搜索结果：Harmony

With the popularity of video-based user-generated content (UGC) on social media, harmony, as dictated by human perceptual principles, is critical in assessing the rhythmic consistency of audio-visual UGCs for better user engagement. In this work, we propose a novel harmony-aware GAN framework, following a specifically designed harmony evaluation strategy to enhance rhythmic synchronization in the automatic music-to-motion synthesis using a UGC dance dataset. This harmony strategy utilizes refined cross-modal beat detection to capture closely correlated audio and visual rhythms in an audio-visual pair. To mimic human attention mechanism, we introduce saliency-based beat weighting and interval-driven beat alignment, which ensures accurate harmony score estimation consistent with human perception. Building on this strategy, our model, employing efficient encoder-decoder and depth-lifting designs, is adversarially trained based on categorized musical meter segments to generate realistic and rhythmic 3D human motions. We further incorporate our harmony evaluation strategy as a weakly supervised perceptual constraint to flexibly guide the synchronized audio-visual rhythms during the gene

Is the specific structure of Western tonal harmony a physical inevitability derived from acoustics, or is it merely one solution among many in a purely algebraic landscape? In this paper, we strip away the physics of vibrating strings and treat harmony as the solution to a simple linear system within the cyclic group $\mathbb{Z}_{12}$. By defining a harmonic system as a partitioning of a generator interval (the "Fifth") into two complementary thirds, we derive a complete classification of all possible harmonic universes in 12-Tone Equal Temperament. We show that every such system corresponds to a specific topological structure, visualized via its Levi graph. Our analysis reveals a counter-intuitive fact: the topological structure of standard Western harmony is not unique. It is one of exactly twelve mathematically isomorphic systems. However, we demonstrate that these shadows are not created equal. We identify a "privileged quartet" of systems that preserve the global connectivity of the Circle of Fifths. Furthermore, by invoking the Chinese Remainder Theorem, we present a compelling argument that the most number-theoretically natural system in $\mathbb{Z}_{12}$ is not the Western

No one has independently reproduced OpenAI's published scores for gpt-oss-20b with tools, because the original paper discloses neither the tools nor the agent harness. We reverse-engineered the model's in-distribution tools: when prompted without tool definitions, gpt-oss still calls tools from its training distribution with high statistical confidence -- a strong prior, not a hallucination. We then built a native harmony agent harness (https://github.com/borislavmavrin/harmonyagent.git) that encodes messages in the model's native format, bypassing the lossy Chat Completions conversion. Together, these yield the first independent reproduction of OpenAI's published scores: 60.4% on SWE Verified HIGH (published 60.7%), 53.3% MEDIUM (53.2%), and 91.7% on AIME25 with tools (90.4%).

Mobile devices face diverse resource constraints and non-IID data class distributions, requiring fast on-device inference for local in-distribution (ID) classes and on-demand remote support for client-specific out-of-distribution (OOD) classes. Hybrid split federated learning (Hybrid SFL) couples personalized client-side front ends (supporting early exit) with a generalized server-side backend for fallback inference, balancing accuracy and cost. However, under client architectural heterogeneity, the existing hybrid SFL suffers from representation skew, where features from customized extractors fail to align in the shared space, leading to a sharp degradation in the server model responsible for OOD prediction. We propose HARMONY, the first hybrid SFL framework to support heterogeneous client architectures. HARMONY modifies meta-learning to simulate diverse extractors across parameters and architectures, and to learn to personalize. To mitigate representation skew, HARMONY conducts server-side contrastive learning to align extracted features, neither sacrificing clients' personalization nor sharing raw labels. Compared to the state of the art across multiple datasets and model famili

Harmony level prediction is receiving increasing attention nowadays. Color plays a crucial role in affecting human aesthetic responses. In this paper, we explore color harmony using a fuzzy-based color model and address the question of its universality. For our experiments, we utilize a dataset containing attractive images from five different domains: fashion, art, nature, interior design, and brand logos. We aim to identify harmony patterns and dominant color palettes within these images using a fuzzy approach. It is well-suited for this task because it can handle the inherent subjectivity and contextual variability associated with aesthetics and color harmony evaluation. Our experimental results suggest that color harmony is largely universal. Additionally, our findings reveal that color harmony is not solely influenced by hue relationships on the color wheel but also by the saturation and intensity of colors. In palettes with high harmony levels, we observed a prevalent adherence to color wheel principles while maintaining moderate levels of saturation and intensity. These findings contribute to ongoing research on color harmony and its underlying principles, offering valuable i

Approximate Nearest Neighbor Search (ANNS) is essential for various data-intensive applications, including recommendation systems, image retrieval, and machine learning. Scaling ANNS to handle billions of high-dimensional vectors on a single machine presents significant challenges in memory capacity and processing efficiency. To address these challenges, distributed vector databases leverage multiple nodes for the parallel storage and processing of vectors. However, existing solutions often suffer from load imbalance and high communication overhead, primarily due to traditional partition strategies that fail to effectively distribute the workload. In this paper, we introduce Harmony, a distributed ANNS system that employs a novel multi-granularity partition strategy, combining dimension-based and vector-based partition. This strategy ensures a balanced distribution of computational load across all nodes while effectively minimizing communication costs. Furthermore, Harmony incorporates an early-stop pruning mechanism that leverages the monotonicity of distance computations in dimension-based partition, resulting in significant reductions in both computational and communication over

In a previous submission, we established a fundamental relation between tone networks and configurations. It was shown that the Eulerian tonnetz can be represented by a $\{12_3\}$ of Daublebsky von Sterneck type D222. We also constructed a tonnetz for Tristan-genus chords (dominant sevenths and half-diminished sevenths) and we showed that this tonnetz can be represented by a $\{12_3\}$ of type D228. In both of these constructions the associated Levi graphs play an important role. Here we look at the tonnetze associated with some other musical systems, thereby offering several concrete examples of an abstract view of music as combinatorial geometry. First, we look at the tonal harmonies typical of the classical period. In the case of diatonic triads, we show the existence of a bipartite graph of type $\{7_3\}$ and girth four that represents the well-known relations between the seven diatonic degrees and their pitch classes. In the case of diatonic seventh chords, we obtain a Fano configuration $\{7_3\}$ which gives a complete characterization of the voice-leading relations that hold between such chords. Next, we construct a tonnetz for pentatonic music based on the Desargues configu

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. In this work, we introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task. We approach this as a bi-level optimization problem, employing a meta-learning framework that leverages gradient-based techniques. The upper level of this framework is dedicated to learning a task-specific mask that delineates the harmony subspace, while the inner level focuses on updating parameters to enhance the overall performance of the unified policy. Empirical evaluations on a series of benchmarks demonstrate the superiority of HarmoDT

In this paper, we introduce HEEPS/MARE, the end-to-end simulator developed for the SAR oceanographic products of ESA Earth Explorer 10 mission, Harmony, expected to launch in Decembre 2029. Harmony is primarily dedicated to the observation of small-scale motion and deformation fields of the Earth surface (oceans, glaciers and ice sheets, solid Earth), thanks to passive SAR/ATI receivers carried by two companion satellites for Sentinel-1. The paper focuses on the raw data generator designed to efficiently simulate large, heterogeneous, moving oceanic areas and produce the acquired SAR/ATI bistatic IQ signals. The heterogeneous sea-surface model, bistatic scattering model, multi-GPU implementation and achieved performance are emphasized. Finally, sample results are presented, to illustrate the ability of Harmony to map wind and surface current vectors at kilometric scale.

Large Language Models (LLMs) offer powerful capabilities for natural language understanding, enabling more intelligent smart home assistants. However, existing systems often rely on cloud-based LLMs, raising concerns around user privacy and system dependency on external connectivity. In this work, we present Harmony, a privacy-preserving and robust smart home assistant powered by the locally deployable Llama3-8B model. Beyond protecting user data, Harmony also addresses reliability challenges of smaller models, such as hallucination and instruction misinterpretation, through structured prompting and modular agent design. Experimental results in both virtual environments and user studies show that Harmony achieves performance comparable to GPT-4-based systems, while enabling offline, proactive, and personalized smart home interaction.

The purpose of offline multi-task reinforcement learning (MTRL) is to develop a unified policy applicable to diverse tasks without the need for online environmental interaction. Recent advancements approach this through sequence modeling, leveraging the Transformer architecture's scalability and the benefits of parameter sharing to exploit task similarities. However, variations in task content and complexity pose significant challenges in policy formulation, necessitating judicious parameter sharing and management of conflicting gradients for optimal policy performance. Furthermore, identifying the optimal parameter subspace for each task often necessitates prior knowledge of the task identifier during inference, limiting applicability in real-world scenarios with variable task content and unknown current tasks. In this work, we introduce the Harmony Multi-Task Decision Transformer (HarmoDT), a novel solution designed to identify an optimal harmony subspace of parameters for each task. We formulate this as a bi-level optimization problem within a meta-learning framework, where the upper level learns masks to define the harmony subspace, while the inner level focuses on updating par

Vision-language contrastive learning frameworks such as CLIP enable learning representations from natural language supervision and provide strong zero-shot classification capabilities. However, due to the nature of the supervisory signal in these paradigms, they lack the ability to learn localized features, leading to degraded performance on dense prediction tasks such as segmentation and detection. On the other hand, self-supervised learning methods have shown the ability to learn granular representations, complementing the high-level features in vision-language training. In this work, we present Harmony, a framework that combines vision-language training with discriminative and generative self-supervision to learn visual features that can be generalized across different downstream vision tasks. Our framework is specifically designed to work on web-scraped data by not relying on negative examples in the self-supervised learning path and addressing the one-to-one correspondence issue using soft CLIP targets generated by an EMA model. Moreover, Harmony optimizes for five different objectives simultaneously, efficiently utilizing the supervision in each data example, making it even m

Traditional approaches for understanding phonological learning have predominantly relied on curated text data. Although insightful, such approaches limit the knowledge captured in textual representations of the spoken language. To overcome this limitation, we investigate the potential of the Featural InfoWaveGAN model to learn iterative long-distance vowel harmony using raw speech data. We focus on Assamese, a language known for its phonologically regressive and word-bound vowel harmony. We demonstrate that the model is adept at grasping the intricacies of Assamese phonotactics, particularly iterative long-distance harmony with regressive directionality. It also produced non-iterative illicit forms resembling speech errors during human language acquisition. Our statistical analysis reveals a preference for a specific [+high,+ATR] vowel as a trigger across novel items, indicative of feature learning. More data and control could improve model proficiency, contrasting the universality of learning.

Color is the most important intrinsic sensory feature that has a powerful impact on product sales. Color is even responsible for raising the aesthetic senses in our brains. Account for individual differences is crucial in color aesthetics. It requires user-driven mechanisms for various e-commerce applications. We propose a method for quantitative evaluation of all types of perceptual responses to color(s): distinct color preference, color harmony, and color combination preference. Preference for color schemes can be predicted by combining preferences for the basic colors and ratings of color harmony. Harmonious pallets are extracted from big data set using comparison algorithms based on fuzzy similarity and grouping. The proposed model results in useful predictions of harmony and preference of multicolored images. For example, in the context of apparel coordination, it allows predicting a preference for a look based on clothing colors. Our approach differs from standard aesthetic models, since in accounts for a personal variation. In addition, it can process not only lower-order color pairs, but also groups of several colors.

The basal ganglia (BG) in the brain exhibit diverse functions for motor, cognition, and emotion. Such BG functions could be made via competitive harmony between the two competing pathways, direct pathway (DP) (facilitating movement) and indirect pathway (IP) (suppressing movement). As a result of break-up of harmony between DP and IP, there appear pathological states with disorder for movement, cognition, and psychiatry. In this paper, we are concerned about the Huntington's disease (HD), which is a genetic neurodegenerative disorder causing involuntary movement and severe cognitive and psychiatric symptoms. For the HD, the number of D2 SPNs ($N_{\rm D2}$) is decreased due to degenerative loss, and hence, by decreasing $x_{\rm D2}$ (fraction of $N_{\rm D2}$), we investigate break-up of harmony between DP and IP in terms of their competition degree ${\cal C}_d$, given by the ratio of strength of DP (${\cal S}_{DP}$) to strength of IP (${\cal S}_{IP}$) (i.e., ${\cal C}_d = {\cal S}_{DP} / {\cal S}_{IP}$). In the case of HD, the IP is under-active, in contrast to the case of Parkinson's disease with over-active IP, which results in increase in ${\cal C}_d$ (from the normal value). Thu

Correlations between quantum theory and music theory - specifically between principles of quantum computing and musical harmony - can lead to new understandings and new methodologies for music theorists and composers. The quantum principle of superposition is shown to be closely related to different interpretations of musical meaning. Superposition is implemented directly in the authors' simulations of quantum computing, as applied in the decision-making processes of computer-generated music composition.

Child drawing development optimization (CDDO) is a recent example of a metaheuristic algorithm. The motive for inventing this method is children's learning behavior and cognitive development, with the golden ratio employed to optimize their artwork's aesthetic value. Unfortunately, CDDO suffers from low performance in the exploration phase, and the local best solution stagnates. Harmony search (HS) is a highly competitive algorithm relative to other prevalent metaheuristic algorithms, as its exploration phase performance on unimodal benchmark functions is outstanding. Thus, to avoid these issues, we present CDDOHS, a hybridization of both standards of CDDO and HS. The hybridized model proposed consists of two phases. Initially, the pattern size (PS) is relocated to the algorithm's core and the initial pattern size is set to 80 % of the total population size. Second, the standard harmony search (HS) is added to the pattern size (PS) for the exploration phase to enhance and update the solution after each iteration. Experiments are evaluated using two distinct standard benchmark functions, known as classical test functions, including 23 common functions and 10 CEC-C06 2019 functions.

Music is a complex socio-cultural construct, which fascinates researchers in diverse fields, as well as the general public. Understanding the historical development of music may help us understand perceptual and cognition, while also yielding insight in the processes of cultural transmission, creativity, and innovation. Here, we present a study of musical features related to harmony, and we document how they evolved over 400 years in western classical music. We developed a variant of the center of effect algorithm to call the most likely for a given set of notes, to represent a musical piece as a sequence of local keys computed measure by measure. We develop measures to quantify key uncertainty, and diversity and novelty in key transitions. We provide specific examples to demonstrate the features represented by these concepts, and we argue how they are related to harmonic complexity and can be used to study the evolution of harmony. We confirm several observations and trends previously reported by musicologists and scientists, with some discrepancies during the Classical period. We report a decline in innovation in harmonic transitions in the early classical period followed by a st

A derivation of Balmer's formula is presented, guided by the principles of simplicity and harmony.