26 accepted papers
Learning truthful task-relevant latent representations $\mathbf{s}$ from observations $\mathbf{o} = f(\mathbf{s})$ is fundamental. Identifiability, the asymptotic guarantee of recovering the ground-truth representation, is critical because it sets the ultimate limit of any model, even with infinite …
Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and a mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SN…
Offline handwritten text recognition (HTR) is blank-dominated: task-relevant evidence lies in sparse ink strokes, yet mainstream recognizers still expend dense spatial compute and full-length width-axis token mixing across the canvas. Spiking neural networks (SNNs) promise activity-proportional comp…
Text-guided stylized image generation has yielded promising advances by leveraging the powerful capabilities of text-to-image diffusion models. However, the inherent coupling of style and content information within the reference image presents a significant challenge. To address this, we propose Sty…
Recently, the Mixture of Expert (MoE) architecture, such as LR-MoE, is often used to alleviate the impact of language confusion on the multilingual ASR (MASR) task. However, it still faces language confusion issues, especially in mismatched domain scenarios. In this paper, we decouple language confu…
In recent years, while the performance of speech-image retrieval has improved significantly, it still lags behind that of image-text retrieval. Leveraging the text modality to enhance speech-image retrieval remains a promising research direction. In this paper, we propose to leverage text supervisio…
Microassembly plays an important role in fabricating complex structures with small basic components in industrial and biomedical fields. Inverted optical microscope could provide high-quality image feedback for microassembly with its continuously improving resolution. However, a compact stage capabl
Micro-nano robots must break the symmetry of the flow field to generate net displacement in the low Reynolds number environment. The spherical micro-robots utilize the frictional forces generated through interaction with the surface. We designed a magnetic microroller robot powered by the rotating A
Identifying time-delayed latent causal process is crucial for understanding temporal dynamics and enabling downstream reasoning. While recent methods have made progress in identifying latent time-delayed causal processes, they cannot address the dynamics in which the influence of some latent factors…
A magnetically controlled catheter system is proposed to enhance the precision and safety of vascular interventions by reducing procedure time and radiation exposure. The system can also function as a support channel for guidewire deployment. A novel navigation approach is introduced, employing an e
Traditional single-cell mechanical characterization techniques (e.g., atomic force microscopy) often face limitations in throughput, require invasive labeling, or fail to replicate physiological microenvironments, impeding their clinical utility for rapid cancer cell analysis. To address these limit
Text to Motion aims to generate human motions from texts. Existing settings rely on limited Action Texts that include action labels (e.g., "walk, bend"), which limits flexibility and practicability in scenarios difficult to describe directly. This paper extends limited Action Texts to arbitrary ones…
Optimizing video inference efficiency has become increasingly important with the growing demand for video analysis in various fields. Some existing methods achieve high efficiency by explicit discard of spatial or temporal information, which poses challenges in fast-changing and fine-grained scenari…
To develop the next generation of intelligent LiDARs, we propose a novel framework of parallel LiDARs and construct a hardware prototype in our experimental platform, DAWN (Digital Artificial World for Natural). It emphasizes the tight integration of physical and digital space in LiDAR systems, with…
Action recognition in videos poses a challenge due to its high computational cost, especially for Joint Space-Time video transformers (Joint VT). Despite their effectiveness, the excessive number of tokens in such architectures significantly limits their efficiency. In this paper, we propose Halting…
Current approaches to Video Question Answering (VideoQA) primarily focus on cross-modality matching, which is limited by the requirement for extensive data annotations and the insufficient capacity for causal reasoning (e.g. attributing accidents). To address these challenges, we introduce a causal…
Few-shot action recognition aims at quickly adapting a pre-trained model to the novel data with a distribution shift using only a limited number of samples. Key challenges include how to identify and leverage the transferable knowledge learned by the pre-trained model. We therefore propose CDTD, or…
Large vision-language models (VLMs) like CLIP have demonstrated good zero-shot learning performance in the unsupervised domain adaptation task. Yet most transfer approaches for VLMs focus on either the language or visual branches overlooking the nuanced interplay between both modalities. In this wor…
"Current methodologies have achieved notable success in the closed-set visual information extraction (VIE) task, while the exploration into open-vocabulary settings is comparatively underdeveloped, which is practical for individual users in terms of inferring information across documents of diverse…
The CTC-based automatic speech recognition (ASR) models without the external language model usually lack the capacity to model conditional dependencies and textual interactions. In this paper, we present a Gated Interlayer Collaboration (GIC) mechanism to improve the performance of CTC-based models,…
Domain generalization person re-identification (DG ReID) aims to train a model on source domains and generalize well on unseen domains. Vision Transformer usually yields better generalization ability than common CNN networks under distribution shifts. However, Transformer-based ReID models inevitabl…
In the last decade, researchers have been trying to develop many microrobots that mimic the extraordinary abilities of bionts in complex environments. How to fabricate the biomimetic microrobot with satisfying deformability and complex shapes to realize desired precise motion is the key issue. In th…
The magnetic microrobot has become a promising approach in many biomedical applications due to its small volume, flexible motion, and untethered micromachines. The micro-chain robot is one of the most popular magnetic microrobots. However, the uncontrollable magnetic moment direction and quantity of…
This paper describes an energy-based learning method that predicts the activities of multiple agents simultaneously. It aims to forecast both upcoming actions and paths of all agents in a scene based on their past activities, which can be jointly formulated by a probabilistic model over time. Learni…
Zebrafish embryo injection is often required in biomedical research using zebrafish. In the injecting operation, trapping and rotating the zebrafish embryo to achieve a proper posture is essential for the high success rate. We proposed an on-chip platform capable of efficient and automatic trapping
Path forecasting is a pivotal step toward understanding dynamic scenes and an emerging topic in the computer vi- sion field. This task is challenging due to the multimodal nature of the future, namely, given a partial history, there is more than one plausible prediction. Yet, the state-of-the-art me…