跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 01:22 — 2026-11-23 01:22(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:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 02:59

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

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

浏览论文库

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

找到 23,345 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.25450

Inverse ECG Reconstruction via a Preconditioned Variational Quantum Linear Solver

Xizhuo Zhang, Chao Lu, Bing Yao

原文摘要

Inverse electrocardiography (ECG) reconstructs heart-surface potentials from body-surface measurements, enabling noninvasive mapping of cardiac electrical activity. However, the reconstruction requires solving dense and ill-conditioned linear systems, whose computational cost grows rapidly with the refined heart mesh. Quantum computing offers new opportunities for solving such systems. This paper presents a hybrid quantum-classical framework for inverse ECG reconstruction, which, to the best of our knowledge, is the first to apply a quantum linear solver to this problem. We first propose a Laplacian-regularized pre-encoding procedure to reduce the dimension of the system while improving its conditioning. Second, the resulting reduced system is encoded and solved using a coherent variational quantum linear solver (VQLS). Finally, we provide a rigorous theoretical proof establishing that the proposed framework preserves the exact solution of the original reconstruction problem throughout all stages of the computational process. Experimental results on a realistic heart-torso geometry demonstrate that our approach holds significant ability for accurate inverse ECG reconstruction. These findings highlight the potential of quantum solvers for noninvasive cardiac imaging, providing a foundation for further research into quantum-enhanced cardiac assessment and other healthcare applications.

cs.LG

新论文 · v1arXiv:2611.25448

Atlas: Accelerating Quantum FTQC Compilation with Optimized Algebraic Rotation Synthesis

Anbang Wu, Pu Pang, Wei Geng

原文摘要

As fault-tolerant quantum computing emerges, Clifford+T gate basis becomes a popular choice where we need to decompose single-qubit rotation gates into gates in this gate basis. Quantum rotation synthesis may lead to remarkable overhead in quantum circuit compilation. Considering variational quantum eigensolver (VQE) applications as an example, a conventional UCCSD ansatz in quantum chemistry can generate $O(n^4)$ rotations for $n$ qubits. Each optimization iteration updates the rotation angles, making rotation synthesis a recurring cost that can delay the VQE training loop. We identify two sources of delay in rotation synthesis: redundant computation during synthesis and uneven synthesis times that leave workers waiting for slow requests. Atlas addresses these costs with three optimizations: search pruning skips invalid synthesis candidates through statistical inference; adaptive arithmetic avoid unnecessary high-overhead big integer/float arithmetic when decomposing the target rotation gate; batch scheduling fills the gap between the synthesis time of varied rotations. Across various benchmarks, synthesis method, and compilation machines, Atlas can consistently accelerate the rotation synthesis process by up to 12.65x.

cs.ET

新论文 · v1arXiv:2611.25446

PAIR-MED: Policy-reward Alternation for Iterative Refinement in Multilingual Medical Reasoning

Fan Gao, Xiaohang Xu, Lang Huang, Nan Lu, Irene Li

原文摘要

Large language models demonstrate strong medical question-answering capabilities, yet reasoning performance remains uneven across languages. Process reward models (PRMs) provide step-level feedback for improving reasoning, but a fixed PRM may become increasingly misaligned with the trajectory distribution of an evolving policy during reinforcement learning, thereby reducing the reliability of its supervision. We propose a policy--reward alternating training framework that jointly adapts a medical PRM and optimizes a multilingual reasoning policy. Following supervised initialization, the current policy generates multilingual trajectories to update the PRM, which then provides process-level rewards for the next policy update. Medical step supervision maintains the PRM's medical foundation, while process, outcome, and language-related rewards guide policy learning. We develop multilingual medical PRMs (PAIR-PRM) and reasoning models (PAIR-MED) at 8B and 9B scales across 12 languages. On the medical subsets of Global-MMLU and MMLU-ProX, our models improve average accuracy by 3.01--7.47% over their corresponding Qwen backbones. On CUREMED-BENCH, PAIR-MED-9B improves the joint language consistency and logical accuracy metric by 12.88% and 7.45% over baselines for in-domain and out-of-domain languages. Further analyses examine PRM adaptation, multilingual reasoning quality, and the contributions of individual training components.

cs.CL

新论文 · v1arXiv:2611.25445

Stereo Visual Odometry with In-the-Loop Geometric Feed-Forward Models Towards Dense Metric Mapping

Fahira Afzal Maken, Sagun Man Singh Shrestha, Edward Vanderfeen, Lucas Carvalho de Lima, Rongxin Li, Changming Sun, Milad Ramezani

原文摘要

We present a stereo visual odometry (SVO) framework that integrates geometric feed-forward models (GFMs) for dense depth prediction with factor-graph-based visual odometry to achieve accurate localisation and dense metric mapping. Our key idea is to exploit sparse but reliable metric geometry estimated from stereo and temporal multi-view observations to calibrate dense GFM predictions, while retaining the robustness and efficiency of model-based SVO. Rather than directly conditioning the GFM on potentially noisy stereo depth, optimised 3D landmarks are used to jointly estimate a scale-shift transformation over all keyframes within each local submap, yielding metrically consistent dense depth predictions. To balance accuracy and computational efficiency, we introduce a hierarchical factor-graph architecture. At the local level, sliding-window optimisation estimates high-frequency camera poses and multi-view-refined 3D landmarks. Dense predictions are generated only for selected keyframes and registered within each submap using SE(3) Generalised ICP. Consecutive submaps are further aligned in Sim(3) using their shared geometry, allowing residual scale inconsistencies to be corrected. These intra- and inter-submap constraints are incorporated into a global factor graph to produce a consistent trajectory and dense metric reconstruction. Extensive experiments on public and in-house datasets demonstrate that the proposed framework achieves competitive odometry accuracy against geometric and learning-based baselines while providing accurate dense metric reconstruction and improved robustness to failures in learned depth prediction.

cs.RO · cs.CV

版本更新 · v5arXiv:2604.24661

Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations

Zhengru Fang, Yu Guo, Huanhuan Lou, Fei Liu, Yuang Zhang, Yihang Tao, Senkang Hu, Wenbo Ding 等 9 位作者

原文摘要

Visual control maps visual streams to actions in reinforcement learning and vision-language-action (VLA) policies. Changing weather, noise, blur, and compression can obscure different task cues within one episode. Existing control benchmarks mainly test scene distractions, while generic restorers optimize whole-image fidelity. We introduce the Visual Degraded Control Suite (VDCS) to evaluate seven degradations under Markov switching. We propose Agent-Centric Observations with Mixture-of-Experts (ACO-MoE), which routes each frame to a repair expert, restores RGB content, and composes task-relevant foregrounds. On eight VDCS tasks, corruption lowers DreamerV3's mean return from 769 to 562. ACO-MoE raises it to 730, recovering 81.2% of the lost return. It also improves returns on DMC-GB and RoboSuite and retains 70% to 97% of clean-input mean return under six unseen perturbation families. We train ACO-MoE on robot demonstrations and deploy it with a 3B-parameter VLA policy on a Piper arm for cube placement in blue and white boxes and cup placement on a coaster. On the blue-box and cup tasks, motion blur and physical low light with added noise reduce success from 100% to at most 10%. ACO-MoE raises success to 75% to 95% over 20 trials per task and condition.

cs.RO

新论文 · v1arXiv:2611.25438

BOOMerang: Autonomous Translation from RTL to Microarchitectural Simulators and Back

Ferran Hermida-Rivera, Jack Toubes, Angela Cui, Chengyi Lux Zhang, Sagar Karandikar

原文摘要

High-level simulators like gem5 are often used to test and demonstrate novel architectural techniques. While these simulators provide high research productivity, they generally lack the means to provide detailed feedback on the realizability of a hardware design. Furthermore, these simulators can frequently fall out-of-sync with the detailed performance characteristics of real hardware designs, which is usually the responsibility of dedicated engineers/teams in industry. While RTL implementation can address these challenges, it can be even more difficult to translate simulator code to high-quality RTL by hand without a large team. In this work, we architect and evaluate agentic loops that automate both parts of the RTL vs. high-level simulator workflow that is critical to high-quality architecture research. Our loops (1) automatically generate accurate high-level models of RTL implementations of CPU designs (BOOM) in a battle-tested microarchitecture simulation framework (gem5) and (2) automatically translate new microarchitectural features implemented in the high-level simulator back to RTL faithfully. Targeting the first loop at autonomously building a gem5 model for the Berkeley Out-of-Order Machine (BOOM) core, we generate a simulator with IPC within 3% of the RTL, meeting targets pursued for simulators in industry, in only 2 days. We use our second loop to automatically translate 72 features from this aligned gem5 simulator into RTL in the BOOM core, while maintaining its low IPC error. Combining translated optimizations together yields a 25% performance improvement for the BOOM core RTL implementation in SPECint 2017, demonstrating that having these loops for moving between high-level simulation and RTL enables actual improvement of processor performance. The agentic loops we developed and the simulators and RTL we generated will be available in open-source.

cs.AR

新论文 · v1arXiv:2611.25433

RoCoKV: Accelerating LLM Inference Serving through Uncertainty and Redundancy Aware KV Cache Compression

Payman Behnam, Elaheh Sobhani, Saad Amin, Yahya Hassan, Daniyal Khan, Biswadeep Chakraborty, Tanish Patwa, Souvik Kundu 等 9 位作者

原文摘要

KV cache compression is critical for large reasoning models, where most of the cost comes from long generated reasoning traces rather than the input prompt. These traces often contain redundant and low-utility tokens due to looping, self-verification, and corrections. However, such tokens may still receive high attention scores, making it difficult to remove them without harming the reasoning process. We propose RoCoKV, a KV cache compression method designed for large reasoning models. RoCoKV introduces two key components. First, uncertainty-guided adaptive pruning adjusts the compression strength based on the model's confidence, allocating more memory during uncertain phases and applying stronger pruning when the model is confident. Second, redundancy-aware token selection reduces the impact of tokens that are highly similar to recent reasoning content, encouraging the model to retain more informative and diverse tokens. Beyond the algorithm, we co-design RoCoKV with the serving stack: we develop fused three-phase CUDA decode kernels and integrate them into vLLM as a drop-in plugin that preserves its paged KV layout and CUDA graph capture, turning algorithmic savings into real end-to-end speedups. Extensive experiments across three reasoning benchmarks and two reasoning models demonstrate that RoCoKV consistently improves reasoning accuracy under constrained KV cache budgets, achieving higher accuracy compared to state-of-the-art KV cache compression methods. For DeepSeek-R1-Distill-Llama-8B in vLLM, RoCoKV achieves a 1.27X speedup and 38% higher throughput on AIME25, the most challenging evaluated reasoning benchmark, and a 1.43X speedup and 45% higher throughput on the long synthetic benchmark, compared with Full-KV.

cs.CL

新论文 · v1arXiv:2611.25428

GenAI-DBT: Evaluating a DBT-Informed Generative AI Platform for Mindfulness Skills Training: A Pilot Randomized Study

Jingchen Ye, Yujia Chen, Leyang Han, Siyuan Wang, Mark Zachary Rosenthal, Yucheng Jin

原文摘要

We evaluated the feasibility, acceptability, and engagement of three digital formats for dialectical behavior therapy (DBT) mindfulness skills training. In a 30-day randomized pilot study, 45 university students were assigned to GenAI-DBT, a general-purpose large language model chatbot (Chatbot), or a static web resource (Web). Forty-two completed the study, and nine completed follow-up interviews. Usability scores were within acceptable ranges across conditions, with no significant between-group differences. GenAI-DBT showed the highest observed participant-week adherence (71.4%, vs. 53.3% for Web and 42.3% for Chatbot), a descriptive difference. Mindful Attention Awareness Scale and Difficulties in Emotion Regulation Scale scores showed no significant time-by-group interactions, and session-level self-reported mood changes did not differ significantly across conditions. GenAI-DBT showed a larger positive change in linguistic valence than Chatbot (4.28 vs. 1.59, P = .02, Cohen's d = 0.99). Interviewees valued contextualized, scenario-based practice and identified response latency, repetition, and limited personalization as areas for improvement. The findings support the feasibility and acceptability of DBT-informed conversational AI for skills practice and motivate further evaluation in larger, more clinically relevant samples. Clinical efficacy remains to be established.

cs.HC

新论文 · v1arXiv:2611.25425

Instance-Optimal Moment Estimation in the Add-Remove Model of Differential Privacy

Shokichi Takakura

原文摘要

In this paper, we study the problem of estimating empirical means, variances, and covariances under pure differential privacy in the add-remove model. While existing mechanisms achieve optimal worst-case error, they may not be optimal for individual datasets. To measure the performance of mechanisms on individual datasets, we introduce instance-dependent error metrics and prove sharp lower bounds on them. Then, we design mechanisms that achieve these lower bounds and demonstrate that they achieve asymptotically better utility compared to existing methods.

stat.ML · cs.LG

新论文 · v1arXiv:2611.25422

From Sequence Uncertainty to Phenotype Hypotheses: Uncertainty-Conditioned Inference over Biomedical Knowledge Graphs

Huixin Zhan, Jason H. Moore

原文摘要

Genomic foundation models provide variant-level evidence, but connecting that evidence to phenotype hypotheses requires accounting for uncertainty throughout structured reasoning. We introduce an uncertainty-conditioned path-energy framework that converts sequence predictions and calibrated predictive uncertainty into explicit distributions over graph-supported phenotype hypotheses, without patient-level phenotype supervision. An interpretable learned energy scores admissible gene--disease--phenotype routes, query uncertainty controls the target temperature, and path probabilities are aggregated into phenotype hypotheses. This formulation makes evidence quality an explicit determinant of hypothesis breadth while retaining traceable multi-path support. Exact normalization over enumerable candidate sets provides a reference for evaluating a Hastings-corrected learned revision operator. On AlzKB and Hetionet, phenotype-level entropy tracks upstream uncertainty, with Spearman correlations of 0.951 and 0.878, respectively; ablations identify the contribution of uncertainty conditioning. In masked-edge recovery, the model exceeds chance and degree-matched probability-permutation controls. Training the energy under the uncertainty-dependent temperature yields higher held-out recall@10 than training under a constant temperature of comparable magnitude. Under gene hold-out, recall@10 exceeds that of a trained DistMult embedding on 24 of 30 graph masks (0.183 versus 0.123); this difference is attributable mainly to three genes with many variants and is not established for all genes. These results establish an uncertainty-aware interface from genomic predictions to graph-supported phenotype hypotheses that combines interpretable probability allocation with held-out association recovery of explicitly stated scope.

cs.LG · q-bio.GN

版本更新 · v2arXiv:2609.27695

GLoTouch: Global-to-Local Haptic Perception Using a Parallel Gripper for Object Search, Recognition, and Grasping Without External Vision

Zonglin Li, Wanruo Zhang, Yiming Wang, Kun Song, Xinyi Zhou, Daolin Ma

原文摘要

Perceiving objects in the environment is a fundamental capability of autonomous robots. In dark or low-light environments, external cameras often fail to reliably perceive object positions and geometry; when visual sensing is unavailable, completing target search, recognition, and grasping through touch alone becomes a key robot manipulation capability. This task must simultaneously address container-scale spatial exploration and object-scale fine-grained geometric perception, which is particularly challenging for low-degree-of-freedom parallel grippers. However, a unified framework remains lacking for connecting container-scale spatial exploration with object-scale fine-grained geometric perception and grasping. To address this challenge, we present \textbf{GLoTouch}, a global-to-local haptic perception and manipulation framework built on a parallel gripper. In the global stage, the gripper holds a passive long-reach probe, combining force measurements with known tool geometry to localize contacts and actively estimate candidate-object positions, coarse contours, and heights. In the local stage, the robot sets down the probe and uses the bilateral visuotactile sensors on the same gripper to directly acquire local haptic observations, which are matched against a given target 3-D model without object-specific training. We evaluate the framework in both simulation and real-robot experiments. Source code will be open-sourced.

cs.RO

新论文 · v1arXiv:2611.25419

DiLE: Discrimination-Aware Latent-Space Learning for Universal Multimodal Embeddings

Ben Kang, Junda Wang, Yuxuan Yuan, Hang Li, Yuhan Liu, Xin Chen, Wanting Geng, Tong Lin 等 12 位作者

原文摘要

Multimodal large language models have greatly improved input understanding in universal multimodal embedding models. However, this understanding does not ensure that their embeddings preserve the evidence needed to distinguish relevant items from confusable alternatives. To preserve essential discriminative evidence in embeddings, this paper proposes DiLE, a discrimination-aware latent-space learning framework that combines task guidance with on-policy retrieval feedback. Specifically, a few learnable queries are used to encode task-relevant information in a compact latent space. Reasoning instructions and auxiliary answer-generation supervision shape these representations to support both task understanding and retrieval discrimination. To address task-specific discriminative needs, we design shared-private expert adaptation that integrates cross-task knowledge sharing with task-specific representation learning. Building on this, the on-policy hard-negative distillation is introduced: the student retrieves confusable candidates, and a reverse KL divergence objective aligns its embedding-based similarity distribution with the teacher's fine-grained relevance distribution over these candidates. Candidates are periodically refreshed using updated student snapshots, tying teacher supervision to the student's evolving retrieval behavior and confusions. Across four model configurations that span two backbone generations, DiLE achieves state-of-the-art performance on MMEB-v2, UVRB, and MRMR, demonstrating its effectiveness across modalities and tasks.

cs.CV

新论文 · v1arXiv:2611.25418

Bilateral Evidence Selection and Reasoning for Mammography Vision--Language Models

Zhengbo Zhou, Dooman Arefan, Shandong Wu

原文摘要

Medical vision--language models (VLMs) often need to identify small, subtle lesions within high-resolution images containing extensive normal anatomy and redundant visual information. Visual-token compression improves efficiency, but preserving salient regions alone can discard the context needed for diagnostic interpretation. This context can extend across images: in bilateral mammography, the opposite breast provides a patient-specific anatomical reference. Yet retaining such evidence does not ensure that the model uses it effectively. We propose Bilateral Evidence Selection and Reasoning (BESR), which connects evidence preservation with comparative assessment through a bilateral-guided token selector and a bilateral reward. Under a shared token budget, the selector jointly prioritizes lesion appearance and its local and bilateral context, while the reward encourages assessments that benefit from the preserved comparison. Experiments on a bilateral dataset constructed from CBIS-DDSM and on VinDr-Mammo demonstrate improved evidence retention and diagnostic performance under constrained visual-token budgets. Inference benchmarking further shows reduced prefill latency.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25417

MIR-Depth: Multi-Range Refinement for Single-View RGB-D Depth Completion of Transparent Objects

Xinzhe Fu, Qi Shao, Yuanfei Xie, Taoyu Wu, Zhihao Cao, Long Hu, Hong Liang, Xianzhi Li 等 11 位作者

原文摘要

Recovering accurate visible-surface depth from a single RGB-D image and an object mask is essential for robotic grasping and manipulation of transparent objects. Specular reflections cause missing depth, while refraction corrupts nonzero returns with background depth, making raw measurements unreliable as surface anchors. Under a fixed sampling budget, refining an initial single-view prediction within a single search interval either misses large refraction offsets or sacrifices fine local resolution. To resolve this single-view trade-off, MIR-Depth constructs Coordinate-Aware Multi-Range Hypotheses: a 3D-aggregated global inverse-depth volume and depth-axis-filtered pixel-wise local volumes around a prior-guided initial depth. Selective Recurrent Refinement then introduces out-of-bounds lookup masking and validity-masked softmax fusion to iteratively update inverse depth from these volumes using a multi-scale ConvGRU. Finally, Spatially Gated Correction applies a learned per-pixel spatial gate to the full-resolution residual, preserving accurate initial geometry without imposing raw sensor readings as hard constraints. Experiments on TransCG, TODD, TRansPose, ClearPose, and HouseCat6D show that MIR-Depth achieves lower error than ReMake, DFNet, BP-Net, and PSD. Real-robot evaluations confirm accurate surface geometry for 6-DoF grasp pose prediction. Code and pretrained models will be publicly available.

cs.CV · cs.RO

版本更新 · v2arXiv:2611.22717

PCRG: Training-Free Pruning and Caching of Reference Tokens for Video Generation

Siyuan Wang, Haoran Li, Yi Yue, Tak L. Fung, Quan Chen

原文摘要

Reference-to-video diffusion transformers pack the variational autoencoder (VAE) latents of all references and the generated tokens into one full-attention sequence, in which reference tokens make up about half. Because attention cost grows quadratically with sequence length, these tokens take up an even larger share of the attention computation, yet most of them are static, smooth or irrelevant to the output. To accelerate reference-conditioned generation, we propose pruning and caching of reference tokens for video generation (PCRG), a training-free, plug-and-play method that uses two signals the model already computes to assign each reference token to one of three tiers, namely pruned, cached or kept. The first is a low-level redundancy r from VAE latents, since a token whose latent barely changes over time or across its neighbors adds little new content. The second is a high-level importance g from the vision-language-model (VLM) conditioner, where the attention that the prompt and any first or last frames pay to a token tells whether the output needs to read it. Tokens that are not redundant are kept, and redundant tokens are cached if important and pruned otherwise. Pruned tokens leave the sequence before the first step with all rotary position embedding positions unchanged. Cached tokens have their keys and values computed once and reused, and kept tokens are processed as usual. On MiniMax-H3, already distilled to 8 timesteps and quantized to int8, PCRG is 1.57x faster end to end on our V2V-Bench and 1.49x faster on the public VACE-Benchmark, while the quality of VBench drops by only 0.24% and 0.17%, respectively. PCRG shortens the sequence rather than changing how attention is computed or which steps are run, so it also stacks on step caching and sparse attention. On V2V-Bench it reaches 1.86x with TeaCache, 1.82x with Spark at nearly unchanged fidelity and 2.15x with Veda.

cs.CV

新论文 · v1arXiv:2611.25416

Standardized Tolerance for Adaptive Reuse and Repair: A Method for HNSW Migration Under Embedding Model Change Scenarios

Hengzhao Ma, Chenyang Zhu, Bin Wang, Xiaochun Yang

原文摘要

When an embedding model changes, the same collection is re-encoded, and its vector index must be adapted to the new embedding space. Because the source and target vectors represent the same objects, suitable connections in the source index can be reused. We propose STARR (Standardized Tolerance for Adaptive Reuse and Repair) to migrate HNSW indexes after an embedding model change. STARR compares standardized edge lengths over the same source neighbor lists in both embedding spaces and uses the correlation between their distance profiles to set the allowable increase in standardized edge length. It reconnects affected vertices by searching the partially migrated graph and shares the resulting candidates with their neighbors. We bound edge rejection under local distance distortion, characterize migration work, and prove that a final repair pass makes every vertex reachable from the entry point at the base layer while respecting degree limits. Single-threaded experiments on MS MARCO, Wikipedia, and CC3M, each with one million objects, show that STARR achieves 5.25--44.54$\times$ construction speedups over Fresh and migrates faster than both DGM variants on all 15 selected transitions. Recall@10 remains within one percentage point of Fresh in 10 cases, and query throughput exceeds DGM-Local in 14 cases. Parameter sweeps on three transitions further demonstrate favorable migration-time--recall tradeoffs beyond the default settings. Across all 240 directed transitions among 16 MS MARCO models, STARR achieves a median construction speedup of 16.71$\times$ with a median recall loss of 1.0 percentage point.

cs.DB

版本更新 · v3arXiv:2609.20816

Paint-Anything: Unified Any-Color Control for Image Generation and Editing

Ji Xie, Dewei Zhou, Xinyu Huang, Zhennan Chen, Xun Wang

原文摘要

Professional design requires any-color control: the ability to specify an object's target color with any 24-bit hex value for image generation and editing. Prior work has explored color generation, editing, and colorization, but often relies on dedicated color representations or specialized inference procedures. Advances in large language models offer a simpler starting point: even compact models can associate hex values with color semantics. We present Paint-Anything, which learns a shared hex-prompt interface for generation and editing through object-level color supervision. We develop a data pipeline that constructs Paint-500K from real images through object grounding, perceptual color labeling, and editing-pair synthesis. Since shadows make real-image labels only approximate colors, we complement this supervision with pure-color anchors whose pixels exactly match their paired hex values. These anchors are used only at high-noise timesteps, leaving low-noise training to natural images. We further introduce Any Color Benchmark (ACBench), comprising ACBench-T2I and ACBench-Edit, to measure object-level hex color fidelity across both tasks. On FLUX.2-4B, Paint-Anything improves ACBench-T2I and ACBench-Edit scores by 85.3% and 28.3%, respectively, relative to the base model, with ablations supporting the training recipe. It also achieves the highest average CompColor score among the compared methods.

cs.CV · cs.AI · cs.LG

新论文 · v1arXiv:2611.25414

Watertight Mesh Optimization of Textured Objects

Nathaniel Burgdorfer, Philippos Mordohai

原文摘要

When reconstructing high-quality 3D assets from images, existing approaches often excel at one objective while compromising another, and frequently overlook the intrinsic quality of the reconstructed surfaces. We present MODL, a framework that jointly optimizes geometry and view-dependent appearance directly on a watertight triangle mesh. Our approach combines Laplacian-preconditioned optimization for smooth vertex updates with curvature-adaptive remeshing to preserve fine details and well-shaped triangles. The triangle mesh is optimized subject to multi-view normalized cross-correlation constraints, but without segmentation, geometric supervision or alpha-blending. Evaluations on object reconstruction datasets demonstrate that MODL achieves competitive novel-view synthesis while producing geometrically accurate models with superior intrinsic mesh quality. Our results highlight the potential of direct mesh optimization to unify photorealistic rendering, geometric reconstruction, and practical 3D asset creation.

cs.CV

新论文 · v1arXiv:2611.25413

WAMotor: Accelerating World Action Models via Speculative Inference under Dual Nonuniform Denoising Dynamics

Zexun Lin, Yuan Feng, Xike Xie

原文摘要

World Action Models (WAMs) unify world modeling and action generation for robotic control by integrating flow-matching velocities, yet suffer from high multi-step denoising latency. Recent studies have explored speculative inference to accelerate WAMs by drafting and verifying denoising steps in parallel. However, existing methods either require training task-specific draft models or overlook critical WAM denoising dynamics when reusing past velocities as drafts. We revisit the denoising dynamics of WAMs and identify a dual nonuniformity that breaks standard velocity-reuse assumptions: velocity smoothness is nonuniform as adjacent velocity residuals differ sharply at early and final steps, so reuse there yields large residuals, which nonuniform integration time steps further translate into local state errors that accumulate into the final action distribution. Accordingly, we formalize this by theoretically deriving a trajectory error tolerance bound that characterizes how velocity residuals and integration time steps affect the final action distribution. Based on this, we propose WAMotor, the first speculative inference method tailored to the dual nonuniformity in WAMs. It selects reliable anchor velocities by deferring speculation and employs time-step-aware verification that scales acceptance thresholds by integration time step size. WAMotor offers plug-and-play benefits, enabling seamless integration with prior WAMs. Extensive evaluations on LIBERO, RoboTwin 2.0, and LIBERO-Plus show that WAMotor achieves 2.86$\times$--4.28$\times$ end-to-end speedups while maintaining task success rates. Our code is available at: https://github.com/Overdue-Lin/WAMotor

cs.RO

新论文 · v1arXiv:2611.25412

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

Xinyi Wang, Yeting Li, Shizhe Cui, Jiaming Guo, Qin Mai, Yecheng Sun, Hengyu Yang, Yujie Sun 等 12 位作者

原文摘要

High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain. We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code. Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection. It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them. Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

cs.CR · cs.AI

新论文 · v1arXiv:2611.25410

SGLayout: Schema-Guided Closed-Loop Refinement for LLM-Driven Parameterized Layout Generation

Siyang Chen, Yuan Pu, Yuhan Qin, Zhaotan Lin, Siyuan Liang, Zhuolun He, Lining Zhang, Bei Yu

原文摘要

Large Language Models (LLMs) have shown strong potential in parameterized layout generation via tool-augmented code synthesis. However, LLMs lack spatial awareness, making one-shot generation unreliable. While layout quality can be evaluated with established techniques, a critical gap remains: geometric-domain evaluation outcomes cannot be directly translated into actionable code-level fixes, trapping iterative refinement in blind refactoring. We propose SGLayout, a self-refining framework that closes this gap via a schema-guided mechanism. Upon code execution, a structured schema captures the correspondence between each code-level instance and its geometric attributes, establishing a bidirectional link between code space and geometry space. Emulating engineer review practices, SGLayout evaluates layouts along two complementary dimensions: intent compliance through quantitative structural checking and qualitative vision-language assessment, and rule compliance through DRC. All identified violations are then back-projected through the schema onto precise code targets, enabling surgical repair. This closed-loop process iterates until layout convergence. On a curated benchmark of 112 parameterized layout generation tasks using GDSFactory, SGLayout achieves a 76.79% pass rate, compared with 50.89% for the strongest baseline.

cs.AR · cs.AI

版本更新 · v2arXiv:2610.02502

BROAD: Bit-Parallel Row-Oriented Arithmetic in DRAM

William C. Tegge, João Paulo Cardoso de Lima, Shouzhi Fang, Jeronimo Castrillon, Alex K. Jones

原文摘要

Processing-using-memory (PUM) architectures perform computation directly within DRAM to reduce costly data movement between memory and processors. Because charge-sharing operations are confined to individual bitlines, existing DRAM-PUM architectures reorganize data into column-oriented, bit-serial representations. This organization is fundamentally incompatible with the row-oriented, word-parallel layouts used by conventional processors and accelerators, requiring expensive data-layout transformations whenever computation transitions between PUM and conventional execution. In this paper, we present BROAD, or Bit-Parallel Row-Oriented Arithmetic in DRAM. BROAD augments the DRAM subarray with two lightweight extensions: migration cells that enable localized horizontal data movement between neighboring bitlines and inversion cells that provide efficient in-array logical inversion. These primitives enable BROAD to operate directly on row-parallel, bit-parallel data, preserving CPU-compatible layouts while exploiting the massive parallelism of the DRAM subarray. In particular, BROAD demonstrates that localized horizontal communication is sufficient to realize shallow arithmetic networks and efficient parallel reduction for multiplication, reducing arithmetic latency while preserving throughput and eliminating costly data-layout transformations, all while maintaining the conventional DRAM array organization. We demonstrate the feasibility and overhead of augmenting DRAM subarrays with migration and inversion cells through detailed transistor-level layout and SPICE-validated circuit simulations. Using the BROAD compiler it is possible to evaluate the performance and data reorganization tradeoffs to ensure the best execution across combined CPU and PUM. Evaluating BROAD on 19 MLPerf benchmarks, there is a 5.9x higher end-to-end performance compared to SIMDRAM for DDR4 PUM execution.

cs.AR

新论文 · v1arXiv:2611.25406

Decision Boundaries Matter: Graph-Regularized Residual Adaptation for Cross-Domain Fake Image Detection

Shichuang Xie, Qishuai Ding, Tong Qiao, Liquan Shen, Guorui Feng

原文摘要

Despite learning transferable features, fake image detectors may struggle on unseen domains due to mismatched decision boundaries. Our analysis shows that features extracted by the frozen forensic encoder remain discriminative, but the source-trained decision boundary does not fully exploit this information. However, correcting this boundary without source data or target labels remains challenging, as unreliable source predictions may lead to incorrect adaptation. To address this issue, we propose Graph-Regularized Residual Adaptation (GraRA), which refines the source decision boundary using only unlabeled target data. To determine which classifier directions to update, GraRA constructs a compact residual subspace from uncertainty-weighted target features and keeps it orthogonal to the source classification direction. To guide these updates, it uses source-score anchors to generate soft labels through target-graph diffusion, while neighborhood consistency regularizes residual learning within the constrained subspace. The learned correction is merged into the source classifier, requiring only 32 optimized coefficients and no additional inference branches. On diverse unseen OpenMMSec domains, GraRA achieves 84.36\% accuracy and 91.34\% AUC, improving over the source detector by 4.33 and 3.50 percentage points, respectively. Further analysis shows that reliable source predictions and locally consistent neighborhoods help guide residual learning, allowing GraRA to correct ranking errors that a simple threshold shift cannot address. \textcolor{cvprblue}{Code will be made publicly available.

cs.CV

新论文 · v1arXiv:2611.25405

ObliGraph: Graph Pattern Query Processing with Full and Differential Obliviousness

Lyu Xu, Xinyi Zhang, Qichen Wang

原文摘要

Graph pattern query is a fundamental primitive in graph databases for retrieving data graphs that match a query graph under various structural constraints. As graph data is increasingly outsourced to third-party cloud servers for scalable query processing, however, both the query graph and the data graphs may leak sensitive structural information through server-side access patterns. In this paper, we study privacy-preserving graph pattern query processing in the outsourced setting, aiming to protect the structures of both the query and data graphs from access-pattern leakage. To this end, we propose $\mathsf{ObliGraph}$, the first oblivious graph search framework that supports multiple classes of graph pattern queries under two privacy modes: $\mathsf{FOS}$ achieves full obliviousness by uniformly evaluating candidate mappings, making the server-side access pattern independent of the structures of the query and data graphs; $\mathsf{DOS}$ further improves query efficiency through pruning while retaining a provable privacy guarantee of differential obliviousness. This design enables a smooth trade-off between stronger privacy and higher efficiency within a single framework. Experiments on real and synthetic datasets demonstrate that $\mathsf{ObliGraph}$ efficiently supports a range of graph pattern queries, achieving substantial improvements while preserving strong privacy guarantees.

cs.DS

新论文 · v1arXiv:2611.25404

Toward a Science of AI Agent Societies

Geon Lee, Fanchen Bu, Soo Yong Lee, Sunwoo Kim, Kijung Shin

原文摘要

AI agents are rapidly evolving from isolated personal assistants into networked actors that interact with one another at scale. We envision the emergence of AI agent societies, with their own social and economic dynamics, as a new research frontier. We argue that AI agent societies should be studied as a distinct object of inquiry: neither simply larger collections of individual agents nor merely simulations of human society. To formalize this perspective, we propose four core properties that a valid AI agent society should satisfy: individualized objectives, rules and governance, autonomy, and scale and complexity. Building on this framework, we identify four classes of societal behaviors worth studying in AI agent societies: economic behaviors, behaviors under conflict-of-interest, unsafe and unethical behaviors, and system-level behaviors. We then outline key technical challenges--including property parameterization, parameter balancing, and robust implementation--and argue that progress on these challenges could enable scientifically informative and practically useful models of AI agent societies. Finally, we revisit existing multi-agent systems through the lens of the proposed core properties, show that they instantiate only subsets of them, and discuss implications for platform design, evaluation, and governance.

cs.AI

新论文 · v1arXiv:2611.25403

Antom 3-in-1 Transformer: A Payment Foundation Model

Weiyu Han, Haoyu Jiang, Jie Sheng, Youxi Pan, Xianglong Liu, Zeqi Ren, Dongquan Yi, Yinhao Liu 等 24 位作者

原文摘要

We report the development of Antom 3-in-1 Transformer, a payment foundation model that integrates sequence, tabular, and graph representations for payment risk detection. The model contains approximately 7B parameters, with approximately 1.7B activated per task route. Antom 3-in-1 Transformer is pretrained to learn reusable behavioral and relational representations, primarily on Ant International's internal payment data. In a cross-business transfer experiment, pretraining improves the target business metric by 34.5% over the same architecture trained from scratch. With only 25% of the training labels, the pretrained model outperforms the full-label scratch baseline in Average Precision (AP) and Recall@0.5% on different merchant domains. In a four-month online experiment on Ant International's billion-scale payment platform, the model reduced the overall loss rate by 37.88% relative to XGB-Online.

cs.LG

版本更新 · v2arXiv:2611.23350

Asymmetric Optical Image Watermarking

Guang Yang

原文摘要

Watermark detectors held by a provider cannot be checked by third parties, and a party that can detect a mark can usually also forge it. We study a two-layer image watermark in which the Fourier transform at the core of the pipeline is performed by a coherent optical 4F unit. Layer 1 carries an Ed25519 signature bound to the image content in Fourier magnitudes, so anyone with the public key verifies offline. Layer 2 is a key-defined carrier written by a secret phase hologram and read by a matched-filter correlator. The optics is a scalar-diffraction simulation with finite modulator bits, pixel aperture, pupil, defocus, misalignment, and sensor noise. No hardware is built. All criteria were fixed in a hashed specification before any optical result. The simulated optical signer reproduces the digital pipeline (field error 1.7e-15, bit agreement 99.997%), verifies at least 99.5% of 877 images under each of 8 post-sensor settings, one unattacked, and accepts none of 40,670 unmarked images. The optical carrier is key-selective: the matched key detects it on 99.8% of the unattacked images, and detection falls to 0% under a scale error of 1% and to 0% under a mask shift of 1 bin. Security rests on the signature and the content binding, for which we separate what is provable from what is measured.

cs.CR · cs.CV

版本更新 · v6arXiv:2506.00452

Learning MMSE Filters for OFDM Channel Estimation: Attention Transformer Gains at Linear Inference

TaeJun Ha, Chaehyun Jung, Hyeonuk Kim, Jeongwoo Park, Jeonghun Park

原文摘要

In orthogonal frequency division multiplexing (OFDM), accurate channel estimation is crucial. Classical signal processing-based approaches, such as linear minimum mean-squared error (LMMSE) estimation, often require second-order statistics that are difficult to obtain in practice. Recent deep neural network (DNN)-based methods have been introduced to address this, but they often suffer from high inference complexity. This paper proposes an Attention-aided MMSE (A-MMSE), a model-based DNN framework that learns the linear MMSE filter via the Attention Transformer. Once trained, the A-MMSE performs channel estimation through a single linear operation, eliminating nonlinear activations during inference and thus reducing computational complexity. To improve the learning efficiency of the A-MMSE, we develop a two-stage Attention encoder that captures the frequency and temporal correlation structure of OFDM channels. We also introduce a rank-adaptive extension that adjusts the filter rank at deployment time, enabling efficient operation under resource-constrained receivers. Numerical simulations show that A-MMSE consistently outperforms baseline methods across a wide range of signal-to-noise ratio (SNR) conditions. In particular, the A-MMSE and its rank-adaptive extension provide an improved performance-complexity trade-off.

eess.SP · cs.AI · stat.ML

新论文 · v1arXiv:2611.25400

Dune: A Zeroth-Order Optimizer with Time-Conditioned Historical Error Regression for VLA Test-Time Adaptation

Chengyang Dong, Ze Chen, Kai Ye, Chutian Wang, Heng Xu, Wei Mo, Maomao Li, Jiayan Xu 等 14 位作者

原文摘要

Test-Time Adaptation (TTA) enables Vision-Language-Action (VLA) models to handle distribution shifts during deployment without source-domain retraining. However, backpropagation-based adaptation incurs heavy memory overhead on resource-constrained robots, whereas zeroth-order (ZO) methods suffer from high estimation variance under limited perturbation budgets. We observe that while ZO estimation enables low-memory adaptation with rapid initial gains, it often stalls or degrades over long-horizon updates due to noisy gradient estimates. To address these limitations, we propose Dune, a zeroth-order optimizer that stabilizes long-horizon adaptation by coupling online historical error prediction with current perturbation observations. Specifically, Dune learns a lightweight, time-conditioned error predictor from past optimization dynamics and fuses its predictions with instantaneous ZO estimates, achieving effective variance reduction without backpropagation or extra forward passes. Additionally, we theoretically characterize how estimation variance restricts convergence in high-dimensional, small-population regimes, motivating the use of historical statistics. Extensive experiments on LIBERO and real-world robots demonstrate that Dune achieves superior success rates under a low memory footprint, with ablations confirming improved closed-loop stability and post-disturbance recovery.

cs.RO · cs.AI

新论文 · v1arXiv:2611.25398

RefreshGrad: An Online Adaptive Data-sampling Method for Diffusion-based Visuomotor Learning

Dijia Zhan, Jinyi Li, Xuemiao Xu, Yan Zhou, Yu Liu, Shaoshan Liu, Jie Tang

原文摘要

Training vision-language-action (VLA) policies from demonstrations typically samples trajectory segments uniformly or relies on static offline data curation before training. However, we find that demonstration data vary sharply in supervision value across temporal windows, and that each window's value to the policy evolves substantially during training rather than being fixed or captured by raw loss alone. Motivated by this finding, we propose RefreshGrad, an online adaptive data-sampling framework that periodically scores temporal windows from the evolving policy using five policy-native signals and dynamically adjusts their sampling weights during training. RefreshGrad focuses optimization on informative, learnable windows without altering the policy architecture, training objective, or inference cost. Across ten LIBERO-Plus manipulation tasks, RefreshGrad boosts average success from 60.7% (Uniform) and 68.2% (FAKTUAL) to 76.1% under visual perturbations, and from 57.4% and 73.3% to 81.3% in clean scenes.

cs.RO