跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

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
+1已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-07 22:49 · 全站最近入库：2026-11-07 17:43各信源进度 →

统计口径与数据新鲜度

统计 2026-11-06 23:03 — 2026-11-07 23:03（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：2026-11-07 22:49最近发现新增版本：2026-11-07 17:43库内论文最新更新时间：2026-11-06 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。

17,100 已收录论文14,661 AI 相关4,056 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 17,100 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-07 22:47（北京时间）
新论文 · v1arXiv:2611.06127

NN-Based FeFET Compact Modeling for SPICE Simulation

Rodion Novkin, Simon Thomann, Hussam Amrouch

原文摘要

Prototyping and early-stage circuit evaluation for emerging transistor technologies require fast and accurate compact models for SPICE simulations. Standard physics-based compact models, such as BSIM, offer high fidelity but demand extensive domain expertise and time-consuming equation formulation for every new physical effect, significantly slowing technology development. Neural network (NN)-based models offer a scalable alternative approach, but they rely heavily on smooth numerical solver data with explicit high-order derivative information. However, measurement data suffers from complex noise patterns, making derivative extraction challenging and complicating NN-based transistor modeling. This work presents a derivative-free NN training framework employing spectral normalization to naturally smooth derivative behavior and filter measurement noise. Using drain current measurements from a fabricated 28 nm ferroelectric device, we design an NN-based compact model that captures the full spectrum of polarization amplitudes and supports dynamic polarization switching in transient simulations. To demonstrate its capability, we deploy the model in a commercial SPICE software to simulate write and read operations for large-scale memory arrays with up to 512x512 size, including parasitic effects. Our approach bridges raw measurements with NN-based SPICE-compatible transistor modeling, significantly reducing model development time and enabling rapid circuit-level prototyping for emerging devices.

cs.ET

查看论文
arXiv ↗PDF ↗
版本更新 · v5arXiv:2509.26468

fev-bench: A Realistic Benchmark for Time Series Forecasting

Oleksandr Shchur, Abdul Fatir Ansari, Caner Turkmen, Lorenzo Stella, Nick Erickson, Pablo Guerron, Michael Bohlke-Schneider, Yuyang Wang

原文摘要

Benchmark quality is critical for meaningful evaluation and sustained progress in time series forecasting, particularly with the rise of pretrained models. Existing benchmarks often have limited domain coverage or overlook real-world settings such as tasks with covariates. Their aggregation procedures frequently lack statistical rigor, making it unclear whether observed performance differences reflect true improvements or random variation. Many benchmarks lack consistent evaluation infrastructure or are too rigid for integration into existing pipelines. To address these gaps, we propose fev-bench, a benchmark of 100 forecasting tasks across seven domains, including 46 with covariates. Supporting the benchmark, we introduce fev, a lightweight Python library for forecasting evaluation emphasizing reproducibility and integration with existing workflows. Using fev, fev-bench employs principled aggregation with bootstrapped confidence intervals to report performance along two dimensions: win rates and skill scores. We report results on fev-bench for pretrained, statistical, and baseline models and identify promising future research directions.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06124

A Post-Quantum Interactive Hashing Theorem

Céline Chevalier, Laurent Holin, Quoc-Huy Vu

原文摘要

Interactive hashing, introduced by Ostrovsky, Venkatesan, and Yung [OVY93], is a building block in many cryptographic protocols, including perfectly hiding commitments from one-way permutations [NOVY92]. Its multi-output generalization is a key ingredient in constructions of statistical zero-knowledge arguments for NP and statistically hiding commitments from arbitrary one-way functions [NOV06,HR07]. In this note, we give a post-quantum security proof for this multi-output interactive hashing protocol with arbitrary relations.

quant-ph · cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06123

From Handcrafted to Generative: RLVR-Optimized Icon Generation for Alexa+

Rohan Sequeira, Matthew Rosenberg, Amin Mahmoudabadbozchelou, Oleg Poliannikov, Jonathan Rubin

原文摘要

Alexa+ devices with screens display animated icons during conversations to visually reinforce what is being said. The original set of these icons was hand-drawn by designers one at a time, a process that produces polished results but is time-consuming and cannot scale to the range of topics encountered in open-ended conversation. We describe an automated pipeline, deployed in production, that generates these vectorised animated icons from a text description alone and surfaces relevant animations to customers based on their ongoing conversation. The pipeline decomposes icon creation into a sequence of stages (image generation, semantic decomposition, vectorisation, styling, and animation). Its quality is determined at the very first of these, image generation, on which every downstream stage depends. We therefore focus on improving this first and most critical stage. Because the icons are rendered on small display canvases under strict design guidelines, generations are often unsuitable for production. Supervised fine-tuning is not viable, as no dataset of line-art icons exists under these constraints. Instead, we design objective verifiers that automatically flag generations violating the design guidelines, and use them to fine-tune a flow matching image generation model via reinforcement learning from verifiable rewards (RLVR). The fine-tuned model raises the pass rate from 15.7% to 58.7% (3.7x) under a VLM judge that is independent of the reward model. Both the trained model and the verifier are deployed in the production pipeline, where the verifier also serves as the automated quality gate before final design review.

cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06122

Ab Initio Accuracy Beyond the Cutoff: Distributed Message-Passing Equivariant Attention at Tens-of-Millions-of-Atom Scale

Allex Kan, Ji Zhang, Hao Yin, Hao Li, Owen Fu, Xunxing Chen, Lin Huang, Zion Wang 等 13 位作者

原文摘要

Molecular dynamics predicts molecular motion from atomic forces and trajectory integration. Density functional theory (DFT) provides first-principles forces, but its $O(N^3)$ cost limits simulations to thousands of atoms; empirical force fields scale to millions but miss bond breaking and charge transfer. Equivariant message-passing Transformers learn the ab initio potential at linear cost. Stacked layers propagate information beyond a single cutoff, giving four layers a receptive field up to 23Å. At this frontier, scale is limited by communication: layers exchange boundary features across devices, force backpropagation repeats the exchange, and moving atoms change neighbor graphs and tensor shapes. We present Tessera, a distributed runtime that fixes workload shapes between rebuilds. It sorts atoms along a space-filling curve into equal-count shards, ensuring identical atom counts and tensor shapes per rank. Peer sets scale as $K^{0.5}$, not $K$. A conservative neighbor skin preserves topology across updates, enabling each rebuild interval to replay as one CUDA Graph. Fused kernels, three-level neighbor search, and overlapped All-to-All complete it. On 512 GPUs, Tessera sustains 30.7M atoms at 89.7% weak-scaling efficiency (77--90% across three per-GPU loads); per-step time rises 1.11--1.29x as machine and problem grow 16x. Graph reuse cuts full-step time $1.87\times$. Across an $8\times$ device increase, neighbor-search cost grows $1.7\times$, versus $3.0\times$ for Morton order. In a live $10.24$M-atom salt solution, NVE energy drift is $0.42\,μ$eV/atom/ps over $10$ ps, and structure matches a serial reference. A 10.06M-atom Norovirus capsid sustains 100 ps of NVT at $\approx 8$ ps/day on 256 A100 GPUs. Over 200,000 steps, it has no broken bonds or anomalously close pairs and uses three compiled variants, with no graph breaks or eager fallbacks.

cs.DC · cs.AI · physics.bio-ph

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06121

3D Pose Estimation in Projection Space via Pixel-level Visible Light Communication

Michikuni Eguchi, Takefumi Hiraki

原文摘要

Projector-based augmented reality enables natural interaction between users and devices by overlaying digital information onto the physical world through projected imagery. A key technical requirement of such systems is accurate positional alignment between the projector and the devices. Pixel-level Visible Light Communication (PVLC) achieves this alignment without external sensing infrastructure by embedding invisible spatial codes into each projected pixel through high-speed brightness modulation that preserves image quality. However, the information that PVLC transmits is inherently planar. PVLC has therefore been limited to devices moving on a flat surface and cannot estimate the 3D pose of devices in three-dimensional space, such as aerial robots. To extend PVLC-based pose estimation to three dimensions, we formulate it as a Perspective-n-Point (PnP) problem. The 2D pixel positions that four coplanar photosensors on the device receive via PVLC serve as the image points, and their known 3D layout provides the object points. Experiments show that the proposed system estimates 3D pose with a latency of approximately 8~ms and a 3D position RMSE of 19.2~mm after Kalman filtering. These results confirm the first realization of real-time 3D pose estimation coordinated with high-quality projected image content without external sensing infrastructure.

cs.RO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06120

ReactWorld: Structuring Interaction Responses for Embodied Video Generation

Hanwei Liu, Huijia Zhang, Hanzhang Wang, Guangyu Liu, Hanbei Zhan, Linjie Hu, Bin Xiao, Xuan Zhou 等 9 位作者

原文摘要

Embodied video world models predict scene changes caused by robot actions, yet generated object responses may remain inconsistent with task intent and contact dynamics. Critical responses in embodied scenes often concentrate in local regions and specific time intervals. Inspired by chain-of-thought reasoning, we introduce ReactWorld, an embodied video generation model guided by structured interaction anticipation. In the generation backbone's feature space, an interaction response field predictor anticipates how the interaction will unfold, explicitly describing participant roles, future motion response intensity, and local motion changes. A response feedback adapter forms increments to object features from the difference between the object branch's outputs with predicted and zeroed local dynamics inputs. It also converts predicted displacements into positional biases for temporal attention. These two mechanisms guide object feature updates and information retrieval across frames, respectively. Through interaction anticipation and generative feedback, ReactWorld achieves an average score of 77.51 on RBench, outperforming PhysisForcing by 3.29 points with improvements in all nine categories. On EZS-Bench, it achieves a Domain score of 86.98 and an average score of 81.87.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05176

Extending the MM-AR Metamodeling Platform with Process Mining Capabilities

Geraldine Hürzeler, Hans-Georg Fill, Daniel Borcard

原文摘要

Process mining derives process models from event data recorded by information systems, but its results are usually presented as two-dimensional visualizations that are separate from the environments in which enterprise models are created and maintained. Metamodeling platforms for extended reality (XR), such as MM-AR, allow users to define modeling languages and to display models in 2D and 3D, but they do not provide access to event data or mining algorithms so far. In this paper we therefore present a first proof-of-concept for showing how an XR-based metamodeling platform can be extended with process discovery capabilities without changes to the platform core through a separate Python service based on the open source PM4Py process mining library. We demonstrate the approach using three common discovery algorithms for obtaining Petri nets and BPMN models based on CSV or XES event logs. A technical evaluation using four public event logs shows that the element counts of the created model instances match those of the PM4Py models in all 16 configurations. The integration adds between about 8 and 53 seconds per run, and this overhead grows with the size of the discovered model rather than the size of the event log. Although the prototype does not yet use the third dimension to encode process information, it established the foundations for studying such approaches.

cs.SE · cs.DB · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.06764

Efficient Classical Simulation of Low-Rank-Width Quantum Circuits Using ZX-Calculus

Fedor Kuyanov, Aleks Kissinger

原文摘要

In this paper, we introduce an algorithm for contracting (i.e. numerically evaluating) ZX-diagrams whose computational complexity is governed by rank-width, a structural graph parameter that behaves nicely under ZX rewrite rules. Our method evaluates a graph-like ZX-diagram in ~O(4^R) time, given its rank-decomposition of width R. By constructing suitable rank-decompositions, we provide a classical simulation algorithm for quantum circuits whose runtime is bounded by both ~O(2^n) and ~O(2^(t/2)), where n is the number of qubits and t is the number of non-Clifford phase gates. Thus, our method is no slower than either the naive state-vector simulation or the elementary stabiliser decomposition baseline, and in practice can be even faster when the reduced ZX-diagram has low rank-width. We benchmark our simulation algorithm against Quimb, a popular tensor contraction library, and observe substantial reductions in floating-point operations, often by several orders of magnitude, for random and structured non-Clifford circuits and for random ZX-diagrams.

quant-ph · cs.CC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06118

Online Adaptation to Latent Physical Properties for Learning from Demonstration

Kotaro Kajitsuka, Masaki Murooka, Fumio Kanehiro

原文摘要

Manipulating visually identical objects with different physical properties requires adapting actions based on information acquired through interaction. We address the problem of learning from demonstrations how to adapt manipulation actions, such as regrasping and changing contact locations, based on physical-property information acquired during interaction. To this end, we propose a learning-from-demonstration method that learns latent representations of physical properties needed to predict object responses and conditions a policy on online estimates of these representations. A dynamics model and object-specific latent representations are jointly learned from demonstrations that include behaviors adapting to the objects' physical properties, and the learned representations are then used to condition an imitation policy. During execution, the dynamics model and policy weights remain fixed, while the latent representation is updated based on the discrepancy between predicted and actual observations, allowing interaction with the object to inform action generation. Real-world and simulation experiments with objects whose centers of mass differ suggest that online adaptation through latent representations of physical properties can improve task success rates. However, in simulation, success rates on center-of-mass locations absent from the demonstrations remained around 30%, indicating limited adaptation to unseen physical properties. Project page: https://isri-aist.github.io/latent-dynamics-project-page/

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2603.06466

Completeness for Prime-Dimensional Phase-Affine Circuits

Colin Blake

原文摘要

Equational reasoning about circuits underpins quantum-circuit optimisation and verification. In the qubit CNOT-dihedral fragment, phase polynomials and layered normal forms support a complete equational theory. We develop the corresponding theory for prime-dimensional qudits, where basis labels, value controls, and phase exponents share prime-field arithmetic. We first describe reversible affine circuits over F_d as transformations x -> Ax + b, with an affine normal form extending Lafont's linear normal form by translations. Adjoining finite-angle diagonal phases by polynomial degree yields linear, quadratic, and cubic calculi. Their binomial-basis identities expose the mixed diagonal gates forced by affine transport. These calculi have unique phase-affine normal forms, and the resulting equational theories are complete: semantic equality coincides with derivable equality.

quant-ph · cs.LO

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06116

The Harness Is the Model: Agent Scaffolding Changes a Fixed LLM's Compliance with Banking Conduct Rules, Unevenly Across Models

Mehmet Murat Huyut

原文摘要

Banks validate language models, but they deploy systems: a model inside a harness that decides what it sees, which tools it can call and who checks its actions. We test whether that harness changes compliance with banking conduct rules when the model is held fixed. Four open-weight models each ran five harnesses (a pipeline that makes one structured decision, a ReAct-style tool loop, a loop in which the policy is reachable only through search, a loop with a long benign customer memory, and a loop with a same-model compliance reviewer) on 156 pre-registered cases in a simulated retail bank whose 11 rule families paraphrase EU consumer-credit, payments, investor-protection, data-protection and anti-money-laundering provisions. Every one of the 3120 two-turn episodes was scored deterministically from the executed tool trace, with violations and over-refusals counted separately. Pooled across models the harness moved the correct-case rate only between 87.3% and 92.1%, but within a model it mattered a great deal: for one model the spread between its best and worst harness was 11.5 percentage points, enough to move it from first to last place among the four models, while for another the harness made no detectable difference; the model x harness interaction itself was suggestive rather than conclusive. The same-model reviewer cut violations from 9.6% to 6.4% without raising over-refusals, contrary to our pre-registered prediction. Rules that require date arithmetic failed in every harness. In an exploratory analysis with two LLM judges and a blind human check, 26% of violations were accompanied by a customer message that denied the action the agent had just executed, which a transcript-only review would record as a correct refusal. For model-risk management the unit of validation should be the model-harness pair, and conduct testing should read the action log, not the conversation.

cs.CL · cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06113

Semantic Prior-Guided Incomplete Cross-Modal Retrieval with Noisy Labels

Jiali Chen, Ruitao Pu, Yingke Chen, Dezhong Peng

原文摘要

Cross-modal retrieval (CMR) aims to bridge the semantic gaps between modalities by learning shared representations. Unfortunately, due to the dynamism and inconsistencies in real-world data acquisition, multimodal datasets frequently encounter severe modality incompleteness. Existing incomplete CMR methods adhere to a label-driven paradigm, relying heavily on categorical annotations as the semantic benchmark. However, label noise is difficult to avoid and often coexists with modality incompleteness. To address this challenge, we propose a novel semantic prior-guided framework for incomplete cross-modal retrieval with noisy labels, termed SPIRN. Specifically, SPIRN uses fixed semantic priors as a consistent reference for robust representation learning, noisy-label handling, and missing-modality completion. Based on this reference, Semantic Priors Guidance (SPG) establishes a stable category-level semantic space, Quality-aware Robust Learning (QRL) dynamically evaluates sample quality to distinguish clean samples from noisy ones and handles noise via reverse learning, Prior-guided Global Label Calibration (PGLC) rectifies corrupted annotations for refined supervision, and Confidence-driven Selective Imputation (CSI) recovers missing modalities from a cross-modal memory bank while filtering unreliable imputations with an increasing threshold. To the best of our knowledge, this is the first framework to jointly tackle the dual challenges of modality incompleteness and label noise in the CMR community. Extensive experiments on four widely used benchmark datasets demonstrate that SPIRN outperforms 11 state-of-the-art methods in various scenarios involving both missing modalities and noisy labels.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.23975

FrameScout: Scouting Query-Relevant Frames for Long Video Understanding

Haonan Hu, Shuhao Chen, Weisen Jiang, Lizhao Gao, James Kwok, Yu Zhang

原文摘要

Long video understanding requires VideoLLMs to answer queries about videos spanning tens of minutes to hours, but such long videos produce far more visual tokens than current VideoLLMs can process. To address this issue, keyframe selectors are proposed to select the most query-relevant frames by computing the similarity between frame and query embeddings. Existing selectors either encode frames independently without temporal context or process chunks in isolation with ranking objectives that are difficult to optimize. To alleviate those limitations, we propose FrameScout with two core designs: (i) a streaming selector architecture that leverages a sliding-window KV cache and successor aggregation to produce temporally-contextualized frame embeddings; (ii) a frame-query contrastive objective that aligns frame and query embeddings in a shared space, directly training the selector to distinguish relevant frames from irrelevant ones. Extensive experiments on three long-video benchmarks and six base VideoLLMs demonstrate that FrameScout consistently achieves state-of-the-art performance. Code is available at https://github.com/Hubert-1102/FrameScout.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06110

Beyond Risk Cues: A Mechanism-Level Benchmark and Verifiable Debate for Scam Video Detection on the Web

Yifan Wang, Junyu Lu, Shun Zhang, Chaozhuo Li, Fanliang Bu, Rong Yin, Lingbin Bu, Changrong Min 等 9 位作者

原文摘要

Online scam videos pose significant threats to individuals and society. Existing studies primarily focus on binary classification, offering limited insights into how scams work and the reasoning behind detection decisions. Moreover, they often overlook the challenge of distinguishing scam videos from superficially similar non-scam content, such as advertisements, and the robustness of detection models against misleading arguments. These limitations hinder reliable scam video detection. To address these limitations, we introduce MechScam, a benchmark comprising 6,614 videos covering diverse scam mechanisms and non-scam categories. MechScam provides explanations supported by video evidence, annotations of potential scam elements and their context, and misleading arguments constructed from genuine evidence. Recognizing that genuine evidence can still be used to justify misleading conclusions, we further propose ScamCourt, a debate framework in which trained prosecution and defense debaters present opposing arguments, while a trained judge makes decisions based on a transcript with verified citations. Extensive experiments show that state-of-the-art MLLMs struggle to distinguish scam videos from similar non-scam content. ScamCourt outperforms larger MLLMs and same-backbone fine-tuned baselines, reducing false positives and showing stronger resistance to misleading arguments. Together, MechScam and ScamCourt contribute to more reliable and interpretable scam video detection. The dataset and code are available at https://github.com/SuperYFan/MechScam.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06108

Learning When to Think Aloud in Latent Reasoning

Zhehao Zhou, Tongrui Su, Shengyu Zhu, Da Li, Zeyu Liu, Jun Zhu, Xueqi Cheng

原文摘要

Latent Chain-of-Thought (CoT) reasoning improves efficiency by shifting intermediate computation into continuous hidden states. However, fully latent methods often struggle on precision-critical tasks such as mathematical reasoning, while existing hybrid approaches retain substantial token-generation overhead. We introduce VITAL, an importance-guided hybrid reasoning framework that selectively verbalizes informative tokens as reasoning anchors while keeping most computation latent. A lightweight gating head dynamically selects between explicit token generation and direct hidden-state feedback. VITAL constructs hybrid trajectories from explicit CoT using token- importance estimation and trains the model through curriculum-based supervised training, followed by reinforcement learning with a reward that balances correctness and conciseness. Experiments show that VITAL consistently out- performs existing fully latent reasoning methods, achieving relative average accuracy gains of 9.6% on GPT-2 and 5.1% on Llama-3.2-1B at comparable reasoning lengths. Compared with hybrid baselines, VITAL achieves higher reasoning accuracy with substantially shorter reasoning trajectories on Qwen3-1.7B.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06105

XuanJian-DINOSAR: A SAR Foundation Model Based on Global and Local Semantic Consistency

Chunxiao Wu, Huixin Huang, Jialei Pan, Qiang Liang, Tao Wu, Cheng Wu, Long Huang, Yuanji Li 等 12 位作者

原文摘要

Self-supervised pre-training on synthetic aperture radar (SAR) imagery enables transferable representations, but the optical-SAR domain gap and speckle perturbations limit representation stability. Most SAR foundation models use masked image modeling (MIM) through pixel reconstruction or structural feature prediction, which is sensitive to speckle or relies on predefined operators. Joint modeling of cross-view semantics and perturbation stability at corresponding spatial locations remains underexplored. We propose XuanJian-DINOSAR, a SAR foundation model based on global and local semantic consistency. We curate over 360K publicly available SAR target chips, detection images, and scene images spanning diverse targets, scenes, and sensors, and adapt an optically pre-trained DINOv2 model to SAR through self-supervised learning. The framework combines DINO global semantic self-distillation, iBOT local masked modeling, and KoLeo feature-distribution regularization to learn globally discriminative and locally structure-aware representations. We introduce a local semantic consistency branch tailored to SAR intensity statistics and coherent imaging characteristics. Shared geometric transformations produce spatially aligned teacher weak views and student strong views. Intensity transformations and Gamma multiplicative speckle perturbations are applied to student views, while a cosine consistency loss aligns patch tokens at corresponding locations, promoting stability under radiometric perturbations. This objective complements the cross-region and cross-scale semantic consistency of DINOv2 multi-crop training, jointly enforcing global and local semantic consistency. Experiments on multiple downstream classification and detection datasets demonstrate state-of-the-art performance on most evaluation metrics, validating the generality and transferability of the learned representations.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28631

AEON: Unifying Video and 3D World Models

Weiqi Zhang, Wenyuan Zhang, Yu-Shen Liu, Junsheng Zhou

原文摘要

Current world models for explicit world simulation typically follow two distinct pathways: (1) video generative models (e.g., Sora), which simulate realistic appearances but fail to preserve 3D consistency; and (2) 3D generative models (e.g., Marble), which generate geometrically consistent scenes but often yield static, less realistic observations. We present AEON, a unified framework that bridges video-based and 3D-based world models and combines the benefits of both. The key insight of AEON lies in a generative model that operates within the text- or image-conditioned video latent space while producing renderable 4D graphics primitives---specifically, 4D Gaussian Splatting (4DGS)---as the explicit world representation. We train a 4D reconstruction model to predict both 4DGS and camera poses from monocular videos, serving as our initialized 4D decoder. Furthermore, we design a domain adapter that translates generative video latents into reconstructive 4D latents through a distillation process on the video VAE. AEON naturally supports video-based world modeling by rendering 4DGS at predicted camera trajectories, and constructs a persistent 4D environment with scene dynamics for realistic world simulation. Consequently, AEON empowers a diverse range of world modeling applications and achieves state-of-the-art performance on standard benchmarks. Project Page: https://weiqi-zhang.github.io/AEON

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06103

SenTrojan: Revealing Analog Hardware Trojan Attacks on Sensors

Kun Wang, Ruochen Zhou, Wenjun Zhu, Shilin Xiao, Kai Wang, Chen Yan, Xiaoyu Ji, Wenyuan Xu

原文摘要

Sensors bridge the physical and digital worlds, making their integrity critical to cyber-physical system security. Existing sensor attacks largely exploit unintended and sensor-specific physical vulnerabilities, limiting their generalizability and motivating a different threat model, i.e., whether an adversary can implant hidden attack surfaces into sensors before deployment. In this paper, we present SenTrojan, an analog hardware Trojan framework for sensors. SenTrojan embeds malicious functionality into analog signal circuitry commonly shared across diverse sensor architectures, and activates the hidden behavior through crafted external physical signals. Once activated, SenTrojan can induce sensor malfunctions ranging from permanent denial-of-service to static or dynamic spoofing. To achieve these effects under different architectural constraints, we introduce two complementary designs. The Logic-Rule-Driven (LRD) Trojan adds lightweight analog monitoring logic to detect trigger features such as frequency and amplitude, enabling reliable activation across various sensor types. The Physical-Effect-Driven (PED) Trojan targets sensors with exploitable native analog effects, e.g., nonlinearity and rectification, and realizes attacks with minimal component insertion. We evaluate SenTrojan on 14 sensors spanning 6 transduction principles and demonstrate its effectiveness across diverse real-world scenarios. Overall, SenTrojan achieves an average successful trigger rate above 95%, maintains over 97% similarity to benign behavior, incurs zero false-trigger rate for LRD designs, and introduces less than 5% average deviation in drift, noise floor, and response time. To our knowledge, this work is the first systematic study of analog sensor Trojans, broadening sensor security from unintended physical vulnerabilities to intentional supply-chain compromise.

cs.CR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06100

Reconciling Privacy with Provenance for Language Model Watermarks

Elise L. Han, Tatsunori Hashimoto

原文摘要

Watermarking has great potential for regulating the use of language models (LMs), but its deployment has been marred by controversy, as many users argue that fine-grained tracking of LM usage violates their privacy. This tension reduces the effectiveness of watermarks, as users engage in evasion strategies such as paraphrasing that can remove much of the watermark signal. We show that provenance and privacy can be reconciled if we shift the goal of watermark design from tracking individuals to estimating aggregate usage. We develop locally differentially private watermarks which provably limit the evidence that any individual text can contribute to detection, while still enabling accurate estimation of population frequencies. We introduce the Red-Green Sequence (RGS) watermark, a private and computationally efficient watermark that achieves accurate frequency estimation at high privacy levels across various models, sample sizes and generation entropies in settings that reflect realistic deployment scenarios. On C4 language modeling tasks, we attain $0.0019$ MSE with $0.0038$ mean absolute bias at a low $\varepsilon$ of 1, while in more challenging settings such as an essay writing task with only 100 text samples, we still find errors on the order of $0.0113$ MSE with $0.004$ mean absolute bias at $\varepsilon=2$.

cs.CR · cs.AI · cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06099

SWEOps-Bench: Evaluating Agents for End-to-End Resolution of Software-Induced Cloud Incidents

Danwen Chen, Guangba Yu, Pengfei Chen

原文摘要

As autonomous agents advance, the traditional boundary between software development and cloud operations gradually blurs, increasing the need for integrated incident detection, localization, and remediation. Existing benchmarks evaluate isolated diagnostic queries or repository-level program repair, failing to test continuous incident resolution across operational clusters and source repositories. We introduce SWEOps-Bench, an interactive benchmark comprising 55 reproducible incident tasks derived from confirmed historical defects across 16 Kubernetes operator projects. Each task preserves the original software repository and initializes in a healthy cluster before a controlled workload triggers the historical fault. Agents investigate runtime evidence and submit source or configuration repairs through a terminal interface, while the harness builds and deploys the changes within a shared time budget. Evaluation covers stage-wise accuracy, verified recovery, penalized lifecycle latency, and token consumption. Across six agent-model configurations, faulty-state detection ranges from 72.7% to 90.9%, whereas overall recovery ranges from only 14.5% to 52.7%, exposing a substantial gap between recognizing incidents and resolving them end to end. Trajectory analysis further shows that reported diagnosis and final recovery only partially coincide: some tasks achieve verified recovery despite an incorrect reported RCA, while runtime symptom clearance can still fail fix-specific functional verification. SWEOps-Bench establishes a rigorous foundation for evaluating autonomous agents in integrated development and operational environments.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06098

Towards Insight-Centric Data Spaces: Integrating Visual Analytics and Decentralized Data Ecosystems

Christina Faßbender, Benjamin Greiner, Benedikt T. Arnold, Georgios Toubekis, Christoph Lange

原文摘要

Visual analytics and dataspaces address complementary challenges in modern data ecosystems: visual analytics enables interactive exploration and human-centered reasoning over complex data, dataspaces provide decentralized infrastructures for sovereign and collaborative data sharing. Both fields have largely evolved independently, resulting in a gap between data management and data understanding in distributed environments.We explore their intersection and argue that integration is essential for next-generation data ecosystems. Visual analytics acts as a cognitive layer for dataspaces by making data availability, quality, provenance, and exchange processes observable and interpretable, while dataspaces reshape visual analytics by introducing decentralized, heterogeneous, and governed data environments. We illustrate this interplay through a semi-synthetic cultural dataspace scenario analyzing exchange patterns and metadata quality across a federated ecosystem. Based on these insights, we identify key open challenges and outline a vision of insight-centric data spaces, in which data management and analysis are tightly integrated into a unified, human-centered environment.

cs.GR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06097

Two-Sided Screening in Quality-Differentiated Markets

Yaohao Liu, Mengfan Ma, Mingyu Xiao

原文摘要

Motivated by digital marketplaces such as Uber and Airbnb, we study how a two-sided platform designs a menu of qualities, consumer prices, and provider wages. Consumers and providers self-select according to their private values and costs, so the platform must design its menu to attract consumers while inducing enough supply to meet their demand. We study this coordination problem over a continuous quality space, requiring supply to cover demand at every quality threshold. We formulate menu design as an optimization over trading distributions, which specify how much trade occurs at or above each quality. Through convexification of the technological cost function, we characterize the profit- and welfare-optimal trading distributions. This characterization shows how production technology alone can reduce menu size without sacrificing optimal profit or welfare, regardless of the type distributions, and determines when optimal menus can be finite. We then show that profit maximization can be highly efficient: under monotone hazard rate conditions on both sides, a profit-optimal menu achieves at least $1/(e-1)$ of optimal social welfare. We next consider the practical setting in which the menu size is restricted to a prescribed number of offers. We establish how the restricted menu approximates the unrestricted optimum in profit. We develop an algorithm that computes a menu within this size limit in polynomial time. The computed menu simultaneously approximates the unrestricted optimal profit and social welfare with additive error.

cs.GT

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.11817

Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code

Yitong Zhang, Shiteng Lu, Jia Li

原文摘要

Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding (GCD) has been widely adopted to improve the reliability of LLM-generated code by enforcing syntactic validity. In this paper, we reveal a counterintuitive risk: this reliability-oriented technique can itself become an attack surface. We uncover a new jailbreak attack, termed CodeSpear, that exploits GCD to induce LLMs into generating malicious code. Our experiments show that simply applying a benign code grammar constraint can effectively jailbreak LLMs. To address this vulnerability, we propose CodeShield, a safety alignment approach that robustly preserves safe behavior even under attacker-controlled grammar constraints. CodeShield aligns the model in the code modality by teaching it to generate honeypot code under GCD. Such code is semantically harmless, so it does not implement the malicious request, and structurally diverse, so it is difficult to suppress through grammar tightening. At the same time, CodeShield still preserves natural-language refusals when natural language is available. Experiments on 10 popular LLMs across 4 benchmarks show that CodeSpear outperforms representative jailbreak baselines and increases the attack success rate by more than 30 percentage points on average. CodeShield also restores safety under CodeSpear while preserving benign utility. Our findings reveal a fundamental risk of GCD and call for greater attention to its potential security implications.

cs.CR · cs.AI · cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06096

Many Pixels, One Composition: Self-Supervised Spectra for Specimen-Level Prediction

Eleftheria Tetoula-Tsonga, George Arvanitakis, Theodoros Giannakas

原文摘要

Can hyperspectral (HS) imaging be used to predict the elemental composition of physical specimens found on the Earth's surface? We approach this problem as a supervised regression task, using an open dataset of specimens, each comprising a HS cube and elemental characterization. In particular, we train an encoder in a self-supervised fashion that operates on pixel-level; then freeze the encoder and train a lightweight attention-based regression head in a supervised manner, by pairing many representations of a given specimen with its corresponding elemental label. In test specimens, our approach significantly outperforms traditional spectral matching and unmixing baselines. It also outperforms supervised learning models based on the mean spectrum (of similar model capacity), while full model fine-tuning achieves the strongest performance, at substantially higher model capacity.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06095

Reasoning-Trace Overflow in Code Generation: An Empirical Study of Explicit Reasoning Models

Lukas Twist, Helen Yannakoudakis, Jie M. Zhang

原文摘要

Explicit reasoning can help language models generate code, but it also introduces a practical risk: the model may spend so much of its output budget reasoning that it never produces usable code. We study this behaviour in relatively small open-weight reasoning models, framing it as reasoning-trace overflow. Across seven models and six code benchmark settings, we measure how much of a fixed 32k-token output budget is spent on reasoning, whether that reasoning improves pass@1, and whether lightweight inference-time controls can mitigate overflow. Our results show that the value of reasoning is highly conditional. Overflow is rare on simpler function-level tasks, but becomes common on harder code-generation benchmarks and for particular model families: on several model--benchmark pairs, more than half of generations exhaust the full 32k-token budget while still reasoning. Most complete overflow is associated with repetitive reasoning loops, although substantial long reasoning also occurs without looping. Disabling reasoning can therefore be competitive for overflow-prone models, simply because it ensures that an answer is produced. At the same time, reasoning remains valuable for stronger models on harder algorithmic and code-understanding tasks. Finally, prompt steering can substantially reduce overflow for some models but is inconsistent, while budgeted transitions provide more direct control and can improve both performance and token efficiency for overflow-prone models. These findings suggest that explicit reasoning should be treated as a controllable resource for code generation, rather than an always-on capability.

cs.AI · cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06093

Drift-adaptive Representation Preservation for Domain-Incremental Learning

Hyunmin Kong, Gyutae Oh, Jitae Shin

原文摘要

Pretrained vision models provide strong general-purpose representations, but in Domain-Incremental Learning (DIL), where the input distribution changes sequentially, adapting to new domains often degrades performance on previously learned ones. We observe that forgetting is not uniform across domains and classes and is not explained by training order alone. This motivates us to track each past domain-class concept individually. We use representation drift, defined as the deviation of a past concept's current representation from a fixed anchor, as a measurable surrogate for forgetting risk. The measured drift then serves two complementary roles. A consolidation loss assigns stronger preservation to high-drift pairs, while prototype construction down-weights highly drifted domains to reduce their influence on the class reference. Preservation is thus allocated by measured drift rather than assumed importance. To obtain this signal during training without storing past raw data, we repurpose a Joint-Embedding Predictive Architecture (JEPA). For each domain-class pair, we store only a compact context summary in the backbone feature space and rerun it through the learned context-to-target relation to measure its drift from the fixed anchor. Across DomainNet, Office-Home, CORe50, and CDDB-Hard, our method sustains a strong accuracy-forgetting balance on every benchmark, using substantially less training memory than accuracy-competitive methods and the smallest storage among compared methods.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06092

Constant-Round Massively Parallel Algorithms for Approximate MSTs in Metric Spaces

Eunjin Oh, Hyeonjun Shin

原文摘要

We develop a unified algorithmic framework for computing approximate minimum spanning trees (MSTs) in metric spaces in the fully scalable Massively Parallel Computation (MPC) model. Using this framework, we obtain the following results for any fixed constant $σ\in(0,1)$: - General metrics: Given all pairwise distances, we compute a $(1+\varepsilon)$-approximate MST in $O(\log(1/\varepsilon))$ rounds using $n^σ$ local space per machine and $\widetilde{O}(n^2)$ total space. - Euclidean spaces: Given $n$ points in $\mathbb{R}^d$, we compute an $O(1/σ^4)$-approximate MST in $O(1)$ rounds using $(nd)^σ$ local space per machine and $O(nd+n^{1+σ})$ total space. - Doubling metrics: Given $n$ points in a metric of doubling dimension $\mathrm{ddim}=O(σ\log n)$, we compute an $O(1/σ)$-approximate MST in $O(\mathrm{ddim}/σ^4)$ rounds using $n^σ$ local space per machine and $\widetilde{O}(n^{1+σ})\cdot 2^{O(\mathrm{ddim})}$ total space. For any fixed constant $\varepsilon\in(0,1)$, these results give the first constant-round MPC algorithms achieving $(1+\varepsilon)$-approximation in general metrics and $O(1)$-approximation in a high-dimensional Euclidean space, respectively. They improve upon the $O(\log\log n+\log(1/\varepsilon))$-round algorithm for general metrics [SODA'25] and the $O(\log\log n\cdot\log\log\log n)$-round algorithm for Euclidean spaces [SODA'24], respectively. Moreover, our round complexity for general metrics is asymptotically optimal in its dependence on $\varepsilon$, matching the $Ω(\log(1/\varepsilon))$ lower bound of [SODA'25] under the 1-vs-2-cycles conjecture. Our result also answers an open question raised by [STOC'23].

cs.DS · cs.CG · cs.DC

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06090

Overview of the NTCIR-19 SciClaimEval Task: Cross-modal Claim Verification in Scientific Papers

Xanh Ho, André Greiner-Petter, Florian Boudin, Yun-Ang Wu, Sunisth Kumar, Tian Cheng Xia, Hiba Akbi, Tim Schopf 等 9 位作者

原文摘要

This paper presents an overview of \emph{SciClaimEval}, a pilot task at NTCIR-19 on verifying scientific claims against the tables and figures of the papers in which they appear. Our dataset pairs authentic claims from 180 papers in machine learning, natural language processing, and medicine with contrastive versions of their tables and figures, one supporting the claim and one minimally modified so that it does not. The task comprises two subtasks: deciding whether a piece of evidence supports a claim, and selecting which of two evidence versions does. Twenty-two teams registered, the highest number among NTCIR-19 tasks, and 14 submitted 177 runs. Most systems built on multimodal large language models, relying on prompting and multi-stage inference rather than task-specific fine-tuning. On the first subtask, the best systems reached 98.1\% pair accuracy, but all six top-ranked systems relied on the contrastive pairs; the best system that judged each claim-evidence pair on its own scored 24.3 points lower. Open-weight models, embedded in carefully designed pipelines, matched proprietary ones. Yet verifying a single claim against its evidence, the setting that matters in practice, remains an open problem.

cs.CL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.06089

STARE: Scene Text-Aware multimodal Retrieval for Everyday objects

Kento Tokura, Ryosuke Korekata, Daichi Yashima, Kei Katsumata, Kanon Amemiya, Miyu Goko, Komei Sugiura

原文摘要

In this study, we focus on service robots that retrieve and transport everyday objects based on free-form instructions that may refer to visual features and scene text. This is challenging because it requires a multimodal understanding of the visual features and spatial relationships of objects, as well as scene text embedded in the environment. To address this, we propose Scene Text-Aware multimodal Retrieval for Everyday objects (STARE), which leverages visual and textual cues in response to free-form instructions. STARE introduces Crosslingual Visual Prompt to enhance scene text interpretation, and models the complex relationships between named entities in the instructions and their corresponding objects. We evaluate STARE using two novel benchmarks, GoGetIt and TextCaps-test, both of which consist of real-world indoor/outdoor images and instructions involving object manipulation and navigation. The results show that STARE outperforms all baseline methods on standard multimodal retrieval metrics. Furthermore, in physical experiments conducted under a zero-shot transfer setting, STARE achieves an overall success rate of 80%. Our project page and code are provided in the Supplementary Materials.

cs.CV

查看论文
arXiv ↗PDF ↗