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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+91新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 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 04:20 — 2026-11-22 04:20(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:2026-11-21 12:19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 1,859 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.26613

AgentRoboCritic:理解前沿智能体在直接机器人控制中的能力

AgentRoboCritic: Understanding the Capability of Frontier Agents on Direct Robot Control

Yiyang Du, Yuxuan Kuang, Qitao Zhao, Yixuan Wang, Zhanqiu Guo, Yi Xu, Xin Li, Wenbin He 等 10 位作者

AI 速读 基于摘要

作者提出以意图为依据的动作级批评框架 AgentRoboCritic,在12个操作基准上系统分析前沿多模态语言智能体直接输出底层动作控制机器人的能力与失败模式。

cs.RO · cs.CL · cs.CV

查看原文摘要

Frontier multimodal language agents such as GPT-6 Astra have demonstrated strong capabilities in controlling robots directly via low-level numerical actions without high-level primitives. However, existing benchmarks report only episode-level success rates, which show neither how these agents succeed nor where they fail. In this paper, we present a systematic action-level analysis of frontier agents on direct robot control across 12 manipulation benchmarks. We introduce AgentRoboCritic, an intent-grounded critique framework in which the policy agent states a local intent alongside each action, and a critic evaluates the action's outcome and failure mode against this intent. Our action-level analysis demonstrates the promising capabilities of frontier agents on direct robot control, including closed-loop recovery from local execution failures, reliable semantic grounding across diverse scenes, and strong zero-shot manipulation without task-specific adaptation. It also identifies their current limitations, including task-relevant physical execution bottlenecks such as grasping and alignment, and uneven recovery across failure modes. Finally, we validate our critic on a 400-action human-annotated benchmark and release a dataset of 12,844 annotated actions alongside a fine-tuned open-source critic, Muse-Glimmer-30B, whose failure-mode accuracy rises from 32.58% to 74.24%, enabling low-cost action-level analysis.

新论文 · v1arXiv:2611.26595

Coda-DaVinci:用代码到视频重新构想视频生成

Coda-DaVinci: Reimagining Video Generation with Code2Video

Yiyan Ji, Qixun Wang, Yang Shi, Zhuoran Zhang, Yifan Xu, Tengfei Liu, Yuqi Tang, Xiaohan Zhang 等 23 位作者

AI 速读 基于摘要

通过受控实验揭示Code2Video中代理粒度、物理模拟和提示的权衡,并提出任务自适应多智能体框架Coda-DaVinci以提升视频生成质量。

cs.CV

查看原文摘要

Code2Video uses agent-authored 3D proxies to guide video generation, enabling explicit control over structure and dynamics. However, how to construct proxies and prompts for optimal downstream quality remains underexplored, as do the capabilities and limitations of this paradigm. Through controlled experiments and blinded human evaluation, we study proxy granularity, physics simulation, and prompting. The results reveal task-dependent trade-offs: coarse proxies favor natural motion, while medium-grained proxies favor consistency. Physics simulation and proxy-aligned prompting further improve average quality. Guided by these findings, we introduce Coda-DaVinci, a task-adaptive agentic framework for Code2Video generation that selects between proxy-guided and direct generation, adapts modeling granularity to each entity, and coordinates simulation with proxy-grounded prompting. Its multi-agent harness preserves scene assets and guides repairs through visual inspection and independent review. Experiments demonstrate leading instruction following on VTR and scene consistency on R2M, improved physical plausibility over direct generation, and higher visual realism than the compared Code2Video baselines. Long-video evaluations further show gains in event structure and consistency across successive interactions, while revealing limitations in transition stability and adherence to scene settings.

新论文 · v1arXiv:2611.26569

文本感知、视觉盲区:多模态图像编辑系统如何处理不安全输入

Text-Aware, Vision-Blind: How Multimodal Image Editing Systems Handle Unsafe Inputs

Ziqing Yang, Yixin Wu, Michael Backes, Yang Zhang

AI 速读 基于摘要

作者构建 EditSafetyBench 基准,发现主流图像编辑系统存在系统性的文本-视觉安全错配:对不安全文本指令拒绝率高,但对携带风险的不安全图像拒绝率低。

cs.CR · cs.CV · cs.LG

查看原文摘要

Multimodal image generation systems have made rapid progress and increasingly emphasize content safety. However, their safety mechanisms tend to rely on a single modality and lack joint consideration of both visual content and text prompts, particularly in instruction-guided image editing, where the uploaded image may itself carry risk. We thus introduce EditSafetyBench, a benchmark that measures system-level safety awareness of advanced image editing systems, containing 5,940 image-instruction pairs, covering safe and unsafe images across 11 risk categories and three edit intents. We then probe the benchmark dataset on four systems, including Gemini, GPT, Qwen API, and Qwen Local. Based on our evaluation, we observe a systematic text-vision safety mismatch: Gemini and GPT refuse 87.1\% and 81.6\% cases containing unsafe-intent editing prompts, while only refusing 24.2\% and 22.4\% cases with both unsafe images and neutral instructions. At the category level, most risks are considered inconsistently by different systems, e.g., GPT allows 70.4\% editing attempts of unsafe political content while Gemini only allows 34.8\%. Notably, sexual content shows the strongest visual sensitivity, likely benefiting from mature NSFW identification works. Our findings highlight the need for safety guardrails that jointly reason over both visual and textual modalities in image editing systems.

版本更新 · v3arXiv:2605.00310

超越视觉保真度:通过下游任务集成评估大规模遥感影像的超分辨率模型

Beyond Visual Fidelity: Benchmarking Super-Resolution Models for Large-Scale Remote Sensing Imagery via Downstream Task Integration

Zhili Li, Kangyang Chai, Zhihao Wang, Xiaowei Jia, Yanhua Li, Gengchen Mai, Sergii Skakun, Zhe Zhu 等 10 位作者

AI 速读 基于摘要

提出GeoSR-Bench基准,将下游任务性能纳入超分辨率模型评估,发现传统保真度指标与任务收益不相关甚至负相关。

cs.CV · cs.AI · cs.LG

查看原文摘要

Super-resolution (SR) techniques have made major advances in reconstructing high-resolution images from low-resolution inputs. The increased resolution provides visual enhancement and utility for monitoring tasks. In particular, SR has been increasingly developed for satellite-based Earth observation, with applications in urban planning, agriculture, ecology, and disaster response. However, existing SR studies and benchmarks typically use fidelity metrics such as PSNR or SSIM, whereas the true utility of super-resolved images lies in supporting downstream tasks such as land cover classification, biomass estimation, and change detection. To bridge this gap, we introduce GeoSR-Bench, a downstream task-integrated SR benchmark dataset to evaluate SR models beyond fidelity metrics. GeoSR-Bench comprises spatially co-located, temporally aligned, and quality-controlled image pairs from about 36,000 locations across diverse land covers, spanning resolutions from 500m to 0.6m. To the best of our knowledge, GeoSR-Bench is the first SR benchmark that directly connects improved image resolution from SR models with downstream Earth monitoring tasks, including land cover segmentation, infrastructure mapping, and biophysical variable estimation. Using GeoSR-Bench, we benchmark GAN, transformer, neural operator, and diffusion-based SR models on perceptual quality and downstream task performance. We conduct experiments with 270 settings, covering 2 cross-platform SR tasks, 9 SR models, 3 downstream task models, and 5 downstream tasks for each SR task. The results show that improvements in traditional SR metrics often do not correlate with gains in task performance, and the correlations can be negative, indicating that these metrics provide limited guidance for selecting superior models for downstream tasks. This reveals the need to integrate downstream tasks into SR model development and evaluation.

版本更新 · v2arXiv:2602.06363

面向不确定模态的鲁棒行人检测

Robust Pedestrian Detection with Uncertain Modality

Qian Bie, Xiao Wang, Bin Yang, Zhixi Yu, Jun Chen, Xin Xu

AI 速读 基于摘要

作者构建RGB-NIR-TIR三元组数据集并提出AUNet,以在模态组合不确定时实现鲁棒行人检测。

cs.CV

查看原文摘要

Existing cross-modal pedestrian detection (CMPD) employs complementary information from RGB and thermal-infrared (TIR) modalities to detect pedestrians in 24h-surveillance systems.RGB captures rich pedestrian details under daylight, while TIR excels at night. However, TIR focuses primarily on the person's silhouette, neglecting critical texture details essential for detection. While the near-infrared (NIR) captures texture under low-light conditions, which effectively alleviates performance issues of RGB and detail loss in TIR, thereby reducing missed detections. To this end, we construct a new Triplet RGB-NIR-TIR (TRNT) dataset, comprising 8,281 pixel-aligned image triplets, establishing a comprehensive foundation for algorithmic research. However, due to the variable nature of real-world scenarios, imaging devices may not always capture all three modalities simultaneously. This results in input data with unpredictable combinations of modal types, which challenge existing CMPD methods that fail to extract robust pedestrian information under arbitrary input combinations, leading to significant performance degradation. To address these challenges, we propose the Adaptive Uncertainty-aware Network (AUNet) for accurately discriminating modal availability and fully utilizing the available information under uncertain inputs. Specifically, we introduce Unified Modality Validation Refinement (UMVR), which includes an uncertainty-aware router to validate modal availability and a semantic refinement to ensure the reliability of information within the modality. Furthermore, we design a Modality-Aware Interaction (MAI) module to adaptively activate or deactivate its internal interaction mechanisms per UMVR output, enabling effective complementary information fusion from available modalities.

版本更新 · v3arXiv:2609.39601

GroundingPI:面向物理智能的视觉基元定位基础模型

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang 等 26 位作者

AI 速读 基于摘要

作者提出一个4B参数的定位基础模型GroundingPI,以点和框作为共享词表中的量化坐标,在34个定位基准上取得领先,并作为视觉骨干提升机器人与自动驾驶下游任务表现。

cs.CV · cs.AI · cs.LG · cs.RO

查看原文摘要

Precise grounding matters. It specifies which object is the target and where that object is, even in clutter and for tiny objects, and it has to be fast enough for closed-loop control. Yet vision-language-action (VLA) and world-action models (WAMs) take perception from general-purpose vision-language and video-generation backbones, which still fail in these settings. We introduce GroundingPI, a 4B grounding foundation model that generates points and boxes as quantized coordinates in a shared vocabulary. Training combines multimodal and spatial pretraining, supervised fine-tuning, and reinforcement learning with GRPO, using supervision from public datasets and dedicated data engines. Against 44 baselines across 34 grounding benchmarks spanning 11 perceptual capabilities, GroundingPI establishes a new state of the art, averaging 73.68%, above the larger GPT-6 Astra (71.54%). As a downstream visual backbone, GroundingPI improves performance on robotic manipulation and autonomous driving. Across RoboTwin 2.0 and RoboCasa-GR1, it outperforms all evaluated backbones in all four out-of-distribution settings, with relative gains of up to 24.8% over the strongest baseline. On RoboCasa-GR1, GroundingPI trained with 50% of the demonstrations outperforms those baselines trained with 75%. Its mean open-loop L2 error on nuScenes is 0.296 m. We systematically analyze GroundingPI's pretraining in scale and data composition. Grounding quality and downstream manipulation improve with pretraining scale, with generalization tracking perceptual gains most closely. Analyzing the data recipe across these 11 perceptual capabilities shows dense grounding's substantial benefits for both, and OCR's potential as a catalyst for perceptual learning. These results support grounding as a perceptual foundation, and dedicated perceptual pretraining as a promising direction for foundation models of physical intelligence.

版本更新 · v3arXiv:2602.07643

分割基础模型在结构与功能医学影像间的泛化能力如何?

How Well Do Segmentation Foundation Models Generalize Across Structural and Functional Medical Imaging?

Yichi Zhang, Le Xue, Feiyang Xiao, Wenbo Zhang, Gang Feng, Chenguang Zheng, Yuan Qi, Yuan Cheng 等 9 位作者

AI 速读 基于摘要

作者构建配对的PET/CT与PET/MRI全身多器官数据集UMD,并直接比较五个代表性3D分割基础模型在结构与功能影像上的开箱即用表现。

cs.CV

查看原文摘要

Segmentation foundation models offer reusable tools for universal medical-image segmentation, but their development and evaluation have largely centered on structural CT and MRI imaging. Functional imaging such as PET provides complementary metabolic information yet remains less studied and validated. Moreover, existing evaluations often involve different datasets and tasks, making modality-associated variation difficult to distinguish from differences in segmentation targets and data distributions. To enable a more direct comparison, we introduce UMD, a whole-body multi-organ dataset comprising 490 PET/CT and 464 PET/MRI examinations with 13 annotated organs (approximately 675,000 2D slices and 12,000 3D organ annotations). UMD evaluates structural and functional images separately on corresponding organs within the same examination, reducing variation in patient anatomy and target selection. We benchmark the out-of-the-box segmentation capabilities of five representative 3D foundation models on UMD. Overall, most evaluated models show limited PET segmentation performance, and some configurations also yield near-zero overlap on CT or MRI under the evaluated workflows. These findings highlight the need to assess tool applicability across different imaging conditions and identify opportunities for cross-modality generalization. UMD provides a paired data resource and evaluation setting for this investigation.

新论文 · v1arXiv:2611.26444

Mind2Act World:面向机器人操作中具身心智、物理动作与心智-动作组合的诊断基准

Mind2Act World: A Diagnostic Benchmark for Embodied Mind, Physical Action, and Mind-Action Composition in Robotic Manipulation

Yuzhi Huang, Jie Wu, Fanding Huang, Junchao Lin, Weichen Zhang, Ziyi Xiong, Yang Li, Zhengwei Xie 等 43 位作者

AI 速读 基于摘要

作者提出一个包含30个仿真操作任务、180种配置的诊断基准,用Mind、Act、Mind2Act三个视图区分系统是缺少某种能力还是无法组合已有能力。

cs.RO · cs.AI · cs.CV

查看原文摘要

Embodied intelligence aims to let robots perform complex physical tasks with human-like adaptability and reliability, which requires three complementary capabilities: history-based cognitive reasoning, precise and timely physical execution, and the composition of reasoning and execution through environmental feedback. Yet existing benchmarks either evaluate reasoning and execution within the same tasks or assess them separately without their composition, so they reveal little about whether a failure comes from reasoning, execution, or their composition. We introduce Mind2Act World, a diagnostic benchmark of 30 simulated manipulation tasks from five real-world application domains. Each task has three difficulty levels and two scene settings (Clean and Random), yielding 180 configurations. The tasks form three views: Mind tests decisions based on past observations, Act tests precise and timely execution, and Mind2Act combines both in closed-loop tasks where action outcomes guide later decisions. Comparing the three views shows whether a system lacks a capability or fails to compose capabilities it already has. A diagnosis harness further attributes the failed episodes of three representative systems to Mind, Act, or their composition and summarizes each system in a profile card. Our evaluation of multimodal agents, vision-language-action models (VLAs), and world-action models (WAMs) shows that competence in a single view does not carry over to Mind2Act tasks. Even the strongest agent succeeds in 52.7% of Mind and 39.0% of Act episodes but in only 12.0% of Mind2Act episodes. The strongest agent retains task state but struggles with sustained contact, whereas end-to-end policies execute practiced motions but retain little task state. These findings point to composing reasoning and execution through environmental feedback as the main open problem.

新论文 · v1arXiv:2611.26434

HumanCOIN:面向第一人称操作中人类意图的12,500小时数据集

HumanCOIN: A 12,500-Hour Dataset for Human Intent in Egocentric Manipulation

Shihan Wu, You Liu, Chunyu He, Minghui Qin, Longhan Jiao, Jinbang Guo, Shaoxuan Xie, Kaixi Tian 等 51 位作者

AI 速读 基于摘要

HumanCOIN 是一个围绕人类意图构建的第一人称操作数据集,通过三层代理信号(注视、肌电、脑电)在万小时规模上记录从决策到动作的意图通路。

cs.CV · cs.RO

查看原文摘要

First-person manipulation datasets treat the observation-action pair as the atomic unit and compress the generation and execution of an action into a policy network's weights, rendering the intent state behind the action unobservable. Human motor control research shows that intent mediates between observation and action and leaves observable traces along the intent pathway from decision to effect: gaze reaches the target before the hand, muscle load builds before contact, and cortical activity precedes the motor command. To record this pathway at scale, we present HumanCOIN, a first-person manipulation dataset built around human intent: 12,500 hours across 38 scene classes with three tiers of proxies. At the output end, the L1 attention tier (10,000 h) infers gaze from headband camera video, exposing the operator's next object of attention and reach before the hand moves. Midway, the L2 exertion tier (2,000 h) records surface EMG from armbands, making load expectations readable before execution is complete. At the origin, the L3 cognition tier (500 h) records scalp EEG, giving early readouts of task decisions and monitoring. Each tier inherits all proxies from the tiers below. The dataset further provides multi-view RGB images, depth maps and point clouds, 6-DoF head and wrist pose, and step-level action and object annotations. The controlled L3 setting additionally measures gaze, hand pose and finger kinematics directly. Clock and calibration data are released with the dataset so that any read rate can be re-aligned. The three tiers cover three stations, from visual orienting to cortical preparation, making the process behind visual-action pairs available for modeling at dataset scale. Project page: https://flagopen.github.io/HumanCOIN.

新论文 · v1arXiv:2611.26427

MemFolder:面向高效智能体记忆管理的结构引导记忆折叠

MemFolder: Structure-Guided Memory Folding for Efficient Agent Memory Management

Xuyang Liu, Chenwen Lu, Junxi Wang, Siyu Ren, Xinying Lin, Siteng Huang, Hongli Sun, Linfeng Zhang 等 9 位作者

AI 速读 基于摘要

MemFolder 通过结构引导的记忆折叠,依次减少记录数量和上下文长度,以降低长期智能体的存储、检索与生成成本。

cs.CL · cs.CV

查看原文摘要

Long-term agents accumulate large external memory stores as interactions unfold, increasing the costs of storage, retrieval, and response generation. Efficiency is constrained by two coupled factors: a growing record count increases retrieval overhead, while longer retrieved contexts increase prefill computation and decoding-time attention costs. Existing methods prune or consolidate records, but pruning can discard useful evidence, whereas consolidation may produce fewer yet longer retrieval units. We introduce MemFolder, a structure-guided memory folding framework that sequentially reduces record count and context length. The framework comprises two core components that share memory groups, using cross-record structure to guide both evidence consolidation and compact representation. RecordFolder grounds entity mentions, progressively selects representative yet complementary anchors, and combines semantic and entity affinity with temporal chaining to consolidate compatible records into fewer retrieval units. ContextFolder encodes the original records within these groups into compact text and uses verification feedback to revise encodings when key facts cannot be recovered. Experiments on the three text-based memory benchmarks LoCoMo, PersonaMem, and LongMemEval and the two multimodal benchmarks M3-Bench-web and M3-Bench-robot demonstrate the strong performance of our methods. Notably, on Mem0, RecordFolder retains 99.0% of the original average performance across the three text-based benchmarks with 50% fewer records, exceeding the strongest baseline by 1.9 percentage points in performance retention. Combined with ContextFolder, existing record compression methods further shorten their output records while retaining most of their performance.

新论文 · v1arXiv:2611.26409

WeMM-Video: Pushing the Frontiers of Open-Source Omni-Modal Video Understanding

Changli Tang, Jie Yang, Tianyi Wang, Lei Li, Daoze Zhang, Zijie Xin, Zhan Liu, Li Li 等 12 位作者

原文摘要

Video understanding, particularly with accompanying audio, remains a central challenge in multimodal intelligence. In this report, we introduce \textbf{WeMM-Video}, a family of Chinese-English bilingual omni-modal foundation models spanning 2B, 4B, 9B, and 35B-A3B variants. Centering on joint audio-visual perception and reasoning, WeMM-Video unifies text, image, audio, and video processing within a hybrid-thinking paradigm, seamlessly supporting both a non-thinking instruct mode for fast, direct responses and a thinking mode for explicit step-by-step reasoning. The models are trained on a large-scale multimodal corpus of approximately 1.2 trillion tokens through progressive pre-training and a multi-stage post-training pipeline incorporating multi-teacher OPD, anti-repetition MrDPO, and specialist RL. Evaluated across more than 120 benchmarks, WeMM-Video demonstrates superior performance in omni-modal video understanding and reasoning, while maintaining highly competitive capabilities across general audio, silent video, image, and text tasks. Specifically, in omni-modal video evaluations, our flagship WeMM-Video-35B-A3B establishes a new open-source state of the art, substantially outperforming proprietary models such as Qwen3.5-Omni-Flash and Seed2.0-Mini-0428 while narrowing the gap with the strong Gemini-3.0-Flash, and our compact WeMM-Video-9B surpasses the larger open-source Qwen3-Omni-30B-A3B-Instruct. We publicly release the WeMM-Video family along with our evaluation and reproduction pipeline to foster further research and development in the open-source community.

cs.CV · eess.AS

版本更新 · v2arXiv:2608.02044

Déjà Cue:通过词汇相对坐标在物体历史中定位状态

Déjà Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

Haofan Cao, Zhichao You, Yunkai Yang, Liang Guo, Jie Wang, Chongshou Li

AI 速读 基于摘要

提出免训练框架Déjà Cue,利用状态词汇的相对参考校准视觉-语言相似度,在物体历史中定位状态时刻,并构建MS-VOST基准。

cs.CV · cs.LG · cs.MM

查看原文摘要

Object tracking preserves identity through visual changes, but cannot tell when an object is whole, cut, or peeled. We study state-moment retrieval: locating when a tracked object exhibits each state in a supplied set of descriptions. However, absolute image--text similarity can favor shared object semantics, obscuring the distinctions needed to localize individual states. Our insight is that the alternatives themselves provide a reference for measuring state evidence. We introduce Déjà Cue, a training-free framework that centers description embeddings on a state-balanced vocabulary mean, producing query directions that compare each state against its alternatives. Using frozen vision--language encoders, Déjà Cue calibrates frame scores and retrieves intervals at multiple durations within contiguous visible runs. We construct MS-VOST by annotating 620 object histories with 2,465 states. With the encoder and temporal search fixed, Déjà Cue improves all three localization metrics over absolute scoring across eight encoder configurations, raising Top-1 temporal IoU by 0.42--1.14 percentage points. These gains persist across four text constructions, and candidate-ranking analysis shows that the vocabulary reference brings relevant intervals forward within the same search space. These results establish the supplied state vocabulary as an object-specific reference for localizing semantic states from frozen visual representations.

新论文 · v1arXiv:2611.26380

EgoCaptioner:面向全面且细粒度的第一人称视频描述

EgoCaptioner: Towards Comprehensive and Fine-Grained Egocentric Video Captioning

Yuqi Tang, Yang Shi, Yuran Wang, Tengfei Liu, Rundong Wang, Zongyang Qiu, Qixun Wang, Zhuoran Zhang 等 17 位作者

AI 速读 基于摘要

提出EgoCaptioner,通过粗到细标注和GRPO强化学习,生成兼具全局概览与细粒度时序步骤的第一人称视频描述。

cs.CV

查看原文摘要

Egocentric video captioning requires fine-grained detail and accurate timing, yet current multimodal large language models (MLLMs) often miss brief actions, confuse their order, or misinterpret the wearer's motion. Existing caption formats also offer limited support for combining detailed narration with precise timing. We present EgoCaptioner, which pairs a video-level overview of the setting, participants, and the wearer's overall activity with timed steps whose narration adapts to varying perceptual demands and marks key moments at specific timestamps. We develop a coarse-to-fine annotation pipeline that establishes event structure before expanding step descriptions, yielding 50,000 training examples from eight egocentric video sources. Complementary rewards assess factual accuracy and coverage, measure step-level temporal alignment, and penalize fragmented or redundant narration, guiding caption refinement through Group Relative Policy Optimization (GRPO). To improve the reliability of factual supervision, we supplement caption references with pose-derived motion facts when sensor data are available. Across five egocentric benchmarks, EgoCaptioner achieves leading performance among evaluated open-source models in caption quality, caption-conditioned question answering, and temporal alignment. It also surpasses Gemini 3.1 Pro on PhysCapBench and all evaluated proprietary baselines on Minerva-Ego under the caption-to-QA protocol. Ablations support the complementary roles of factual and temporal rewards and show that coarse-to-fine annotation provides more effective supervision than single-pass annotation.

新论文 · v1arXiv:2611.26249

Beyond Covers and Titles: Evidence-First Ranking for Robust Cold-Start Recommendation

Fuyi Wang, Yuxin Cao, Yifan Liao, Renyang Liu, Lin Li, Wei Song

原文摘要

Short-video platforms rank new uploads before anyone has watched them, using content towers that read a video's cover, title and frames. Existing attacks on content-aware recommenders perturb pixels or features and ignore platform re-encoding, and existing defenses train against norm-bounded perturbations that neither match real edits nor preserve recommendation quality. We show with REAP, a realizable attack through {a simulated platform channel (H.264 transcoding, rescaling, cropping and JPEG)}, that packaging edits raise a cold video by 32.0 rank-percentile points in unrelated audiences. We then observe that cold-start ranking does not need the packaging at all: a tower that sees only the video body ranks cold items best. Building on this, we propose Evidence-First Ranking (EFR), which scores cold videos from their body, admits packaging only through a support-gated residual bounded by $γ$, and merges cold and warm rankings by rank percentile, yielding an exact certificate against any packaging edit. On MicroLens-100K, EFR cuts the attack gain by 81% and raises cold-start Recall@100 from 0.1133 to 0.170, while keeping the merged NDCG@10 within 4% of the undefended system.

cs.CV

版本更新 · v2arXiv:2610.41373

Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization

Tianyu Xiong, Rui Li, Jiaqi Yang

原文摘要

We present Queryable Gaussian View Index (QGVI) for querying existing Gaussian scene assets and their associated calibrated reference data. Text-view retrieval and selective RGB camera localization return poses in the asset's coordinate frame. QGVI-T turns Gaussian-rendered views into a language-searchable index of scene locations, binding structured captions to known camera poses and place identifiers. Semantic and lexical retrieval select views from distinct places without online rendering, VLM calls, or a scene-specific pose network. The image route, QGVI-I, filters LoGS-based geometric estimates using distinct inlier query keypoints. It omits photometric refinement and preserves accepted pose coordinates. On nine development scenes, QGVI-T achieves 58.3% Top-1 and 78.3% Top-5 joint relevance-and-validity success, compared with 26.1% and 34.6% for our CityLoC reimplementation with refinement. QGVI-I achieves 97.3% scene-mean pose success at 1 m/2 degrees, with pooled false-acceptance and false-rejection rates of 0.707% and 1.142%. A paired cached evaluation retains all 1,775 initializer poses correct at this threshold. Recorded median text query latency is 0.020 s. Matched controls show competitive BM25 retrieval and slightly lower false acceptance for thresholded full LoGS; grid augmentation suggests modest gains on novel-view-derived descriptions. We report model-judged semantic success separately from source-camera recovery, with source-verified or estimated scales for geometric evaluation.

cs.CV

版本更新 · v2arXiv:2608.16367

Depth-Dominant Skeleton Detection for Natural Scenes

Chengkun Rao, Xinrong Hu, Min Li, Yangjun Ou, Ziwei Luo, Ye Li, Zhaojing Wang, Junwei Tang 等 10 位作者

原文摘要

Existing natural-scene skeleton detectors follow an RGB-representation-based feature encoding paradigm: they locate skeletons within the RGB appearance space, in which the skeleton's shape and topology can only be inferred implicitly from entangled color and texture cues. Despite notable progress, this encoding paradigm degrades markedly on complex scenes such as cluttered or occluded ones, where appearance distractors overwhelm the weak structural signal. We observe that depth images are inherently insensitive to color and texture and provide clear regional contours and inter-region spatial relationships, which naturally eases the difficulty of skeleton detection in complex scenes. Motivated by this, we propose for the first time a novel skeleton detection paradigm built on depth-representation-dominant feature encoding, in which depth dominates and RGB serves as the auxiliary, and present a model, DDSkel, under this paradigm. DDSkel adopts an asymmetric encoder design that fuses the feature representation of RGB images into that of depth images, with the RGB branch containing only 23% of the parameters of the depth branch. DDSkel has a simple structure without intricate designs. Nevertheless, with only about 19% of the trainable parameters of the largest state-of-the-art methods, DDSkel attains the highest F-measure scores on four mainstream benchmarks, namely SK506, SK-LARGE, WH-SYMMAX, and SymPASCAL. Extensive experiments suggest that for natural-image skeleton detection, the depth-dominant paradigm is a more suitable choice than the RGB-based paradigm, achieving better performance with substantially fewer parameters.

cs.CV

新论文 · v1arXiv:2611.26211

SpecWM: Turning Verification into Refinement for Streaming World Models

Jiaming Li, Lingzhen Li, Xiaze Yang, Chenyu Zhu, Kaiqi Liu, Xiaotong Zhao, Songlian Li, Toyota Li 等 12 位作者

原文摘要

Recently, video world models have advanced interactive generation, with large models offering higher quality and smaller models enabling faster inference. Existing speculative methods combine their strengths through fast draft generation and selective target regeneration guided by rewards on decoded frames. However, verification covers only the external scorer's evaluation dimensions and adds decoding and scoring costs. Moreover, these scores provide no correction, requiring costly target regeneration for rejected drafts. To address these limitations, we propose Speculative World Model (SpecWM), a unified, training-free inference framework for streaming world models. It verifies draft chunks using the target's latent velocity field. Verification also yields a reusable correction; two thresholds select Accept, Refine, or Reject. Specifically, one-step refinement reuses it to improve perceptual quality, while three-step refinement strengthens camera following and trajectory consistency. These findings motivate transition-aware refinement. On WBench Navigation, SpecWM improves visual quality at 1.63$\times$ speedup over the target and raises NavScore from the draft's 75.99 to 85.63, achieving the best quality-speed-control trade-off. Additionally, our LongSpecBench shows sustained quality and control over long, multi-turn rollouts, while experiments on Hy-Nomas validate SpecWM across backbones and denoising budgets.

cs.CV

版本更新 · v2arXiv:2611.24157

GenRF: Generative Registration-free Image Fusion

Linfeng Tang, Zhijun Fan, Yang Chen, Zizhuo Li, Hao Zhang, Jiayi Ma

原文摘要

Multi-modal image fusion combines complementary observations to improve scene visibility and perception. However, in real-world acquisition, differences in sensing principles and configurations introduce geometric discrepancies, while degradations further compromise source quality. Existing methods typically rely on explicit registration, yet large parallax complicates correspondence estimation, while mismatched fields of view leave some regions without cross-modal counterparts. Meanwhile, independent restoration underuses cross-modal information, whereas restoration-fusion methods assuming alignment remain vulnerable to misregistration. This study revisits misaligned and degraded image fusion in the era of generative foundation models, in which cross-attention enables position-agnostic complementary information aggregation, while generative priors support degradation recovery and inference in missing regions. Building on this perspective, we propose GenRF, which adapts pretrained FLUX through LoRA to jointly enhance degraded observations, infer missing cross-modal context, and fuse complementary information without explicitly estimating deformation fields. Extensive experiments on real-world infrared and visible captures show that GenRF delivers high-quality fusion directly from unregistered, degraded images without preprocessing, while improving downstream task performance under misalignment. Additional experiments demonstrate that GenRF can generalize to misaligned multi-exposure and multi-focus image fusion without task-specific fine-tuning.

cs.CV

新论文 · v1arXiv:2611.26165

StreamEgo: Streaming Exocentric-to-Egocentric Video Generation

Tianyi Xu, Boyang Lyu, Yunkai Tang, Kairan Ding, Jiahang Li, Weiyu Guo, Yandong Guo, Shuchen Weng 等 9 位作者

原文摘要

Exocentric-to-egocentric (Exo2Ego) video generation transforms third-person recordings into first-person viewpoints, unlocking immersive AR/VR experiences and scalable demonstration synthesis for embodied robotics. Extending it to a streaming setting is expected to further enable live applications. However, existing methods suffer from degraded manipulation regions, overfitting and confinement to fixed-length clips with prohibitive latency. To address these limitations, we present StreamEgo, a real-time framework for unbounded, generalizable Exo2Ego video generation. To resolve intricate manipulation dynamics while supporting the streaming pipeline, a streaming dual-branch prior provides pixel-aligned guidance for translating appearance and skeletal kinematics. We also introduce a region-aware loss curriculum to improve generalization and stabilize multi-objective diffusion training. Furthermore, we distill the model into a chunk-wise autoregressive model, augmented with a region-aware corruption mechanism and a first-chunk curriculum, enabling high-quality, generalizable real-time streaming Exo2Ego generation at 24.3 FPS on a single H100 GPU.

cs.CV

版本更新 · v2arXiv:2611.18729

SCALE: Towards Whole-Slide Counterfactual Explanations in Cancer Histopathology

Weiyi Qin, Yingci Liu-Swetz, Shiwei Tan, Yi Wang, Mohammad Alexanderani, Dimitrios Korentzelos, Peizi Li, Soo Yeon Sohn 等 14 位作者

原文摘要

Accurate cancer diagnosis depends on histopathological evaluation, in which tumor morphology drives disease classification and therapeutic decision-making. While deep learning models have demonstrated strong performance in predicting diagnostic and prognostic properties from histopathology images, their clinical adoption remains limited by a lack of interpretability. Unlike conventional medical images where diagnostic findings are spatially localized, histopathological images are characterized by complex textural patterns distributed across the entire whole slide image (WSI), making it difficult to explain model predictions through region-based localization alone. Counterfactual explanations offer a promising alternative by asking "what changes in the image could have altered the model prediction." To achieve this, we propose SCALE, a framework for generating such counterfactual explanations for histopathological DL models. Across nine counterfactual directions spanning multiple cancer types, SCALE generates counterfactual explanations that consistently shift model predictions toward the intended diagnostic target while maintaining biological feasibility. In a blinded review by pathologists, SCALE demonstrated superior morphological plausibility compared to baseline methods (win rate of 91.7%) and robust counterfactual effectiveness (target consistency of 96.7%). These results suggest that SCALE generates morphologically plausible and effective counterfactual explanations that can be applied to improve the interpretability of deep learning models for histopathology.

cs.CV

新论文 · v1arXiv:2611.26103

UniVEP: Unifying Velocity and Endpoint Prediction for Robot Manipulation

Zhengtu Liang, Qiwei Liang, Tao Lin, Shihang Weng, Boyang Cai, Xiangyu Chen, Yikeng Chen, Jiaming Liang 等 11 位作者

原文摘要

Flow-matching robot policies usually use one prediction target throughout action generation, even though recovering actions from noise and polishing nearly clean actions bring different challenges. We systematically compare velocity prediction (V), endpoint prediction (X), and velocity-weighted endpoint prediction (X--V) across multiple robot policies, benchmarks, and inference budgets. On StarVLA and LiLa-WAM, X--V works best for few-step generation, while V gains more from iterative refinement. We further uncover their complementary strengths across noise levels: clean actions have concentrated covariance spectra, endpoint predictions stay more stable under high noise, and velocity predictions offer more accurate corrections near clean actions. Inspired by these findings, we introduce UniVEP, which learns both prediction targets together with consistency supervision and switches from endpoint recovery to velocity refinement as noise drops. Each step only needs one network run, and joint training also boosts single-step endpoint generation. Tests on simulated and real-world manipulation show better success rates and efficiency. On RoboTwin, UniVEP hits 61.36% success with one StarVLA run, beating the best single-target baseline at sixteen runs (59.96%). With LiLa-WAM, two runs outperform the best sixteen-step single-target baseline and cut inference latency by 77.1%.

cs.RO · cs.CV

新论文 · v1arXiv:2611.26098

Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation

Yipan Xu, Shuyong Gao, Jiyuan Fu, Keliang Yin, Jiayu Chen, Qianyu Guo, Yang Liu, Wenqiang Zhang

原文摘要

Text-to-video generation has made remarkable progress with diffusion models and transformer-based video architectures, yet generating coherent long videos from evolving textual descriptions remains challenging. Training long-video models from scratch requires substantial computation and large-scale multi-event data, while training-free multi-prompt generation must activate new prompt semantics without breaking temporal continuity. We identify a frequency-agnostic boundary coupling problem in existing transition strategies: weak coupling causes abrupt changes, flicker, and background jumps, whereas overly strong or coarse coupling may over-preserve source semantics and produce ghosting or duplicated subjects around prompt boundaries. To address this problem, we propose FreqSync, a training-free framework that formulates prompt transitions as frequency-selective boundary coupling. FreqSync combines Frequency-Synchronized Source-Conditioned Attention (FS-SCA) with Residual-Clipped Spectral Stitching (RCSS), enabling adjacent segments to share stable low- and mid-frequency structure and motion cues while keeping high-frequency prompt-specific details target-dominant under explicit residual constraints. Extensive experiments show that FreqSync achieves state-of-the-art transition smoothness and prompt alignment while maintaining strong perceptual video quality, demonstrating its effectiveness for coherent multi-prompt long video generation.

cs.CV

版本更新 · v4arXiv:2606.08918

GeoMetric: Injecting Metric Geographic Structure into Worldwide Image Geo-Localization

Junchao Cui, Wenqi Shi, Xiangyang Luo, Biru Zhu, Xuanzi Ma, Nan Wu

原文摘要

Worldwide image geo-localization estimates where a photograph was taken on Earth. Existing methods infer location from visual appearance alone, an unreliable cue for geography: near-identical scenes occur on different continents. We present GeoMetric, a three-phase retrieval framework that encodes geographic distance directly in the representation. Phase I trains image, text, and location encoders into a unit hypersphere. The location encoder combines ScaleFusion and GeoAnchorAttention. ScaleFusion projects a coordinate onto an equal-area chart and encodes it with three Fourier bands, fusing them by attention into one multi-scale embedding. GeoAnchorAttention adds a global prior from fixed spherical anchors without mixing samples, so each coordinate embedding is batch-independent. A trimodal contrastive objective aligns images, reverse-geocoded texts, and coordinates, masking semantic and geographic false negatives. Phase II retrieves candidates, each carrying a GPS coordinate and granularity-aware geographic text. Phase III lets a frozen open-source 8B-parameter large multimodal model (LMM) choose the coordinate from those candidates. On four benchmarks, GeoMetric is best in 15 of 20 threshold cells, and ablations show that the components act at different scales: the text encoder carries coarse geographic context, while the location encoder resolves fine-grained distinctions.

cs.CV

新论文 · v1arXiv:2611.26040

Streaming-AAA: Streaming AAA Game Video Generation at High Resolution, High Frame Rate, and Low Latency

Zhihao Hu, Jianqi Ma, Jun Zhang, Jiayang Bai, Haifeng Shi, Yanxiang Zhuang, Zhongqian Sun, Weidong Zhang 等 9 位作者

原文摘要

Controllable streaming video generation offers a promising route toward interactive game simulation, yet existing methods remain far from practical gameplay. They often fail to jointly achieve high visual fidelity, high frame rates, and low interaction latency, resulting in poor responsiveness and degraded user experience. We present Streaming-AAA, a new paradigm for controllable infinite generation of AAA-quality game videos. Our system generates 1080p gameplay videos at 43 FPS with 198 ms end-to-end latency interaction on merely NVIDIA A800 GPUs, while supporting long-horizon play without severe temporal degradation or collapse. Streaming-AAA is built upon three key designs. First, we redesign the VAE architecture for efficient high-resolution decoding, enabling real-time synthesis at 1080p. Second, we pretrain the diffusion model using diffusion forcing and significantly extend the temporal training horizon, allowing the model to capture long-term dependencies and maintain persistent memory. Third, we perform post-training distillation and memory compression to improve inference efficiency while retaining visual quality and temporal consistency. Experiments show that Streaming-AAA substantially improves visual fidelity, frame rate, latency, and long-term stability over prior controllable video generation approaches, enabling a significantly more playable experience for interactive AAA game video generation.

cs.CV

新论文 · v1arXiv:2611.25946

Point Dynamics as Proxy for Robotic World Models

Dong An, Tianyu Liu, Haoran Ding, Wen Yang, Anqing Duan, Zhengzhong Liu, Eric P. Xing, Guangyi Liu

原文摘要

Robotic world models predict future video frames from the current observation and a sequence of robot actions. While recent models follow the given actions closely, manipulated objects often collapse or move inconsistently with the action. We attribute this to the conditioning: an action, or a rendering of the robot, specifies where the robot goes but not how the scene responds, leaving a single video model to infer the interaction dynamics implicitly while also rendering appearance. We therefore separate dynamics prediction from visual rendering, with 3D point dynamics as the proxy between them. Specifically, we lift the first frame into 3D points, simulate how they respond to the robot's motion with a learned point dynamics model, and render the simulated points back into pixel-aligned videos that any video model can read. In controlled experiments on the DROID dataset with two video renderers of different architectures, this point dynamics proxy reduces object motion error by 8.6% and 6.2% without degrading image quality, and by 8.1% on a real bimanual robot. Moreover, the video follows the simulation: more accurate dynamics yield more accurate object motion, and editing the points steers the video. This suggests that advances in dynamics modeling can translate into more faithful robotic world models.

cs.CV

版本更新 · v2arXiv:2610.36760

GeoGSplat: Geometry-Grounded Non-Pixel-Aligned Gaussian Splatting

Jiale Wang, Chen Zhao, Haoyang Zhang, Yanhao Wu, Fei He, Yanhu Shan, Rui Wu, Wei Ke 等 9 位作者

原文摘要

Feed-forward Gaussian Splatting enables efficient novel view synthesis, but pixel-aligned prediction makes the primitive count grow with image resolution and view count, leading to substantial redundancy and increased computational cost. Non-pixel-aligned methods address this limitation by predicting a fixed number of Gaussians. Without explicit ray and depth constraints, these methods yield misplaced Gaussian centers, causing rendering artifacts under large viewpoint changes. To address this issue, we introduce GeoGSplat, a geometry-grounded feed-forward model that explicitly incorporates geometric priors into the non-pixel-aligned framework. A dual-branch encoder constructs Anchors and Triplane to capture coarse 3D structure and fine-grained scene features, respectively. Subsequently, a hierarchical decoder progressively decodes dense 3D points and Gaussian primitives, enabling 3D reconstruction and novel view synthesis. GeoGSplat surpasses both state-of-the-art pixel-aligned and non-pixel-aligned Gaussian Splatting methods on DTU and NRGBD in terms of novel view synthesis and reconstruction. The advantage of our geometry-grounded paradigm further increases as target viewpoints move farther from the input cameras, demonstrating stronger generalization to large viewpoint changes. Project Page: https://comedy0913.github.io/projects/geogsplat

cs.CV

新论文 · v1arXiv:2611.25873

WHU-Road3D: A dataset and benchmark towards fine-grained road surface mapping

Xiaoxin Mi, Zhen Cao, Chong Liu, Yuhao Li, Zhen Dong, Bisheng Yang, Yang Jia, Shengwu Xiong

原文摘要

Accurately extracting and mapping road surface elements is crucial for applications such as high-definition maps, road asset management, and intelligent transportation systems. This study first provides a comprehensive review of the benchmark datasets for extracting and mapping road elements, encompassing overhead-to-perspective data, large-to-local scales, and coarse-to-fine details. Subsequently, we thoroughly review the relevant approaches for extracting road surface elements. However, we argue that existing datasets still require enhancements in semantic richness, data modality diversity, and scenario complexity. To bridge these gaps, this paper presents WHU-Road3D, a large-scale multimodal dataset for fine-grained road surface mapping to address these shortcomings. WHU-Road3D provides approximately 100 km of diverse Chinese highways and urban streets. It features a rich combination of MLS point clouds, associated panoramic images, vehicle trajectories, detailed vectorized annotations, and pointwise instance annotations for road surface elements. The dataset carefully annotates 15 distinct categories of road elements, including common markings like road boundaries, zebra crossings, lane dividers, stop lines, as well as 10 types of direction symbols. To our knowledge, WHU-Road3D stands as the first multimodal dataset for mapping such a comprehensive range of road surface elements, designed to facilitate cutting-edge research in instance segmentation, full-element extraction and mapping on road surfaces. Beyond these immediate applications, WHU-Road3D also provides a valuable source for hierarchical road topology reasoning, map updating, and street scene generation. The dataset, along with the code for our benchmark methods, will be made publicly available at \href{https://github.com/WHU-USI3DV/WHU-Road3D.git}{https://github.com/WHU-USI3DV/WHU-Road3D.git}.

cs.CV

新论文 · v1arXiv:2611.25849

EgoWitness: Benchmarking Instance-Level Spatial Memory and Reasoning in Egocentric Video Streams

Zhengru Fang, Zehao Liu, Mingyu Tsoi, Yaoyu Zhu, Junlong Li, Fengmao Lv, Sijie Cheng, Yuanliang Sun 等 10 位作者

原文摘要

Recalling where and when an object was last seen and who saw it requires recognizing it across days and people. Existing long-video benchmarks focus on events, object categories, or relative locations, leaving instance-level spatial memory largely untested in multimodal models. To address this gap, we present EgoWitness, a benchmark for instance-level spatial memory and reasoning in egocentric video. Its 8,453 human-verified questions span approximately 324 hours of week-long and short-horizon recordings and test seven abilities, from recognizing an object or room to recalling who saw it and reasoning about room visits. Over one million reviewed masks of 34 registered landmarks and 21 movable-object labels are linked through room timelines. Among twelve direct vision-language models (VLMs), open-weight models reach at most 46.97% accuracy, and none exceeds 35% on identifying who saw an object last. We therefore propose EgoClue, a spatial-memory agent that retrieves candidate intervals, verifies instance identity, and computes spatial and temporal relations with five tools. Two-stage training with supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) raises its 4B controller from 23.64% to 72.65% accuracy on 1,320 held-out questions. Evidence-trace synthesis matches the best direct VLM at 74.85% on week-long questions and achieves 80.56% in environments excluded from training.

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:2611.25711

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