Hasil untuk "Vocational guidance. Career development"

Youngwoo Shin, Jiwan Hur, Junmo Kim

Visual autoregressive (VAR) models generate images through next-scale prediction, naturally achieving coarse-to-fine, fast, high-fidelity synthesis mirroring human perception. In practice, this hierarchy can drift at inference time, as limited capacity and accumulated error cause the model to deviate from its coarse-to-fine nature. We revisit this limitation from an information-theoretic perspective and deduce that ensuring each scale contributes high-frequency content not explained by earlier scales mitigates the train-inference discrepancy. With this insight, we propose Scaled Spatial Guidance (SSG), training-free, inference-time guidance that steers generation toward the intended hierarchy while maintaining global coherence. SSG emphasizes target high-frequency signals, defined as the semantic residual, isolated from a coarser prior. To obtain this prior, we leverage a principled frequency-domain procedure, Discrete Spatial Enhancement (DSE), which is devised to sharpen and better isolate the semantic residual through frequency-aware construction. SSG applies broadly across VAR models leveraging discrete visual tokens, regardless of tokenization design or conditioning modality. Experiments demonstrate SSG yields consistent gains in fidelity and diversity while preserving low latency, revealing untapped efficiency in coarse-to-fine image generation. Code is available at https://github.com/Youngwoo-git/SSG.

Haohang Xu, Lin Liu, Zhibo Zhang et al.

Diffusion-based image editing models have achieved significant progress in real world applications. However, conventional models typically rely on natural language prompts, which often lack the precision required to localize target objects. Consequently, these models struggle to maintain background consistency due to their global image regeneration paradigm. Recognizing that visual cues provide an intuitive means for users to highlight specific areas of interest, we utilize bounding boxes as guidance to explicitly define the editing target. This approach ensures that the diffusion model can accurately localize the target while preserving background consistency. To achieve this, we propose FineEdit, a multi-level bounding box injection method that enables the model to utilize spatial conditions more effectively. To support this high precision guidance, we present FineEdit-1.2M, a large scale, fine-grained dataset comprising 1.2 million image editing pairs with precise bounding box annotations. Furthermore, we construct a comprehensive benchmark, termed FineEdit-Bench, which includes 1,000 images across 10 subjects to effectively evaluate region based editing capabilities. Evaluations on FineEdit-Bench demonstrate that our model significantly outperforms state-of-the-art open-source models (e.g., Qwen-Image-Edit and LongCat-Image-Edit) in instruction compliance and background preservation. Further assessments on open benchmarks (GEdit and ImgEdit Bench) confirm its superior generalization and robustness.

Jiazhi Guan, Quanwei Yang, Luying Huang et al.

Human-centric video generation has advanced rapidly, yet existing methods struggle to produce controllable and physically consistent Human-Object Interaction (HOI) videos. Existing works rely on dense control signals, template videos, or carefully crafted text prompts, which limit flexibility and generalization to novel objects. We introduce a framework, namely DISPLAY, guided by Sparse Motion Guidance, composed only of wrist joint coordinates and a shape-agnostic object bounding box. This lightweight guidance alleviates the imbalance between human and object representations and enables intuitive user control. To enhance fidelity under such sparse conditions, we propose an Object-Stressed Attention mechanism that improves object robustness. To address the scarcity of high-quality HOI data, we further develop a Multi-Task Auxiliary Training strategy with a dedicated data curation pipeline, allowing the model to benefit from both reliable HOI samples and auxiliary tasks. Comprehensive experiments show that our method achieves high-fidelity, controllable HOI generation across diverse tasks. The project page can be found at \href{https://mumuwei.github.io/DISPLAY/}.

Nanako Shimaoka, Naoyuki Kamiyama, Shinji Hotta et al.

In this paper, we consider a structure-aware optimization problem for decision diagrams used for health guidance. In particular, we focus on decision diagrams that decide to whom public sectors suggest consulting a medical worker. Furthermore, these diagrams decide which notification method should be used for each target person. In this paper, we formulate this problem as an integer program. Then we evaluate its practical usefulness through numerical examples.

Ryan Marinelli

As AI advances, broader consensus is needed to determine research priorities. This endeavor discusses offensive AI and provides guidance by leveraging Sustainable Development Goals (SDGs) and interpretability techniques. The objective is to more effectively establish priorities that balance societal benefits against risks. The two forms of offensive AI evaluated in this study are vulnerability detection agents, which solve Capture- The-Flag challenges, and AI-powered malware.

Jiuniu Wang, Gongjie Zhang, Quanhao Qian et al.

Scalable Vector Graphics (SVGs) are fundamental to digital design and robot control, encoding not only visual structure but also motion paths in interactive drawings. In this work, we introduce RoboSVG, a unified multimodal framework for generating interactive SVGs guided by textual, visual, and numerical signals. Given an input query, the RoboSVG model first produces multimodal guidance, then synthesizes candidate SVGs through dedicated generation modules, and finally refines them under numerical guidance to yield high-quality outputs. To support this framework, we construct RoboDraw, a large-scale dataset of one million examples, each pairing an SVG generation condition (e.g., text, image, and partial SVG) with its corresponding ground-truth SVG code. RoboDraw dataset enables systematic study of four tasks, including basic generation (Text-to-SVG, Image-to-SVG) and interactive generation (PartialSVG-to-SVG, PartialImage-to-SVG). Extensive experiments demonstrate that RoboSVG achieves superior query compliance and visual fidelity across tasks, establishing a new state of the art in versatile SVG generation. The dataset and source code of this project will be publicly available soon.

Shaoyue Wen, Michael Middleton, Songming Ping et al.

Pilots operating modern cockpits often face high cognitive demands due to complex interfaces and multitasking requirements, which can lead to overload and decreased performance. This study introduces AdaptiveCoPilot, a neuroadaptive guidance system that adapts visual, auditory, and textual cues in real time based on the pilot's cognitive workload, measured via functional Near-Infrared Spectroscopy (fNIRS). A formative study with expert pilots (N=3) identified adaptive rules for modality switching and information load adjustments during preflight tasks. These insights informed the design of AdaptiveCoPilot, which integrates cognitive state assessments, behavioral data, and adaptive strategies within a context-aware Large Language Model (LLM). The system was evaluated in a virtual reality (VR) simulated cockpit with licensed pilots (N=8), comparing its performance against baseline and random feedback conditions. The results indicate that the pilots using AdaptiveCoPilot exhibited higher rates of optimal cognitive load states on the facets of working memory and perception, along with reduced task completion times. Based on the formative study, experimental findings, qualitative interviews, we propose a set of strategies for future development of neuroadaptive pilot guidance systems and highlight the potential of neuroadaptive systems to enhance pilot performance and safety in aviation environments.

Danyi Gao

This paper addresses the performance bottlenecks of existing text-driven image generation methods in terms of semantic alignment accuracy and structural consistency. A high-fidelity image generation method is proposed by integrating text-image contrastive constraints with structural guidance mechanisms. The approach introduces a contrastive learning module that builds strong cross-modal alignment constraints to improve semantic matching between text and image. At the same time, structural priors such as semantic layout maps or edge sketches are used to guide the generator in spatial-level structural modeling. This enhances the layout completeness and detail fidelity of the generated images. Within the overall framework, the model jointly optimizes contrastive loss, structural consistency loss, and semantic preservation loss. A multi-objective supervision mechanism is adopted to improve the semantic consistency and controllability of the generated content. Systematic experiments are conducted on the COCO-2014 dataset. Sensitivity analyses are performed on embedding dimensions, text length, and structural guidance strength. Quantitative metrics confirm the superior performance of the proposed method in terms of CLIP Score, FID, and SSIM. The results show that the method effectively bridges the gap between semantic alignment and structural fidelity without increasing computational complexity. It demonstrates a strong ability to generate semantically clear and structurally complete images, offering a viable technical path for joint text-image modeling and image generation.

Weichao Zeng, Yan Shu, Zhenhang Li et al.

Centred on content modification and style preservation, Scene Text Editing (STE) remains a challenging task despite considerable progress in text-to-image synthesis and text-driven image manipulation recently. GAN-based STE methods generally encounter a common issue of model generalization, while Diffusion-based STE methods suffer from undesired style deviations. To address these problems, we propose TextCtrl, a diffusion-based method that edits text with prior guidance control. Our method consists of two key components: (i) By constructing fine-grained text style disentanglement and robust text glyph structure representation, TextCtrl explicitly incorporates Style-Structure guidance into model design and network training, significantly improving text style consistency and rendering accuracy. (ii) To further leverage the style prior, a Glyph-adaptive Mutual Self-attention mechanism is proposed which deconstructs the implicit fine-grained features of the source image to enhance style consistency and vision quality during inference. Furthermore, to fill the vacancy of the real-world STE evaluation benchmark, we create the first real-world image-pair dataset termed ScenePair for fair comparisons. Experiments demonstrate the effectiveness of TextCtrl compared with previous methods concerning both style fidelity and text accuracy.

Yuqian Fu, Yuanheng Zhu, Haoran Li et al.

Efficient exploration is crucial in cooperative multi-agent reinforcement learning (MARL), especially in sparse-reward settings. However, due to the reliance on the unimodal policy, existing methods are prone to falling into the local optima, hindering the effective exploration of better policies. Furthermore, in sparse-reward settings, each agent tends to receive a scarce reward, which poses significant challenges to inter-agent cooperation. This not only increases the difficulty of policy learning but also degrades the overall performance of multi-agent tasks. To address these issues, we propose a Consistency Policy with Intention Guidance (CPIG), with two primary components: (a) introducing a multimodal policy to enhance the agent's exploration capability, and (b) sharing the intention among agents to foster agent cooperation. For component (a), CPIG incorporates a Consistency model as the policy, leveraging its multimodal nature and stochastic characteristics to facilitate exploration. Regarding component (b), we introduce an Intention Learner to deduce the intention on the global state from each agent's local observation. This intention then serves as a guidance for the Consistency Policy, promoting cooperation among agents. The proposed method is evaluated in multi-agent particle environments (MPE) and multi-agent MuJoCo (MAMuJoCo). Empirical results demonstrate that our method not only achieves comparable performance to various baselines in dense-reward environments but also significantly enhances performance in sparse-reward settings, outperforming state-of-the-art (SOTA) algorithms by 20%.

Dario Izzo, Emmanuel Blazquez, Robin Ferede et al.

Spacecraft and drones aimed at exploring our solar system are designed to operate in conditions where the smart use of onboard resources is vital to the success or failure of the mission. Sensorimotor actions are thus often derived from high-level, quantifiable, optimality principles assigned to each task, utilizing consolidated tools in optimal control theory. The planned actions are derived on the ground and transferred onboard where controllers have the task of tracking the uploaded guidance profile. Here we argue that end-to-end neural guidance and control architectures (here called G&CNets) allow transferring onboard the burden of acting upon these optimality principles. In this way, the sensor information is transformed in real time into optimal plans thus increasing the mission autonomy and robustness. We discuss the main results obtained in training such neural architectures in simulation for interplanetary transfers, landings and close proximity operations, highlighting the successful learning of optimality principles by the neural model. We then suggest drone racing as an ideal gym environment to test these architectures on real robotic platforms, thus increasing confidence in their utilization on future space exploration missions. Drone racing shares with spacecraft missions both limited onboard computational capabilities and similar control structures induced from the optimality principle sought, but it also entails different levels of uncertainties and unmodelled effects. Furthermore, the success of G&CNets on extremely resource-restricted drones illustrates their potential to bring real-time optimal control within reach of a wider variety of robotic systems, both in space and on Earth.

Zuozhuo Dai, Zhenghao Zhang, Yao Yao et al.

Image animation is a key task in computer vision which aims to generate dynamic visual content from static image. Recent image animation methods employ neural based rendering technique to generate realistic animations. Despite these advancements, achieving fine-grained and controllable image animation guided by text remains challenging, particularly for open-domain images captured in diverse real environments. In this paper, we introduce an open domain image animation method that leverages the motion prior of video diffusion model. Our approach introduces targeted motion area guidance and motion strength guidance, enabling precise control the movable area and its motion speed. This results in enhanced alignment between the animated visual elements and the prompting text, thereby facilitating a fine-grained and interactive animation generation process for intricate motion sequences. We validate the effectiveness of our method through rigorous experiments on an open-domain dataset, with the results showcasing its superior performance. Project page can be found at https://animationai.github.io/AnimateAnything.

Xudong Zhang, Shuang Gao, Xiaohu Nan et al.

Camera localization is a classical computer vision task that serves various Artificial Intelligence and Robotics applications. With the rapid developments of Deep Neural Networks (DNNs), end-to-end visual localization methods are prosperous in recent years. In this work, we focus on the scene coordinate prediction ones and propose a network architecture named as Structure Guidance Learning (SGL) which utilizes the receptive branch and the structure branch to extract both high-level and low-level features to estimate the 3D coordinates. We design a confidence strategy to refine and filter the predicted 3D observations, which enables us to estimate the camera poses by employing the Perspective-n-Point (PnP) with RANSAC. In the training part, we design the Bundle Adjustment trainer to help the network fit the scenes better. Comparisons with some state-of-the-art (SOTA) methods and sufficient ablation experiments confirm the validity of our proposed architecture.

Junwen He, Yifan Wang, Lijun Wang et al.

Depth-aware panoptic segmentation is an emerging topic in computer vision which combines semantic and geometric understanding for more robust scene interpretation. Recent works pursue unified frameworks to tackle this challenge but mostly still treat it as two individual learning tasks, which limits their potential for exploring cross-domain information. We propose a deeply unified framework for depth-aware panoptic segmentation, which performs joint segmentation and depth estimation both in a per-segment manner with identical object queries. To narrow the gap between the two tasks, we further design a geometric query enhancement method, which is able to integrate scene geometry into object queries using latent representations. In addition, we propose a bi-directional guidance learning approach to facilitate cross-task feature learning by taking advantage of their mutual relations. Our method sets the new state of the art for depth-aware panoptic segmentation on both Cityscapes-DVPS and SemKITTI-DVPS datasets. Moreover, our guidance learning approach is shown to deliver performance improvement even under incomplete supervision labels.

Nicolas Brieu, Felix J. Segerer, Ansh Kapil et al.

Unsupervised and unpaired domain translation using generative adversarial neural networks, and more precisely CycleGAN, is state of the art for the stain translation of histopathology images. It often, however, suffers from the presence of cycle-consistent but non structure-preserving errors. We propose an alternative approach to the set of methods which, relying on segmentation consistency, enable the preservation of pathology structures. Focusing on immunohistochemistry (IHC) and multiplexed immunofluorescence (mIF), we introduce a simple yet effective guidance scheme as a loss function that leverages the consistency of stain translation with stain isolation. Qualitative and quantitative experiments show the ability of the proposed approach to improve translation between the two domains.

Yongsheng Yu, Dawei Du, Libo Zhang et al.

Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks. Previous works usually predict the auxiliary structures (e.g., edges, segmentation and contours) to help fill visually realistic patches in a multi-stage fashion. However, imprecise auxiliary priors may yield biased inpainted results. Besides, it is time-consuming for some methods to be implemented by multiple stages of complex neural networks. To solve this issue, we develop an end-to-end multi-modality guided transformer network, including one inpainting branch and two auxiliary branches for semantic segmentation and edge textures. Within each transformer block, the proposed multi-scale spatial-aware attention module can learn the multi-modal structural features efficiently via auxiliary denormalization. Different from previous methods relying on direct guidance from biased priors, our method enriches semantically consistent context in an image based on discriminative interplay information from multiple modalities. Comprehensive experiments on several challenging image inpainting datasets show that our method achieves state-of-the-art performance to deal with various regular/irregular masks efficiently.

M. V. Simkin

In the recent article Janosov, Battiston, & Sinatra report that they separated the inputs of talent and luck in creative careers. They build on the previous work of Sinatra et al which introduced the Q-model. Under the model the popularity of different elements of culture is a product of two factors: a random factor and a Qfactor, or talent. The latter is fixed for an individual but randomly distributed among different people. This way they explain how some individuals can consistently produce high-impact work. They extract the Q-factors for different scientists, writers, and movie makers from statistical data on popularity of their work. However, in their article they reluctantly state that there is little correlation between popularity and quality ratings of of books and movies (correlation coefficients 0.022 and 0.15). I analyzed the data of the original Q-factor article and obtained a correlation between the citation-based Q-factor and Nobel Prize winning of merely 0.19. I also briefly review few other experiments that found a meager, sometimes even negative, correlation between popularity and quality of cultural products. I conclude that, if there is an ability associated with a high Q-factor it should be more of a marketing ability than an ability to produce a higher quality product. Janosov,

Jin Han Lee, Myung-Kyu Han, Dong Wook Ko et al.

Estimating accurate depth from a single image is challenging because it is an ill-posed problem as infinitely many 3D scenes can be projected to the same 2D scene. However, recent works based on deep convolutional neural networks show great progress with plausible results. The convolutional neural networks are generally composed of two parts: an encoder for dense feature extraction and a decoder for predicting the desired depth. In the encoder-decoder schemes, repeated strided convolution and spatial pooling layers lower the spatial resolution of transitional outputs, and several techniques such as skip connections or multi-layer deconvolutional networks are adopted to recover the original resolution for effective dense prediction. In this paper, for more effective guidance of densely encoded features to the desired depth prediction, we propose a network architecture that utilizes novel local planar guidance layers located at multiple stages in the decoding phase. We show that the proposed method outperforms the state-of-the-art works with significant margin evaluating on challenging benchmarks. We also provide results from an ablation study to validate the effectiveness of the proposed method.

Hiroshi Aida, Takahiro Tsukahara, Yasuo Kawaguchi

A structure consisting of quasi-laminar and turbulent regions in a stripe pattern, which can be found in a transitional plane channel flow, is called `turbulent stripe'. In the previous works, the emergence of this structure was confirmed only in the case of decreasing Reynolds number from turbulent regime. In the present study, its formation from a turbulent spot has been investigated using a direct numerical simulation in a relatively large-scale computational domain of $L_x \times L_y \times L_z = 731.4δ\times 2δ\times 365.7δ$ at ${\rm Re}_τ= 56$ and $L_x \times L_y \times L_z = 640δ\times 2δ\times 320δ$ at ${\rm Re}_τ= 64$. We observed the stripe pattern of quasi-laminar and turbulent regions inside of the spot. However, the turbulent eddies decayed more rapidly for ${\rm Re}_τ= 56$ than those for ${\rm Re}_τ= 64$.. The developed spot at ${\rm Re}_τ= 64$. was found to be different form from that at ${\rm Re}_τ= 56$.

Thomas E. Harrison, Bernard J. McNamara, Paula Szkody et al.

We report astrometric parallaxes for three well known dwarf novae obtained using the Fine Guidance Sensors on the Hubble Space Telescope. We found a parallax for SS Aurigae of Pi = 5.00 +/- 0.64 mas, for SS Cygni we found Pi = 6.02 +/- 0.46 mas, and for U Geminorum we obtained Pi = 10.37 +/- 0.50 mas. These represent the first true trigonometric parallaxes of any dwarf novae. We briefly compare these results with previous distance estimates. This program demonstrates that with a very modest amount of HST observing time, the Fine Guidance Sensors can deliver parallaxes of unrivaled precision.