PSTTS: A Plug-and-Play Token Selector for Efficient Event-based Spatio-temporal Representation Learning

Mainstream event-based spatio-temporal representation learning methods typically process event streams by converting them into sequences of event frames, achieving remarkable performance. However, they neglect the high spatial sparsity and inter-frame motion redundancy inherent in event frame sequences, leading to significant computational overhead. Existing token sparsification methods for RGB videos rely on unreliable intermediate token representations and neglect the influence of event noise, making them ineffective for direct application to event data. In this paper, we propose Progressive Spatio-Temporal Token Selection (PSTTS), a Plug-and-Play module for event data without introducing any additional parameters. PSTTS exploits the spatio-temporal distribution characteristics embedded in raw event data to effectively identify and discard spatio-temporal redundant tokens, achieving an optimal trade-off between accuracy and efficiency. Specifically, PSTTS consists of two stages, Spatial Token Purification and Temporal Token Selection. Spatial Token Purification discards noise and non-event regions by assessing the spatio-temporal consistency of events within each event frame to prevent interference with subsequent temporal redundancy evaluation. Temporal Token Selection evaluates the motion pattern similarity between adjacent event frames, precisely identifying and removing redundant temporal information. We apply PSTTS to four representative backbones UniformerV2, VideoSwin, EVMamba, and ExACT on the HARDVS, DailyDVS-200, and SeACT datasets. Experimental results demonstrate that PSTTS achieves significant efficiency improvements. Specifically, PSTTS reduces FLOPs by 29-43.6% and increases FPS by 21.6-41.3% on the DailyDVS-200 dataset, while maintaining task accuracy. Our code will be available.

FunAudio-ASR Technical Report

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model size scaling, and deep integration with large language models (LLMs). However, LLMs are prone to hallucination, which can significantly degrade user experience in real-world ASR applications. In this paper, we present FunAudio-ASR, a large-scale, LLM-based ASR system that synergistically combines massive data, large model capacity, LLM integration, and reinforcement learning to achieve state-of-the-art performance across diverse and complex speech recognition scenarios. Moreover, FunAudio-ASR is specifically optimized for practical deployment, with enhancements in streaming capability, noise robustness, code-switching, hotword customization, and satisfying other real-world application requirements. Experimental results show that while most LLM-based ASR systems achieve strong performance on open-source benchmarks, they often underperform on real industry evaluation sets. Thanks to production-oriented optimizations, FunAudio-ASR achieves SOTA performance on real application datasets, demonstrating its effectiveness and robustness in practical settings.

Focus Through Motion: RGB-Event Collaborative Token Sparsification for Efficient Object Detection

Existing RGB-Event detection methods process the low-information regions of both modalities (background in images and non-event regions in event data) uniformly during feature extraction and fusion, resulting in high computational costs and suboptimal performance. To mitigate the computational redundancy during feature extraction, researchers have respectively proposed token sparsification methods for the image and event modalities. However, these methods employ a fixed number or threshold for token selection, hindering the retention of informative tokens for samples with varying complexity. To achieve a better balance between accuracy and efficiency, we propose FocusMamba, which performs adaptive collaborative sparsification of multimodal features and efficiently integrates complementary information. Specifically, an Event-Guided Multimodal Sparsification (EGMS) strategy is designed to identify and adaptively discard low-information regions within each modality by leveraging scene content changes perceived by the event camera. Based on the sparsification results, a Cross-Modality Focus Fusion (CMFF) module is proposed to effectively capture and integrate complementary features from both modalities. Experiments on the DSEC-Det and PKU-DAVIS-SOD datasets demonstrate that the proposed method achieves superior performance in both accuracy and efficiency compared to existing methods. The code will be available at https://github.com/Zizzzzzzz/FocusMamba.

Bidirectional Image-Event Guided Low-Light Image Enhancement

Under extreme low-light conditions, traditional frame-based cameras, due to their limited dynamic range and temporal resolution, face detail loss and motion blur in captured images. To overcome this bottleneck, researchers have introduced event cameras and proposed event-guided low-light image enhancement algorithms. However, these methods neglect the influence of global low-frequency noise caused by dynamic lighting conditions and local structural discontinuities in sparse event data. To address these issues, we propose an innovative Bidirectional guided Low-light Image Enhancement framework (BiLIE). Specifically, to mitigate the significant low-frequency noise introduced by global illumination step changes, we introduce the frequency high-pass filtering-based Event Feature Enhancement (EFE) module at the event representation level to suppress the interference of low-frequency information, and preserve and highlight the high-frequency edges.Furthermore, we design a Bidirectional Cross Attention Fusion (BCAF) mechanism to acquire high-frequency structures and edges while suppressing structural discontinuities and local noise introduced by sparse event guidance, thereby generating smoother fused representations.Additionally, considering the poor visual quality and color bias in existing datasets, we provide a new dataset (RELIE), with high-quality ground truth through a reliable enhancement scheme. Extensive experimental results demonstrate that our proposed BiLIE outperforms state-of-the-art methods by 0.96dB in PSNR and 0.03 in LPIPS.

Near-Field Secure Beamfocusing With Receiver-Centered Protected Zone

This work studies near-field secure communications through transmit beamfocusing. We examine the benefit of having a protected eavesdropper-free zone around the legitimate receiver, and we determine the worst-case secrecy performance against a potential eavesdropper located anywhere outside the protected zone. A max-min optimization problem is formulated for the beamfocusing design with and without artificial noise transmission. Despite the NP-hardness of the problem, we develop a synchronous gradient descent-ascent framework that approximates the global maximin solution. A low-complexity solution is also derived that delivers excellent performance over a wide range of operating conditions. We further extend this study to a scenario where it is not possible to physically enforce a protected zone. To this end, we consider secure communications through the creation of a virtual protected zone using a full-duplex legitimate receiver. Numerical results demonstrate that exploiting either the physical or virtual receiver-centered protected zone with appropriately designed beamfocusing is an effective strategy for achieving secure near-field communications.

Sonata: Self-Supervised Learning of Reliable Point Representations

In this paper, we question whether we have a reliable self-supervised point cloud model that can be used for diverse 3D tasks via simple linear probing, even with limited data and minimal computation. We find that existing 3D self-supervised learning approaches fall short when evaluated on representation quality through linear probing. We hypothesize that this is due to what we term the "geometric shortcut", which causes representations to collapse to low-level spatial features. This challenge is unique to 3D and arises from the sparse nature of point cloud data. We address it through two key strategies: obscuring spatial information and enhancing the reliance on input features, ultimately composing a Sonata of 140k point clouds through self-distillation. Sonata is simple and intuitive, yet its learned representations are strong and reliable: zero-shot visualizations demonstrate semantic grouping, alongside strong spatial reasoning through nearest-neighbor relationships. Sonata demonstrates exceptional parameter and data efficiency, tripling linear probing accuracy (from 21.8% to 72.5%) on ScanNet and nearly doubling performance with only 1% of the data compared to previous approaches. Full fine-tuning further advances SOTA across both 3D indoor and outdoor perception tasks.

mmE5: Improving Multimodal Multilingual Embeddings via High-quality Synthetic Data

Multimodal embedding models have gained significant attention for their ability to map data from different modalities, such as text and images, into a unified representation space. However, the limited labeled multimodal data often hinders embedding performance. Recent approaches have leveraged data synthesis to address this problem, yet the quality of synthetic data remains a critical bottleneck. In this work, we identify three criteria for high-quality synthetic multimodal data. First, broad scope ensures that the generated data covers diverse tasks and modalities, making it applicable to various downstream scenarios. Second, robust cross-modal alignment makes different modalities semantically consistent. Third, high fidelity ensures that the synthetic data maintains realistic details to enhance its reliability. Guided by these principles, we synthesize datasets that: (1) cover a wide range of tasks, modality combinations, and languages, (2) are generated via a deep thinking process within a single pass of a multimodal large language model, and (3) incorporate real-world images with accurate and relevant texts, ensuring fidelity through self-evaluation and refinement. Leveraging these high-quality synthetic and labeled datasets, we train a multimodal multilingual E5 model mmE5. Extensive experiments demonstrate that mmE5 achieves state-of-the-art performance on the MMEB Benchmark and superior multilingual performance on the XTD benchmark. Our codes, datasets and models are released in https://github.com/haon-chen/mmE5.

Examining False Positives under Inference Scaling for Mathematical Reasoning

Recent advancements in language models have led to significant improvements in mathematical reasoning across various benchmarks. However, most of these benchmarks rely on automatic evaluation methods that only compare final answers using heuristics, without verifying the underlying reasoning steps. This limitation results in false positive solutions, where models may produce correct final answers but with flawed deduction paths. In this paper, we systematically examine the prevalence of false positive solutions in mathematical problem solving for language models. We analyze the characteristics and extent of this issue across different open-source models, datasets of varying difficulty levels, and decoding strategies. Specifically, we explore how false positives influence the inference time scaling behavior of language models. Our experimental results reveal that: (1) false positive solutions persist across different models, datasets, and decoding methods, (2) sampling-based inference time scaling methods do not alleviate the problem, and (3) the pass@N evaluation metric is more susceptible to false positives, suggesting a significantly lower scaling ceiling than what automatic evaluations indicate. Additionally, we analyze specific instances of false positives and discuss potential limitations in self-improvement techniques and synthetic data generation under such conditions.

Chain-of-Retrieval Augmented Generation

This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer. Conventional RAG methods usually perform a single retrieval step before the generation process, which limits their effectiveness in addressing complex queries due to imperfect retrieval results. In contrast, our proposed method, CoRAG (Chain-of-Retrieval Augmented Generation), allows the model to dynamically reformulate the query based on the evolving state. To train CoRAG effectively, we utilize rejection sampling to automatically generate intermediate retrieval chains, thereby augmenting existing RAG datasets that only provide the correct final answer. At test time, we propose various decoding strategies to scale the model's test-time compute by controlling the length and number of sampled retrieval chains. Experimental results across multiple benchmarks validate the efficacy of CoRAG, particularly in multi-hop question answering tasks, where we observe more than 10 points improvement in EM score compared to strong baselines. On the KILT benchmark, CoRAG establishes a new state-of-the-art performance across a diverse range of knowledge-intensive tasks. Furthermore, we offer comprehensive analyses to understand the scaling behavior of CoRAG, laying the groundwork for future research aimed at developing factual and grounded foundation models.

SMamba: Sparse Mamba for Event-based Object Detection

Transformer-based methods have achieved remarkable performance in event-based object detection, owing to the global modeling ability. However, they neglect the influence of non-event and noisy regions and process them uniformly, leading to high computational overhead. To mitigate computation cost, some researchers propose window attention based sparsification strategies to discard unimportant regions, which sacrifices the global modeling ability and results in suboptimal performance. To achieve better trade-off between accuracy and efficiency, we propose Sparse Mamba (SMamba), which performs adaptive sparsification to reduce computational effort while maintaining global modeling capability. Specifically, a Spatio-Temporal Continuity Assessment module is proposed to measure the information content of tokens and discard uninformative ones by leveraging the spatiotemporal distribution differences between activity and noise events. Based on the assessment results, an Information-Prioritized Local Scan strategy is designed to shorten the scan distance between high-information tokens, facilitating interactions among them in the spatial dimension. Furthermore, to extend the global interaction from 2D space to 3D representations, a Global Channel Interaction module is proposed to aggregate channel information from a global spatial perspective. Results on three datasets (Gen1, 1Mpx, and eTram) demonstrate that our model outperforms other methods in both performance and efficiency.