Yanfeng Lu

Jinye Qu, Zeyu Gao, Tielin Zhang et al.

Spiking Neural Networks (SNNs) have garnered widespread interest for their energy efficiency and brain-inspired event-driven properties. While recent methods like Spiking-YOLO have expanded the SNNs to more challenging object detection tasks, they often suffer from high latency and low detection accuracy, making them difficult to deploy on latency sensitive mobile platforms. Furthermore, the conversion method from Artificial Neural Networks (ANNs) to SNNs is hard to maintain the complete structure of the ANNs, resulting in poor feature representation and high conversion errors. To address these challenges, we propose two methods: timesteps compression and spike-time-dependent integrated (STDI) coding. The former reduces the timesteps required in ANN-SNN conversion by compressing information, while the latter sets a time-varying threshold to expand the information holding capacity. We also present a SNN-based ultra-low latency and high accurate object detection model (SUHD) that achieves state-of-the-art performance on nontrivial datasets like PASCAL VOC and MS COCO, with about remarkable 750x fewer timesteps and 30% mean average precision (mAP) improvement, compared to the Spiking-YOLO on MS COCO datasets. To the best of our knowledge, SUHD is the deepest spike-based object detection model to date that achieves ultra low timesteps to complete the lossless conversion.

Zeyu Gao, Yao Mu, Chen Chen et al.

End-to-end autonomous driving provides a feasible way to automatically maximize overall driving system performance by directly mapping the raw pixels from a front-facing camera to control signals. Recent advanced methods construct a latent world model to map the high dimensional observations into compact latent space. However, the latent states embedded by the world model proposed in previous works may contain a large amount of task-irrelevant information, resulting in low sampling efficiency and poor robustness to input perturbations. Meanwhile, the training data distribution is usually unbalanced, and the learned policy is challenging to cope with the corner cases during the driving process. To solve the above challenges, we present a SEMantic Masked recurrent world model (SEM2), which introduces a semantic filter to extract key driving-relevant features and make decisions via the filtered features, and is trained with a multi-source data sampler, which aggregates common data and multiple corner case data in a single batch, to balance the data distribution. Extensive experiments on CARLA show our method outperforms the state-of-the-art approaches in terms of sample efficiency and robustness to input permutations.

Hardik B. Sailor, Aw Ai Ti, Chen Fang Yih Nancy et al.

We present MERaLiON-SER, a robust speech emotion recognition model designed for English and Southeast Asian languages. The model is trained using a hybrid objective combining weighted categorical cross-entropy and Concordance Correlation Coefficient (CCC) losses for joint discrete and dimensional emotion modelling. This dual approach enables the model to capture both the distinct categories of emotion (like happy or angry) and the fine-grained, such as arousal (intensity), valence (positivity/negativity), and dominance (sense of control), leading to a more comprehensive and robust representation of human affect. Extensive evaluations across multilingual Singaporean languages (English, Chinese, Malay, and Tamil ) and other public benchmarks show that MERaLiON-SER consistently surpasses both open-source speech encoders and large Audio-LLMs. These results underscore the importance of specialised speech-only models for accurate paralinguistic understanding and cross-lingual generalisation. Furthermore, the proposed framework provides a foundation for integrating emotion-aware perception into future agentic audio systems, enabling more empathetic and contextually adaptive multimodal reasoning.

Zhiyuan Li, Yanfeng Lu, Yao Mu et al.

Vision Language Navigation in Continuous Environments (VLN-CE) represents a frontier in embodied AI, demanding agents to navigate freely in unbounded 3D spaces solely guided by natural language instructions. This task introduces distinct challenges in multimodal comprehension, spatial reasoning, and decision-making. To address these challenges, we introduce Cog-GA, a generative agent founded on large language models (LLMs) tailored for VLN-CE tasks. Cog-GA employs a dual-pronged strategy to emulate human-like cognitive processes. Firstly, it constructs a cognitive map, integrating temporal, spatial, and semantic elements, thereby facilitating the development of spatial memory within LLMs. Secondly, Cog-GA employs a predictive mechanism for waypoints, strategically optimizing the exploration trajectory to maximize navigational efficiency. Each waypoint is accompanied by a dual-channel scene description, categorizing environmental cues into 'what' and 'where' streams as the brain. This segregation enhances the agent's attentional focus, enabling it to discern pertinent spatial information for navigation. A reflective mechanism complements these strategies by capturing feedback from prior navigation experiences, facilitating continual learning and adaptive replanning. Extensive evaluations conducted on VLN-CE benchmarks validate Cog-GA's state-of-the-art performance and ability to simulate human-like navigation behaviors. This research significantly contributes to the development of strategic and interpretable VLN-CE agents.

Sheng Yang, Tong Zhan, Shichen Qiao et al.

Reliable 3D object perception is essential in autonomous driving. Owing to its sensing capabilities in all weather conditions, 4D radar has recently received much attention. However, compared to LiDAR, 4D radar provides much sparser point cloud. In this paper, we propose a 3D object detection method, termed ZFusion, which fuses 4D radar and vision modality. As the core of ZFusion, our proposed FP-DDCA (Feature Pyramid-Double Deformable Cross Attention) fuser complements the (sparse) radar information and (dense) vision information, effectively. Specifically, with a feature-pyramid structure, the FP-DDCA fuser packs Transformer blocks to interactively fuse multi-modal features at different scales, thus enhancing perception accuracy. In addition, we utilize the Depth-Context-Split view transformation module due to the physical properties of 4D radar. Considering that 4D radar has a much lower cost than LiDAR, ZFusion is an attractive alternative to LiDAR-based methods. In typical traffic scenarios like the VoD (View-of-Delft) dataset, experiments show that with reasonable inference speed, ZFusion achieved the state-of-the-art mAP (mean average precision) in the region of interest, while having competitive mAP in the entire area compared to the baseline methods, which demonstrates performance close to LiDAR and greatly outperforms those camera-only methods.

Zhengyuan Liu, Geyu Lin, Hui Li Tan et al.

The integration of generative artificial intelligence into educational applications has enhanced personalized and interactive learning experiences, and it shows strong potential to promote young learners language acquisition. However, it is still challenging to ensure consistent and robust performance across different languages and cultural contexts, and kids-friendly design requires simplified instructions, engaging interactions, and age-appropriate scaffolding to maintain motivation and optimize learning outcomes. In this work, we introduce SingaKids, a dialogic tutor designed to facilitate language learning through picture description tasks. Our system integrates dense image captioning, multilingual dialogic interaction, speech understanding, and engaging speech generation to create an immersive learning environment in four languages: English, Mandarin, Malay, and Tamil. We further improve the system through multilingual pre-training, task-specific tuning, and scaffolding optimization. Empirical studies with elementary school students demonstrate that SingaKids provides effective dialogic teaching, benefiting learners at different performance levels.

Jia-Yi Chang, Yan-Feng Lu, Ya-Jun Liu et al.

Remote tiny face detection applied in unmanned system is a challeng-ing work. The detector cannot obtain sufficient context semantic information due to the relatively long distance. The received poor fine-grained features make the face detection less accurate and robust. To solve the problem of long-distance detection of tiny faces, we propose an enhanced network model (YOLOv3-C) based on the YOLOv3 algorithm for unmanned platform. In this model, we bring in multi-scale features from feature pyramid networks and make the features fu-sion to adjust prediction feature map of the output, which improves the sensitivity of the entire algorithm for tiny target faces. The enhanced model improves the accuracy of tiny face detection in the cases of long-distance and high-density crowds. The experimental evaluation results demonstrated the superior perfor-mance of the proposed YOLOv3-C in comparison with other relevant detectors in remote tiny face detection. It is worth mentioning that our proposed method achieves comparable performance with the state of the art YOLOv4[1] in the tiny face detection tasks.

Yan-Feng Lu, Li-Hao Jia, Hong Qaio et al.

Biologically inspired model (BIM) for image recognition is a robust computational architecture, which has attracted widespread attention. BIM can be described as a four-layer structure based on the mechanisms of the visual cortex. Although the performance of BIM for image recognition is robust, it takes the randomly selected ways for the patch selection, which is sightless, and results in heavy computing burden. To address this issue, we propose a novel patch selection method with oriented Gaussian-Hermite moment (PSGHM), and we enhanced the BIM based on the proposed PSGHM, named as PBIM. In contrast to the conventional BIM which adopts the random method to select patches within the feature representation layers processed by multi-scale Gabor filter banks, the proposed PBIM takes the PSGHM way to extract a small number of representation features while offering promising distinctiveness. To show the effectiveness of the proposed PBIM, experimental studies on object categorization are conducted on the CalTech05, TU Darmstadt (TUD), and GRAZ01 databases. Experimental results demonstrate that the performance of PBIM is a significant improvement on that of the conventional BIM.