paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

FusionBERT: Multi-View Image--3D Retrieval via Cross-Attention Visual Fusion and Normal-Aware 3D Encoder

Wei Li, Yufan Ren, Hanqing Jiang, Jianhui Ding, Zhen Peng, Leman Feng, Yichun Shentu, Guoqiang Xu, Baigui Sun

We propose FusionBERT, a novel multi-view visual fusion framework for image--3D multimodal retrieval. Existing image--3D representation learning methods predominantly focus on feature alignment of a single object image and its 3D model, limiting their applicability in realistic scenarios where an object is typically observed and captured from multiple viewpoints. Although multi-view observations naturally provide complementary geometric and appearance cues, existing multimodal large models rarely explore how to effectively fuse such multi-view visual information for better cross-modal retrieval. To address this limitation, we introduce a multi-view image--3D retrieval framework named FusionBERT, which innovatively utilizes a cross-attention-based multi-view visual aggregator to adaptively integrate features from multi-view images of an object. The proposed multi-view visual encoder fuses inter-view complementary relationships and selectively emphasizes informative visual cues across multiple views to get a more robustly fused visual feature for better 3D model matching. Furthermore, FusionBERT proposes a normal-aware 3D model encoder that can further enhance the 3D geometric feature of an object model by jointly encoding point normals and 3D positions, enabling a more robust representation learning for textureless or color-degraded 3D models. Extensive image--3D retrieval experiments on both synthetic 3D models and real-world industrial mechanical objects demonstrate that FusionBERT achieves significantly higher retrieval accuracy than SOTA multimodal large models under both single-view and multi-view settings, establishing a strong baseline for multi-view multimodal retrieval.

arXiv

VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models

Qijia He, Xunmei Liu, Hammaad Memon, Ziang Li, Zixian Ma, Jaemin Cho, Zhongzheng Ren, Daniel S Weld, Ranjay Krishna

Scalable Vector Graphics (SVG) are essential for technical illustration and digital design, offering resolution independence and semantic editability. In practice, original vector files are frequently lost, leaving only rasterized versions (e.g., PNG, JPEG) that resist modification, while manual reconstruction is prohibitively expensive. Progress on automating raster-to-SVG conversion has been bottlenecked by two gaps: existing SVG datasets are dominated by icons and decorative graphics that lack the complexity of professional diagrams, and existing benchmarks rely on pixel- or embedding-level similarity that fails to capture structural correctness (e.g., broken connectivity, misplaced arrows). We close both gaps with paired contributions targeting diagram-centric figures (e.g., model architectures, flowcharts, schematics). For training, we introduce VFIG-Data, the largest figure-to-SVG dataset of its kind at 66K pairs, combining real paper figures converted via a describe-and-generate pipeline with programmatic diagrams that supply noise-free supervision over arrow styles, fonts, and geometry. For evaluation, we introduce VFIG-Bench, a structure-aware evaluation suite, paired with VFIG-Bench-OOD, an out-of-distribution set of figures manually curated from highly cited arXiv papers. Beyond pixel and embedding similarity, our protocol reports rubric-based VLM-Judge scores and Elo ratings from pairwise human preference evaluation. Built on these contributions, VFIG is a VLM family trained with a simple-to-complex SFT curriculum followed by RL with rendering-aware rewards. VFIG achieves state-of-the-art open-source performance, outperforming the best open-source VLM baseline by over 30%, and matches Claude Sonnet 4.6 on VFIG-BENCH: Gemini-Judge 78.2% vs. 76.7% and GPT-Judge 87.5% vs. 87.4%. It remains slightly behind the strongest proprietary models GPT-5.2 and Gemini-3.

arXiv

EdgeCrafter: Compact ViTs for Edge Dense Prediction via Task-Specialized Distillation

Longfei Liu, Yongjie Hou, Yang Li, Qirui Wang, Youyang Sha, Yongjun YU, Yinzhi Wang, Peizhe Ru, Xuanlong Yu, Xi Shen

Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict computation and memory budgets. In practice, lightweight systems for object detection, instance segmentation, and pose estimation are still dominated by CNN-based architectures such as YOLO, while compact Vision Transformers (ViTs) often struggle to achieve comparable accuracy-efficiency trade-offs, even with large-scale pretraining. We argue that this gap arises primarily from insufficient task-specific representation learning in small-scale ViTs, rather than from an inherent mismatch between ViTs and edge dense prediction. To address this issue, we introduce EdgeCrafter, a unified compact ViT framework for edge dense prediction centered on ECDet, a detection model built on a distilled compact backbone and an edge-friendly encoder-decoder design. The resulting detection-distilled representation transfers directly to instance segmentation and human pose estimation through lightweight task-specific prediction modules. Without using task annotations beyond COCO, ECDet-S achieves 51.7 box AP with fewer than 10M parameters, while ECInsSeg-X and ECPose-X reach 48.4 mask AP and 74.8 keypoint AP, respectively. As a complementary but more compute-intensive setting, Objects365 detection pretraining consistently improves performance across all scales, with the X variants reaching 59.9 box AP, 49.8 mask AP, and 75.9 keypoint AP. These results show that compact ViTs, when combined with task-specialized distillation and edge-aware design, can be a practical and competitive solution for edge dense prediction. Code is available at: https://intellindust-ai-lab.github.io/projects/EdgeCrafter

arXiv

A multi-center analysis of deep learning methods for video polyp detection and segmentation

Noha Ghatwary, Pedro Chavarias Solano, Mohamed Ramzy Ibrahim, Adrian Krenzer, Frank Puppe, Stefano Realdon, Renato Cannizzaro, Jiacheng Wang, Liansheng Wang, Thuy Nuong Tran, Lena Maier-Hein, Amine Yamlahi, Patrick Godau, Quan He, Qiming Wan, Mariia Kokshaikyna, Mariia Dobko, Haili Ye, Heng Li, Ragu B, Antony Raj, Hanaa Nagdy, Osama E Salem, James E. East, Dominique Lamarque, Thomas de Lange, Sharib Ali

Colonic polyps are well-recognized precursors to colorectal cancer (CRC), typically detected during colonoscopy. However, the variability in appearance, location, and size of these polyps complicates their detection and removal, leading to challenges in effective surveillance, intervention, and subsequently CRC prevention. The processes of colonoscopy surveillance and polyp removal are highly reliant on the expertise of gastroenterologists and occur within the complexities of the colonic structure. As a result, there is a high rate of missed detections and incomplete removal of colonic polyps, which can adversely impact patient outcomes. Recently, automated methods that use machine learning have been developed to enhance polyps detection and segmentation, thus helping clinical processes and reducing missed rates. These advancements highlight the potential for improving diagnostic accuracy in real-time applications, which ultimately facilitates more effective patient management. Furthermore, integrating sequence data and temporal information could significantly enhance the precision of these methods by capturing the dynamic nature of polyp growth and the changes that occur over time. To rigorously investigate these challenges, data scientists and experts gastroenterologists collaborated to compile a comprehensive dataset that spans multiple centers and diverse populations. This initiative aims to underscore the critical importance of incorporating sequence data and temporal information in the development of robust automated detection and segmentation methods. This study evaluates the applicability of deep learning techniques developed in real-time clinical colonoscopy tasks using sequence data, highlighting the critical role of temporal relationships between frames in improving diagnostic precision.

arXiv

OODBench: Out-of-Distribution Benchmark for Large Vision-Language Models

Ling Lin, Yang Bai, Heng Su, Congcong Zhu, Yaoxing Wang, Yang Zhou, Huazhu Fu, Jingrun Chen

Existing Visual-Language Models (VLMs) have achieved significant progress by being trained on massive-scale datasets, typically under the assumption that data are independent and identically distributed (IID). However, in real-world scenarios, it is often impractical to expect that all data processed by an AI system satisfy this assumption. Furthermore, failure to appropriately handle out-of-distribution (OOD) objects may introduce safety risks in real-world applications (e.g., autonomous driving or medical assistance). Unfortunately, current research has not yet provided valid benchmarks that can comprehensively assess the performance of VLMs in response to OOD data. Therefore, we propose OODBench, a predominantly automated method with minimal human verification, for constructing new benchmarks and evaluating the ability of VLMs to process OOD data. OODBench contains 40K instance-level OOD instance-category pairs, and we show that current VLMs still exhibit notable performance degradation on OODBench, even when the underlying image categories are common. In addition, we propose a reliable automated assessment metric that employs a Basic-to-Advanced Progression of prompted questions to assess the impact of OOD data on questions of varying difficulty more fully. Lastly, we summarize substantial findings and insights to facilitate future research in the acquisition and evaluation of OOD data.

arXiv

MiDAS: A Multimodal Data Acquisition System and Dataset for Robot-Assisted Minimally Invasive Surgery

Keshara Weerasinghe, Seyed Hamid Reza Roodabeh, Andrew Hawkins, Zhaomeng Zhang, Zachary Schrader, Homa Alemzadeh

Background: Robot-assisted minimally invasive surgery (RMIS) research increasingly relies on multimodal data, yet access to proprietary robot telemetry remains a major barrier. We introduce MiDAS, an open-source, platform-agnostic system enabling time-synchronized, non-invasive multimodal data acquisition across surgical robotic platforms. Methods: MiDAS integrates electromagnetic and RGB-D hand tracking, foot pedal sensing, and surgical video capturing without requiring proprietary robot interfaces. We validated MiDAS on the open-source Raven-II and the clinical da Vinci Xi by collecting multimodal datasets of peg transfer and hernia repair suturing tasks performed by surgical residents. Correlation analysis and downstream gesture recognition experiments were conducted. Results: External hand and foot sensing closely approximated internal robot kinematics and non-invasive motion signals achieved gesture recognition performance comparable to proprietary telemetry. Conclusion: MiDAS enables reproducible multimodal RMIS data collection and is released with annotated datasets, including the first multimodal dataset capturing hernia repair suturing on high-fidelity simulation models.

arXiv

SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking

Muhammad Taha Mukhtar, Syed Musa Ali Kazmi, Khola Naseem, Muhammad Ali Chattha, Andreas Dengel, Sheraz Ahmed, Muhammad Naseer Bajwa, Muhammad Imran Malik

Very-high-resolution remote-sensing imagery provides a scalable basis for delineating informal settlements, but sparse annotations, severe imbalance between informal-settlement and background pixels, and cross-city heterogeneity in urban morphology and image--mask correspondence complicate model development. We present SLUM-i, a semi-supervised semantic segmentation framework together with a geographically diverse seven-city Earth observation benchmark spanning three continents. The benchmark combines a newly annotated Lahore dataset and companion Karachi and Mumbai datasets with four publicly released city datasets, totaling 14,458 RGB image--mask tiles. We quantify cross-city heterogeneity using class composition, boundary morphology, grayscale separability, correspondence between mask boundaries and image edges, and divergence between measured feature distributions. For label-efficient mapping, SLUM-i combines representation-guided unlabeled-pool curation, using embeddings from a vision foundation model (DINOv2-Small) to remove the least-similar tiles, and Class-Aware Adaptive Thresholding, which adapts pseudo-label acceptance by class through global mean-confidence and per-class mean-softmax exponential moving averages. Experiments at 10%, 20%, and 30% label budgets, using convolutional and vision-transformer backbones and five random seeds, demonstrate improvements over the corresponding UniMatch baselines in multiple city--budget settings, reaching +5.9 percentage points in mean intersection-over-union. At the 30% budget, the ResNet-101 configuration matches or exceeds its corresponding fully labeled supervised baseline in four of seven cities. Both components operate only during training and add no inference overhead.

arXiv

RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotion

Zhe Li, Boan Zhu, Yangyang Wei, Shuanghao Bai, Yuheng Ji, Yibo Peng, Tao Huang, Pengwei Wang, Zhongyuan Wang, S. -H. Gary Chan, Chang Xu, Cheng Chi, Jianfei Yang, Shanghang Zhang

Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art humanoid locomotion systems rely on either curated motion capture trajectories or sparse text commands, leaving a critical gap between visual understanding and control. Text-to-motion methods suffer from semantic sparsity and staged pipeline errors, while video-based approaches only perform mechanical pose mimicry without genuine visual understanding. We propose RoboMirror, the first retargeting-free video-to-locomotion framework embodying "understand before you imitate". Leveraging VLMs, it distills raw egocentric/third-person videos into visual motion intents, which directly condition a diffusion-based policy to generate physically plausible, semantically aligned locomotion without explicit pose reconstruction or retargeting. Extensive experiments validate the effectiveness of RoboMirror, it enables telepresence via egocentric videos, drastically reduces third-person control latency by 80%, and achieves a 3.7% higher task success rate than baselines. By reframing humanoid control around video understanding, we bridge the visual understanding and action gap.

arXiv

A Survey of Body and Face Motion: Datasets, Performance Evaluation Metrics and Generative Techniques

Lownish Rai Sookha, Nikhil Pakhale, Mudasir Ganaie, Abhinav Dhall

Body and face motion play an integral role in communication. They convey crucial information on the participants. Advances in generative modeling and multi-modal learning have enabled motion generation from signals such as speech, conversational context and visual cues. However, generating expressive and coherent face and body dynamics remains challenging due to the complex interplay of verbal / non-verbal cues and individual personality traits. This survey reviews body and face motion generation, covering core concepts, representations techniques, generative approaches, datasets and evaluation metrics. We highlight future directions to enhance the realism, coherence and expressiveness of avatars in dyadic settings. To the best of our knowledge, this work is the first comprehensive review to cover both body and face motion. Detailed resources are listed on https://lownish23csz0010.github.io/mogen/.

arXiv

Comprehension of Multilingual Expressions Referring to Target Objects in Visual Inputs

Francisco Nogueira, Alexandre Bernardino, Bruno Martins

Referring Expression Comprehension (REC) requires models to localize objects in images based on different types of natural language descriptions. Even with significant progress, research on the area remains predominantly English-centric, despite increasing global deployment demands. This work addresses multilingual REC through two main contributions. First, we construct a unified multilingual dataset spanning 10 languages, by systematically expanding 12 existing English REC benchmarks through machine translation and context-based translation enhancement. Second, we introduce an attention-anchored efficient neural architecture that uses a multilingual SigLIP2 encoder. Our attention-based approach generates coarse spatial anchors from attention distributions, which are subsequently refined through learned residuals. Experimental evaluation demonstrates competitive performance on standard benchmarks despite the use of a relatively small model. Multilingual evaluation shows consistent capabilities across languages, establishing the practical feasibility of efficient multilingual visual grounding systems.

arXiv

Mitigating Error Accumulation in Co-Speech Motion Generation via Global Rotation Diffusion and Multi-Level Constraints

Xiangyue Zhang, Jianfang Li, Jianqiang Ren, Jiaxu Zhang

Reliable long-horizon co-speech gesture generation requires precise motion representation and consistent structural priors across all joints. Existing generative methods typically operate on local joint rotations, which are defined hierarchically based on the skeleton structure. This leads to cumulative errors during generation, manifesting as unstable and implausible motions at end-effectors. In this work, we propose GlobalDiff, a diffusion-based framework that operates directly in the space of global joint rotations for the first time, fundamentally decoupling each joint's prediction from upstream dependencies and alleviating hierarchical error accumulation. To compensate for the absence of structural priors in global rotation space, we introduce a multi-level constraint scheme. Specifically, a joint structure constraint introduces virtual anchor points around each joint to better capture fine-grained orientation. A skeleton structure constraint enforces angular consistency across bones to maintain structural integrity. A temporal structure constraint utilizes a multi-scale variational encoder to align the generated motion with ground-truth temporal patterns. These constraints jointly regularize the global diffusion process and reinforce structural awareness. Extensive evaluations on standard co-speech benchmarks show that GlobalDiff generates smooth and accurate motions, improving the performance by 46.0% compared to the current SOTA under multiple speaker identities.

arXiv

World-in-World: World Models in a Closed-Loop World

Jiahan Zhang, Muqing Jiang, Nanru Dai, TaiMing Lu, Arda Uzunoglu, Shunchi Zhang, Yana Wei, Jiahao Wang, Vishal M. Patel, Paul Pu Liang, Daniel Khashabi, Cheng Peng, Rama Chellappa, Tianmin Shu, Alan Yuille, Yilun Du, Jieneng Chen

Generative world models (WMs) can now simulate worlds with striking visual realism, which naturally raises the question of whether they can endow embodied agents with predictive perception for decision making. Progress on this question has been limited by fragmented evaluation: most existing benchmarks adopt open-loop protocols that emphasize visual quality in isolation, leaving the core issue of embodied utility unresolved, i.e., do WMs actually help agents succeed at embodied tasks? To address this gap, we introduce World-in-World, the first open platform that benchmarks WMs in a closed-loop world that mirrors real agent-environment interactions. World-in-World provides a unified online planning strategy and a standardized action API, enabling heterogeneous WMs for decision making. We curate four closed-loop environments that rigorously evaluate diverse WMs, prioritize task success as the primary metric, and move beyond the common focus on visual quality; we also present the first data scaling law for world models in embodied settings. Our study uncovers three surprises: (1) visual quality alone does not guarantee task success, controllability matters more; (2) scaling post-training with action-observation data is more effective than upgrading the pretrained video generators; and (3) allocating more inference-time compute allows WMs to substantially improve closed-loop performance.

arXiv

Recurrent Cross-View Object Geo-Localization

Xiaohan Zhang, Si-Yuan Cao, Xiaokai Bai, Yiming Li, Zhangkai Shen, Zhe Wu, Lun Luo, Qi Ming, Xiaoxi Hu, Hui-liang Shen

Cross-view object geo-localization (CVOGL) aims to determine the location of a specific object in high-resolution satellite imagery given a query image with a point prompt. Existing approaches treat CVOGL as a one-shot detection process, directly regressing object locations from cross-view information aggregation, but they are vulnerable to feature noise and lack mechanisms for error correction. In this paper, we propose ReCOT, a Recurrent Cross-view Object geo-localization Transformer, which models CVOGL as a recurrent localization process. ReCOT introduces a set of learnable tokens that encode task-specific intent from the query image and prompt embeddings, and iteratively attend to the reference features to refine the predicted location. To enhance this recurrent process, we incorporate two complementary modules: (1) a SAM-based knowledge distillation strategy that transfers segmentation priors from the Segment Anything Model (SAM) to provide clearer semantic guidance without additional inference cost, and (2) a Reference Feature Enhancement Module (RFEM) that introduces hierarchical attention to emphasize object-relevant regions in the reference features. Extensive experiments on CVOGL benchmarks demonstrate that ReCOT achieves state-of-the-art (SOTA) performance while significantly reducing parameters compared to previous SOTA approaches. Our code is available at https://github.com/Temperature-ai/ReCOT.git.

arXiv

Vision-Based Calorie Estimation for Bangladeshi Street Food: A Comparative Study of Detection and Regression Models

Aparup Dhar, Antu Das, Pritom Barua, MD Tamim Hossain

With obesity emerging as a major global health concern, accurate calorie estimation systems have become increasingly important for effective dietary management. Current vision-based approaches are inappropriate for Bangladeshi street food, which is widely consumed and culturally significant, because they mostly focus on Western cuisines and often overlook portion size. The purpose of this research is to offer a vision-based calorie estimation methodology that was created especially for street food in Bangladesh. Training, validation and testing splits were created from a proprietary dataset of 3,885 photos from six classes (Singara, Somusa, Puri, Peaju, Beguni, and Coin as a reference). Five detection and segmentation architectures, YOLOv8n, YOLO11n, YOLO12n, YOLO26n and RF-DETR, were methodically compared. Food dimensions were scaled using a Bangladeshi 5 Taka coin as a reference. To predict calories, extracted geometric characteristics were subsequently fed into machine learning regression models such as Random Forest, Gradient Boost and AdaBoost. YOLO11n outperformed other models with the best detection performance, achieving 96.1% mAP@50 and balanced mask metrics. With a mean absolute error (MAE) of 5.68, root mean squared error (RMSE) of 7.23, and an R2 score of 95.0%, Random Forest regression produced the best results for calorie estimation. YOLO11n in conjunction with Random Forest regression offers a precise and effective calorie estimation for street food in Bangladesh, which is useful for dietary monitoring and mobile health apps. The code and dataset are publicly available on https://github.com/hossain-tamim/BD-CAL .

arXiv

Lightweight Deep Learning-Based Channel Estimation for RIS-Aided Extremely Large-Scale MIMO Systems on Resource-Limited Edge Devices

Muhammad Kamran Saeed, Ashfaq Khokhar, Shakil Ahmed

Next-generation wireless technologies such as 6G aim to meet demanding requirements such as ultra-high data rates, low latency, and enhanced connectivity. Extremely Large-Scale MIMO (XL-MIMO) and Reconfigurable Intelligent Surface (RIS) are key enablers, with XL-MIMO boosting spectral and energy efficiency through numerous antennas, and RIS offering dynamic control over the wireless environment via passive reflective elements. However, realizing their full potential depends on accurate Channel State Information (CSI). Recent advances in deep learning have facilitated efficient cascaded channel estimation. However, the scalability and practical deployment of existing estimation models in XL-MIMO systems remain limited. The growing number of antennas and RIS elements introduces a significant barrier to real-time and efficient channel estimation, drastically increasing data volume, escalating computational complexity, requiring advanced hardware, and resulting in substantial energy consumption. To address these challenges, we propose a lightweight deep learning framework for efficient cascaded channel estimation in XL-MIMO systems, designed to minimize computational complexity and make it suitable for deployment on resource-constrained edge devices. Using spatial correlations in the channel, we introduce a patch-based training mechanism that reduces the dimensionality of input to patch-level representations while preserving essential information, allowing scalable training for large-scale systems. Simulation results under diverse conditions demonstrate that our framework significantly improves estimation accuracy and reduces computational complexity, regardless of the increasing number of antennas and RIS elements in XL-MIMO systems.

arXiv

Prompt Engineering in Segment Anything Model: Methodologies, Applications, and Emerging Challenges

Yidong Jiang, Jiangtong Li, Daiwei Cheng

The Segment Anything Model (SAM) has transformed image segmentation by introducing a prompt-based paradigm that enables strong zero-shot generalization. In this framework, prompts serve as a semantic interface between human intent and machine perception, making prompt engineering a central factor in model performance. Despite its importance, prompt engineering within SAM and its variants has not yet been systematically reviewed in the literature. This survey addresses that gap by providing a structured and comprehensive overview of prompt engineering techniques developed for SAM and its rapidly growing ecosystem. We introduce a hierarchical taxonomy that organizes methods into geometric prompts, textual semantic prompts, and multimodal fusion prompts, and analyze how these categories reflect different design principles and application goals. In addition, we examine the transition from manually crafted prompts to more advanced, automated approaches based on detector outputs, prototype learning, reinforcement learning, and vision-language models. Beyond categorizing existing work, we trace how prompt engineering has enabled SAM to generalize across domains such as medical imaging, remote sensing, industrial inspection, and anomaly detection. We further identify key challenges---including prompt sensitivity, cross-modal misalignment, and computational inefficiency---and highlight promising research directions such as causal prompt reasoning, collaborative multi-agent prompting, and diffusion-based progressive refinement. By consolidating these developments into a unified perspective, our survey provides a timely reference for understanding the role of prompt engineering in segmentation foundation models and lays the groundwork for future advances in this evolving field.

arXiv

IMPLICITSTAINER: Resolution Agnostic Data-Efficient Virtual Staining Using Neural Implicit Functions

Tushar Kataria, Beatrice Knudsen, Shireen Y. Elhabian

Hematoxylin and eosin (H&E)-stained slides are central to cancer diagnosis and monitoring, visualizing tissue architecture and cellular morphology. However, H&E lacks the molecular specificity needed to distinguish cell states and functional activation. Antibody-based stains, such as immunohistochemistry (IHC), are therefore required to identify specific phenotypes (e.g., CD3$^+$ T cells or HER2-positive tumor cells) but are costly, time-consuming, and not universally available. Deep learning-based image translation methods, often termed virtual staining, offer a complementary alternative by generating virtual immunostains directly from H&E images. Most existing virtual staining methods are patch-based and operate at fixed resolutions, often requiring large datasets and additional post-hoc super-resolution models to generate high-resolution images. Furthermore, GAN- and diffusion-based approaches introduce stochasticity into generated stains which, although beneficial for visual realism in natural images, can lead to hallucinations and structural distortions that affect the accuracy and reliability required for clinical use. We propose IMPLICITSTAINER, a deterministic framework that reformulates virtual staining as a continuous pixel-level translation problem. In contrast to existing patch-based approaches, IMPLICITSTAINER formulates image translation as a continuous spatial mapping using neural implicit deep learning models. Each target-domain (IHC) pixel is predicted from a high-dimensional embedding of the corresponding source-domain H&E pixel, its local spatial neighborhood, and explicit coordinate information. IMPLICITSTAINER enables resolution-agnostic inference, improves robustness in low-data regimes, and yields deterministic, reproducible outputs. Across more than twenty baselines, IMPLICITSTAINER achieves SOTA performance on virtual staining tasks, including IHC and mIF.

arXiv

EchoMask: Speech-Queried Attention-based Mask Modeling for Holistic Co-Speech Motion Generation

Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Jianqiang Ren, Liefeng Bo, Zhigang Tu

Masked modeling has shown promise in co-speech gesture generation. However, it struggles to identify semantically significant frames for effective motion masking. In this work, we propose a speech-queried attention-based mask modeling framework for holistic co-speech gesture generation. Our key insight is to leverage motion-aligned speech features to guide the masked motion modeling process, selectively masking rhythm-related and semantically expressive motion frames. Specifically, we first propose a motion-audio alignment module (MAM) to construct a latent motion-audio joint space. In this space, both low-level and high-level speech features are projected, enabling motion-aligned speech representation using learnable speech queries. Then, a speech-queried attention mechanism (SQA) is introduced to compute frame-level attention scores through interactions between motion keys and speech queries, guiding selective masking toward motion frames with high attention scores. Finally, the motion-aligned speech features are also injected into the generation network to facilitate co-speech motion generation. Qualitative and quantitative evaluations confirm that our method outperforms existing state-of-the-art approaches, successfully producing high-quality co-speech motion.

arXiv

DrivingWorld: Constructing World Model for Autonomous Driving via Video GPT

Xiaotao Hu, Mingkai Jia, Xiaoyang Guo, Qian Zhang, Xiao-Xiao Long, Wei Yin

Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous driving by building video-based world models capable of generating realistic future video sequences and predicting ego states. However, prior works tend to produce unsatisfactory results, as the classic GPT framework is designed to handle 1D contextual information, such as text, and lacks the inherent ability to model the spatial and temporal dynamics essential for video generation. In this paper, we present DrivingWorld, a GPT-style world model for autonomous driving, featuring several spatial-temporal fusion mechanisms. This design enables effective modeling of both spatial and temporal dynamics, facilitating high-fidelity, long-duration video generation. Specifically, we propose a next-state prediction strategy to model temporal coherence between consecutive frames and apply a next-token prediction strategy to capture spatial information within each frame. To further enhance generalization ability, we propose a novel masking strategy and reweighting strategy for token prediction to mitigate long-term drifting issues and enable precise control. Our work demonstrates the ability to produce high-fidelity and consistent video clips of over 40 seconds in duration, which is over 2 times longer than state-of-the-art driving world models. Experiments show that, in contrast to prior works, our method achieves superior visual quality and significantly more accurate controllable future video generation. Our code is available at https://github.com/YvanYin/DrivingWorld.

arXiv

SemTalk: Holistic Co-speech Motion Generation with Frame-level Semantic Emphasis

Xiangyue Zhang, Jianfang Li, Jiaxu Zhang, Ziqiang Dang, Jianqiang Ren, Liefeng Bo, Zhigang Tu

Co-speech gesture generation must carefully integrate common rhythmic motion with rare yet essential semantic gestures. In this work, we propose SemTalk for holistic co-speech gesture generation with frame-level semantic emphasis. Our key insight is to separately learn base motions and sparse motions, and then adaptively fuse them. In particular, coarse2fine cross-attention module and rhythmic consistency learning are explored to establish rhythm-related base motion, ensuring a coherent foundation that synchronizes gestures with the speech rhythm. Subsequently, semantic emphasis learning is designed to generate semantic-aware sparse motion, focusing on frame-level semantic cues. Finally, to integrate sparse motion into the base motion and generate semantic-emphasized co-speech gestures, we further leverage a learned semantic score for adaptive synthesis. Qualitative and quantitative comparisons on two public datasets demonstrate that our method outperforms the state-of-the-art, delivering high-quality co-speech motion with enhanced semantic richness over a stable base motion.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.