Wenfu Wang

Wenfu Wang, Chenxing Li, Liqiang Zhang et al.

In this work, we present Covo-Audio, a 7B-parameter end-to-end LALM that directly processes continuous audio inputs and generates audio outputs within a single unified architecture. Through large-scale curated pretraining and targeted post-training, Covo-Audio achieves state-of-the-art or competitive performance among models of comparable scale across a broad spectrum of tasks, including speech-text modeling, spoken dialogue, speech understanding, audio understanding, and full-duplex voice interaction. Extensive evaluations demonstrate that the pretrained foundation model exhibits strong speech-text comprehension and semantic reasoning capabilities on multiple benchmarks, outperforming representative open-source models of comparable scale. Furthermore, Covo-Audio-Chat, the dialogue-oriented variant, demonstrates strong spoken conversational abilities, including understanding, contextual reasoning, instruction following, and generating contextually appropriate and empathetic responses, validating its applicability to real-world conversational assistant scenarios. Covo-Audio-Chat-FD, the evolved full-duplex model, achieves substantially superior performance on both spoken dialogue capabilities and full-duplex interaction behaviors, demonstrating its competence in practical robustness. To mitigate the high cost of deploying end-to-end LALMs for natural conversational systems, we propose an intelligence-speaker decoupling strategy that separates dialogue intelligence from voice rendering, enabling flexible voice customization with minimal text-to-speech (TTS) data while preserving dialogue performance. Overall, our results highlight the strong potential of 7B-scale models to integrate sophisticated audio intelligence with high-level semantic reasoning, and suggest a scalable path toward more capable and versatile LALMs.

Xiang He, Chenxing Li, Jinting Wang et al.

Large Audio-Language Models (LALMs) have made significant progress in audio understanding, yet they primarily operate as perception-and-answer systems without explicit reasoning processes. Existing methods for enhancing audio reasoning rely either on supervised chain-of-thought (CoT) fine-tuning, which is limited by training data quality, or on reinforcement learning (RL) with coarse rewards that do not directly evaluate reasoning quality. As a result, the generated reasoning chains often appear well-structured yet lack specific acoustic grounding. We propose Audio-DeepThinker, a framework built on two core ideas. First, we introduce a hybrid reasoning similarity reward that directly supervises the quality of generated reasoning chains by combining an LLM evaluator assessing logical path alignment, key step coverage, and analytical depth with an embedding similarity component enforcing semantic alignment with reference reasoning chains. Second, we propose a progressive two-stage curriculum that enables high-quality CoT reasoning to emerge through pure RL exploration, without any supervised reasoning fine-tuning, from an instruction-tuned model that possesses no prior chain-of-thought capability. Stage 1 trains on foundational audio QA with the hybrid reward to foster basic reasoning patterns, while Stage 2 shifts to acoustically challenging boundary cases with an LLM-only reward for greater reasoning diversity. Audio-DeepThinker achieves state-of-the-art results on MMAR (74.0%), MMAU-test-mini (78.5%), and MMSU (77.26%), winning 1st Place in the Interspeech 2026 Audio Reasoning Challenge (Single Model Track). Interpretability analyses further reveal that RL training primarily reshapes upper-layer MoE gating mechanisms and that reasoning tokens crystallize progressively in the upper transformer layers, offering mechanistic insights into how audio reasoning emerges through exploration.

Linjiong Zhu, Wenfu Wang, Weijie Yang et al.

Autonomous driving application is developing towards specific scenes. Park scene has features such as low speed, fixed routes, short connection, less complex traffic, and hence is suitable for bringing autonomous driving technology into reality. This paper targets park scene, and proposes a visual path tracking lateral control method using only one webcam. First, we calculate error of distance and error of angle from camera images, and then use fuzzy logic to fuzzify them into a combined error degree. The PID control algorithm takes it as input, and outputs steering wheel angle control command. Fuzzification could tolerate the error brought by image transformation and lane detection, making PID control more stably. Our experiments in both virtual and real scene show that our method can accurately and robustly follow the path, even at night. Compared with pure pursuit, our method can make 5 meters turning.

Tianxin Xie, Wentao Lei, Guanjie Huang et al.

Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content, including virtual reality, world modeling, gaming, and filmmaking. However, existing T2AV models remain incapable of generating physically plausible sounds, primarily due to their limited understanding of physical principles. To situate current research progress, we present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to systematically evaluate the audio physics grounding capabilities of existing T2AV models. PhyAVBench comprises 1,000 groups of paired text prompts with controlled physical variables that implicitly induce sound variations, enabling a fine-grained assessment of models' sensitivity to changes in underlying acoustic conditions. We term this evaluation paradigm the Audio-Physics Sensitivity Test (APST). Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation, covering 6 major audio physics dimensions, 4 daily scenarios (music, sound effects, speech, and their mix), and 50 fine-grained test points, ranging from fundamental aspects such as sound diffraction to more complex phenomena, e.g., Helmholtz resonance. Each test point consists of multiple groups of paired prompts, where each prompt is grounded by at least 20 newly recorded or collected real-world videos, thereby minimizing the risk of data leakage during model pre-training. Both prompts and videos are iteratively refined through rigorous human-involved error correction and quality control to ensure high quality. We argue that only models with a genuine grasp of audio-related physical principles can generate physically consistent audio-visual content. We hope PhyAVBench will stimulate future progress in this critical yet largely unexplored domain.

Shu Wu, Chenxing Li, Wenfu Wang et al.

Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards. However, the explicit reasoning process has yet to show significant benefits for audio question answering, and effectively leveraging deep reasoning remains an open challenge, with LALMs still falling short of human-level auditory-language reasoning. To address these limitations, we propose Audio-Thinker, a reinforcement learning framework designed to enhance the reasoning capabilities of LALMs, with a focus on improving adaptability, consistency, and effectiveness. Our approach introduces an adaptive think accuracy reward, enabling the model to adjust its reasoning strategies based on task complexity dynamically. Furthermore, we incorporate an external reward model to evaluate the overall consistency and quality of the reasoning process, complemented by think-based rewards that help the model distinguish between valid and flawed reasoning paths during training. Experimental results demonstrate that our Audio-Thinker model outperforms existing reasoning-oriented LALMs across various benchmark tasks, exhibiting superior reasoning and generalization capabilities.

Xusheng Yang, Long Zhou, Wenfu Wang et al.

We propose \textbf{U-Codec}, an \textbf{U}ltra low frame-rate neural speech \textbf{Codec} that achieves high-fidelity reconstruction and fast speech generation at an extremely low frame-rate of 5Hz (5 frames per second). Extreme compression at 5Hz typically leads to severe intelligibility and spectral detail loss, we introduce a Transformer-based inter-frame long-term dependency module and systematically explore residual vector quantization (RVQ) depth and codebook size to identify optimal configurations. Moreover, we apply U-Codec into a large language model (LLM)-based auto-regressive TTS model, which leverages global and local hierarchical architecture to effectively capture dependencies across multi-layer tokens. We extend LLM-based TTS from 3-layer RVQ at 50Hz to 32-layer RVQ at 5Hz. Experimental results demonstrate that U-Codec improves LLM-based TTS inference speed by around 3 $\times$ over high-frame-rate codecs while maintaining similarity and naturalness. These results validate the feasibility of using highly compressed 5Hz discrete tokens for fast and high-fidelity speech synthesis.

Jiliang Hu, Wenfu Wang, Zuchao Li et al.

Recent advances in large audio language models (LALMs) have greatly enhanced multimodal conversational systems. However, existing benchmarks remain limited -- they are mainly English-centric, rely on synthetic speech, and lack comprehensive, discriminative evaluation across multiple dimensions. To address these gaps, we present Voice Chat Bot Bench (VCB Bench) -- a high-quality Chinese benchmark built entirely on real human speech. VCB Bench evaluates LALMs from three complementary perspectives: instruction following (including speech-level control beyond text commands), knowledge understanding (general knowledge, reasoning, and daily dialogue), and robustness (stability under perturbations in content, environment, and speaker traits). Experiments on representative LALMs reveal notable performance gaps and highlight future directions for improvement. VCB Bench provides a reproducible and fine-grained evaluation framework, offering standardized methodology and practical insights for advancing Chinese voice conversational models.

Yisu Liu, Chenxing Li, Wanqian Zhang et al.

Controllable text-to-audio generation aims to synthesize audio from textual descriptions while satisfying user-specified constraints, including event types, temporal sequences, and onset and offset timestamps. This enables precise control over both the content and temporal structure of the generated audio. Despite recent progress, existing methods still face inherent trade-offs among accurate temporal localization, open-vocabulary scalability, and practical efficiency. To address these challenges, we propose DegDiT, a novel dynamic event graph-guided diffusion transformer framework for open-vocabulary controllable audio generation. DegDiT encodes the events in the description as structured dynamic graphs. The nodes in each graph are designed to represent three aspects: semantic features, temporal attributes, and inter-event connections. A graph transformer is employed to integrate these nodes and produce contextualized event embeddings that serve as guidance for the diffusion model. To ensure high-quality and diverse training data, we introduce a quality-balanced data selection pipeline that combines hierarchical event annotation with multi-criteria quality scoring, resulting in a curated dataset with semantic diversity. Furthermore, we present consensus preference optimization, facilitating audio generation through consensus among multiple reward signals. Extensive experiments on AudioCondition, DESED, and AudioTime datasets demonstrate that DegDiT achieves state-of-the-art performances across a variety of objective and subjective evaluation metrics.

Zhuolin He, Xinrun Li, Jiacheng Tang et al.

Conventional camera-based 3D object detectors in autonomous driving are limited to recognizing a predefined set of objects, which poses a safety risk when encountering novel or unseen objects in real-world scenarios. To address this limitation, we present OS-Det3D, a two-stage training framework designed for camera-based open-set 3D object detection. In the first stage, our proposed 3D object discovery network (ODN3D) uses geometric cues from LiDAR point clouds to generate class-agnostic 3D object proposals, each of which are assigned a 3D objectness score. This approach allows the network to discover objects beyond known categories, allowing for the detection of unfamiliar objects. However, due to the absence of class constraints, ODN3D-generated proposals may include noisy data, particularly in cluttered or dynamic scenes. To mitigate this issue, we introduce a joint selection (JS) module in the second stage. The JS module uses both camera bird's eye view (BEV) feature responses and 3D objectness scores to filter out low-quality proposals, yielding high-quality pseudo ground truth for unknown objects. OS-Det3D significantly enhances the ability of camera 3D detectors to discover and identify unknown objects while also improving the performance on known objects, as demonstrated through extensive experiments on the nuScenes and KITTI datasets.

Wenfu Wang, Zhijie Pan

We focus on the very challenging task of semantic segmentation for autonomous driving system. It must deliver decent semantic segmentation result for traffic critical objects real-time. In this paper, we propose a very efficient yet powerful deep neural network for driving scene semantic segmentation termed as Driving Segmentation Network (DSNet). DSNet achieves state-of-the-art balance between accuracy and inference speed through efficient units and architecture design inspired by ShuffleNet V2 and ENet. More importantly, DSNet highlights classes most critical with driving decision making through our novel Driving Importance-weighted Loss. We evaluate DSNet on Cityscapes dataset, our DSNet achieves 71.8% mean Intersection-over-Union (IoU) on validation set and 69.3% on test set. Class-wise IoU scores show that Driving Importance-weighted Loss could improve most driving critical classes by a large margin. Compared with ENet, DSNet is 18.9% more accurate and 1.1+ times faster which implies great potential for autonomous driving application.

Wenfu Wang, Weijie Yang, An Chen et al.

Urban traffic systems worldwide are suffering from severe traffic safety problems. Traffic safety is affected by many complex factors, and heavily related to all drivers' behaviors involved in traffic system. Drivers with aggressive driving behaviors increase the risk of traffic accidents. In order to manage the safety level of traffic system, we propose Driving Safety Credit inspired by credit score in financial security field, and design a scoring method using trajectory data and violation records. First, we extract driving habits, aggressive driving behaviors and traffic violation behaviors from driver's trajectories and traffic violation records. Next, we train a classification model to filtered out irrelevant features. And at last, we score each driver with selected features. We verify our proposed scoring method using 40 days of traffic simulation, and proves the effectiveness of our scoring method.