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

+1111新增论文
+874其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 07:46 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 08:22 — 2026-11-20 08:22(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:2026-11-20 07:46最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 11 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 07:44(北京时间)
新论文 · v1arXiv:2611.22084

When Lower Harm Misleads: Auditing Concept Corrections

Tianyou Lai, Wentao Yue, Hongji Li, Chaoyuan Hao, Qilei Li

原文摘要

An expert who corrects a concept prediction, such as a BI-RADS descriptor in breast ultrasound, expects the diagnosis to improve. Objectives that reduce the harm of such corrections are judged by harm and accuracy, yet harm also falls when a model responds less to every correction or starts from a worse uncorrected prediction, the reference for harm. We propose a correction audit, a reproducible evaluation protocol that separates these explanations: it splits each correction into harm and useful gain on identical events, separates the starting prediction from the correction response, and compares objectives with amplitude baselines matched in source harm. On three breast-ultrasound sources, worst-case correction training, evaluated from the mean-case model's start, lowers harm but gives up more useful gain in all 21 source comparisons pooled over six seeds, raising the corrected negative log-likelihood (NLL); from the same start, selecting between the objectives by harm picks the less helpful model on all three sources. On CUB, a monotonic harm penalty at its reported weight lowers path-level harm in all 80 concept sets while raising the NLL in all 80, almost entirely before any correction. At a fixed start, rescaling both responses to the same source harm reproduces the penalty's mean harm, useful gain and NLL on single-concept corrections within a prespecified margin of 0.0005 nat, although the two responses point in different directions. Lower harm therefore signals better corrections only when it is read together with useful gain, absolute risk and the start it is measured from.

cs.AI · cs.CV

新论文 · v1arXiv:2611.21955

SCAN: Site-Aware Collaborative Privacy-Preserving Adaptation of Vision-Language Models for Neurological Disease Classification

Nikhil J. Dhinagar, Rishab Pendam, Harmony S. Cen, Sophia I. Thomopoulos, John P. John, Mahir H. Khan, Sook-Lei Liew, Erik Kaestner 等 10 位作者

原文摘要

Worldwide neuroimaging data could strengthen diagnostic foundation models, but privacy rules often prevent centralizing brain MRI scans. We present SCAN, a site-aware collaborative adaptation framework for Neurological Disease Classification that lets new sites adapt a 3D medical vision-language model (VLM) without retraining or sharing patient scans. Each site keeps exact class prototypes for local prediction and can share privacy-protected class summaries: norm-bounded sums and counts perturbed once with calibrated noise. Using 7,641 scans from 67 sites across 12 countries, covering Alzheimer's disease (AD), stroke, epilepsy and controls, we assess local adaptation, cross-site benefits, and effects on existing sites. At seven unseen sites, the frozen VLM's zero-shot AUCs were 0.833-0.945 for AD and stroke. Training-free local prototypes improved epilepsy AUC at three sites from 0.598/0.625/0.508 to 0.684/0.729/0.762 and AD AUC at one site from 0.833 to 0.863, nearly matching a classifier trained at each site (mean AUC 0.757 vs. 0.759). With differential privacy ($ε$ = 4), new sites contributed without materially reducing accuracy at existing sites (AUC change $\leq$0.2%), although gains from sharing were limited, and membership attacks performed near chance. SCAN offers hospitals a worldwide framework to adapt and share brain MRI VLMs without exchanging scans or retraining.

cs.CV · eess.IV

新论文 · v1arXiv:2611.20546

A Gaussian Primitive Data Management Framework for Efficient 3DGS Trajectory Rendering

Haolun Ma, Ziyi Liu, Zizhuo Xu, Chuhan Hu, Lei Li

原文摘要

Trajectory rendering, which renders novel views of a reconstructed 3D scene along a camera path, is a core operation in digital twins and autonomous inspection. Structured 3D Gaussian Splatting (3DGS) renders a single view in real time by decoding sparse anchors into Gaussians on demand, but it renders a trajectory view by view: every view projects all anchors to select them, re-decodes anchors already requested by neighboring views, and runs all steps on the GPU while the CPU idles. We treat this as a spatial data management problem, where anchors are spatial objects, views are range queries, and decoded Gaussians are shared derived data, and propose GDM-GS, which removes redundancy at three levels. Within a view, an anchor index and an occluder index answer each view as a holed-frustum range query, so out-of-view and provably hidden anchors are never decoded. Across views, shared materialization decodes each requested anchor once per group of consecutive views while preserving each view's selection. Across processors, a hybrid pipeline balances selections between the CPU and the GPU before grouped decoding under bounded memory. Experiments on large-scale public scenes show that GDM-GS substantially reduces trajectory rendering latency while preserving image quality.

cs.DB · cs.CV · cs.GR

版本更新 · v2arXiv:2609.02349

GlyphAnchor: Enhancing Visual Text Rendering via Position-Anchored Glyph Priors

Qiang Xiang, Shuang Sun, Binglei Li, Yibo Chen, Xu Tang, Yao Hu, Junping Zhang

原文摘要

Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arranged text or rare characters. Existing approaches either improve native text rendering through stronger backbones and data-centric training without explicit glyph priors, or incorporate glyph priors through specialized designs that remain insufficiently accurate and robust under challenging scenarios. We introduce GlyphAnchor, a novel text-rendering enhancement method for both text-to-image and image-editing diffusion transformer models. GlyphAnchor enhances the backbone with lightweight glyph patch conditions whose positions are anchored to the target image through the model's native positional encoding. We train this capability with staged supervised finetuning and further refine it with text-aware post-training to improve robustness. We also introduce InfoTextBench, a benchmark for evaluating text-rich visual text rendering in both generation and editing settings. Experiments across multiple backbones and benchmarks, including long, complex, and densely arranged text and rare character scenarios, show that GlyphAnchor consistently improves text fidelity while preserving overall image quality.

cs.CV

版本更新 · v3arXiv:2602.13585

Diff-Aid: Inference-time Adaptive Interaction Denoising for Rectified Text-to-Image Generation

Binglei Li, Mengping Yang, Zhiyu Tan, Qiang Xiang, Junping Zhang, Hao Li

原文摘要

Recent text-to-image (T2I) diffusion models have achieved remarkable advancement, yet faithfully following complex textual descriptions remains challenging due to insufficient interactions between textual and visual features. Prior approaches enhance such interactions via architectural design or handcrafted textual condition weighting, but lack flexibility and overlook the dynamic interactions across different blocks and denoising stages. To provide a more flexible and efficient solution to this problem, we propose Diff-Aid, a lightweight inference-time method that adaptively adjusts per-token text and image interactions across transformer blocks and denoising timesteps. Beyond improving generation quality, Diff-Aid yields interpretable modulation patterns that reveal how different blocks, timesteps, and textual tokens contribute to semantic alignment during denoising. As a plug-and-play module, Diff-Aid can be seamlessly integrated into downstream applications for further improvement, including style LoRAs, controllable generation, and zero-shot editing. Experiments on strong baselines (SD 3.5 and FLUX) demonstrate consistent improvements in prompt adherence, visual quality, and human preference across various metrics. Our code and models will be released.

cs.CV

新论文 · v1arXiv:2611.15059

Test-Time Selective Adaptation for Cross-Modal UAV Object Tracking with Token Shift

Yun Xiao, Hailong Ye, Zhicheng Zhao, Lei Liu, Amir Hussain

原文摘要

Cross-modal unmanned aerial vehicle (UAV) object tracking faces modality-induced appearance discrepancies and abrupt target-position shifts that can arise from modality switching, UAV motion, and inter-sensor offsets. Although existing methods model modality and spatial variations, they primarily rely on offline representation learning and offer limited localization-oriented adaptation during testing. To address these challenges, we propose Test-Time Selective Adaptation with Token Shift (TSAT), which derives spatial and temporal adaptation signals from unlabeled test sequences for online optimization. Specifically, we design a controllable token shift auxiliary task, which imposes explicit spatial correspondence between predefined token translations and resultant localization offsets, generating stable annotation-free spatial adaptation signals. Furthermore, we introduce a temporal backward prediction auxiliary task to exploit frame-wise temporal dependencies, effectively mitigating cumulative localization errors in continuous tracking. To suppress interference from unreliable tracking samples, we develop a reliability-aware update gating strategy to screen valid adaptation signals and stabilize online parameter updates. Experiments on CM-UOT demonstrate that TSAT achieves state-of-the-art performance against existing test-time adaptation methods, exhibiting superior robustness under frequent modality switching and severe spatial displacement. Experiments across tracking frameworks and datasets further validate the effectiveness and generalization capability of TSAT.

cs.CV

版本更新 · v2arXiv:2604.23195

AnalogRetriever: Learning Cross-Modal Representations for Analog Circuit Retrieval

Yihan Wang, Lei Li, Yao Lai, Jing Wang, Yan Lu

原文摘要

Analog circuit design relies heavily on reusing existing intellectual property (IP), yet searching across heterogeneous representations such as SPICE netlists, schematics, and functional descriptions remains challenging. Existing methods are largely limited to exact matching within a single modality, failing to capture cross-modal semantic relationships. To bridge this gap, we present AnalogRetriever, a unified tri-modal retrieval framework for analog circuit search. We first build a high-quality dataset on top of Masala-CHAI through a two-stage repair pipeline that raises the netlist compile rate from 22.0\% to 99.97\%. Built on this foundation, AnalogRetriever encodes schematics and descriptions with a vision-language model and netlists with a port-aware relational graph convolutional network, mapping all three modalities into a shared embedding space via curriculum contrastive learning. Experiments show that AnalogRetriever achieves an average Recall@1 of 75.2\% across all six cross-modal retrieval directions, significantly outperforming existing baselines. When integrated into the AnalogCoder agentic framework as a retrieval-augmented generation module, it consistently improves functional pass rates and enables previously unsolved tasks to be completed.

cs.CV · cs.AI

版本更新 · v3arXiv:2606.08043

OmniFaceRig: Fully Automatic Inner-Mouth-Aware Face Rigging Across Diverse 3D Character Topologies

Chao Wang, Guangyao Ma, John Doublestein, Junming Chen, Yiming Lin, Zhaoen Su, Xiaomin Luo, Yushan Yin 等 14 位作者

原文摘要

Facial rigging--creating Facial Action Coding System (FACS) blendshapes and inner-mouth geometry (teeth, gums, and tongue)--remains a major bottleneck in 3D character production. We present OmniFaceRig, a fully automatic end-to-end pipeline that converts a static surface-only 3D character mesh, with no pre-modeled oral cavity, into an inner-mouth-aware FACS rig with up to 155 blendshapes, procedurally fitted teeth, gums, and tongue, and re-packed UV/texture. It supports humans, humanoids, and long- and short-muzzled animals with no manual landmarks, user-provided templates, or per-asset setup. OmniFaceRig combines a hybrid vision-language and computer vision riggability checker, a four-model face segmentation ensemble, keypoint-driven template registration, procedural inner-mouth construction, and collision-aware blendshape transfer. For non-human characters, it selects topology-specific templates with a nose-landmark-free design and uses as-rigid-as-possible deformation with signed-distance-field constraints to reduce teeth-face intersections. We also introduce Omni-Bench, an open-source benchmark of more than 1,000 biped 3D characters rigged with FACS blendshapes and inner-mouth geometry, spanning humans, humanoids, cats, dogs, and other animals. Experiments show high rigging success, nearly complete face detection recall, low inner-mouth penetration, and 20-30 s end-to-end latency per asset on a single A100 GPU.

cs.GR · cs.CV

版本更新 · v2arXiv:2605.04503

DiffCap-Bench: A Comprehensive, Challenging, Robust Benchmark for Image Difference Captioning

Yuancheng Wei, Haojie Zhang, Linli Yao, Lei Li, Jiali Chen, Tao Huang, Yiting Lu, Duojun Huang 等 10 位作者

原文摘要

Image Difference Captioning (IDC) generates natural language descriptions that precisely identify differences between two images, serving as a key benchmark for fine-grained change perception, cross-modal reasoning, and image editing data construction. However, existing benchmarks lack diversity and compositional complexity, and standard lexical-overlap metrics (e.g., BLEU, METEOR) fail to capture semantic consistency or penalize hallucinations, which together prevent a comprehensive and robust evaluation of multimodal large language models (MLLMs) on IDC. To address these gaps, we introduce DiffCap-Bench, a comprehensive IDC benchmark covering ten distinct difference categories to ensure diversity and compositional complexity. Furthermore, we propose an LLM-as-a-Judge evaluation protocol grounded in human-validated Difference Lists, enabling a robust assessment of models' ability to both capture and describe visual changes. Through extensive evaluation of state-of-the-art MLLMs, we reveal significant performance gaps between proprietary and open-source models, highlight the critical importance of reasoning capability, and identify clear limitations in model scaling. Our framework also demonstrates strong alignment with human expert judgments and strong correlation with downstream image editing data construction quality. These findings establish DiffCap-Bench as both a reliable IDC evaluation framework and a practical predictor of downstream utility. The benchmark and code will be made publicly available to support further research.

cs.CV · cs.AI

版本更新 · v2arXiv:2610.16914

FOCUS: A Subspecialty Foundation Model for Intraoperative Central Nervous System Pathology

Xing Liu, Yifan Guo, Hongtai Lv, Lei Lou, Yuyi Tan, Jiang Du, Xijia Zhang, Ming Zhang 等 21 位作者

原文摘要

Intraoperative frozen-section diagnosis of central nervous system (CNS) lesions guides surgical decisions but is challenged by artefacts, diagnostic complexity and time constraints. Most pathology foundation models have limited exposure to CNS frozen tissue. Here we present FOCUS, a subspecialty foundation model pretrained on 27,930 frozen-section whole-slide images enriched for CNS tissue. FOCUS ranked first across all 11 diagnostic and 12 biomarker-prediction tasks in the internal test cohort, achieving mean AUCs of 0.969 and 0.877, respectively. This advantage was retained in the temporal and external test cohorts. We further organized a WHO-aligned diagnostic hierarchy, where FOCUS also outperformed comparator models. In a reader study, FOCUS assistance enabled junior readers to approach or exceed unassisted senior readers in hierarchical diagnostic accuracy and granularity. More importantly, FOCUS assistance enabled readers to correctly identify a mean of 63.0% of initially missed lymphoma cases (73.2% among junior readers), potentially avoiding unnecessary extensive resection. These findings highlight the potential of FOCUS to provide clinically actionable support for intraoperative CNS pathology and inform surgical decisions.

cs.CV

首次观测 · 记录 #1ACL Anthology · ACL 2026:acl:2026.acl-long.571ACL Anthology · ACL 2026

Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters

Zhiyu Xu Peking University, Lean Wang DeepSeek and Peking University, Yuanxin Liu Peking University, Lei Li, Hao Zhou Tencent, Fandong Meng WeChat AI, Tencent Inc., Jie Zhou, Xu Sun Peking University

原文摘要

Vision-Language Models (VLMs) have demonstrated remarkable proficiency in general multi-modal understanding; yet they struggle to efficiently acquire continually evolving domain-specific skills. Conventional approaches to enhancing VLM capabilities, such as Supervised Fine-Tuning (SFT), require extensive dataset curation and substantial computational resources. Model merging has emerged as an efficient alternative that enables the transfer of domain-specific expertise from Large Language Models (LLMs) to VLMs without incurring additional training data requirements or significant computational overhead. Unlike conventional merging of homogeneous LLMs, which mainly aggregates existing capabilities, cross-modal skill injection aims to induce emergent cross-modal capabilities by integrating a domain-expert LLM into a VLM. However, existing research lacks a systematic analysis of the applicability and methodology of cross-modal skill injection. In this study, we investigate cross-modal skill injection across three main aspects: scenarios, methods, and hyperparameters. For scenarios, we find that cross-modal skill injection generally performs well in instruction-following and cross-lingual settings, yet struggles with mathematical reasoning. For methods, we find that classic approaches such as TA and DARE consistently achieve superior performance over alternative merging methods. We also provide a systematic and quantitative analysis of the hyperparameter tuning that these classic methods critically depend on.

cs.CL · cs.CV

Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · 2026 · 正式发表