跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

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

arXiv 最近完成扫描:2026-11-22 21:02 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-21 23:42 — 2026-11-22 23:42(北京时间) · 点击数字查看对应简报;AI 相关包含在新增论文内。

最近完成检查:2026-11-22 21:02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 8,809 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-22 21:00(北京时间)
版本更新 · v2arXiv:2611.24917

Unified Law for Visual Tasks (The Four Laws of Computer Vision)

Sen Fang, Yalin Feng, Yancheng Zhang, Yanxin Zhang, Zonglin Lyu, Hongbin Zhong, Liwei Che, Rui Wu 等 10 位作者

原文摘要

In this paper, we propose a Unified Law for Visual Tasks, which could be further divided into Four Laws of Computer Vision, with the goal of enabling a single framework or method to uniformly train on and perform nearly all visual tasks. Our starting point is an inspiration and hypothesis: if the world information is encoded into image, which we call World Snapshots, then image processing is world processing, and image generation is World Snapshot generation. Furthermore, if all visual and visualization tasks can be reformulated as generation tasks, then a unified method, World Snapshot Models (WSMs), can perform the vast majority of visual tasks, much as large language models have largely unified natural language processing. This paper validates these laws across more than 1,000 trained and evaluated visual tasks (defined by distinct input-output mappings) and presents a unified training framework for future visual-task research and applications.

cs.CV

新论文 · v1arXiv:2611.25787

GeoPillars: A Large-Kernel Pillar Detector for Single-Sweep LiDAR Under Point Sparsity, and a Decomposition of Its Gain

Chaitanya Dumbre, Shubham Sarkar, Akash Mohapatra, Ghanasham Patil, Sheetal Girase

原文摘要

GeoPillars is a pillar-based 3D detector for single-sweep LiDAR under a hard budget of eight points per 0.4 m pillar, a budget that discards 46.6% of in-range points. It adds geometric pillar features, grouped vector attention within each pillar, a learned absolute positional prior on the bird's-eye-view (BEV) grid, a large-kernel backbone, auxiliary surface-normal supervision and a full-resolution detection head. Trained on 123k synthetic CARLA scans and evaluated on cars, it reaches 81.33 BEV AP@0.7, 13.76 points above CenterPoint at the same input budget and 1.91 points above CenterPoint at its native, denser budget. These are in-distribution figures, because the validation split is per-frame rather than scene-disjoint. A rung-by-rung decomposition shows that the new components explain little of the gain. Raising the detection-head resolution alone recovers 10.19 of the 13.76 points, the joint change of encoder, backbone, neck and positional prior adds 3.37, and the normal-supervision branch adds 0.20, which is within run-to-run variation. With heading reversals folded out, orientation error is similar for all seven models, although GeoPillars reverses headings about half as often as a resolution-matched baseline. It is also the slowest of the seven models. Evaluated zero-shot on 6,743 real nuScenes keyframes, no model transfers, and each retains 3.7% to 12.2% of its CARLA accuracy. A collection defect left LiDAR intensity constant, so every model learned from geometry alone. Code and checkpoints are publicly available.

cs.CV

新论文 · v1arXiv:2611.25776

Suppressing the Shortcut Hidden Behind the Gains of VideoLLM Fine-Tuning

Youngwoo Shin, Jongsuk Kim, Junmo Kim

原文摘要

Supervised fine-tuning (SFT) is the stage in which Video Large Language Models (VideoLLMs) advance their capability to reason over video. However, the VideoLLM also learns to answer from textual regularities of its training data, a shortcut that bypasses the video. The regularities behind the shortcut are hard to define at the data level, and the shortcut forms regardless of training epoch, data size, or backbone. The shortcut is hidden behind a rise in accuracy within the training distribution, yet it is not required for the rise and even costs SFT the gain the video offers under distribution shift. We therefore propose Video-Evidence Training via Orthogonal projection (VETO), which intervenes on the fine-tuning update where the shortcut is written rather than on the data. VETO calibrates the subspace that the text alone occupies in the activations of the base model and projects the update onto its orthogonal complement. The VideoLLM is thus left to ground its answer in the full input, with the shortcut suppressed as it forms and never defined. Across seven VideoLLMs, VETO preserves the gain of SFT on the training distribution and suppresses the shortcut. On six benchmarks under shift it gains more than SFT and answers from the full input rather than the shortcut. Code is available at https://github.com/Youngwoo-git/VETO.

cs.CV

新论文 · v1arXiv:2611.25771

Driver Gaze Target Identification via Gaze Estimation and Structured Driving Scene Understanding

Xinze Cao, Ke Wang, Deyong Guan, Yuanquan Li, Ke Zhang

原文摘要

Identifying a driver's gaze target provides object-level information for visual attention monitoring in intelligent vehicles. Gaze-zone classification and continuous attention localization provide limited information about the identity of the attended scene target. This paper proposes a modular framework that identifies object- or region-level gaze targets from synchronized in-cabin driver images and forward-view road images. The framework comprises four components: MFGaze, which combines a Vision Transformer pretrained with a masked autoencoder (MAE) and head-pose conditioning through feature-wise linear modulation (FiLM); panoptic scene understanding, which constructs a structured candidate set; polynomial ridge regression, which maps gaze features to 2D scene-image coordinates through individualized calibration; and entropy-driven target inference, which adaptively fuses boundary-distance geometry with class-level semantic priors. Experiments evaluate the framework using three public gaze datasets, a laboratory test using Cityscapes road scenes and self-collected gaze data, and the Look Both Ways (LBW) dataset. The complete framework achieves an overall Top-1 gaze target identification accuracy of 96.27% in the laboratory experiment. After sequence-specific calibration, it achieves Top-1 accuracies of 79.92% for task-relevant objects and 85.58% for the road class on LBW. MFGaze achieves the lowest mean angular errors among the compared methods, with 4.06$^\circ$, 4.23$^\circ$, and 10.52$^\circ$ on MPIIFaceGaze, ETH-XGaze, and Gaze360, respectively, and demonstrates strong cross-dataset generalization. Sensitivity analyses show stable performance under hyperparameter perturbations. These results support the framework as a source of object-level gaze information for driver monitoring.

cs.CV · cs.LG

版本更新 · v2arXiv:2610.04185

Referring Multi-Object Tracking in Moving-Camera Videos via Global Motion Compensation

Hsin-Chen Pai, Jyun-Kai Wang, Yi-Cheng Peng, Wei-Ta Chu

原文摘要

Referring multi-object tracking (RMOT) takes a video and a language expression as input and tracks all referred objects. Many tracking requirements involve how an object moves rather than how it appears. However, in a video captured by a moving camera, a parked vehicle may appear to move, while a moving vehicle may show little displacement. Existing RMOT methods relate motion with text but do not explicitly remove camera-induced motion. In this paper, we propose extracting residual motion across frames by estimating camera motion in driver-view videos and compare motion characteristics with the query expression. We consider the motion-matching extent and integrate it with the RMOT method's prediction result through late fusion. In the evaluation, we verify the performance gain of taking the motion compensation module as a plug-in across different RMOT hosts.

cs.CV

新论文 · v1arXiv:2611.25761

AdaptReg: Skip-level FiLM Adapter for Task-Specific Adaptation of a Frozen Registration Foundation Model

Shuyue Shi, Rong Yuan, Lin Tian

原文摘要

Longitudinal PSMA-PET/CT registration is a key step in assessing treatment response in prostate cancer, and it requires more than generic alignment accuracy: the deformation must preserve lesion volume, so that measured changes in metabolic tumor volume (MTV) and total lesion glycolysis (TLG) reflect treatment response rather than registration artifacts. We propose AdaptReg, which adapts a frozen registration foundation model to such task-specific requirements through a lightweight trainable adapter branch with identity-preserving initialization. Keeping uniGradICON fully frozen, we apply FiLM-style per-voxel affine modulation ($γ$, $β$) to its decoder skip connections; the modulation is generated from anatomical semantic features of a frozen TotalSegmentator encoder and supervised by a lesion volume-preservation loss. On the official Codabench validation set (20 pairs), AdaptReg achieves DSC 0.7585, HD95 6.33 mm, MTV/TLG errors of 1.68%/2.11%, and 0.0022% non-diffeomorphic voxels, improving on the uniGradICON + instance optimization baseline by $+0.05$ DSC and reducing the MTV/TLG errors by 70.9%/67.7%. On the hidden official test set (160 pairs), AdaptReg achieves CT DSC 0.816, PET DSC 0.598, and MTV/TLG errors of 4.02%/3.46%, ranking fourth among 16 teams in the final PSMAReg evaluation. Code: https://github.com/shishuyue/AdaptReg

cs.CV · cs.LG

版本更新 · v3arXiv:2602.07045

VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote Sensing

Zhiming Luo, Hebaixu Wang, Haonan Guo, Jing Zhang, Bo Du

原文摘要

Recent advancements in Multimodal Large Language Models (MLLMs) have enabled complex reasoning. However, existing remote sensing (RS) benchmarks remain heavily biased toward perception tasks, such as object recognition and scene classification. This limitation hinders the development of MLLMs for cognitively demanding RS applications. To address this, we propose a Vision Language ReaSoning Benchmark (VLRS-Bench), which is the first benchmark exclusively dedicated to complex RS reasoning. Structured across the three core dimensions of Cognition, Decision, and Prediction, VLRS-Bench comprises 2,000 question-answer pairs with an average question length of 129.87 words, spanning 14 tasks and up to eight temporal phases. VLRS-Bench is constructed via a specialized pipeline that integrates RS-specific priors and expert knowledge to ensure geospatial realism and reasoning complexity. Experimental results reveal significant bottlenecks in existing state-of-the-art MLLMs, providing critical insights for advancing multimodal reasoning within the remote sensing community.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25747

SAM 3 Sees More Than It Detects: Promptable Concept Maps Beyond Categories

Yu-Huan Wu, Yun Liu, Liangli Zhen

原文摘要

Promptable segmenters answer what a thing is. Dense prediction tasks also ask class-agnostic questions, such as what stands out or hides, how light is blocked, transmitted or reflected, and where structure lies. Robots, surveillance systems and image editors build on their answers. We study promptable concept maps (PCM), which extend SAM 3's promptable concept segmentation from noun instances to maps of concepts named by short noun phrases such as `"transparent object", with "none" as an answer. PCM-Bench groups the standard test sets of seven such tasks by the question they ask. On it, we find that SAM 3 sees more than it detects. Its semantic path responds to many of these concepts, yet a low image-level presence score can block every detection of its instance path. We present UNVEIL, which trains a copy of SAM 3's semantic path for these maps, with LoRA on copies of its last blocks. A separate presence decoder learns from verified negatives whether a concept occurs. With one text phrase per query, UNVEIL maps region concepts such as salient and camouflaged objects, shadows, transparent objects and mirrors. The same weights map thin structures such as edges and skeletons as well as object categories. Run next to SAM 3, it leaves SAM 3's own outputs unchanged. On each of the seven tasks, UNVEIL reaches the highest score among the compared promptable models, including SAM 3's official fine-tuning and pipelines built on multimodal LLMs. Code is available at https://github.com/yuhuan-wu/UNVEIL.

cs.CV · cs.AI

版本更新 · v4arXiv:2604.25322

Simulation of temporomandibular joint space changes based on rigid-body transformation using virtual and semi-virtual models: a proof-of-concept study

Agnieszka Anna Tomaka, Krzysztof Domino, Michał Tarnawski, Emil Kalinowski, Małgorzata Domino, Dariusz Pojda

原文摘要

The integration of multimodal data within a common coordinate system is essential for spatial analysis of the stomatognathic system. This proof-of-concept study aims to use a multimodal data integration methodology for digital modeling of spatial changes in the temporomandibular joint (TMJ) across various mandible positions. As two digital models were investigated, the study also aimed to investigate inter-model differences in the simulated TMJ joint spaces. A transformation tree framework was proposed to integrate cone-beam computed tomography (CBCT), facial, and dental representation images into a common coordinate system and to simulate seven mandible positions using rigid-body transformations. Data were collected from a single participant. Spatial changes in mandible positions were propagated to TMJ articular surface positions using both models, although the results were model-related. The model-based uncertainty was quantified using two metrics - the consistency error and the model disagreement. The consistency error presented anisotropy in the latero-lateral direction. The model disagreement were not uniform across mandible positions and were higher (p<0.0156) at the TMJ level (1.46 mm) than at the dental level (0.47 mm). The proposed methodology may prove useful in future research investigating the geometric relationships between mandible position and the TMJ. However, given the proof-of-concept nature of this study, the numerical findings should not be generalized to broader clinical populations.

cs.CV

新论文 · v1arXiv:2611.25731

Towards High-Fidelity Learned Video Compression

Bumyoon Kim, Yongseong Kim, Inhyuk Jeong, Byeungwoo Jeon

原文摘要

Professional video workflows operate at qualities that learned video codecs do not reach. We measure how much of a professional quality range a codec covers, from the lowest quality of the standard test conditions, VVC at QP 37, to the highest 4:2:2 grade of the production codec ProRes. To compare inter-frame coding alone, every codec receives original frames as references at the intra positions. On 10-bit YCbCr 4:2:2 test sequences, four recent learned codecs cover 24 to 38% of this range. Their encoders are feed-forward networks with a fixed latent capacity, the number of latent values per sample, of at most 0.25, and removing their quantization raises the quality by at most 1 dB. We propose a learned inter-frame codec whose encoder searches, as the encoders of conventional codecs do. It searches block motion, which a learned network refines, and it searches among learned block transforms whose latent capacity ranges up to 1, selecting the partition, the skip decisions, and the quantized coefficients by a rate-distortion cost. Our codec reaches the upper end of the range on all six sequences. With all residual blocks fixed to 16x16, whose latent capacity is 0.25, the same codec covers 55% of the range, with or without quantization.

cs.CV

新论文 · v1arXiv:2611.25730

CGM: Chaos-Guided Graph Attention and Expert Routing for Autism Stereotypy Detection

Hafsa Aslam, Yue Li, Saba Aslam, Abdur Rasool, Qiao Pan, Muhammad Rizwan, Ovidiu Bagdasar

原文摘要

Skeleton graph attention for autism video analysis weights joints by content alone, giving an erratic wrist the same standing as a still one. Stereotypy, however, is defined by how unpredictably movement unfolds rather than how much of it occurs: in our cohort, every amplitude-based kinematic descriptor falls in stereotyped clips, while windowed Sample Entropy of angular velocity alone rises (Hedges' g = +1.05). We compute this irregularity as a per-joint, per-frame tensor that structurally drives computation. The proposed chaos-guided graph attention and mixture-of-experts model (CGM) couples two mechanisms. First, a learned pairwise term added to the graph-attention logit concentrates attention on irregular joints and re-ranks the remaining edge weight toward jointly irregular pairs; its unconstrained coefficient neither vanishes nor inverts, and zeroing the tensor realigns attention in 94% of clips. Second, a gate conditioned on the same signal routes each frame to two of four experts, whose weights track frame-level irregularity. Under subject-grouped five-fold cross-validation on 116 clips, CGM reaches 0.930 balanced accuracy, exceeding the graph-attention baseline by +0.187; the component ordering replicates on the public MMASD dataset, and on held-out Panoptic Studio sessions, CGM keeps 0.86 specificity without retraining, against at most 0.35 for chaos-free baselines. In ablation, routing without irregularity yields no reliable gain, whereas chaos modulation alone contributes +0.132. A severity index from the same tensor reaches 0.87 split-half reliability, separates the cohorts with Hedges' g = +1.08, and stays consistent within children across therapy recordings, supporting video-only monitoring of stereotypy during intervention.

cs.CV · cs.LG

新论文 · v1arXiv:2611.25728

What's in the box? Revealing Object Layouts Inside Opaque Boxes via Contactless Vibration Excitation and Sensing

Ethan Turok, Matan Kichler, Shai Bagon, Mark Sheinin

原文摘要

Can we reveal what is inside an opaque box by observing its surface vibrations? Objects inside a box alter its mechanical response, providing cues about their hidden locations. We introduce a method that uses these cues to predict a box's 2D occupancy layout entirely remotely. A nearby speaker excites vibrations, which we measure on one visible wall using a grid of laser points and a camera measuring each point's speckle-pattern shifts. Our model, WhisperBox, learns to encode these vibrations into a latent representation and decode it into an occupancy map of the box's contents. The method requires no physical contact to excite or sense vibrations. We demonstrate layout recovery across various boxes and single- and multiple-object scenes, with generalization to unseen object instances, positions, orientations, and weights, as well as changes in laser placement and excitation source. Our analysis reveals that informative frequency bands need not coincide with the box's resonances and that the learned latent space captures object placement and supports arithmetic operations. These results demonstrate the potential of remote vibration sensing to infer spatial layouts hidden from view.

cs.CV

新论文 · v1arXiv:2611.25724

Verifying Before Enhancing: Target Evidence Chain Verification for Infrared Small Target Detection

Jiayi Zuo, Songwei Pei, Shuhuai Wang, Yifei Wu, Shangguang Wang

原文摘要

Infrared small target detection is essential for early warning, surveillance, remote sensing, and space-based target perception. However, infrared small targets are typically tiny, weakly textured, and boundary-blurred, making them difficult to distinguish from complex backgrounds. Moreover, target-like background structures can produce salient responses across multiple scales, making response strength alone insufficient for reliable target discrimination. To address this challenge, we propose VBE-UNet, a Target Evidence Chain Verification Network that assesses candidate reliability beyond response magnitude through complementary evidence cues. Specifically, counterfactual background explanation models local target evidence, while joint evidence verification integrates cross-scale support and perturbation-based contribution verification to guide feature recomposition. The resulting reliability estimates guide selective feature refinement, promoting target-relevant responses while reducing unsupported background activations. Extensive experiments on IRSTD-1K, NUDT-SIRST, and NUAA-SIRST demonstrate that VBE-UNet achieves superior detection accuracy and lower false-alarm rates compared with state-of-the-art methods. Ablation studies and evidence reliability analysis further validate the effectiveness of the proposed verification framework.

cs.CV · cs.AI

版本更新 · v2arXiv:2608.00574

Relax Within, Balance Across: Load Balancing under Composition Shifts in Vision-Language Mixture-of-Experts

Ziang Wu, Peng Jin, Qishen Yin, Munan Ning, Hao Li, Peizhen Zhang, Huihui Zhou, Li Yuan

原文摘要

Vision-language mixture-of-experts (MoE) models such as Qwen3-VL need balanced loads for fast parallel serving. Standard training pools image and text tokens into one auxiliary loss, assuming training balance holds at inference. Yet we find a surprising mismatch: on a fixed router, balance shifts sharply whenever resolution, dynamic tiling, or image count changes the image-to-text token ratio. Splitting load by modality reveals cross-modal load cancellation: opposing image and text errors cancel near the training ratio, hiding strong skew until the mix changes. To quantify this shift, we derive an exact quadratic law: under fixed modality profiles, one reference run predicts the full response curve, and the image-text gap governs sensitivity. Meanwhile, patches within an image route similarly while patch counts vary, letting large images dominate flat pooling. We propose ReBA (Relax Within, Balance Across) to separate modality losses by token fraction and weight images equally, letting each image specialize while keeping overall visual load even. Across four split backbones, ReBA turns fragile single-ratio balance into stable balance across resolutions, tilings, and image counts without hurting accuracy. Large modality gaps in released native MoEs also show its promise for native post-training. Code is available at https://github.com/ZiangWu-77/ReBA.

cs.CV · cs.AI

新论文 · v1arXiv:2611.25722

DACA: Dual-Anchor Collaborative Agent for Zero-Shot 3D Visual Grounding

Jiaming Liu, Linghe Kong, Guixu Zhang, Huaxi Huang

原文摘要

3D visual grounding (3D-VG) is a task that bridges the natural language and 3D space, serving as a foundational capability for embodied intelligence and human-computer interaction. Although recent 3D-VG agents overcome the reliance on pre-processed 3D point clouds, they essentially employ a unidirectional, pipeline-style tool-calling architecture. This architecture separates semantic understanding from geometric reconstruction, leading to error accumulation and an inability to autonomously recover from failures. To address this flaw, this paper proposes the Dual-Anchor Collaborative Agent (DACA), which reinterprets 3D-VG as a semantic-geometric dual-anchor collaborative reasoning paradigm. DACA comprises two complementary specialized tools: the semantic anchor tool holds the visual semantic features of the target and achieves efficient target tracking via optical flow and VLM local verification; the geometric anchor tool holds the 3D spatial geometric features of the target and performs global spatial reasoning via voxelization and multi-keypoint projection. The two components exchange information bidirectionally via a standardized tool call protocol, autonomously deciding on the next perception-action step to form a closed-loop optimization. Experiments on the ScanRefer and Nr3D benchmarks demonstrate that zero-shot DACA achieves an overall Acc@0.25 of 73.6\% on ScanRefer and 70.4\% overall accuracy on Nr3D, far surpassing the latest zero-shot 3D-VG methods. The code and models are available at https://github.com/liujia99/DACA

cs.CV

新论文 · v1arXiv:2611.25719

SteerTrace: Tracing How Target Attacks Steer World Action Models

Yukun Dai, Tianshi Wang, Fengling Li, Jingjing Li, Xin Li, Lei Zhu

原文摘要

World action models (WAMs) predict future videos and actions with one backbone, and their imagined future is often seen as a safety signal. We introduce SteerTrace, a targeted universal attack on WAMs that also traces its effect inside the model. One $\ell_\infty$-bounded (4/255) perturbation per model, shared across frames, tasks, and camera views, pushes the executed action toward an attacker-chosen target. On eight WAMs from four families (FastWAM, Faster-WAM, OpenWAM and LingBot-VA) on LIBERO and RoboTwin, it drives task success close to zero and moves the attacked action toward the target. Same-budget noise and BadWAM produce little action shift in the target direction. We use the signed targeted effect to measure how much of the effect each intervention removes or reproduces. Under the standard attack, restoring future tokens removes 61-94% of the targeted effect in the five models whose action experts attend to them. When the attack is constrained to keep the predicted future close to the clean prediction, the targeted effect can become more dependent on current-frame tokens. In three of these five models, restoring current-frame tokens removes 87-99% of the effect, compared with 9-15% for future tokens. In six models, restoring just 0.36% of the FFN neurons in layers 10-29 of the video expert removes 72-96% of the targeted effect. Residual directions 2-16 hold only 11-18% of the shift energy, yet removing them cancels most of the targeted effect.

cs.CV · cs.AI

版本更新 · v2arXiv:2611.19247

GameWM: Toward Next-Generation Video Games with Interaction-Centric World Models

Bing He, Runze Wang, Fei Zha, Zhongyuan Wu, Ke Xu, Tao Zhuang, Yuxuan Xie, Zhongyuan Liu

原文摘要

For more than half a century, video games have pursued better graphics, more natural interaction, and more engaging gameplay. Generative video models (VMs) now bear on all three. Neural networks already draw most of the pixels in shipped games, and recent world models let a lightweight game engine keep the world state while a VM turns the engine's coarse proxy video into final frames. These systems, however, treat the VM as a renderer that only restyles motion the engine has already authored, which leaves most of its generative capacity unused and limits the diversity a game can offer. We present GameWM, a design for next-generation games built on a clear division of labor. The GameWM-engine keeps what must be exact: rules, state, camera, and the layout of the world, which also spares the video model from having to remember it. The GameWM-VM generates what is expensive to author by hand: the look of the world and the detail of the player's interactions. One game mechanic can then be realized in many visually and physically distinct ways, while its outcome stays exactly as the engine computed it. To realize this division of labor, we build GameWM as a complete system: a data engine centered on interactions rather than exploration, an interface through which authored character sheets, scene art, and skill descriptions enter the model, and a model family from 5B to 33B parameters with a real-time causal variant for play. Together they give every player a fresh version of the same game: each player's own character, world, and skills turn the same engine mechanics into a new experience, while every event keeps the timing and outcome the GameWM-engine computed.

cs.CV

新论文 · v1arXiv:2611.25713

Interpreting DeepStack-Style Vision-Language Models: Do Input or Deeper-Layer Visual Tokens Drive Answers?

Yucheng Du, Yi Nian, Ruixue Lian, Yue Zhao, Xiyang Hu

原文摘要

DeepStack-style vision-language models feed visual tokens to the language model at its input, and again at deeper layers. We call these the main entry and the later entries. What do the later entries add when the model already has the image? We give the entries versions that differ in one object's color and see which one the answer follows. On photographs, the original DeepStack follows the later entries, while Qwen3-VL-8B/32B follow the main entry. Does weakening the main entry give the later features more influence? On synthetic images, we keep this conflict and reduce color saturation at the main entry only. The unchanged later features gain a stronger effect on the relative scores of the two colors, in all four models, including Granite Vision. This holds even under mild desaturation, when accuracy without the conflict stays at 100%. To test whether later features can also correct errors, we degrade both entries and restore only the later ones. The same blur costs both Qwen models 50 percentage points of accuracy on stripe orientation. The 32B model recovers 48 points and the 8B model only 8. Accuracy with one clean entry predicted which entry each model can lose, and five of six tested predictions held on new GQA attribute questions. With the other entry zeroed, Qwen3-VL-8B loses only 0.3 points on its main entry alone, and DeepStack at most 3.45 points on either entry alone. In split inference on these questions, DeepStack can then send only its main-entry features at higher precision. This takes 49% fewer bytes than all entries at a shared precision, at similar accuracy.

cs.CV

新论文 · v1arXiv:2611.25712

SkillLens: Action-Guided Dense Visual Dynamics for Proficiency Estimation

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

原文摘要

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

cs.CV

新论文 · v1arXiv:2611.25711

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

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

原文摘要

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

cs.CV

版本更新 · v2arXiv:2501.12935

OMINI: Towards Consistent 3D Object Manipulation via Generative Texturing and Adaptive Lighting

Ruisi Zhao, Zechuan Zhang, Zongxin Yang, Yi Yang

原文摘要

Enabling object manipulation based on a single static image, from geometric editing to animation, remains a significant challenge. Existing methods often struggle to jointly support these tasks, while also suffering from fidelity degradation in object appearance and scene illumination. In this work, we introduce OMINI, a unified framework that addresses these challenges through two complementary strategies. First, OMINI lifts the 2D object into a 3D representation and adopts a Refine-before-Render design. Both geometric editing and animation are then performed by manipulating and rendering the refined 3D asset, maintaining appearance consistency throughout the manipulation process. Second, we propose two dedicated modules for fidelity enhancement: TextuRefiner refines rendered views of the 3D asset under appearance and geometric guidance, thereby generating fine-grained texture details; IllumiCorrector corrects environmental illumination using HSL-based color correction and VLM-guided intensity optimization, enabling visually plausible renderings with shadows. Extensive experiments demonstrate that OMINI outperforms existing methods, producing visually consistent results. The GPU stages of OMINI are run on a single NVIDIA RTX 3090.

cs.CV

新论文 · v1arXiv:2611.25708

Slide2PPT: Native PowerPoint Reconstruction with Localization-Guided Refinement

Baoliang Chen, Xinlong Bu, Lingyu Zhu, Xiangjie Sui

原文摘要

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

cs.CV

版本更新 · v2arXiv:2611.23615

Weight Space Programming for Vision Language Model Repair

Avinash Goutham Aluguvelly

原文摘要

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

cs.CV · cs.AI

版本更新 · v2arXiv:2608.11770

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

Vaishnav Raju

原文摘要

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

cs.CV · cs.DC · cs.LG

新论文 · v1arXiv:2611.25696

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

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

原文摘要

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

cs.CV

新论文 · v1arXiv:2611.25689

D3-Cache: Accelerating Diffusion Models with Dynamic Mode Decomposition

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

原文摘要

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

cs.CV

版本更新 · v2arXiv:2604.02930

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

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

原文摘要

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

cs.CV

版本更新 · v2arXiv:2609.16811

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

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

原文摘要

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

cs.CV

新论文 · v1arXiv:2611.25680

Beyond Entity Recognition: Vision-Centric Knowledge Visual Question Answering

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

原文摘要

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

cs.CV · cs.AI

新论文 · v1arXiv:2611.25675

Minimal Memory for Correctable Visual Continuation

Xiyang Zhang, Yuanhe Tian, Hongzhi Wang, Yan Song

原文摘要

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

cs.CV