arXiv subjects

Yongqi Wang

Publications and source records attributed to Yongqi Wang.

At least 19 recordsLinked to original sources

arXiv2026

Qwen-Music Technical Report

We introduce Qwen-Music, a music generation model that produces high-fidelity songs with complete vocals. It supports text-to-music generation from descriptions, lyrics, and musical attributes, and cover song generation with different styles and vocal characteristics. Qwen-Music comprises three components: Qwen-Music-Tokenizer, Qwen-Music-LLM, and Qwen-Music-Render. The tokenizer compresses audio into a 25 Hz single-codebook stream of Music Semantic Tokens that preserve semantic and melodic information. The LLM performs autoregressive modeling with a melody-token-based chain-of-thought (Melody-CoT) mechanism that plans melodies before full-song generation, improving musicality, structural coherence, and reference-melody preservation. The renderer enriches discrete semantic tokens with acoustic details to produce high-fidelity stereo waveforms. We train the LLM using a quality-aware pre-training curriculum followed by progressive post-training with supervised initialization, offline DPO, and online GSPO to improve musicality and instruction following. On 600 evaluation inputs, Qwen-Music achieves state-of-the-art results in 13 of 16 objective musicality and audio-quality metrics. Professional evaluators also prefer Qwen-Music over leading proprietary systems. For cover generation, Qwen-Music preserves reference melodies more accurately than Suno V5.5, Suno V5, and MiniMax Cover on the AI-generated reference set, and outperforms MiniMax Cover on most metrics on the real-world popular-song reference set.

cs.SD↗

arXiv2026

Design of ALPHA Phase I: A Plasma Haloscope for 10--20 GHz Post-Inflation Axions

The axion is a well-motivated hypothetical particle capable of resolving both the strong CP problem and the dark matter mystery, with recent post-inflationary cosmological simulations favoring masses above 40 μeV. Plasma haloscopes serve as a promising experimental approach to reach theoretically preferred sensitivities in this mass range. ALPHA, hosted at Yale Wright Laboratory, is an international collaboration developing plasma haloscopes to search for QCD dark matter axions. In this letter we present the detailed design and sensitivity projection for the first phase of the ALPHA experiment, which will search the mass range from 10 GHz to 20 GHz (~40 μeV to 80 μeV). This search will make use of wire-array plasma resonators to decouple the physical size from the resonant frequency, a limitation typically faced by traditional microwave cavities, allowing broadband sensitivity approaching KSVZ coupling strengths.

hep-ex↗

arXiv2026

Qwen-Audio-VAE Technical Report

We introduce \textbf{Qwen-Audio-VAE}, a suite of low-bitrate, fast-encoding continuous audio autoencoders designed for scalable general audio generation. The model is built around a simple but important principle: an audio VAE should not only reconstruct diverse audio with high fidelity, but also produce compact latent representations fast enough to support large-scale text-to-audio training. Qwen-Audio-VAE combines a causal encoder-decoder, window Transformer blocks, and multi-discriminator training to achieve a strong balance between reconstruction quality and compression rate. The model is trained at scale on 5 million hours of multi-domain audio, enabling robust reconstruction across heterogeneous acoustic conditions. To further improve computational efficiency, we adopt an asymmetric encoder-decoder backbone and introduce latency-aware encoder pruning to maximize encoding throughput. Experiments on public speech, music, and sound reconstruction benchmarks show that Qwen-Audio-VAE generalizes well across diverse audio domains and is particularly efficient, requiring only 541 ms to encode 32 minutes of audio. Overall, Qwen-Audio-VAE provides a high-quality, compact, and high-throughput representation backbone for efficient general audio generation.

eess.AS↗

arXiv2026

Performance of a SuperCDMS HVeV Detector with Sub-eV Energy Resolution and Single Charge-sensitivity

We present a detailed characterization of a new generation of athermal-phonon single-charge sensitive Si HVeV detectors, the best of which achieved 589~meV~$\pm$~5~meV baseline resolution. Our sub-eV energy resolution enables precise measurements of single-photon events and reveal consistent energy losses of 0.92~eV~$\pm$~0.02~eV per charge excitation across two facilities. We demonstrate that the noise for these detectors is well described using a standard Transition Edge Sensor noise model. We also measure a nominal phonon collection efficiency of 45\%~$\pm$~3\%~(stat.)~$\pm$~6\%~(syst.) in the best performing device, establishing these detectors as the most efficient athermal phonon detectors to date, limited only by intrinsic limitations of quasiparticle generation.

physics.ins-det↗

arXiv2026

Not All Negative Samples Are Equal: LLMs Learn Better from Plausible Reasoning

Learning from negative samples holds great promise for improving Large Language Model (LLM) reasoning capability, yet existing methods treat all incorrect responses as equally informative, overlooking the crucial role of sample quality. To address this, we propose Plausible Negative Samples (PNS), a method that synthesizes high-quality negative samples exhibiting expected format and structural coherence while ultimately yielding incorrect answers. PNS trains a dedicated model via reverse reinforcement learning (RL) guided by a composite reward combining format compliance, accuracy inversion, reward model assessment, and chain-of-thought evaluation, generating responses nearly indistinguishable from correct solutions. We further validate PNS as a plug-and-play data source for preference optimization across three backbone models on seven mathematical reasoning benchmarks. Results demonstrate that PNS consistently outperforms other negative sample synthesis methods, achieving an average improvement of 2.03% over RL-trained models.

cs.LG↗

arXiv2026

Qwen3-ASR Technical Report

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR models that support language identification and ASR for 52 languages and dialects. Both of them leverage large-scale speech training data and the strong audio understanding ability of their foundation model Qwen3-Omni. We conduct comprehensive internal evaluation besides the open-sourced benchmarks as ASR models might differ little on open-sourced benchmark scores but exhibit significant quality differences in real-world scenarios. The experiments reveal that the 1.7B version achieves SOTA performance among open-sourced ASR models and is competitive with the strongest proprietary APIs while the 0.6B version offers the best accuracy-efficiency trade-off. Qwen3-ASR-0.6B can achieve an average TTFT as low as 92ms and transcribe 2000 seconds speech in 1 second at a concurrency of 128. Qwen3-ForcedAligner-0.6B is an LLM based NAR timestamp predictor that is able to align text-speech pairs in 11 languages. Timestamp accuracy experiments show that the proposed model outperforms the three strongest force alignment models and takes more advantages in efficiency and versatility. To further accelerate the community research of ASR and audio understanding, we release these models under the Apache 2.0 license.

cs.CL↗

arXiv2026

From Atoms to Chains: Divergence-Guided Reasoning Curriculum for Unlabeled LLM Domain Adaptation

Adapting Large Language Models (LLMs) to specialized domains without human-annotated data is a crucial yet formidable challenge. Widely adopted knowledge distillation methods often devolve into coarse-grained mimicry, where the student model inefficiently targets its own weaknesses and risks inheriting the teacher's reasoning flaws. This exposes a critical pedagogical dilemma: how to devise a reliable curriculum when the teacher itself is not an infallible expert. Our work resolves this by capitalizing on a key insight: while LLMs may exhibit fallibility in complex, holistic reasoning, they often exhibit high fidelity on focused, atomic sub-problems. Based on this, we propose Divergence-Guided Reasoning Curriculum (DGRC), which constructs a learning path from atomic knowledge to reasoning chains by dynamically deriving two complementary curricula from disagreements in reasoning pathways. When a student and teacher produce conflicting results, DGRC directs the teacher to perform a diagnostic analysis: it analyzes both reasoning paths to formulate atomic queries that target the specific points of divergence, and then self-answers these queries to create high-confidence atomic question-answer pairs. These pairs then serve a dual purpose: (1) providing an atomic curriculum to rectify the student's knowledge gaps, and (2) serving as factual criteria to filter the teacher's original reasoning chains, yielding a verified CoT curriculum that teaches the student how to integrate atomic knowledge into complete reasoning paths. Experiments across the medical and legal domains on student models of various sizes demonstrate the effectiveness of our DGRC framework. Notably, our method achieves a 7.76% relative improvement for the 1.5B student model in the medical domain over strong unlabeled baseline.

cs.LG↗

arXiv2026

Structured Reasoning for Large Language Models

Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary verification and revisions even if they have reached the correct answers. This limitation stems from the unstructured nature of reasoning trajectories and the lack of targeted supervision for critical reasoning abilities. To address this, we propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components. We mainly implement SCR using a Generate-Verify-Revise paradigm. Specifically, we construct structured training data and apply Dynamic Termination Supervision to guide the model in deciding when to terminate reasoning. To avoid interference between learning signals for different reasoning abilities, we adopt a progressive two-stage reinforcement learning strategy: the first stage targets initial generation and self-verification, and the second stage focuses on revision. Extensive experiments on three backbone models show that SCR substantially improves reasoning efficiency and self-verification. Besides, compared with existing reasoning paradigms, it reduces output token length by up to 50%.

cs.CL↗

arXiv2025

Qwen3-Omni Technical Report

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-Omni matches the performance of same-sized single-modal models within the Qwen series and excels particularly on audio tasks. Across 36 audio and audio-visual benchmarks, Qwen3-Omni achieves open-source SOTA on 32 benchmarks and overall SOTA on 22, outperforming strong closed-source models such as Gemini-2.5-Pro, Seed-ASR, and GPT-4o-Transcribe. Qwen3-Omni adopts a Thinker-Talker MoE architecture that unifies perception and generation across text, images, audio, and video, yielding fluent text and natural real-time speech. It supports text interaction in 119 languages, speech understanding in 19 languages, and speech generation in 10 languages. To reduce first-packet latency in streaming synthesis, Talker autoregressively predicts discrete speech codecs using a multi-codebook scheme. Leveraging the representational capacity of these codebooks, we replace computationally intensive block-wise diffusion with a lightweight causal ConvNet, enabling streaming from the first codec frame. In cold-start settings, Qwen3-Omni achieves a theoretical end-to-end first-packet latency of 234 ms. To further strengthen multimodal reasoning, we introduce a Thinking model that explicitly reasons over inputs from any modality. Since the research community currently lacks a general-purpose audio captioning model, we fine-tuned Qwen3-Omni-30B-A3B to obtain Qwen3-Omni-30B-A3B-Captioner, which produces detailed, low-hallucination captions for arbitrary audio inputs. Qwen3-Omni-30B-A3B, Qwen3-Omni-30B-A3B-Thinking, and Qwen3-Omni-30B-A3B-Captioner are publicly released under the Apache 2.0 license.

cs.CL↗

arXiv2025

CURE: Critical-Token-Guided Re-Concatenation for Entropy-Collapse Prevention

Recent advances in Reinforcement Learning with Verified Reward (RLVR) have driven the emergence of more sophisticated cognitive behaviors in large language models (LLMs), thereby enhancing their reasoning capabilities. However, in prior RLVR pipelines, the repeated use of static initial-state sampling drawn exactly from the dataset distribution during each sampling phase produced overly deterministic, low diversity model behavior, which manifested as rapid entropy collapse and hindered sustained performance gains during prolonged training. To address this issue, we introduce CURE (Critical-token-gUided Re concatenation for Entropy-collapse prevention), a two-stage framework that balances exploration and exploitation. Specifically, in the first stage, to deliberately steer the model toward novel yet coherent contexts, we re-generate at high-entropy critical tokens and jointly optimize the original and the branched trajectories. The further comparison with vanilla DAPO shows that the regeneration process achieves a better performance on math reasoning tasks while sustaining a high-level entropy degree for exploration. In the second stage, we continue training with static initial-state sampling by DAPO, intentionally placing the model in a familiar state to gradually strengthen exploitation. Extensive experiments on Qwen-2.5-Math-7B show that, compared to other RLVR methods, CURE achieves a 5% performance gain across six math benchmarks, establishing state-of-the-art performance in both entropy and accuracy. A series of experiments further validate the effectiveness of our approach. Code is available at https://github.com/bytedance/CURE.

cs.LG↗

arXiv2025

Controllable Text-to-Speech Synthesis with Masked-Autoencoded Style-Rich Representation

Controllable TTS models with natural language prompts often lack the ability for fine-grained control and face a scarcity of high-quality data. We propose a two-stage style-controllable TTS system with language models, utilizing a quantized masked-autoencoded style-rich representation as an intermediary. In the first stage, an autoregressive transformer is used for the conditional generation of these style-rich tokens from text and control signals. The second stage generates codec tokens from both text and sampled style-rich tokens. Experiments show that training the first-stage model on extensive datasets enhances the content robustness of the two-stage model as well as control capabilities over multiple attributes. By selectively combining discrete labels and speaker embeddings, we explore fully controlling the speaker's timbre and other stylistic information, and adjusting attributes like emotion for a specified speaker. Audio samples are available at https://style-ar-tts.github.io.

cs.MM↗

arXiv2025

METOR: A Unified Framework for Mutual Enhancement of Objects and Relationships in Open-vocabulary Video Visual Relationship Detection

Open-vocabulary video visual relationship detection aims to detect objects and their relationships in videos without being restricted by predefined object or relationship categories. Existing methods leverage the rich semantic knowledge of pre-trained vision-language models such as CLIP to identify novel categories. They typically adopt a cascaded pipeline to first detect objects and then classify relationships based on the detected objects, which may lead to error propagation and thus suboptimal performance. In this paper, we propose Mutual EnhancemenT of Objects and Relationships (METOR), a query-based unified framework to jointly model and mutually enhance object detection and relationship classification in open-vocabulary scenarios. Under this framework, we first design a CLIP-based contextual refinement encoding module that extracts visual contexts of objects and relationships to refine the encoding of text features and object queries, thus improving the generalization of encoding to novel categories. Then we propose an iterative enhancement module to alternatively enhance the representations of objects and relationships by fully exploiting their interdependence to improve recognition performance. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate that our framework achieves state-of-the-art performance.

cs.CV↗

arXiv2025

TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching

Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy tones, thus limiting the expressive potential of synthetic voices. We introduce TechSinger, an advanced system for controllable singing voice synthesis that supports five languages and seven vocal techniques. TechSinger leverages a flow-matching-based generative model to produce singing voices with enhanced expressive control over various techniques. To enhance the diversity of training data, we develop a technique detection model that automatically annotates datasets with phoneme-level technique labels. Additionally, our prompt-based technique prediction model enables users to specify desired vocal attributes through natural language, offering fine-grained control over the synthesized singing. Experimental results demonstrate that TechSinger significantly enhances the expressiveness and realism of synthetic singing voices, outperforming existing methods in terms of audio quality and technique-specific control. Audio samples can be found at https://gwx314.github.io/tech-singer/.

cs.SD↗

arXiv2025

End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting

Open-vocabulary video visual relationship detection aims to expand video visual relationship detection beyond annotated categories by detecting unseen relationships between both seen and unseen objects in videos. Existing methods usually use trajectory detectors trained on closed datasets to detect object trajectories, and then feed these trajectories into large-scale pre-trained vision-language models to achieve open-vocabulary classification. Such heavy dependence on the pre-trained trajectory detectors limits their ability to generalize to novel object categories, leading to performance degradation. To address this challenge, we propose to unify object trajectory detection and relationship classification into an end-to-end open-vocabulary framework. Under this framework, we propose a relationship-aware open-vocabulary trajectory detector. It primarily consists of a query-based Transformer decoder, where the visual encoder of CLIP is distilled for frame-wise open-vocabulary object detection, and a trajectory associator. To exploit relationship context during trajectory detection, a relationship query is embedded into the Transformer decoder, and accordingly, an auxiliary relationship loss is designed to enable the decoder to perceive the relationships between objects explicitly. Moreover, we propose an open-vocabulary relationship classifier that leverages the rich semantic knowledge of CLIP to discover novel relationships. To adapt CLIP well to relationship classification, we design a multi-modal prompting method that employs spatio-temporal visual prompting for visual representation and vision-guided language prompting for language input. Extensive experiments on two public datasets, VidVRD and VidOR, demonstrate the effectiveness of our framework. Our framework is also applied to a more difficult cross-dataset scenario to further demonstrate its generalization ability.

cs.CV↗

arXiv2025

K2: On Optimizing Distributed Transactions in a Multi-region Data Store with TrueTime Clocks (Extended Version)

TrueTime clocks (TTCs) that offer accurate and reliable time within limited uncertainty bounds have been increasingly implemented in many clouds. Multi-region data stores that seek decentralized synchronization for high performance represent an ideal application of TTC. However, the co-designs between the two were often undervalued or failed to realize their full potential. This paper proposes K2, a multi-region data store that intensely explores the opportunity of using TTC for distributed transactions. Compared to its pioneer, Google Spanner, K2 augments TTC's semantics in three core design pillars. First, K2 carries a new timestamp-generating scheme that is capable of providing a small time uncertainty bound at scale. Second, K2 revitalizes existing multi-version timestamp-ordered concurrency control to realize multi-version properties for read-write transactions. Third, K2 introduces a new TTC-based visibility control protocol that provides efficient reads at replicas. Our evaluation shows that, K2 achieves an order of magnitude higher transaction throughput relative to other practical geo-distributed transaction protocols while ensuring a lower visibility delay at asynchronous replicas.

cs.DB↗

arXiv2025

Technical Approach for the EMI Challenge in the 8th Affective Behavior Analysis in-the-Wild Competition

Emotional Mimicry Intensity (EMI) estimation plays a pivotal role in understanding human social behavior and advancing human-computer interaction. The core challenges lie in dynamic correlation modeling and robust fusion of multimodal temporal signals. To address the limitations of existing methods--insufficient exploitation of cross-modal synergies, sensitivity to noise, and constrained fine-grained alignment capabilities--this paper proposes a dual-stage cross-modal alignment framework. Stage 1 develops vision-text and audio-text contrastive learning networks based on a CLIP architecture, achieving preliminary feature-space alignment through modality-decoupled pre-training. Stage 2 introduces a temporal-aware dynamic fusion module integrating Temporal Convolutional Networks (TCN) and gated bidirectional LSTM to capture macro-evolution patterns of facial expressions and local dynamics of acoustic features, respectively. A novel quality-guided fusion strategy further enables differentiable weight allocation for modality compensation under occlusion and noise. Experiments on the Hume-Vidmimic2 dataset demonstrate superior performance with an average Pearson correlation coefficient of 0.51 across six emotion dimensions on the validate set. Remarkably, our method achieved 0.68 on the test set, securing runner-up in the EMI Challenge Track of the 8th ABAW (Affective Behavior Analysis in the Wild) Competition, offering a novel pathway for fine-grained emotion analysis in open environments.

cs.CV↗

arXiv2025

Design of an Expression Recognition Solution Based on the Global Channel-Spatial Attention Mechanism and Proportional Criterion Fusion

Facial expression recognition is a challenging classification task that holds broad application prospects in the field of human-computer interaction. This paper aims to introduce the method we will adopt in the 8th Affective and Behavioral Analysis in the Wild (ABAW) Competition, which will be held during the Conference on Computer Vision and Pattern Recognition (CVPR) in 2025.First of all, we apply the frequency masking technique and the method of extracting data at equal time intervals to conduct targeted processing on the original videos. Then, based on the residual hybrid convolutional neural network and the multi-branch convolutional neural network respectively, we design feature extraction models for image and audio sequences. In particular, we propose a global channel-spatial attention mechanism to enhance the features initially extracted from both the audio and image modalities respectively.Finally, we adopt a decision fusion strategy based on the proportional criterion to fuse the classification results of the two single modalities, obtain an emotion probability vector, and output the final emotional classification. We also design a coarse - fine granularity loss function to optimize the performance of the entire network, which effectively improves the accuracy of facial expression recognition.In the facial expression recognition task of the 8th ABAW Competition, our method ranked third on the official validation set. This result fully confirms the effectiveness and competitiveness of the method we have proposed.

cs.CV↗

arXiv2025

Solution for 8th Competition on Affective & Behavior Analysis in-the-wild

In this report, we present our solution for the Action Unit (AU) Detection Challenge, in 8th Competition on Affective Behavior Analysis in-the-wild. In order to achieve robust and accurate classification of facial action unit in the wild environment, we introduce an innovative method that leverages audio-visual multimodal data. Our method employs ConvNeXt as the image encoder and uses Whisper to extract Mel spectrogram features. For these features, we utilize a Transformer encoder-based feature fusion module to integrate the affective information embedded in audio and image features. This ensures the provision of rich high-dimensional feature representations for the subsequent multilayer perceptron (MLP) trained on the Aff-Wild2 dataset, enhancing the accuracy of AU detection.

cs.CV↗