Jamendo-QA: A Large-Scale Music Question Answering Dataset

We introduce Jamendo-QA, a large-scale dataset for Music Question Answering (Music-QA). The dataset is built on freely licensed tracks from the Jamendo platform and is automatically annotated using the Qwen-Omni model. Jamendo-QA provides question-answer pairs and captions aligned with music audio, enabling both supervised training and zero-shot evaluation. Our resource aims to fill the gap of music-specific QA datasets and foster further research in music understanding, retrieval, and generative applications. In addition to its scale, Jamendo-QA covers a diverse range of genres, instruments, and metadata attributes, allowing robust model benchmarking across varied musical contexts. We also provide detailed dataset statistics and highlight potential biases such as genre and gender imbalance to guide fair evaluation. We position Jamendo-QA as a scalable and publicly available benchmark that can facilitate future research in music understanding, multimodal modeling, and fair evaluation of music-oriented QA systems.

Video Object Segmentation-Aware Audio Generation

Existing multimodal audio generation models often lack precise user control, which limits their applicability in professional Foley workflows. In particular, these models focus on the entire video and do not provide precise methods for prioritizing a specific object within a scene, generating unnecessary background sounds, or focusing on the wrong objects. To address this gap, we introduce the novel task of video object segmentation-aware audio generation, which explicitly conditions sound synthesis on object-level segmentation maps. We present SAGANet, a new multimodal generative model that enables controllable audio generation by leveraging visual segmentation masks along with video and textual cues. Our model provides users with fine-grained and visually localized control over audio generation. To support this task and further research on segmentation-aware Foley, we propose Segmented Music Solos, a benchmark dataset of musical instrument performance videos with segmentation information. Our method demonstrates substantial improvements over current state-of-the-art methods and sets a new standard for controllable, high-fidelity Foley synthesis. Code, samples, and Segmented Music Solos are available at https://saganet.notion.site

Pairwise and Attribute-Aware Decision Tree-Based Preference Elicitation for Cold-Start Recommendation

Recommender systems (RSs) are intelligent filtering methods that suggest items to users based on their inferred preferences, derived from their interaction history on the platform. Collaborative filtering-based RSs rely on users past interactions to generate recommendations. However, when a user is new to the platform, referred to as a cold-start user, there is no historical data available, making it difficult to provide personalized recommendations. To address this, rating elicitation techniques can be used to gather initial ratings or preferences on selected items, helping to build an early understanding of the user's tastes. Rating elicitation approaches are generally categorized into two types: non-personalized and personalized. Decision tree-based rating elicitation is a personalized method that queries users about their preferences at each node of the tree until sufficient information is gathered. In this paper, we propose an extension to the decision tree approach for rating elicitation in the context of music recommendation. Our method: (i) elicits not only item ratings but also preferences on attributes such as genres to better cluster users, and (ii) uses item pairs instead of single items at each node to more effectively learn user preferences. Experimental results demonstrate that both proposed enhancements lead to improved performance, particularly with a reduced number of queries.

High-Quality Sound Separation Across Diverse Categories via Visually-Guided Generative Modeling

We propose DAVIS, a Diffusion-based Audio-VIsual Separation framework that solves the audio-visual sound source separation task through generative learning. Existing methods typically frame sound separation as a mask-based regression problem, achieving significant progress. However, they face limitations in capturing the complex data distribution required for high-quality separation of sounds from diverse categories. In contrast, DAVIS circumvents these issues by leveraging potent generative modeling paradigms, specifically Denoising Diffusion Probabilistic Models (DDPM) and the more recent Flow Matching (FM), integrated within a specialized Separation U-Net architecture. Our framework operates by synthesizing the desired separated sound spectrograms directly from a noise distribution, conditioned concurrently on the mixed audio input and associated visual information. The inherent nature of its generative objective makes DAVIS particularly adept at producing high-quality sound separations for diverse sound categories. We present comparative evaluations of DAVIS, encompassing both its DDPM and Flow Matching variants, against leading methods on the standard AVE and MUSIC datasets. The results affirm that both variants surpass existing approaches in separation quality, highlighting the efficacy of our generative framework for tackling the audio-visual source separation task.

From Language to Locomotion: Retargeting-free Humanoid Control via Motion Latent Guidance

Natural language offers a natural interface for humanoid robots, but existing language-guided humanoid locomotion pipelines remain cumbersome and unreliable. They typically decode human motion, retarget it to robot morphology, and then track it with a physics-based controller. However, this multi-stage process is prone to cumulative errors, introduces high latency, and yields weak coupling between semantics and control. These limitations call for a more direct pathway from language to action, one that eliminates fragile intermediate stages. Therefore, we present RoboGhost, a retargeting-free framework that directly conditions humanoid policies on language-grounded motion latents. By bypassing explicit motion decoding and retargeting, RoboGhost enables a diffusion-based policy to denoise executable actions directly from noise, preserving semantic intent and supporting fast, reactive control. A hybrid causal transformer-diffusion motion generator further ensures long-horizon consistency while maintaining stability and diversity, yielding rich latent representations for precise humanoid behavior. Extensive experiments demonstrate that RoboGhost substantially reduces deployment latency, improves success rates and tracking accuracy, and produces smooth, semantically aligned locomotion on real humanoids. Beyond text, the framework naturally extends to other modalities such as images, audio, and music, providing a general foundation for vision-language-action humanoid systems.

The Rhythm In Anything: Audio-Prompted Drums Generation with Masked Language Modeling

Musicians and nonmusicians alike use rhythmic sound gestures, such as tapping and beatboxing, to express drum patterns. While these gestures effectively communicate musical ideas, realizing these ideas as fully-produced drum recordings can be time-consuming, potentially disrupting many creative workflows. To bridge this gap, we present TRIA (The Rhythm In Anything), a masked transformer model for mapping rhythmic sound gestures to high-fidelity drum recordings. Given an audio prompt of the desired rhythmic pattern and a second prompt to represent drumkit timbre, TRIA produces audio of a drumkit playing the desired rhythm (with appropriate elaborations) in the desired timbre. Subjective and objective evaluations show that a TRIA model trained on less than 10 hours of publicly-available drum data can generate high-quality, faithful realizations of sound gestures across a wide range of timbres in a zero-shot manner.

TISDiSS: A Training-Time and Inference-Time Scalable Framework for Discriminative Source Separation

Source separation is a fundamental task in speech, music, and audio processing, and it also provides cleaner and larger data for training generative models. However, improving separation performance in practice often depends on increasingly large networks, inflating training and deployment costs. Motivated by recent advances in inference-time scaling for generative modeling, we propose Training-Time and Inference-Time Scalable Discriminative Source Separation (TISDiSS), a unified framework that integrates early-split multi-loss supervision, shared-parameter design, and dynamic inference repetitions. TISDiSS enables flexible speed-performance trade-offs by adjusting inference depth without retraining additional models. We further provide systematic analyses of architectural and training choices and show that training with more inference repetitions improves shallow-inference performance, benefiting low-latency applications. Experiments on standard speech separation benchmarks demonstrate state-of-the-art performance with a reduced parameter count, establishing TISDiSS as a scalable and practical framework for adaptive source separation.

ACMID: Automatic Curation of Musical Instrument Dataset for 7-Stem Music Source Separation

Most current music source separation (MSS) methods rely on supervised learning, limited by training data quan- tity and quality. Though web-crawling can bring abundant data, platform-level track labeling often causes metadata mismatches, impeding accurate "audio-label" pair acquisi- tion. To address this, we present ACMID: a dataset for MSS generated through web crawling of extensive raw data, fol- lowed by automatic cleaning via an instrument classifier built on a pre-trained audio encoder that filters and aggregates clean segments of target instruments from the crawled tracks, resulting in the refined ACMID-Cleaned dataset. Leverag- ing abundant data, we expand the conventional classifica- tion from 4-stem (Vocal/Bass/Drums/Others) to 7-stem (Pi- ano/Drums/Bass/Acoustic Guitar/Electric Guitar/Strings/Wind- Brass), enabling high granularity MSS systems. Experiments on SOTA MSS model demonstrates two key results: (i) MSS model trained with ACMID-Cleaned achieved a 2.39dB improvement in SDR performance compared to that with ACMID-Uncleaned, demostrating the effectiveness of our data cleaning procedure; (ii) incorporating ACMID-Cleaned to training enhances MSS model's average performance by 1.16dB, confirming the value of our dataset. Our data crawl- ing code, cleaning model code and weights are available at: https://github.com/scottishfold0621/ACMID.

MelCap: A Unified Single-Codebook Neural Codec for High-Fidelity Audio Compression

Neural audio codecs have recently emerged as powerful tools for high-quality and low-bitrate audio compression, leveraging deep generative models to learn latent representations of audio signals. However, existing approaches either rely on a single quantizer that only processes speech domain, or on multiple quantizers that are not well suited for downstream tasks. To address this issue, we propose MelCap, a unified "one-codebook-for-all" neural codec that effectively handles speech, music, and general sound. By decomposing audio reconstruction into two stages, our method preserves more acoustic details than previous single-codebook approaches, while achieving performance comparable to mainstream multi-codebook methods. In the first stage, audio is transformed into mel-spectrograms, which are compressed and quantized into compact single tokens using a 2D tokenizer. A perceptual loss is further applied to mitigate the over-smoothing artifacts observed in spectrogram reconstruction. In the second stage, a Vocoder recovers waveforms from the mel discrete tokens in a single forward pass, enabling real-time decoding. Both objective and subjective evaluations demonstrate that MelCap achieves quality on comparable to state-of-the-art multi-codebook codecs, while retaining the computational simplicity of a single-codebook design, thereby providing an effective representation for downstream tasks.

VoiceAssistant-Eval: Benchmarking AI Assistants across Listening, Speaking, and Viewing

The growing capabilities of large language models and multimodal systems have spurred interest in voice-first AI assistants, yet existing benchmarks are inadequate for evaluating the full range of these systems' capabilities. We introduce VoiceAssistant-Eval, a comprehensive benchmark designed to assess AI assistants across listening, speaking, and viewing. VoiceAssistant-Eval comprises 10,497 curated examples spanning 13 task categories. These tasks include natural sounds, music, and spoken dialogue for listening; multi-turn dialogue, role-play imitation, and various scenarios for speaking; and highly heterogeneous images for viewing. To demonstrate its utility, we evaluate 21 open-source models and GPT-4o-Audio, measuring the quality of the response content and speech, as well as their consistency. The results reveal three key findings: (1) proprietary models do not universally outperform open-source models; (2) most models excel at speaking tasks but lag in audio understanding; and (3) well-designed smaller models can rival much larger ones. Notably, the mid-sized Step-Audio-2-mini (7B) achieves more than double the listening accuracy of LLaMA-Omni2-32B-Bilingual. However, challenges remain: multimodal (audio plus visual) input and role-play voice imitation tasks are difficult for current models, and significant gaps persist in robustness and safety alignment. VoiceAssistant-Eval identifies these gaps and establishes a rigorous framework for evaluating and guiding the development of next-generation AI assistants. Code and data will be released at https://mathllm.github.io/VoiceAssistantEval/ .