Jian Luan

Tianwen Wei, Jian Luan, Wei Liu et al.

We present the Chinese Elementary School Math Word Problems (CMATH) dataset, comprising 1.7k elementary school-level math word problems with detailed annotations, source from actual Chinese workbooks and exams. This dataset aims to provide a benchmark tool for assessing the following question: to what grade level of elementary school math do the abilities of popular large language models (LLMs) correspond? We evaluate a variety of popular LLMs, including both commercial and open-source options, and discover that only GPT-4 achieves success (accuracy $\geq$ 60\%) across all six elementary school grades, while other models falter at different grade levels. Furthermore, we assess the robustness of several top-performing LLMs by augmenting the original problems in the CMATH dataset with distracting information. Our findings reveal that GPT-4 is able to maintains robustness, while other model fail. We anticipate that our study will expose limitations in LLMs' arithmetic and reasoning capabilities, and promote their ongoing development and advancement.

Qinzhuo Wu, Weikai Xu, Wei Liu et al.

Recently, mobile AI agents based on VLMs have been gaining increasing attention. These works typically utilize VLM as a foundation, fine-tuning it with instruction-based mobile datasets. However, these VLMs are typically pre-trained on general-domain data, which often results in a lack of fundamental capabilities specific to the mobile domain. Therefore, they may struggle to recognize specific UI elements and understand intra-UI fine-grained information. In addition, the current fine-tuning task focuses on interacting with the most relevant element for the given instruction. These fine-tuned VLMs may still ignore the relationships between UI pages, neglect the roles of elements in page transitions and lack inter-UI understanding. To address issues, we propose a VLM called MobileVLM, which includes two additional pre-training stages to enhance both intra- and inter-UI understanding. We defined four UI-based pre-training tasks, enabling the model to better perceive fine-grained elements and capture page transition actions. To address the lack of mobile pre-training data, we built a large Chinese mobile dataset Mobile3M from scratch, which contains 3 million UI pages, and real-world transition actions, forming a directed graph structure. Experimental results show MobileVLM excels on both our test set and public mobile benchmarks, outperforming existing VLMs.

Hongda Sun, Weikai Xu, Wei Liu et al.

Recent advances in large language models (LLMs) have revolutionized the landscape of reasoning tasks. To enhance the capabilities of LLMs to emulate human reasoning, prior studies have focused on modeling reasoning steps using various thought structures like chains, trees, or graphs. However, LLM-based reasoning still encounters the following challenges: (1) Limited adaptability of preset structures to diverse tasks; (2) Insufficient precision in exploiting known conditions to derive new ones; and (3) Inadequate consideration of historical reasoning experiences for subsequent reasoning steps. To this end, we propose DetermLR, a novel perspective that rethinks the reasoning process as an evolution from indeterminacy to determinacy. First, we categorize known conditions into two types: determinate and indeterminate premises This provides an oveall direction for the reasoning process and guides LLMs in converting indeterminate data into progressively determinate insights. Subsequently, we leverage quantitative measurements to prioritize more relevant premises to explore new insights. Furthermore, we automate the storage and extraction of available premises and reasoning paths with reasoning memory, preserving historical reasoning details for subsequent reasoning steps. Comprehensive experimental results demonstrate that DetermLR surpasses all baselines on various logical reasoning benchmarks: LogiQA, ProofWriter, FOLIO, PrOntoQA, and LogicalDeduction. Compared to previous multi-step reasoning methods, DetermLR achieves higher accuracy with fewer reasoning steps, highlighting its superior efficiency and effectiveness in solving logical reasoning tasks.

Shihan Deng, Weikai Xu, Hongda Sun et al.

With the remarkable advancements of large language models (LLMs), LLM-based agents have become a research hotspot in human-computer interaction. However, there is a scarcity of benchmarks available for LLM-based mobile agents. Benchmarking these agents generally faces three main challenges: (1) The inefficiency of UI-only operations imposes limitations to task evaluation. (2) Specific instructions within a singular application lack adequacy for assessing the multi-dimensional reasoning and decision-making capacities of LLM mobile agents. (3) Current evaluation metrics are insufficient to accurately assess the process of sequential actions. To this end, we propose Mobile-Bench, a novel benchmark for evaluating the capabilities of LLM-based mobile agents. First, we expand conventional UI operations by incorporating 103 collected APIs to accelerate the efficiency of task completion. Subsequently, we collect evaluation data by combining real user queries with augmentation from LLMs. To better evaluate different levels of planning capabilities for mobile agents, our data is categorized into three distinct groups: SAST, SAMT, and MAMT, reflecting varying levels of task complexity. Mobile-Bench comprises 832 data entries, with more than 200 tasks specifically designed to evaluate multi-APP collaboration scenarios. Furthermore, we introduce a more accurate evaluation metric, named CheckPoint, to assess whether LLM-based mobile agents reach essential points during their planning and reasoning steps.

Qinzhuo Wu, Wei Liu, Jian Luan et al.

Recently, tool-augmented LLMs have gained increasing attention. Given an instruction, tool-augmented LLMs can interact with various external tools in multiple rounds and provide a final answer. However, previous LLMs were trained on overly detailed instructions, which included API names or parameters, while real users would not explicitly mention these API details. This leads to a gap between trained LLMs and real-world scenarios. In addition, most works ignore whether the interaction process follows the instruction. To address these issues, we constructed a training dataset called MGToolBench, which contains statement and category-level instructions to better reflect real-world scenarios. In addition, we propose ToolPlanner, a two-stage reinforcement learning framework that utilizes path planning and two feedback mechanisms to enhance the LLM's task completion and instruction-following capabilities. Experimental results show that ToolPlanner significantly improves the Match Rate, Pass Rate and Win Rate by 26.8%, 20.2%, and 5.6% compared to the SOTA model. Human evaluation verifies that the multi-granularity instructions can better align with users' usage habits. Our data and code will be released upon acceptance.

Bowen Shen, Zheng Lin, Daren Zha et al.

Structured pruning fundamentally reduces computational and memory overheads of large language models (LLMs) and offers a feasible solution for end-side LLM deployment. Structurally pruned models remain dense and high-precision, highly compatible with further tuning and compression. However, as the coarse-grained structured pruning poses large damage to the highly interconnected model, achieving a high compression ratio for scaled-up LLMs remains a challenge. In this paper, we introduce a task-agnostic structured pruning approach coupled with a compact Transformer architecture design. The proposed approach, named TransAct, reduces transitional activations inside multi-head attention (MHA) and multi-layer perceptron (MLP) modules, while preserving the inter-module activations that are sensitive to perturbations. Hence, the LLM is pruned into an intra-module low-rank architecture, significantly reducing weights, KV Cache and attention computation. TransAct is implemented on the LLaMA model and evaluated on downstream benchmarks. Results verify the optimality of our approach at high compression with respect to both efficiency and performance. Further, ablation studies reveal the strength of activation-guided iterative pruning and provide experimental analysis on the redundancy of MHA and MLP modules.

Gang Li, Jizhong Liu, Heinrich Dinkel et al.

Recently, reinforcement learning (RL) has been shown to greatly enhance the reasoning capabilities of large language models (LLMs), and RL-based approaches have been progressively applied to visual multimodal tasks. However, the audio modality has largely been overlooked in these developments. Thus, we conduct a series of RL explorations in audio understanding and reasoning, specifically focusing on the audio question answering (AQA) task. We leverage the group relative policy optimization (GRPO) algorithm to Qwen2-Audio-7B-Instruct, and our experiments demonstrated state-of-the-art performance on the MMAU Test-mini benchmark, achieving an accuracy rate of 64.5%. The main findings in this technical report are as follows: 1) The GRPO algorithm can be effectively applied to large audio language models (LALMs), even when the model has only 8.2B parameters; 2) With only 38k post-training samples, RL significantly outperforms supervised fine-tuning (SFT), indicating that RL-based approaches can be effective without large datasets; 3) The explicit reasoning process has not shown significant benefits for AQA tasks, and how to efficiently utilize deep thinking remains an open question for further research; 4) LALMs still lag far behind humans auditory-language reasoning, suggesting that the RL-based approaches warrant further exploration. Our project is available at https://github.com/xiaomi-research/r1-aqa and https://huggingface.co/mispeech/r1-aqa.

Renren Jin, Pengzhi Gao, Yuqi Ren et al.

Reinforcement learning with verifiable rewards (RLVR) has emerged as a predominant approach for enhancing the reasoning capabilities of large language models (LLMs). However, the entropy of LLMs usually collapses during RLVR training, causing premature convergence to suboptimal local minima and hinder further performance improvement. Although various approaches have been proposed to mitigate entropy collapse, a comprehensive study of entropy in RLVR remains lacking. To address this gap, we conduct extensive experiments to investigate the entropy dynamics of LLMs trained with RLVR and analyze how model entropy correlates with response diversity, calibration, and performance across various benchmarks. Our findings reveal that the number of off-policy updates, the diversity of training data, and the clipping thresholds in the optimization objective are critical factors influencing the entropy of LLMs trained with RLVR. Moreover, we theoretically and empirically demonstrate that tokens with positive advantages are the primary contributors to entropy collapse, and that model entropy can be effectively regulated by adjusting the relative loss weights of tokens with positive and negative advantages during training.

Guohong Liu, Jialei Ye, Jiacheng Liu et al.

Mobile GUI agents are designed to autonomously execute diverse device-control tasks by interpreting and interacting with mobile screens. Despite notable advancements, their resilience in real-world scenarios where screen content may be partially manipulated by untrustworthy third parties remains largely unexplored. Owing to their black-box and autonomous nature, these agents are vulnerable to manipulations that could compromise user devices. In this work, we present the first systematic investigation into the vulnerabilities of mobile GUI agents. We introduce a scalable attack simulation framework AgentHazard, which enables flexible and targeted modifications of screen content within existing applications. Leveraging this framework, we develop a comprehensive benchmark suite comprising both a dynamic task execution environment and a static dataset of vision-language-action tuples, totaling over 3,000 attack scenarios. The dynamic environment encompasses 58 reproducible tasks in an emulator with various types of hazardous UI content, while the static dataset is constructed from 210 screenshots collected from 14 popular commercial apps. Importantly, our content modifications are designed to be feasible for unprivileged third parties. We evaluate 7 widely-used mobile GUI agents and 5 common backbone models using our benchmark. Our findings reveal that all examined agents are significantly influenced by misleading third-party content (with an average misleading rate of 28.8% in human-crafted attack scenarios) and that their vulnerabilities are closely linked to the employed perception modalities and backbone LLMs. Furthermore, we assess training-based mitigation strategies, highlighting both the challenges and opportunities for enhancing the robustness of mobile GUI agents. Our code and data will be released at https://agenthazard.github.io.

Qinzhuo Wu, Zhizhuo Yang, Hanhao Li et al.

Recent advances in mobile Graphical User Interface (GUI) agents highlight the growing need for comprehensive evaluation benchmarks. While new online benchmarks offer more realistic testing than offline ones, they tend to focus on the agents' task instruction-following ability while neglecting their reasoning and exploration ability. Moreover, these benchmarks do not consider the random noise in real-world mobile environments. This leads to a gap between benchmarks and real-world environments. To addressing these limitations, we propose MobileBench-OL, an online benchmark with 1080 tasks from 80 Chinese apps. It measures task execution, complex reasoning, and noise robustness of agents by including 5 subsets, which set multiple evaluation dimensions. We also provide an auto-eval framework with a reset mechanism, enabling stable and repeatable real-world benchmarking. Evaluating 12 leading GUI agents on MobileBench-OL shows significant room for improvement to meet real-world requirements. Human evaluation further confirms that MobileBench-OL can reliably measure the performance of leading GUI agents in real environments. Our data and code will be released upon acceptance.

Heinrich Dinkel, Zhiyong Yan, Tianzi Wang et al.

Contrastive Language Audio Pretraining (CLAP) is a widely-used method to bridge the gap between audio and text domains. Current CLAP methods enable sound and music retrieval in English, ignoring multilingual spoken content. To address this, we introduce general language audio pretraining (GLAP), which expands CLAP with multilingual and multi-domain abilities. GLAP demonstrates its versatility by achieving competitive performance on standard audio-text retrieval benchmarks like Clotho and AudioCaps, while significantly surpassing existing methods in speech retrieval and classification tasks. Additionally, GLAP achieves strong results on widely used sound-event zero-shot benchmarks, while simultaneously outperforming previous methods on speech content benchmarks. Further keyword spotting evaluations across 50 languages emphasize GLAP's advanced multilingual capabilities. Finally, multilingual sound and music understanding is evaluated across four languages. Checkpoints and Source: https://github.com/xiaomi-research/dasheng-glap.

Xiaolin Hu, Xiang Cheng, Peiyu Liu et al.

Low-rank adaptation (LoRA) reduces the computational and memory demands of fine-tuning large language models (LLMs) by approximating updates with low-rank matrices. However, low-rank approximation in two-dimensional space fails to capture high-dimensional structures within the target matrix. Recently, tensor decomposition methods have been explored for fine-tuning LLMs, leveraging their ability to extract structured information. Yet, these approaches primarily rely on random initialization, and the impact of initialization on tensor adaptation remains underexplored. In this paper, we reveal that random initialization significantly diverges from the validation loss achieved by full fine-tuning. To address this, we propose Weight-Decomposed Tensor Adaptation (DoTA), which leverages the Matrix Product Operator (MPO) decomposition of pre-trained weights for effective initialization in fine-tuning LLMs. Additionally, we introduce QDoTA, a quantized version of DoTA designed for 4-bit quantization. Experiments on commonsense and arithmetic reasoning tasks show that DoTA outperforms random initialization methods with fewer parameters. QDoTA further reduces memory consumption and achieves comparable performance to DoTA on commonsense reasoning tasks. We will release our code to support future research.

Yuanchun Li, Hao Wen, Weijun Wang et al. · tsinghua

Since the advent of personal computing devices, intelligent personal assistants (IPAs) have been one of the key technologies that researchers and engineers have focused on, aiming to help users efficiently obtain information and execute tasks, and provide users with more intelligent, convenient, and rich interaction experiences. With the development of smartphones and IoT, computing and sensing devices have become ubiquitous, greatly expanding the boundaries of IPAs. However, due to the lack of capabilities such as user intent understanding, task planning, tool using, and personal data management etc., existing IPAs still have limited practicality and scalability. Recently, the emergence of foundation models, represented by large language models (LLMs), brings new opportunities for the development of IPAs. With the powerful semantic understanding and reasoning capabilities, LLM can enable intelligent agents to solve complex problems autonomously. In this paper, we focus on Personal LLM Agents, which are LLM-based agents that are deeply integrated with personal data and personal devices and used for personal assistance. We envision that Personal LLM Agents will become a major software paradigm for end-users in the upcoming era. To realize this vision, we take the first step to discuss several important questions about Personal LLM Agents, including their architecture, capability, efficiency and security. We start by summarizing the key components and design choices in the architecture of Personal LLM Agents, followed by an in-depth analysis of the opinions collected from domain experts. Next, we discuss several key challenges to achieve intelligent, efficient and secure Personal LLM Agents, followed by a comprehensive survey of representative solutions to address these challenges.

Wuwei Huang, Renren Jin, Wen Zhang et al.

Recent studies on end-to-end speech translation(ST) have facilitated the exploration of multilingual end-to-end ST and end-to-end simultaneous ST. In this paper, we investigate end-to-end simultaneous speech translation in a one-to-many multilingual setting which is closer to applications in real scenarios. We explore a separate decoder architecture and a unified architecture for joint synchronous training in this scenario. To further explore knowledge transfer across languages, we propose an asynchronous training strategy on the proposed unified decoder architecture. A multi-way aligned multilingual end-to-end ST dataset was curated as a benchmark testbed to evaluate our methods. Experimental results demonstrate the effectiveness of our models on the collected dataset. Our codes and data are available at: https://github.com/XiaoMi/TED-MMST.

Jiaze Li, Haoran Xu, Wanyi Wu et al.

Federated learning is a paradigm of joint learning in which clients collaborate by sharing model parameters instead of data. However, in the non-iid setting, the global model experiences client drift, which can seriously affect the final performance of the model. Previous methods tend to correct the global model that has already deviated based on the loss function or gradient, overlooking the impact of the client samples. In this paper, we rethink the role of the client side and propose Federated Balanced Learning, i.e., FBL, to prevent this issue from the beginning through sample balance on the client side. Technically, FBL allows unbalanced data on the client side to achieve sample balance through knowledge filling and knowledge sampling using edge-side generation models, under the limitation of a fixed number of data samples on clients. Furthermore, we design a Knowledge Alignment Strategy to bridge the gap between synthetic and real data, and a Knowledge Drop Strategy to regularize our method. Meanwhile, we scale our method to real and complex scenarios, allowing different clients to adopt various methods, and extend our framework to further improve performance. Numerous experiments show that our method outperforms state-of-the-art baselines. The code is released upon acceptance.

Quandong Wang, Yuxuan Yuan, Xiaoyu Yang et al.

While Large Language Models (LLMs) have achieved remarkable success in various fields, the efficiency of training and inference remains a major challenge. To address this issue, we propose SUBLLM, short for Subsampling-Upsampling-Bypass Large Language Model, an innovative architecture that extends the core decoder-only framework by incorporating subsampling, upsampling, and bypass modules. The subsampling modules are responsible for shortening the sequence, while the upsampling modules restore the sequence length, and the bypass modules enhance convergence. In comparison to LLaMA, the proposed SUBLLM exhibits significant enhancements in both training and inference speeds as well as memory usage, while maintaining competitive few-shot performance. During training, SUBLLM increases speeds by 26% and cuts memory by 10GB per GPU. In inference, it boosts speeds by up to 37% and reduces memory by 1GB per GPU. The training and inference speeds can be enhanced by 34% and 52% respectively when the context window is expanded to 8192. Our code is available at https://github.com/XiaoMi/subllm.

Shaojie Zhang, Pei Fu, Ruoceng Zhang et al.

Autonomous Graphical User Interface (GUI) agents rely on accurate GUI grounding, which maps language instructions to on-screen coordinates, to execute user commands. However, current models, whether trained via supervised fine-tuning (SFT) or reinforcement fine-tuning (RFT), lack self-awareness of their capability boundaries, leading to overconfidence and unreliable predictions. We first systematically evaluate probabilistic and verbalized confidence in general and GUI-specific models, revealing a misalignment between confidence and actual accuracy, which is particularly critical in dynamic GUI automation tasks, where single errors can cause task failure. To address this, we propose HyperClick, a novel framework that enhances reliable GUI grounding through uncertainty calibration. HyperClick introduces a dual reward mechanism, combining a binary reward for correct actions with a truncated Gaussian-based spatial confidence modeling, calibrated using the Brier score. This approach jointly optimizes grounding accuracy and confidence reliability, fostering introspective self-criticism. Extensive experiments on seven challenge benchmarks show that HyperClick achieves state-of-the-art performance while providing well-calibrated confidence. By enabling explicit confidence calibration and introspective self-criticism, HyperClick reduces overconfidence and supports more reliable GUI automation.

Renren Jin, Jiangcun Du, Wuwei Huang et al.

Increasing the number of parameters in large language models (LLMs) usually improves performance in downstream tasks but raises compute and memory costs, making deployment difficult in resource-limited settings. Quantization techniques, which reduce the bits needed for model weights or activations with minimal performance loss, have become popular due to the rise of LLMs. However, most quantization studies use pre-trained LLMs, and the impact of quantization on instruction-tuned LLMs and the relationship between perplexity and benchmark performance of quantized LLMs are not well understood. Evaluation of quantized LLMs is often limited to language modeling and a few classification tasks, leaving their performance on other benchmarks unclear. To address these gaps, we propose a structured evaluation framework consisting of three critical dimensions: (1) knowledge \& capacity, (2) alignment, and (3) efficiency, and conduct extensive experiments across ten diverse benchmarks. Our experimental results indicate that LLMs with 4-bit quantization can retain performance comparable to their non-quantized counterparts, and perplexity can serve as a proxy metric for quantized LLMs on most benchmarks. Furthermore, quantized LLMs with larger parameter scales can outperform smaller LLMs. Despite the memory savings achieved through quantization, it can also slow down the inference speed of LLMs. Consequently, substantial engineering efforts and hardware support are imperative to achieve a balanced optimization of decoding speed and memory consumption in the context of quantized LLMs.

Shaojie Zhang, Jiahui Yang, Jianqin Yin et al.

Multimodal Large Language Models (MLLMs) have demonstrated significant success in visual understanding tasks. However, challenges persist in adapting these models for video comprehension due to the large volume of data and temporal complexity. Existing Video-LLMs using uniform frame sampling often struggle to capture the query-related crucial spatiotemporal clues of videos effectively. In this paper, we introduce Q-Frame, a novel approach for adaptive frame selection and multi-resolution scaling tailored to the video's content and the specific query. Q-Frame employs a training-free, plug-and-play strategy generated by a text-image matching network like CLIP, utilizing the Gumbel-Max trick for efficient frame selection. Q-Frame allows Video-LLMs to process more frames without exceeding computational limits, thereby preserving critical temporal and spatial information. We demonstrate Q-Frame's effectiveness through extensive experiments on benchmark datasets, including MLVU, LongVideoBench, and Video-MME, illustrating its superiority over existing methods and its applicability across various video understanding tasks.

Yuxuan Liu, Hongda Sun, Wei Liu et al.

Mobile phone agents can assist people in automating daily tasks on their phones, which have emerged as a pivotal research spotlight. However, existing procedure-oriented agents struggle with cross-app instructions, due to the following challenges: (1) complex task relationships, (2) diverse app environment, and (3) error propagation and information loss in multi-step execution. Drawing inspiration from object-oriented programming principles, we recognize that object-oriented solutions is more suitable for cross-app instruction. To address these challenges, we propose a self-evolving multi-agent framework named MobileSteward, which integrates multiple app-oriented StaffAgents coordinated by a centralized StewardAgent. We design three specialized modules in MobileSteward: (1) Dynamic Recruitment generates a scheduling graph guided by information flow to explicitly associate tasks among apps. (2) Assigned Execution assigns the task to app-oriented StaffAgents, each equipped with app-specialized expertise to address the diversity between apps. (3) Adjusted Evaluation conducts evaluation to provide reflection tips or deliver key information, which alleviates error propagation and information loss during multi-step execution. To continuously improve the performance of MobileSteward, we develop a Memory-based Self-evolution mechanism, which summarizes the experience from successful execution, to improve the performance of MobileSteward. We establish the first English Cross-APP Benchmark (CAPBench) in the real-world environment to evaluate the agents' capabilities of solving complex cross-app instructions. Experimental results demonstrate that MobileSteward achieves the best performance compared to both single-agent and multi-agent frameworks, highlighting the superiority of MobileSteward in better handling user instructions with diverse complexity.

Yuhan Chen, Ang Lv, Jian Luan et al.

Many positional encodings (PEs) are designed to exhibit long-term decay, based on an entrenched and long-standing inductive opinion: tokens farther away from the current position carry less relevant information. We argue that long-term decay is outdated in the era of LLMs, as LLMs are now applied to tasks demanding precise retrieval of in-context information from arbitrary positions. Firstly, we present empirical analyses on various PEs, demonstrating that models inherently learn attention with only a local-decay pattern while forming a U-shape pattern globally, contradicting the principle of long-term decay. Furthermore, we conduct a detailed analysis of rotary position encoding (RoPE, a prevalent relative positional encoding in LLMs), and found that the U-shape attention is caused by some learned components, which are also the key factor limiting RoPE's expressiveness and extrapolation.Inspired by these insights, we propose High-frequency rotary Position Encoding (HoPE). HoPE replaces the specific components in RoPE with position-independent ones, retaining only high-frequency signals, which also breaks the principle of long-term decay in theory. HoPE achieves two major advantages: (1) Without constraints imposed by long-term decay, contradictory factors that limit spontaneous attention optimization and model extrapolation performance are removed. (2) Components representing positions and semantics are are optimized. These enhances model's context awareness and extrapolation, as validated by extensive experiments.

Xinyue Guo, Xiaoran Yang, Lipan Zhang et al.

Sound effect editing-modifying audio by adding, removing, or replacing elements-remains constrained by existing approaches that rely solely on low-level signal processing or coarse text prompts, often resulting in limited flexibility and suboptimal audio quality. To address this, we propose AV-Edit, a generative sound effect editing framework that enables fine-grained editing of existing audio tracks in videos by jointly leveraging visual, audio, and text semantics. Specifically, the proposed method employs a specially designed contrastive audio-visual masking autoencoder (CAV-MAE-Edit) for multimodal pre-training, learning aligned cross-modal representations. These representations are then used to train an editorial Multimodal Diffusion Transformer (MM-DiT) capable of removing visually irrelevant sounds and generating missing audio elements consistent with video content through a correlation-based feature gating training strategy. Furthermore, we construct a dedicated video-based sound editing dataset as an evaluation benchmark. Experiments demonstrate that the proposed AV-Edit generates high-quality audio with precise modifications based on visual content, achieving state-of-the-art performance in the field of sound effect editing and exhibiting strong competitiveness in the domain of audio generation.

Shaojie Zhang, Ruoceng Zhang, Pei Fu et al.

In the field of AI-driven human-GUI interaction automation, while rapid advances in multimodal large language models and reinforcement fine-tuning techniques have yielded remarkable progress, a fundamental challenge persists: their interaction logic significantly deviates from natural human-GUI communication patterns. To fill this gap, we propose "Blink-Think-Link" (BTL), a brain-inspired framework for human-GUI interaction that mimics the human cognitive process between users and graphical interfaces. The system decomposes interactions into three biologically plausible phases: (1) Blink - rapid detection and attention to relevant screen areas, analogous to saccadic eye movements; (2) Think - higher-level reasoning and decision-making, mirroring cognitive planning; and (3) Link - generation of executable commands for precise motor control, emulating human action selection mechanisms. Additionally, we introduce two key technical innovations for the BTL framework: (1) Blink Data Generation - an automated annotation pipeline specifically optimized for blink data, and (2) BTL Reward -- the first rule-based reward mechanism that enables reinforcement learning driven by both process and outcome. Building upon this framework, we develop a GUI agent model named BTL-UI, which demonstrates competitive performance across both static GUI understanding and dynamic interaction tasks in comprehensive benchmarks. These results provide conclusive empirical validation of the framework's efficacy in developing advanced GUI Agents.

Kaidi Wang, Yi He, Wenhao Guan et al.

Video dubbing aims to generate high-fidelity speech that is precisely temporally aligned with the visual content. Existing methods still suffer from limitations in speech naturalness and audio-visual synchronization, and are limited to monolingual settings. To address these challenges, we propose SyncVoice, a vision-augmented video dubbing framework built upon a pretrained text-to-speech (TTS) model. By fine-tuning the TTS model on audio-visual data, we achieve strong audiovisual consistency. We propose a Dual Speaker Encoder to effectively mitigate inter-language interference in cross-lingual speech synthesis and explore the application of video dubbing in video translation scenarios. Experimental results show that SyncVoice achieves high-fidelity speech generation with strong synchronization performance, demonstrating its potential in video dubbing tasks.

Jiawei Chen, Xu Tan, Jian Luan et al.

High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz) to convey expression and emotion. However, higher sampling rate causes the wider frequency band and longer waveform sequences and throws challenges for singing voice synthesis (SVS) in both frequency and time domains. Conventional SVS systems that adopt small sampling rate cannot well address the above challenges. In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice. HiFiSinger consists of a FastSpeech based acoustic model and a Parallel WaveGAN based vocoder to ensure fast training and inference and also high voice quality. To tackle the difficulty of singing modeling caused by high sampling rate (wider frequency band and longer waveform), we introduce multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling. Specifically, 1) To handle the larger range of frequencies caused by higher sampling rate, we propose a novel sub-frequency GAN (SF-GAN) on mel-spectrogram generation, which splits the full 80-dimensional mel-frequency into multiple sub-bands and models each sub-band with a separate discriminator. 2) To model longer waveform sequences caused by higher sampling rate, we propose a multi-length GAN (ML-GAN) for waveform generation to model different lengths of waveform sequences with separate discriminators. 3) We also introduce several additional designs and findings in HiFiSinger that are crucial for high-fidelity voices, such as adding F0 (pitch) and V/UV (voiced/unvoiced flag) as acoustic features, choosing an appropriate window/hop size for mel-spectrogram, and increasing the receptive field in vocoder for long vowel modeling. Experiment results show that HiFiSinger synthesizes high-fidelity singing voices with much higher quality: 0.32/0.44 MOS gain over 48kHz/24kHz baseline and 0.83 MOS gain over previous SVS systems.

Yuanbo Hou, Frank K. Soong, Jian Luan et al.

Detecting singing-voice in polyphonic instrumental music is critical to music information retrieval. To train a robust vocal detector, a large dataset marked with vocal or non-vocal label at frame-level is essential. However, frame-level labeling is time-consuming and labor expensive, resulting there is little well-labeled dataset available for singing-voice detection (S-VD). Hence, we propose a data augmentation method for S-VD by transfer learning. In this study, clean speech clips with voice activity endpoints and separate instrumental music clips are artificially added together to simulate polyphonic vocals to train a vocal/non-vocal detector. Due to the different articulation and phonation between speaking and singing, the vocal detector trained with the artificial dataset does not match well with the polyphonic music which is singing vocals together with the instrumental accompaniments. To reduce this mismatch, transfer learning is used to transfer the knowledge learned from the artificial speech-plus-music training set to a small but matched polyphonic dataset, i.e., singing vocals with accompaniments. By transferring the related knowledge to make up for the lack of well-labeled training data in S-VD, the proposed data augmentation method by transfer learning can improve S-VD performance with an F-score improvement from 89.5% to 93.2%.

Yahuan Cong, Ran Zhang, Jian Luan

Current end-to-end autoregressive TTS systems (e.g. Tacotron 2) have outperformed traditional parallel approaches on the quality of synthesized speech. However, they introduce new problems at the same time. Due to the autoregressive nature, the time cost of inference has to be proportional to the length of text, which pose a great challenge for online serving. On the other hand, the style of synthetic speech becomes unstable and may change obviously among sentences. In this paper, we propose a Phrase based Parallel End-to-End TTS System (PPSpeech) to address these issues. PPSpeech uses autoregression approach within a phrase and executes parallel strategies for different phrases. By this method, we can achieve both high quality and high efficiency. In addition, we propose acoustic embedding and text context embedding as the conditions of encoder to keep successive and prevent from abrupt style or timbre change. Experiments show that, the synthesis speed of PPSpeech is much faster than sentence level autoregressive Tacotron 2 when a sentence has more than 5 phrases. The speed advantage increases with the growth of sentence length. Subjective experiments show that the proposed system with acoustic embedding and context embedding as conditions can make the style transition across sentences gradient and natural, defeating Global Style Token (GST) obviously in MOS.

Yi Ren, Xu Tan, Tao Qin et al.

In this paper, we develop DeepSinger, a multi-lingual multi-singer singing voice synthesis (SVS) system, which is built from scratch using singing training data mined from music websites. The pipeline of DeepSinger consists of several steps, including data crawling, singing and accompaniment separation, lyrics-to-singing alignment, data filtration, and singing modeling. Specifically, we design a lyrics-to-singing alignment model to automatically extract the duration of each phoneme in lyrics starting from coarse-grained sentence level to fine-grained phoneme level, and further design a multi-lingual multi-singer singing model based on a feed-forward Transformer to directly generate linear-spectrograms from lyrics, and synthesize voices using Griffin-Lim. DeepSinger has several advantages over previous SVS systems: 1) to the best of our knowledge, it is the first SVS system that directly mines training data from music websites, 2) the lyrics-to-singing alignment model further avoids any human efforts for alignment labeling and greatly reduces labeling cost, 3) the singing model based on a feed-forward Transformer is simple and efficient, by removing the complicated acoustic feature modeling in parametric synthesis and leveraging a reference encoder to capture the timbre of a singer from noisy singing data, and 4) it can synthesize singing voices in multiple languages and multiple singers. We evaluate DeepSinger on our mined singing dataset that consists of about 92 hours data from 89 singers on three languages (Chinese, Cantonese and English). The results demonstrate that with the singing data purely mined from the Web, DeepSinger can synthesize high-quality singing voices in terms of both pitch accuracy and voice naturalness (footnote: Our audio samples are shown in https://speechresearch.github.io/deepsinger/.)

Jie Wu, Jian Luan

This paper presents a high quality singing synthesizer that is able to model a voice with limited available recordings. Based on the sequence-to-sequence singing model, we design a multi-singer framework to leverage all the existing singing data of different singers. To attenuate the issue of musical score unbalance among singers, we incorporate an adversarial task of singer classification to make encoder output less singer dependent. Furthermore, we apply multiple random window discriminators (MRWDs) on the generated acoustic features to make the network be a GAN. Both objective and subjective evaluations indicate that the proposed synthesizer can generate higher quality singing voice than baseline (4.12 vs 3.53 in MOS). Especially, the articulation of high-pitched vowels is significantly enhanced.

Peiling Lu, Jie Wu, Jian Luan et al.

This paper presents XiaoiceSing, a high-quality singing voice synthesis system which employs an integrated network for spectrum, F0 and duration modeling. We follow the main architecture of FastSpeech while proposing some singing-specific design: 1) Besides phoneme ID and position encoding, features from musical score (e.g.note pitch and length) are also added. 2) To attenuate off-key issues, we add a residual connection in F0 prediction. 3) In addition to the duration loss of each phoneme, the duration of all the phonemes in a musical note is accumulated to calculate the syllable duration loss for rhythm enhancement. Experiment results show that XiaoiceSing outperforms the baseline system of convolutional neural networks by 1.44 MOS on sound quality, 1.18 on pronunciation accuracy and 1.38 on naturalness respectively. In two A/B tests, the proposed F0 and duration modeling methods achieve 97.3% and 84.3% preference rate over baseline respectively, which demonstrates the overwhelming advantages of XiaoiceSing.