steps, exceeding the strongest 400K baseline at half the training cost, with the largest gains concentrated on attribute binding, spatial relations, and multi-object prompts.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.09886

Entanglement-assisted quantum locally recoverable codes: bounds and constructions with availability

Rutuja Kshirsagar, Gretchen L. Matthews, Julia Shapiro

原文摘要

In this work, we define entanglement-assisted quantum locally recoverable codes with availability, in which any set of up to $δ-1$ erased qudits can be recovered from any one of $t$ local recovery sets, each of size at most $r+δ-1$, with the recovery sets intersecting exactly in the erased coordinates, where $r$ is a (small) positive integer. We show that shared entanglement permits $t>1$, meaning that multiple local recovery sets can be available for the same set of up to $δ-1$ erasures. We establish a Singleton-like bound for this family of codes and present random constructions based on classical linear codes with Vandermonde parity-check matrices. We also provide explicit constructions of entanglement-assisted quantum locally recoverable codes with availability from several classical code families and their folded versions, including Tamo-Barg codes, fiber-product codes, and algebraic-geometry codes such as one-point Hermitian and Suzuki codes.

cs.IT · quant-ph

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2511.14613

3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology

Mohammad Vali Sanian, Arshia Hemmat, Amirhossein Vahidi, Jonas Maaskola, Jimmy Tsz Hang Lee, Martin Prete, Stanislaw Makarchuk, Yeliz Demirci 等 13 位作者

原文摘要

A 3D transcriptomic profile of a tissue can give a holistic view of its organization in health and disease, but spatial transcriptomics (ST) is costly, so usually only some serial sections are profiled, while H&E is available for all. Most methods that infer ST from histology treat each section independently and ignore 3D structure, while existing 3D-aware approaches are not generative and do not scale well. We present Holographic Tissue Expression Inpainting and Analysis (HoloTea), a 3D-aware flow-matching framework that imputes spot-level gene expression on an unprofiled section from its H&E and the measured expression of adjacent profiled sections. Our key idea is to take the measured expression at the same registered position on neighboring sections and feed this cross-section context to the flow model through a lightweight ControlNet, so that predictions follow anatomical continuity along z. To capture the discrete, zero-inflated nature of counts, the flow starts from a learned zero-inflated negative binomial (ZINB) prior that, on an unprofiled section, is predicted from the measured expression of the nearest profiled section. A global attention block with a small set of inducing tokens adds whole-slide context at a cost linear in the number of spots, so training and inference scale to large 3D ST datasets. Across three ST datasets spanning different tissue types and resolutions, HoloTea consistently improves 3D expression accuracy and generalization compared to 2D and 3D baselines. We envision HoloTea advancing the creation of accurate 3D virtual tissues, ultimately accelerating biomarker discovery and deepening our understanding of disease. Code is available at https://github.com/Lotfollahi-lab/HoloTea.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.15312

Do people apply different norms to humans and large language models acting on their behalf? Evidence from norm elicitations in two canonical economic games

Paweł Niszczota, Elia Antoniou

原文摘要

While delegating tasks to large language models (LLMs) can save people time, there is growing evidence that offloading tasks to such models produces social costs. We elicit appropriateness of behavior in two canonical economic games to study whether people have different norms for humans and LLMs acting on their behalf. More specifically, we study the social appropriateness of a spectrum of possible behaviors: when LLMs divide resources on our behalf (Dictator Game and Ultimatum Game) and when they evaluate the fairness of resource splits (Ultimatum Game). We use the Krupka-Weber norm elicitation task to detect possible shifts in social appropriateness ratings. Results of two pre-registered and incentivized experimental studies using representative samples from the UK and US (N = 2,658) show three key findings. First, in the Dictator Game, the most socially appropriate allocation remains the equal split when the Dictator is a human or an LLM acting on behalf of a human, but self-serving allocations are judged less appropriate when implemented by an LLM. Second, in the Ultimatum Game, rejecting offers from an LLM Proposer is judged as more appropriate than rejecting identical offers from a human Proposer, with this difference concentrated among relatively generous offers. Lastly, rejection decisions implemented by an LLM Responder are judged no less appropriate than identical rejection decisions implemented by a human Responder. Post hoc, these patterns are consistent with the notion that people grant LLMs bounded agency in the investigated resource-allocation scenarios. Our findings have implications for the design of AI systems.

cs.GT · cs.AI · cs.CL · cs.CY · cs.HC · econ.GN

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13396

The AI Era's Lines of Code? A Case Study on What an Engineer's Token Spend Measures

Shyam Agarwal, Olga Lvova, Agnia Sergeyuk, Anastasiia Serova, Timofey Bryksin, Thomas Zimmermann, Bogdan Vasilescu

原文摘要

Organizations use engineers' token spend to monitor AI adoption, set budgets, and measure productivity, but the metric's relationship with engineering output is unclear. We link five weeks of token usage in coding agents to the commits of 404 engineers at JetBrains, and analyze a company survey of 412 employees. We find that token spend varied mostly between engineers, and which engineers spent the most stayed largely the same over the five weeks. Among weeks with similar commit counts, the 90th percentile of spend was 39 to 240 times the 10th. Within an engineer, doubling spend was associated with about 10% more commits. Available work metrics explained 38% of the variation in spend between engineers and 13% of the week-to-week variation within an engineer. In the survey, respondents in technical roles reported in nearly nine of ten agent evaluations using agents for tasks beyond coding, such as analysis, research, and planning. Token spend therefore measures how much engineers use agents across many kinds of work and not the outcome and value of that work. We recommend using token spend at most for resource accounting, and evaluating agent-assisted work with evidence about tasks and outcomes.

cs.SE · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13392

Minimum Membership Dominating Set and Its Generalization: Leafage vs. Asteroidal Number

Yuma Tamura, Daichi Wakayama, Akira Suzuki, Xiao Zhou

原文摘要

The Dominating Set problem is known to be fixed-parameter tractable when parameterized by leafage, a structural graph parameter defined on chordal graphs. We investigate whether this tractability extends to its variants with natural constraints. Specifically, we study the Minimum Membership Dominating Set problem and its generalization, the Min. $(σ, ρ)$-Dominating Set problem. Given a graph $G$ and a positive integer $\ell$, Minimum Membership Dominating Set asks whether there is a dominating set $D$ such that every vertex in $G$ is dominated by at most $\ell$ vertices in $D$. We first show a negative result: Minimum Membership Dominating Set parameterized by leafage plus $\ell$ is W[1]-hard, demonstrating that even this natural constraint serves as a severe barrier to designing FPT algorithms. To complement this, we present an XP algorithm for the Min. $(σ, ρ)$-Dominating Set problem parameterized by asteroidal number plus $μ$, where $σ$ and $ρ$ are finite sets of non-negative integers and $μ$ is the maximum value in $σ\cup ρ$. Note that asteroidal number generalizes leafage to arbitrary graphs. Combining this algorithm with our structural bound that every graph $G$ admits a dominating set such that no vertex is dominated by more than $7\mathsf{an}(G)-6$ vertices, where $\mathsf{an}(G)$ denotes the asteroidal number of $G$, we show that Minimum Membership Dominating Set admits an XP algorithm parameterized solely by asteroidal number.

cs.DS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.13388

Online-Adaptive Fuzzy Cognitive Maps for Neuro-symbolic Financial Forecasting

Brandon Rodriguez, Abel Deulofeu, Olaoluwa Adigun

原文摘要

We present a neuro-symbolic framework that pairs online-adaptive Fuzzy Cognitive Maps (FCMs) with long short-term memory (LSTM) networks for financial forecasting. Financial markets exhibit regime shifts and nonlinear dynamics. Existing models often trade off one of these key properties: these models capture temporal patterns but hide causal drivers, or they recover causal graphs that cannot adapt post-training. We close this gap with two frameworks. Framework I constructs an FCM from live dual-source price series and macroeconomic indicators, and adapts its edges online through an error-driven Hebbian rule. We introduce the Asymmetric Additive Residual Fusion method to seamlessly combine the FCM and LSTM predictions under Framework I. Framework II constructs a literature-grounded, LLM-augmented FCM where every edge carries a verifiable citation that gives an auditable map of factor interactions. On NASDAQ Composite data, Framework I matched the performance of the LSTM baseline on state-directional accuracy and outperformed LSTM by 7.6 percentage points on the return-sign accuracy. Framework I outperformed standalone FCM models across both evaluation metrics. The adaptive maps converged to new regimes within 10-15 trading days, and Framework II center-node FCMs scored 68.9% to 85.7% on the state-directional accuracy.

cs.AI

查看论文
arXiv ↗PDF ↗