Classifier-free guidance (CFG) has helped diffusion models achieve great conditional generation in various fields. Recently, more diffusion guidance methods have emerged with improved generation quality and human preference. However, can these emerging diffusion guidance methods really achieve solid and significant improvements? In this paper, we rethink recent progress on diffusion guidance. Our work mainly consists of four contributions. First, we reveal a critical evaluation pitfall that common human preference models exhibit a strong bias towards large guidance scales. Simply increasing the CFG scale can easily improve quantitative evaluation scores due to strong semantic alignment, even if image quality is severely damaged (e.g., oversaturation and artifacts). Second, we introduce a novel guidance-aware evaluation (GA-Eval) framework that employs effective guidance scale calibration to enable fair comparison between current guidance methods and CFG by identifying the effects orthogonal and parallel to CFG effects. Third, motivated by the evaluation pitfall, we design Transcendent Diffusion Guidance (TDG) method that can significantly improve human preference scores in the conventional evaluation framework but actually does not work in practice. Fourth, in extensive experiments, we empirically evaluate recent eight diffusion guidance methods within the conventional evaluation framework and the proposed GA-Eval framework. Notably, simply increasing the CFG scales can compete with most studied diffusion guidance methods, while all methods suffer severely from winning rate degradation over standard CFG. Our work would strongly motivate the community to rethink the evaluation paradigm and future directions of this field.
This paper explains the Visual Milestone Planning (VMP) method using an agile vocabulary to facilitate its adoption by agile practitioners as a front end for a hybrid development process. VMP is a visual and collaborative planning approach which promotes a shared understanding of the work approach and commitment through the direct manipulation by team members of the reified planning constructs involved in the development of the plan. Once the product backlog has been established and relevant milestones identified, a novel construct called the milestone planning matrix is used to document the allocation of product backlog items to milestones. The milestones due dates are later determined by grouping sticky notes representing the work to be performed into time-boxes called work packages and accommodating them on a resource and time scaled scheduling canvas very much as it would be done in a Tetris game.
Abstract Career development theories can help practitioners to support their clients’ career development, yet evidence suggests that they are not well used in practice. This study explores career practitioners’ perceptions of the value that career development theories can add in guidance. Data were gathered through semi-structured interviews with thirty UK career practitioners exploring their perceptions of the benefits of theory-driven practice and were analysed with a reflexive thematic analysis. Three themes were developed: theories add value through boosting the confidence of client and practitioner, through deepening the understanding of client and practitioner, and through directly and indirectly improving career guidance conversations.
The relevance of this scientific study lies in the growing significance of analyzing state-level strategies in the sphere of vocational guidance as a critical factor contributing to the formation and development of the welfare state. In contemporary socio-political discourse, the role of professional orientation has shifted from a narrow educational task to a broader instrument of socio-economic regulation and social integration. Accordingly, this research seeks to explore the interconnection between state-led career guidance policies and the structural evolution of the welfare state. The central objective is to evaluate the extent to which national policies in vocational guidance contribute to enhancing social development indicators and consolidating welfare institutions.
The study sets out a series of research tasks to achieve this aim. These include: the theoretical and methodological analysis of the state's role in career guidance as a developmental mechanism; the identification of global trends in public policy on youth career assistance; a comparative assessment of international best practices in implementing vocational orientation strategies; the development of methodological tools to evaluate the impact of diverse state approaches on welfare development; and the formulation of policy recommendations for public administration bodies regarding the use of career guidance as a strategic tool for social state advancement.
The research is grounded in a systems analysis approach, allowing the examination of vocational guidance as part of a complex and interrelated system operating under conditions of political and economic uncertainty. A comprehensive set of qualitative and quantitative research methods was employed, including comparative analysis, logical reasoning, synthesis, deduction, classification techniques, and sociological surveys. The empirical part of the study is supported by visualized data in the form of tables and charts, which illustrate the characteristics and effectiveness of various state approaches, stages of career guidance implementation, structural models of vocational education institutions, and the results of surveys conducted among target populations.
Keywords: methods of improving the state activity, sustainable social development, shortage of personnel, vocational guidance of applicants.
Score-based generative models require guidance in order to generate plausible, on-manifold samples. The most popular guidance method, Classifier-Free Guidance (CFG), is only applicable in settings with labeled data and requires training an additional unconditional score-based model. More recently, Auto-Guidance adopts a smaller, less capable version of the original model to guide generation. While each method effectively promotes the fidelity of generated data, each requires labeled data or the training of additional models, making it challenging to guide score-based models when (labeled) training data are not available or training new models is not feasible. We make the surprising discovery that the positive curvature of log density estimates in saddle regions provides strong guidance for score-based models. Motivated by this, we develop saddle-free guidance (SFG) which maintains estimates of maximal positive curvature of the log density to guide individual score-based models. SFG has the same computational cost of classifier-free guidance, does not require additional training, and works with off-the-shelf diffusion and flow matching models. Our experiments indicate that SFG achieves state-of-the-art FID and FD-DINOv2 metrics in single-model unconditional ImageNet-512 generation. When SFG is combined with Auto-Guidance, its unconditional samples achieve general state-of-the-art in FD-DINOv2 score. Our experiments with FLUX.1-dev and Stable Diffusion v3.5 indicate that SFG boosts the diversity of output images compared to CFG while maintaining excellent prompt adherence and image fidelity.
We study masked discrete diffusion models with classifier-free guidance (CFG). Assuming no score error nor discretization error, we derive an explicit solution to the guided reverse dynamics, so that how guidance influences the sampling behavior can be precisely characterized. When the full data distribution is a mixture over classes and the goal is to sample from a specific class, guidance amplifies class-specific regions while suppresses regions shared with other classes. This effect depends on the guidance strength $w$ and induces distinct covariance structures in the sampled distribution. Notably, we observe quantitatively different behaviors in $1$D and $2$D. We also show that for large $w$, the decay rate of the total variation ($\mathrm{TV}$) along the reverse dynamics is double-exponential in $w$ for both $1$D and $2$D. These findings highlight the role of guidance, not just in shaping the output distribution, but also in controlling the dynamics of the sampling trajectory. Our theoretical analysis is supported by experiments that illustrate the geometric effects of guidance and its impact on convergence.
AI development environments are evolving into observability first platforms that integrate real time telemetry, prompt traces, and evaluation feedback into the developer workflow. This paper introduces telemetry aware integrated development environments (IDEs) enabled by the Model Context Protocol (MCP), a system that connects IDEs with prompt metrics, trace logs, and versioned control for real time refinement. We present design patterns for local prompt iteration, CI based optimization, and autonomous agents that adapt behavior using telemetry. Rather than focusing on a single algorithm, we describe an architecture that supports integration with frameworks like DSPy, PromptWizard, and Prompts as Programs. We demonstrate this through Opik, an open source MCP server for LLM telemetry, and position our approach within the emerging LLMOps ecosystem. This work lays a foundation for future research on prompt optimization, IDE agent tooling, and empirical benchmarking in telemetry rich AI development workflows.
Classifier free guidance has shown strong potential in diffusion-based reinforcement learning. However, existing methods rely on joint training of the guidance module and the diffusion model, which can be suboptimal during the early stages when the guidance is inaccurate and provides noisy learning signals. In offline RL, guidance depends solely on offline data: observations, actions, and rewards, and is independent of the policy module's behavior, suggesting that joint training is not required. This paper proposes modular training methods that decouple the guidance module from the diffusion model, based on three key findings: Guidance Necessity: We explore how the effectiveness of guidance varies with the training stage and algorithm choice, uncovering the roles of guidance and diffusion. A lack of good guidance in the early stage presents an opportunity for optimization. Guidance-First Diffusion Training: We introduce a method where the guidance module is first trained independently as a value estimator, then frozen to guide the diffusion model using classifier-free reward guidance. This modularization reduces memory usage, improves computational efficiency, and enhances both sample efficiency and final performance. Cross-Module Transferability: Applying two independently trained guidance models, one during training and the other during inference, can significantly reduce normalized score variance (e.g., reducing IQR by 86%). We show that guidance modules trained with one algorithm (e.g., IDQL) can be directly reused with another (e.g., DQL), with no additional training required, demonstrating baseline-level performance as well as strong modularity and transferability. We provide theoretical justification and empirical validation on bullet D4RL benchmarks. Our findings suggest a new paradigm for offline RL: modular, reusable, and composable training pipelines.
Federated Recommendation (FedRec) has emerged as a key paradigm for building privacy-preserving recommender systems. However, existing FedRec models face a critical dilemma: memory-efficient single-knowledge models suffer from a suboptimal knowledge replacement practice that discards valuable personalization, while high-performance dual-knowledge models are often too memory-intensive for practical on-device deployment. We propose Federated Recommendation with Knowledge Guidance (FedRKG), a model-agnostic framework that resolves this dilemma. The core principle, Knowledge Guidance, avoids full replacement and instead fuses global knowledge into preserved local embeddings, attaining the personalization benefits of dual-knowledge within a single-knowledge memory footprint. Furthermore, we introduce Adaptive Guidance, a fine-grained mechanism that dynamically modulates the intensity of this guidance for each user-item interaction, overcoming the limitations of static fusion methods. Extensive experiments on benchmark datasets demonstrate that FedRKG significantly outperforms state-of-the-art methods, validating the effectiveness of our approach. The code is available at https://github.com/Jaehyung-Lim/fedrkg.
Classifier-free guidance has become a staple for conditional generation with denoising diffusion models. However, a comprehensive understanding of classifier-free guidance is still missing. In this work, we carry out an empirical study to provide a fresh perspective on classifier-free guidance. Concretely, instead of solely focusing on classifier-free guidance, we trace back to the root, i.e., classifier guidance, pinpoint the key assumption for the derivation, and conduct a systematic study to understand the role of the classifier. On 1D data, we find that both classifier guidance and classifier-free guidance achieve conditional generation by pushing the denoising diffusion trajectories away from decision boundaries, i.e., areas where conditional information is usually entangled and is hard to learn. To validate this classifier-centric perspective on high-dimensional data, we assess whether a flow-matching postprocessing step that is designed to narrow the gap between a pre-trained diffusion model's learned distribution and the real data distribution, especially near decision boundaries, can improve the performance. Experiments on various datasets verify our classifier-centric understanding.
ABSTRACT Background People with intellectual disabilities may find difficulties in their school-to-work transition. The current study aimed to determine which factors have been investigated and which are relevant to this transition process. Method A systematic review was undertaken using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and included studies published between 2011 and 2023 on initiatives that facilitate the school-to-work transition. Results Four broad types of interventions were encountered: career and vocational guidance, training for the development of key competencies, school-based transition programs, and work-based learning. Most studies were quantitative and included key competencies in training activities that focus on specific skills that facilitate the school-to-work transition process. Conclusions In order to enable the continuity of processes related to school-to-work transition and to improve inclusive employment and social skills for people with intellectual disabilities, there is a clear need to collect initiatives across countries.
سیّد سینا معصومی, محمد حسین اصغرپور, مهرزاد جمشیدی گیلانی
استان گیلان به واسطه شرایط جغرافیایی و اقلیمی و ظرفیتها و پتانسیلهای خاص میتواند با ایجاد و توسعه زنجیره ارزش حشرات خوراکی، منجر به کارآفرینی کشاورزی و رونق اقتصاد محلی شود. به این منظور مطالعه حاضر با هدف تبیین زنجیره ارزش حشرات خوراکی و تدوین راهبردهایی برای ایجاد و توسعه این زنجیره انجام شد. در این مطالعه برای جمعآوری دادههای مورد نظر از اطلاعات کتابخانهای و میدانی (پرسشنامه و مصاحبه) استفاده و سپس یافتههای پژوهش در دو مرحله تجزیه و تحلیل شد. در مرحله اول، صنایع مرتبط با حشرات خوراکی با توجه به پتانسیلهای استان گیلان مورد بررسی قرار گرفت. بر اساس نتایج تحلیل دو صنعت تولید مواد خوراکی بر پایه حشرات و حفظ و پرورش حشرات خوراکی بهعنوان صنایع در حال توسعه در استان گیلان شناسایی شدند. سپس در مرحله دوم به منظور دستیابی به راهبردهایی جهت ایجاد و توسعه صنایع حشرات خوراکی در استان گیلان از روش کیفی داده بنیاد استفاده شد. بر اساس یافتههای حاصل از مصاحبههای نیمه ساختار یافته با خبرگان صنعتی، پنج راهبرد برای در ایجاد و توسعه زنجیره ارزش صنایع مرتبط با حشرات خوراکی در استان گیلان تدوین، و متناسب با هر راهبرد اقداماتی عملیاتی پیشنهاد شد. ازجمله اقدامات تجویزی میتوان به ایجاد انجمنهای تخصصی با همکاری نهادهای علمی-پژوهشی در خصوص ابعاد علمی و فنی حشرات خوراکی اشاره کرد. در نهایت ایجاد پلتفرمی چند ذینفعی برای تسهیل تحقیق و توسعه در این زمینه به منظور اعتلای این صنعت پیشنهاد میشود.
Vocational guidance. Career development, Agriculture (General)
Background. The vocational guidance minimum for students involves the training of teachers-navigators. Systematizing many years of experience in career guidance, the author offers a comprehensive support system for career guidance consultants as a part of specialized programs of additional professional education for teachers-navigators.
Purpose. Analysis of the pilot version of recommendations for teachers-navigators.
Materials and methods. The principles of a systematic approach are chosen as the methodological basis: integrity, structure, hierarchy, multiplicity, that are consistent with the modern understanding of career guidance as a systemic process. An empirical study was conducted using interviews of random respondents in the form of questionnaire survey. The article contains a set of sources presented by normative legal acts, theoretical studies of the problem elaboration in scientific sources and psychological and pedagogical practice, as well as survey materials
Results. Representatives of the educational sphere are often unaware of modern scientific concepts of professional self-determination of students and do not apply them in practice. The request of the professional community for the proposed resource has been identified. In the database, the author combined the key concepts of career guidance, professional self-determination, career navigation, personal potential and potential for choice and self-determination. The author analyzes the feedback from two large segments of the target audience: career guidance consultants (33%) and teacher navigators (67%). We discovered the following: on the one hand, the database is really a resource for teachers-navigators and requires further strengthening; on the other hand, audience often has a request for ready-made solutions (instructions, typical scenarios), but isn’t ready for independent development, that is ensured by the database form itself.
Diffusion models benefit from instillation of task-specific information into the score function to steer the sample generation towards desired properties. Such information is coined as guidance. For example, in text-to-image synthesis, text input is encoded as guidance to generate semantically aligned images. Proper guidance inputs are closely tied to the performance of diffusion models. A common observation is that strong guidance promotes a tight alignment to the task-specific information, while reducing the diversity of the generated samples. In this paper, we provide the first theoretical study towards understanding the influence of guidance on diffusion models in the context of Gaussian mixture models. Under mild conditions, we prove that incorporating diffusion guidance not only boosts classification confidence but also diminishes distribution diversity, leading to a reduction in the differential entropy of the output distribution. Our analysis covers the widely adopted sampling schemes including DDPM and DDIM, and leverages comparison inequalities for differential equations as well as the Fokker-Planck equation that characterizes the evolution of probability density function, which may be of independent theoretical interest.
We introduce segmentation-free guidance, a novel method designed for text-to-image diffusion models like Stable Diffusion. Our method does not require retraining of the diffusion model. At no additional compute cost, it uses the diffusion model itself as an implied segmentation network, hence named segmentation-free guidance, to dynamically adjust the negative prompt for each patch of the generated image, based on the patch's relevance to concepts in the prompt. We evaluate segmentation-free guidance both objectively, using FID, CLIP, IS, and PickScore, and subjectively, through human evaluators. For the subjective evaluation, we also propose a methodology for subsampling the prompts in a dataset like MS COCO-30K to keep the number of human evaluations manageable while ensuring that the selected subset is both representative in terms of content and fair in terms of model performance. The results demonstrate the superiority of our segmentation-free guidance to the widely used classifier-free method. Human evaluators preferred segmentation-free guidance over classifier-free 60% to 19%, with 18% of occasions showing a strong preference. Additionally, PickScore win-rate, a recently proposed metric mimicking human preference, also indicates a preference for our method over classifier-free.
Color information is the most commonly used prior knowledge for depth map super-resolution (DSR), which can provide high-frequency boundary guidance for detail restoration. However, its role and functionality in DSR have not been fully developed. In this paper, we rethink the utilization of color information and propose a hierarchical color guidance network to achieve DSR. On the one hand, the low-level detail embedding module is designed to supplement high-frequency color information of depth features in a residual mask manner at the low-level stages. On the other hand, the high-level abstract guidance module is proposed to maintain semantic consistency in the reconstruction process by using a semantic mask that encodes the global guidance information. The color information of these two dimensions plays a role in the front and back ends of the attention-based feature projection (AFP) module in a more comprehensive form. Simultaneously, the AFP module integrates the multi-scale content enhancement block and adaptive attention projection block to make full use of multi-scale information and adaptively project critical restoration information in an attention manner for DSR. Compared with the state-of-the-art methods on four benchmark datasets, our method achieves more competitive performance both qualitatively and quantitatively.
It is clear, from the major press coverage that Virtual Reality (VR) development is garnering, that there is a huge amount of development interest in VR across multiple industries, including video streaming, gaming and simulated learning. Even though PC, web, and mobile are still the top platforms for software development, it is important for university computer science (CS) programs to expose students to VR as a development platform. Additionally, it is important for CS students to learn how to learn about new technologies, since change is constant in the CS field. CS curriculum changes happen much slower than the pace of technology adoption. As new technologies are introduced, CS faculty and students often learn together, especially in smaller CS programs. This paper describes how student-led VR projects are used, across the CS curriculum, as basic CS concepts are covered. The student-led VR projects are engaging, and promote learning and creativity. Additionally, each student project inspires more students to try their hand at VR development as well.