arXiv subjects

Junbo Zhang

Publications and source records attributed to Junbo Zhang.

At least 37 records · Page 2Linked to original sources

arXiv2026

GLAP: General contrastive audio-text pretraining across domains and languages

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.

cs.SD↗

arXiv2025

JoyAgent-JDGenie: Technical Report on the GAIA

Large Language Models are increasingly deployed as autonomous agents for complex real-world tasks, yet existing systems often focus on isolated improvements without a unifying design for robustness and adaptability. We propose a generalist agent architecture that integrates three core components: a collective multi-agent framework combining planning and execution agents with critic model voting, a hierarchical memory system spanning working, semantic, and procedural layers, and a refined tool suite for search, code execution, and multimodal parsing. Evaluated on a comprehensive benchmark, our framework consistently outperforms open-source baselines and approaches the performance of proprietary systems. These results demonstrate the importance of system-level integration and highlight a path toward scalable, resilient, and adaptive AI assistants capable of operating across diverse domains and tasks.

cs.CL↗

arXiv2025

RideAgent: An LLM-Enhanced Optimization Framework for Automated Taxi Fleet Operations

Efficient management of electric ride-hailing fleets, particularly pre-allocation and pricing during peak periods to balance spatio-temporal supply and demand, is crucial for urban traffic efficiency. However, practical challenges include unpredictable demand and translating diverse, qualitative managerial objectives from non-expert operators into tractable optimization models. This paper introduces RideAgent, an LLM-powered agent framework that automates and enhances electric ride-hailing fleet management. First, an LLM interprets natural language queries from fleet managers to formulate corresponding mathematical objective functions. These user-defined objectives are then optimized within a Mixed-Integer Programming (MIP) framework, subject to the constraint of maintaining high operational profit. The profit itself is a primary objective, estimated by an embedded Random Forest (RF) model leveraging exogenous features. To accelerate the solution of this MIP, a prompt-guided LLM analyzes a small sample of historical optimal decision data to guide a variable fixing strategy. Experiments on real-world data show that the LLM-generated objectives achieve an 86% text similarity to standard formulations in a zero-shot setting. Following this, the LLM-guided variable fixing strategy reduces computation time by 53.15% compared to solving the full MIP with only a 2.42% average optimality gap. Moreover, this variable fixing strategy outperforms five cutting plane methods by 42.3% time reduction with minimal compromise to solution quality. RideAgent offers a robust and adaptive automated framework for objective modeling and accelerated optimization. This framework empowers non-expert fleet managers to personalize operations and improve urban transportation system performance.

math.OC↗

arXiv2025

Improving Open-world Continual Learning under the Constraints of Scarce Labeled Data

Open-world continual learning (OWCL) adapts to sequential tasks with open samples, learning knowledge incrementally while preventing forgetting. However, existing OWCL still requires a large amount of labeled data for training, which is often impractical in real-world applications. Given that new categories/entities typically come with limited annotations and are in small quantities, a more realistic situation is OWCL with scarce labeled data, i.e., few-shot training samples. Hence, this paper investigates the problem of open-world few-shot continual learning (OFCL), challenging in (i) learning unbounded tasks without forgetting previous knowledge and avoiding overfitting, (ii) constructing compact decision boundaries for open detection with limited labeled data, and (iii) transferring knowledge about knowns and unknowns and even update the unknowns to knowns once the labels of open samples are learned. In response, we propose a novel OFCL framework that integrates three key components: (1) an instance-wise token augmentation (ITA) that represents and enriches sample representations with additional knowledge, (2) a margin-based open boundary (MOB) that supports open detection with new tasks emerge over time, and (3) an adaptive knowledge space (AKS) that endows unknowns with knowledge for the updating from unknowns to knowns. Finally, extensive experiments show that the proposed OFCL framework outperforms all baselines remarkably with practical importance and reproducibility. The source code is released at https://github.com/liyj1201/OFCL.

cs.LG↗

arXiv2025

AirRadar: Inferring Nationwide Air Quality in China with Deep Neural Networks

Monitoring real-time air quality is essential for safeguarding public health and fostering social progress. However, the widespread deployment of air quality monitoring stations is constrained by their significant costs. To address this limitation, we introduce \emph{AirRadar}, a deep neural network designed to accurately infer real-time air quality in locations lacking monitoring stations by utilizing data from existing ones. By leveraging learnable mask tokens, AirRadar reconstructs air quality features in unmonitored regions. Specifically, it operates in two stages: first capturing spatial correlations and then adjusting for distribution shifts. We validate AirRadar's efficacy using a year-long dataset from 1,085 monitoring stations across China, demonstrating its superiority over multiple baselines, even with varying degrees of unobserved data. The source code can be accessed at https://github.com/CityMind-Lab/AirRadar.

cs.LG↗

arXiv2025

Non-collective Calibrating Strategy for Time Series Forecasting

Deep learning-based approaches have demonstrated significant advancements in time series forecasting. Despite these ongoing developments, the complex dynamics of time series make it challenging to establish the rule of thumb for designing the golden model architecture. In this study, we argue that refining existing advanced models through a universal calibrating strategy can deliver substantial benefits with minimal resource costs, as opposed to elaborating and training a new model from scratch. We first identify a multi-target learning conflict in the calibrating process, which arises when optimizing variables across time steps, leading to the underutilization of the model's learning capabilities. To address this issue, we propose an innovative calibrating strategy called Socket+Plug (SoP). This approach retains an exclusive optimizer and early-stopping monitor for each predicted target within each Plug while keeping the fully trained Socket backbone frozen. The model-agnostic nature of SoP allows it to directly calibrate the performance of any trained deep forecasting models, regardless of their specific architectures. Extensive experiments on various time series benchmarks and a spatio-temporal meteorological ERA5 dataset demonstrate the effectiveness of SoP, achieving up to a 22% improvement even when employing a simple MLP as the Plug (highlighted in Figure 1). Code is available at https://github.com/hanyuki23/SoP.

cs.LG↗

arXiv2025

Unified Vision-Language-Action Model

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the rich temporal and causal structure embedded in visual observations. In this paper, we present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences. This formulation enables flexible multimodal tasks learning, particularly from large-scale video data. By incorporating world modeling during post-training, UniVLA captures causal dynamics from videos, facilitating effective transfer to downstream policy learning--especially for long-horizon tasks. Our approach sets new state-of-the-art results across several widely used simulation benchmarks, including CALVIN, LIBERO, and Simplenv-Bridge, significantly surpassing previous methods. For example, UniVLA achieves 95.5% average success rate on LIBERO benchmark, surpassing pi0-FAST's 85.5%. We further demonstrate its broad applicability on real-world ALOHA manipulation and autonomous driving.

cs.CV↗

arXiv2025

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders

Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and extensible SE method. Our approach involves initially extracting audio embeddings from noisy speech using a pre-trained audioencoder, which are then denoised by a compact encoder network. Subsequently, a vocoder synthesizes the clean speech from denoised embeddings. An ablation study substantiates the parameter efficiency of the denoise encoder with a pre-trained audioencoder and vocoder. Experimental results on both speech enhancement and speaker fidelity demonstrate that our generative audioencoder-based SE system outperforms models utilizing discriminative audioencoders. Furthermore, subjective listening tests validate that our proposed system surpasses an existing state-of-the-art SE model in terms of perceptual quality.

eess.AS↗

arXiv2025

X-ARES: A Comprehensive Framework for Assessing Audio Encoder Performance

We introduces X-ARES (eXtensive Audio Representation and Evaluation Suite), a novel open-source benchmark designed to systematically assess audio encoder performance across diverse domains. By encompassing tasks spanning speech, environmental sounds, and music, X-ARES provides two evaluation approaches for evaluating audio representations: linear fine-tuning and unparameterized evaluation. The framework includes 22 distinct tasks that cover essential aspects of audio processing, from speech recognition and emotion detection to sound event classification and music genre identification. Our extensive evaluation of state-of-the-art audio encoders reveals significant performance variations across different tasks and domains, highlighting the complexity of general audio representation learning.

cs.SD↗

arXiv2025

Reinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering

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.

cs.SD↗

arXiv2025

Order-Robust Class Incremental Learning: Graph-Driven Dynamic Similarity Grouping

Class Incremental Learning (CIL) aims to enable models to learn new classes sequentially while retaining knowledge of previous ones. Although current methods have alleviated catastrophic forgetting (CF), recent studies highlight that the performance of CIL models is highly sensitive to the order of class arrival, particularly when sequentially introduced classes exhibit high inter-class similarity. To address this critical yet understudied challenge of class order sensitivity, we first extend existing CIL frameworks through theoretical analysis, proving that grouping classes with lower pairwise similarity during incremental phases significantly improves model robustness to order variations. Building on this insight, we propose Graph-Driven Dynamic Similarity Grouping (GDDSG), a novel method that employs graph coloring algorithms to dynamically partition classes into similarity-constrained groups. Each group trains an isolated CIL sub-model and constructs meta-features for class group identification. Experimental results demonstrate that our method effectively addresses the issue of class order sensitivity while achieving optimal performance in both model accuracy and anti-forgetting capability. Our code is available at https://github.com/AIGNLAI/GDDSG.

cs.LG↗

arXiv2025

The ICME 2025 Audio Encoder Capability Challenge

This challenge aims to evaluate the capabilities of audio encoders, especially in the context of multi-task learning and real-world applications. Participants are invited to submit pre-trained audio encoders that map raw waveforms to continuous embeddings. These encoders will be tested across diverse tasks including speech, environmental sounds, and music, with a focus on real-world usability. The challenge features two tracks: Track A for parameterized evaluation, and Track B for parameter-free evaluation. This challenge provides a platform for evaluating and advancing the state-of-the-art in audio encoder design.

cs.SD↗

arXiv2024

Analyzing the Scalability of Bi-static Backscatter Networks for Large Scale Applications

Backscatter radio is a promising technology for low-cost and low-power Internet-of-Things (IoT) networks. The conventional monostatic backscatter radio is constrained by its limited communication range, which restricts its utility in wide-area applications. An alternative bi-static backscatter radio architecture, characterized by a dis-aggregated illuminator and receiver, can provide enhanced coverage and, thus, can support wide-area applications. In this paper, we analyze the scalability of the bi-static backscatter radio for large-scale wide-area IoT networks consisting of a large number of unsynchronized, receiver-less tags. We introduce the Tag Drop Rate (TDR) as a measure of reliability and develop a theoretical framework to estimate TDR in terms of the network parameters. We show that under certain approximations, a small-scale prototype can emulate a large-scale network. We then use the measurements from experimental prototypes of bi-static backscatter networks (BNs) to refine the theoretical model. Finally, based on the insights derived from the theoretical model and the experimental measurements, we describe a systematic methodology for tuning the network parameters and identifying the physical layer design requirements for the reliable operation of large-scale bi-static BNs. Our analysis shows that even with a modest physical layer requirement of bit error rate (BER) 0.2, 1000 receiver-less tags can be supported with 99.9% reliability. This demonstrates the feasibility of bi-static BNs for large-scale wide-area IoT applications.

eess.SY↗

arXiv2024

RoLD: Robot Latent Diffusion for Multi-task Policy Modeling

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language models, thus limiting their multi-task performance and practical applications. In this study, we propose a novel approach that decouples robot action trajectory encoding and control policy generation by leveraging latent action trajectory spaces, enhancing the generalization ability of policy generation on multi-task manipulation tasks. First, we pre-train a task-agnostic auto-encoder to project an action trajectory of several frames accompanied with observations into a latent action trajectory space on large-scale datasets collected with multiple embodiments in various environments. Then we propose learning a diffusion model based on the latent action trajectory space to generate actions of next steps. Through experiments on two widely used benchmarks, results demonstrate that our proposed method outperforms baselines by 7%-29% in terms of average success rate across eight tasks. Our method can consistently benefit from pre-training while baselines cannot. Our method is more than two times faster than our baseline.

cs.RO↗

arXiv2024

UMOD: A Novel and Effective Urban Metro Origin-Destination Flow Prediction Method

Accurate prediction of metro Origin-Destination (OD) flow is essential for the development of intelligent transportation systems and effective urban traffic management. Existing approaches typically either predict passenger outflow of departure stations or inflow of destination stations. However, we argue that travelers generally have clearly defined departure and arrival stations, making these OD pairs inherently interconnected. Consequently, considering OD pairs as a unified entity more accurately reflects actual metro travel patterns and allows for analyzing potential spatio-temporal correlations between different OD pairs. To address these challenges, we propose a novel and effective urban metro OD flow prediction method (UMOD), comprising three core modules: a data embedding module, a temporal relation module, and a spatial relation module. The data embedding module projects raw OD pair inputs into hidden space representations, which are subsequently processed by the temporal and spatial relation modules to capture both inter-pair and intra-pair spatio-temporal dependencies. Experimental results on two real-world urban metro OD flow datasets demonstrate that adopting the OD pairs perspective is critical for accurate metro OD flow prediction. Our method outperforms existing approaches, delivering superior predictive performance.

cs.LG↗

arXiv2024

Closeby Habitable Exoplanet Survey (CHES). II. An Observation Strategy for the Target Stars

The Closeby Habitable Exoplanet Survey (CHES) constitutes a mission intricately designed to systematically survey approximately 100 solar-type stars located within the immediate proximity of the solar system, specifically within a range of 10 parsecs. The core objective of this mission is the detection and characterization of potentially habitable Earth-like planets or super-Earths within the habitable zone of these stars. The CHES mission obtains high-precision astrometric measurements of planets orbiting the target stars by observing angular distance variations between the target star and reference stars. As a result, we surveyed the relevant parameters of both target and reference stars in detail, conducting a thorough analysis and calculation of the required observation accuracy, the number of observations, and the priority assigned to each target star. Observational emphasis will be concentrated on targets considered of higher priority, ensuring the effectiveness of their observation capabilities. Through this approach, we formulate a five-year observation strategy that will cover all the target stars within a six-month timeframe. The strategy not only fulfills the required observing capability but also exhibit high efficiency simultaneously, providing an executable program for future mission. Over the span of the mission's five-year duration, a cumulative observation time of 29,220 hours will be available. Approximately 86 percent of this, totaling 25,120 hours, is allocated for the observation of target stars. This allocation leaves approximately 4,100 hours for extended scientific observation programs. We have also performed simulated observations based on this strategy and verified its observational capability for exoplanets.

astro-ph.EP↗

arXiv2024

Personalized Federated Continual Learning via Multi-granularity Prompt

Personalized Federated Continual Learning (PFCL) is a new practical scenario that poses greater challenges in sharing and personalizing knowledge. PFCL not only relies on knowledge fusion for server aggregation at the global spatial-temporal perspective but also needs model improvement for each client according to the local requirements. Existing methods, whether in Personalized Federated Learning (PFL) or Federated Continual Learning (FCL), have overlooked the multi-granularity representation of knowledge, which can be utilized to overcome Spatial-Temporal Catastrophic Forgetting (STCF) and adopt generalized knowledge to itself by coarse-to-fine human cognitive mechanisms. Moreover, it allows more effectively to personalized shared knowledge, thus serving its own purpose. To this end, we propose a novel concept called multi-granularity prompt, i.e., coarse-grained global prompt acquired through the common model learning process, and fine-grained local prompt used to personalize the generalized representation. The former focuses on efficiently transferring shared global knowledge without spatial forgetting, and the latter emphasizes specific learning of personalized local knowledge to overcome temporal forgetting. In addition, we design a selective prompt fusion mechanism for aggregating knowledge of global prompts distilled from different clients. By the exclusive fusion of coarse-grained knowledge, we achieve the transmission and refinement of common knowledge among clients, further enhancing the performance of personalization. Extensive experiments demonstrate the effectiveness of the proposed method in addressing STCF as well as improving personalized performance. Our code now is available at https://github.com/SkyOfBeginning/FedMGP.

cs.LG↗

arXiv2024

Enhancing Automated Audio Captioning via Large Language Models with Optimized Audio Encoding

Automated audio captioning (AAC) is an audio-to-text task to describe audio contents in natural language. Recently, the advancements in large language models (LLMs), with improvements in training approaches for audio encoders, have opened up possibilities for improving AAC. Thus, we explore enhancing AAC from three aspects: 1) a pre-trained audio encoder via consistent ensemble distillation (CED) is used to improve the effectivity of acoustic tokens, with a querying transformer (Q-Former) bridging the modality gap to LLM and compress acoustic tokens; 2) we investigate the advantages of using a Llama 2 with 7B parameters as the decoder; 3) another pre-trained LLM corrects text errors caused by insufficient training data and annotation ambiguities. Both the audio encoder and text decoder are optimized by low-rank adaptation (LoRA). Experiments show that each of these enhancements is effective. Our method obtains a 33.0 SPIDEr-FL score, outperforming the winner of DCASE 2023 Task 6A.

cs.SD↗