Yuhao Wang

Heyang Liu, Ziyang Cheng, Yuhao Wang et al.

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their applicability and reach. However, the scarcity of comprehensive speech-to-speech (S2S) benchmarks in Mandarin contexts impedes systematic evaluation for developers and hinders fair model comparison for users. In this work, we propose VocalBench-zh, an ability-level divided evaluation suite adapted to Mandarin context consisting of 10 well-crafted subsets and over 10K high-quality instances, covering 12 user-oriented characters. The evaluation experiment on 14 mainstream models reveals the common challenges for current routes, and highlights the need for new insights into next-generation speech interactive systems. The evaluation codes and datasets will be available at https://github.com/SJTU-OmniAgent/VocalBench-zh.

Yuhao Wang, Heyang Liu, Ziyang Cheng et al.

Speech large language models (LLMs) have emerged as a prominent research focus in speech processing. We introduce VocalNet-1B and VocalNet-8B, a series of high-performance, low-latency speech LLMs enabled by a scalable and model-agnostic training framework designed for real-time voice interaction. Central to our contribution is the first application of multi-token prediction (MTP) to speech LLMs. This approach represents a paradigm shift from standard next-token prediction (NTP), offering simultaneous improvements in generation speed and quality. Informed by analysis of MTP's effect on speech generation and experimental comparisons, we designed a straightforward and highly effective MTP implementation. Experiments demonstrate that VocalNet performs on par with mainstream Omni LLMs even with limited training data, and significantly surpasses existing open-source speech LLMs. To foster reproducibility and community advancement, all model weights, inference code, training data, and framework implementations have been made publicly available at https://github.com/SJTU-OmniAgent/VocalNet

Yuhao Wang, Ziyang Cheng, Heyang Liu et al.

Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex flow-matching models for speech synthesis. To overcome this, we introduce VocalNet-M2, a novel low-latency SLM that integrates a multi-codebook tokenizer and a multi-token prediction (MTP) strategy. Our model directly generates multi-codebook speech tokens, thus eliminating the need for a latency-inducing flow-matching model. Furthermore, our MTP strategy enhances generation efficiency and improves overall performance. Extensive experiments demonstrate that VocalNet-M2 achieves a substantial reduction in first chunk latency (from approximately 725ms to 350ms) while maintaining competitive performance across mainstream SLMs. This work also provides a comprehensive comparison of single-codebook and multi-codebook strategies, offering valuable insights for developing efficient and high-performance SLMs for real-time interactive applications.

Yuhao Wang, Junwei Pan, Xinhang Li et al.

Sequential recommendation (SR) aims to capture users' dynamic interests and sequential patterns based on their historical interactions. Recently, the powerful capabilities of large language models (LLMs) have driven their adoption in SR. However, we identify two critical challenges in existing LLM-based SR methods: 1) embedding collapse when incorporating pre-trained collaborative embeddings and 2) catastrophic forgetting of quantized embeddings when utilizing semantic IDs. These issues dampen the model scalability and lead to suboptimal recommendation performance. Therefore, based on LLMs like Llama3-8B-instruct, we introduce a novel SR framework named MME-SID, which integrates multimodal embeddings and quantized embeddings to mitigate embedding collapse. Additionally, we propose a Multimodal Residual Quantized Variational Autoencoder (MM-RQ-VAE) with maximum mean discrepancy as the reconstruction loss and contrastive learning for alignment, which effectively preserve intra-modal distance information and capture inter-modal correlations, respectively. To further alleviate catastrophic forgetting, we initialize the model with the trained multimodal code embeddings. Finally, we fine-tune the LLM efficiently using LoRA in a multimodal frequency-aware fusion manner. Extensive experiments on three public datasets validate the superior performance of MME-SID thanks to its capability to mitigate embedding collapse and catastrophic forgetting. The implementation code and datasets are publicly available for reproduction: https://github.com/Applied-Machine-Learning-Lab/MME-SID.

Heyang Liu, Yuhao Wang, Ziyang Cheng et al.

The rapid advancement of large language models (LLMs) has accelerated the development of multimodal models capable of speech communications. Unlike text interactions, speech conveys diverse information, including acoustic variations, paralanguage cues, and environmental context. However, existing evaluations of speech interaction models lack instances mimicking real scenarios and predominantly focus on the quality of their textual responses, overlooking critical aspects of vocal performance. To address this gap, we propose VocalBench, a comprehensive benchmark to assess the speech conversational abilities, comprising 9,400 carefully curated instances across four key dimensions: semantic quality, acoustic performance, conversational abilities, and robustness. It covers a broad range of fundamental skills essential for effective vocal interactions. For the evaluation scheme, we propose several objective evaluation indicators and incorporate an additional LLM-as-a-judge approach to score open-ended questions. Experimental results on 15 mainstream systems reveal significant variability, each exhibiting distinct strengths and weaknesses, and provide valuable insights to guide future research in speech interaction systems.

Ruiyang Ren, Yuhao Wang, Kun Zhou et al.

Large language models (LLMs), with advanced linguistic capabilities, have been employed in reranking tasks through a sequence-to-sequence approach. In this paradigm, multiple passages are reranked in a listwise manner and a textual reranked permutation is generated. However, due to the limited context window of LLMs, this reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. This not only increases computational costs but also restricts the LLM from fully capturing all the comparison information for all candidates. To address these challenges, we propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking. To achieve it, we first propose the relevance-aware listwise reranking framework, which incorporates explicit list-view relevance scores to improve reranking efficiency and enable global comparison across the entire candidate set. Second, to ensure the comparability of the computed scores, we propose self-calibrated training that uses point-view relevance assessments generated internally by the LLM itself to calibrate the list-view relevance assessments. Extensive experiments and comprehensive analysis on the BEIR benchmark and TREC Deep Learning Tracks demonstrate the effectiveness and efficiency of our proposed method.

Tongzhou Wu, Yuhao Wang, Maolin Wang et al.

Sequential recommendation aims to capture user preferences by modeling sequential patterns in user-item interactions. However, these models are often influenced by noise such as accidental interactions, leading to suboptimal performance. Therefore, to reduce the effect of noise, some works propose explicitly identifying and removing noisy items. However, we find that simply relying on collaborative information may result in an over-denoising problem, especially for cold items. To overcome these limitations, we propose a novel framework: Interest Alignment for Denoising Sequential Recommendation (IADSR) which integrates both collaborative and semantic information. Specifically, IADSR is comprised of two stages: in the first stage, we obtain the collaborative and semantic embeddings of each item from a traditional sequential recommendation model and an LLM, respectively. In the second stage, we align the collaborative and semantic embeddings and then identify noise in the interaction sequence based on long-term and short-term interests captured in the collaborative and semantic modalities. Our extensive experiments on four public datasets validate the effectiveness of the proposed framework and its compatibility with different sequential recommendation systems.