Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought

We introduce Skywork R1V, a multimodal reasoning model extending the an R1-series Large language models (LLM) to visual modalities via an efficient multimodal transfer method. Leveraging a lightweight visual projector, Skywork R1V facilitates seamless multimodal adaptation without necessitating retraining of either the foundational language model or the vision encoder. To strengthen visual-text alignment, we propose a hybrid optimization strategy that combines Iterative Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), significantly enhancing cross-modal integration efficiency. Additionally, we introduce an adaptive-length Chain-of-Thought distillation approach for reasoning data generation. This approach dynamically optimizes reasoning chain lengths, thereby enhancing inference efficiency and preventing excessive reasoning overthinking. Empirical evaluations demonstrate that Skywork R1V, with only 38B parameters, delivers competitive performance, achieving a score of 69.0 on the MMMU benchmark and 67.5 on MathVista. Meanwhile, it maintains robust textual reasoning performance, evidenced by impressive scores of 72.0 on AIME and 94.0 on MATH500. The Skywork R1V model weights have been publicly released to promote openness and reproducibility.

Analyzable Chain-of-Musical-Thought Prompting for High-Fidelity Music Generation

Autoregressive (AR) models have demonstrated impressive capabilities in generating high-fidelity music. However, the conventional next-token prediction paradigm in AR models does not align with the human creative process in music composition, potentially compromising the musicality of generated samples. To overcome this limitation, we introduce MusiCoT, a novel chain-of-thought (CoT) prompting technique tailored for music generation. MusiCoT empowers the AR model to first outline an overall music structure before generating audio tokens, thereby enhancing the coherence and creativity of the resulting compositions. By leveraging the contrastive language-audio pretraining (CLAP) model, we establish a chain of "musical thoughts", making MusiCoT scalable and independent of human-labeled data, in contrast to conventional CoT methods. Moreover, MusiCoT allows for in-depth analysis of music structure, such as instrumental arrangements, and supports music referencing -- accepting variable-length audio inputs as optional style references. This innovative approach effectively addresses copying issues, positioning MusiCoT as a vital practical method for music prompting. Our experimental results indicate that MusiCoT consistently achieves superior performance across both objective and subjective metrics, producing music quality that rivals state-of-the-art generation models. Our samples are available at https://MusiCoT.github.io/.

Music Era Recognition Using Supervised Contrastive Learning and Artist Information

Does popular music from the 60s sound different than that of the 90s? Prior study has shown that there would exist some variations of patterns and regularities related to instrumentation changes and growing loudness across multi-decadal trends. This indicates that perceiving the era of a song from musical features such as audio and artist information is possible. Music era information can be an important feature for playlist generation and recommendation. However, the release year of a song can be inaccessible in many circumstances. This paper addresses a novel task of music era recognition. We formulate the task as a music classification problem and propose solutions based on supervised contrastive learning. An audio-based model is developed to predict the era from audio. For the case where the artist information is available, we extend the audio-based model to take multimodal inputs and develop a framework, called MultiModal Contrastive (MMC) learning, to enhance the training. Experimental result on Million Song Dataset demonstrates that the audio-based model achieves 54% in accuracy with a tolerance of 3-years range; incorporating the artist information with the MMC framework for training leads to 9% improvement further.

A Long-Tail Friendly Representation Framework for Artist and Music Similarity

The investigation of the similarity between artists and music is crucial in music retrieval and recommendation, and addressing the challenge of the long-tail phenomenon is increasingly important. This paper proposes a Long-Tail Friendly Representation Framework (LTFRF) that utilizes neural networks to model the similarity relationship. Our approach integrates music, user, metadata, and relationship data into a unified metric learning framework, and employs a meta-consistency relationship as a regular term to introduce the Multi-Relationship Loss. Compared to the Graph Neural Network (GNN), our proposed framework improves the representation performance in long-tail scenarios, which are characterized by sparse relationships between artists and music. We conduct experiments and analysis on the AllMusic dataset, and the results demonstrate that our framework provides a favorable generalization of artist and music representation. Specifically, on similar artist/music recommendation tasks, the LTFRF outperforms the baseline by 9.69%/19.42% in Hit Ratio@10, and in long-tail cases, the framework achieves 11.05%/14.14% higher than the baseline in Consistent@10.

InstructME: An Instruction Guided Music Edit And Remix Framework with Latent Diffusion Models

Music editing primarily entails the modification of instrument tracks or remixing in the whole, which offers a novel reinterpretation of the original piece through a series of operations. These music processing methods hold immense potential across various applications but demand substantial expertise. Prior methodologies, although effective for image and audio modifications, falter when directly applied to music. This is attributed to music's distinctive data nature, where such methods can inadvertently compromise the intrinsic harmony and coherence of music. In this paper, we develop InstructME, an Instruction guided Music Editing and remixing framework based on latent diffusion models. Our framework fortifies the U-Net with multi-scale aggregation in order to maintain consistency before and after editing. In addition, we introduce chord progression matrix as condition information and incorporate it in the semantic space to improve melodic harmony while editing. For accommodating extended musical pieces, InstructME employs a chunk transformer, enabling it to discern long-term temporal dependencies within music sequences. We tested InstructME in instrument-editing, remixing, and multi-round editing. Both subjective and objective evaluations indicate that our proposed method significantly surpasses preceding systems in music quality, text relevance and harmony. Demo samples are available at https://musicedit.github.io/

Efficient Neural Music Generation

Recent progress in music generation has been remarkably advanced by the state-of-the-art MusicLM, which comprises a hierarchy of three LMs, respectively, for semantic, coarse acoustic, and fine acoustic modelings. Yet, sampling with the MusicLM requires processing through these LMs one by one to obtain the fine-grained acoustic tokens, making it computationally expensive and prohibitive for a real-time generation. Efficient music generation with a quality on par with MusicLM remains a significant challenge. In this paper, we present MeLoDy (M for music; L for LM; D for diffusion), an LM-guided diffusion model that generates music audios of state-of-the-art quality meanwhile reducing 95.7% or 99.6% forward passes in MusicLM, respectively, for sampling 10s or 30s music. MeLoDy inherits the highest-level LM from MusicLM for semantic modeling, and applies a novel dual-path diffusion (DPD) model and an audio VAE-GAN to efficiently decode the conditioning semantic tokens into waveform. DPD is proposed to simultaneously model the coarse and fine acoustics by incorporating the semantic information into segments of latents effectively via cross-attention at each denoising step. Our experimental results suggest the superiority of MeLoDy, not only in its practical advantages on sampling speed and infinitely continuable generation, but also in its state-of-the-art musicality, audio quality, and text correlation. Our samples are available at https://Efficient-MeLoDy.github.io/.

RECAP: Retrieval Augmented Music Captioner

With the prevalence of stream media platforms serving music search and recommendation, interpreting music by understanding audio and lyrics interactively has become an important and challenging task. However, many previous works focus on refining individual components of encoder-decoder architecture mapping music to caption tokens, ignoring the potential usage of audio and lyrics correspondence. In this paper, we propose to explicitly learn the multi-modal alignment with retrieval augmentation by contrastive learning. By learning audio-lyrics correspondence, the model is guided to learn better cross-modal attention weights, thus generating high-quality caption words. We provide both theoretical and empirical results that demonstrate the advantage of the proposed method.

Modeling Beats and Downbeats with a Time-Frequency Transformer

Transformer is a successful deep neural network (DNN) architecture that has shown its versatility not only in natural language processing but also in music information retrieval (MIR). In this paper, we present a novel Transformer-based approach to tackle beat and downbeat tracking. This approach employs SpecTNT (Spectral-Temporal Transformer in Transformer), a variant of Transformer that models both spectral and temporal dimensions of a time-frequency input of music audio. A SpecTNT model uses a stack of blocks, where each consists of two levels of Transformer encoders. The lower-level (or spectral) encoder handles the spectral features and enables the model to pay attention to harmonic components of each frame. Since downbeats indicate bar boundaries and are often accompanied by harmonic changes, this step may help downbeat modeling. The upper-level (or temporal) encoder aggregates useful local spectral information to pay attention to beat/downbeat positions. We also propose an architecture that combines SpecTNT with a state-of-the-art model, Temporal Convolutional Networks (TCN), to further improve the performance. Extensive experiments demonstrate that our approach can significantly outperform TCN in downbeat tracking while maintaining comparable result in beat tracking.

SpecTNT: a Time-Frequency Transformer for Music Audio

Transformers have drawn attention in the MIR field for their remarkable performance shown in natural language processing and computer vision. However, prior works in the audio processing domain mostly use Transformer as a temporal feature aggregator that acts similar to RNNs. In this paper, we propose SpecTNT, a Transformer-based architecture to model both spectral and temporal sequences of an input time-frequency representation. Specifically, we introduce a novel variant of the Transformer-in-Transformer (TNT) architecture. In each SpecTNT block, a spectral Transformer extracts frequency-related features into the frequency class token (FCT) for each frame. Later, the FCTs are linearly projected and added to the temporal embeddings (TEs), which aggregate useful information from the FCTs. Then, a temporal Transformer processes the TEs to exchange information across the time axis. By stacking the SpecTNT blocks, we build the SpecTNT model to learn the representation for music signals. In experiments, SpecTNT demonstrates state-of-the-art performance in music tagging and vocal melody extraction, and shows competitive performance for chord recognition. The effectiveness of SpecTNT and other design choices are further examined through ablation studies.

Supervised Metric Learning for Music Structure Feature

Music structure analysis (MSA) methods traditionally search for musically meaningful patterns in audio: homogeneity, repetition, novelty, and segment-length regularity. Hand-crafted audio features such as MFCCs or chromagrams are often used to elicit these patterns. However, with more annotations of section labels (e.g., verse, chorus, and bridge) becoming available, one can use supervised feature learning to make these patterns even clearer and improve MSA performance. To this end, we take a supervised metric learning approach: we train a deep neural network to output embeddings that are near each other for two spectrogram inputs if both have the same section type (according to an annotation), and otherwise far apart. We propose a batch sampling scheme to ensure the labels in a training pair are interpreted meaningfully. The trained model extracts features that can be used in existing MSA algorithms. In evaluations with three datasets (HarmonixSet, SALAMI, and RWC), we demonstrate that using the proposed features can improve a traditional MSA algorithm significantly in both intra- and cross-dataset scenarios.