57 accepted papers
Representation learning is fundamental to modern machine learning, powering applications such as text retrieval and multimodal understanding. However, learning robust and generalizable representations remains challenging. While prior work has demonstrated that active noise injection, a form of data
Recent progress in large-scale generative models has substantially advanced video generation, yet existing methods remain constrained by a rigid inference paradigm. Bidirectional diffusion models excel at global coherence and visual fidelity but suffer from slow inference, while autoregressive model…
Recent advances have empowered large language models (LLMs) with remarkable fine-grained instruction-following capabilities in text generation tasks. However, embedding methods typically rely solely on the hidden state of the input's last token, limiting their ability to capture complete semantic si…
Scaling video generation from seconds to minutes faces a critical bottleneck: while short-video data is abundant and high-fidelity, coherent long-form data is scarce and limited to narrow domains. While multi-resolution image training works because higher resolution is largely an interpolation of th…
Differentiable simulators have advanced policy learning and model-based control across diverse robotic tasks. To date, actuator dynamics remain underexplored and are a major source of sim-to-real error, especially on low-cost platforms where the linear current–torque model τ = K_tI breaks down under…
Recent advances in machine learning and deep learning have significantly enhanced robot control by improving object detection and visual feature extraction. However, ensuring theoretical guarantees of stability and convergence in learning-enabled control systems remains a major challenge. In this pa
Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel
The accuracy of path following is crucial for collision-free navigation of hyper-redundant robots, especially in narrow environments. However, the existing path following methods only consider the deviations of joints and the end effector, while ignoring the deviations of the robot body. In this let
Existing video generation models struggle to follow complex text prompts and synthesize multiple objects, raising the need for additional grounding input for improved controllability. In this work, we propose to decompose videos into visual primitives -- blob video representation, a general represen…
Recent breakthroughs in single-image 3D portrait reconstruction have enabled telepresence systems to stream 3D portrait videos from a single camera in real-time, democratizing telepresence. However, per-frame 3D reconstruction exhibits temporal inconsistency and forgets the user's appearance. On the…
Rencent advancements in large language models (LLM) have shown impressive versatility across various tasks. Short text matching is one of the fundamental technologies in natural language processing. In previous studies, the common approach to applying them to Chinese is segmenting each sentence into
The implantation of ultra-flexible neural probes is one of the key technical challenges in the field of brain-computer interfaces. Existing implantation techniques are constrained in both the overall surgical procedure and operational reliability. This study introduces a novel microneedle-forceps me
Due to the advantages of dexterity and adaptability, cable-driven hyper-redundant robots (CDHRRs) are promising for detection in confined spaces like narrow internal cavities. However, due to redundant degrees of freedom (DoFs), CDHRRs are susceptible to the singular configuration, which aggravates
Differentiable simulation has become a powerful tool for system identification. While prior work has focused on identifying robot properties using robot-specific data or object properties using object-specific data, our approach calibrates object properties by using information from the robot, witho
Multiple object tracking (MOT) from unmanned aerial vehicle (UAV) platforms requires efficient motion modeling. This is because UAV-MOT faces both local object motion and global camera motion. Motion blur also increases the difficulty of detecting large moving objects. Previous UAV motion modeling a…
The rapid development of Unmanned Aerial Vehicle (UAV) technology has facilitated the widespread use of UAVs in daily life, this advancement brings huge regulatory demand for UAVs. Automatic identification of UAVs using radio frequency (RF) signals can effectively reduce regulatory costs. Previous s…
Extracting tubular structures from images is a widespread and challenging task in computer vision. To explore these continuous structures, iterative tracing methods offer a promising direction. However, in scenes with dense and blurred branches, existing tracing methods tend to jump to adjacent bran…
Learning generative models of 3D point clouds is one of the fundamental problems in 3D generative learning. One of the key properties of point clouds is their permutation invariance, i.e., changing the order of points in a point cloud does not change the shape they represent. In this paper, we analy…
In robotic teleoperation, it is crucial to be able to dynamically adjust interactions with the environment. Drawing inspiration from human behavior during interactions, Variable Impedance Control (VIC) has been widely adopted to enhance robotic flexibility and adaptability. However, maintaining the
In recent years, it has been found that "grandmother cells" in the primary visual cortex (V1) of macaques can directly recognize visual input with complex shapes. This inspires us to examine the value of these cells in promoting the research of medical image segmentation. In this paper, we design a…
Large language models(LLMs) have achieved remarkable performance on various tasks. However, LLMs suffer from severe limitations in domain generalisation, primarily due to inherent limitations. Closed-source LLMs face constraints in fine-tuning, while open-source LLMs contend with the scarcity of dom…
Spiking Neural Networks (SNNs) are attracting attention due to their energy efficiency and importance in neuromorphic computing. Therefore, we propose an SNN-based method for classifying drone RF signals in complex electromagnetic environments. Specifically, we designed a new SNNs model called Spiki…
Existing text-to-image models struggle to follow complex text prompts, raising the need for extra grounding inputs for better controllability. In this work, we propose to decompose a scene into visual primitives - denoted as dense blob representations - that contain fine-grained details of the scene…
We introduce DIFFTACTILE, a physics-based differentiable tactile simulation system designed to enhance robotic manipulation with dense and physically accurate tactile feedback. In contrast to prior tactile simulators which primarily focus on manipulating rigid bodies and often rely on simplified app…
Curvilinear structures, which include line-like continuous objects, are fundamental geometrical elements in image-based applications. Reconstructing these structures from images constitutes a pivotal research area in computer vision. However, the complex topology and ambiguous image evidence render…
Soft robotic manipulators with many degrees of freedom can carry out complex tasks safely around humans. However, manufacturing of soft robotic hands with several degrees of freedom requires a complex multi-step manual process, which significantly increases their cost. We present a design of a multi…
Modeling and analyzing object and shape has been well studied in the past. However, manipulation of these complex tools and articulated objects remains difficult for autonomous agents. Our human hands, however, are dexterous and adaptive. We can easily adapt a manipulation skill on one object to all…
Despite recent exponential advancements in computer vision and reinforcement learning, it remains challenging for robots to interact with liquids. These challenges are particularly pronounced due to the limitations imposed by opaque containers, transparent liquids, fine-grained splashes, and visual…
The recent successful detection of gravitational waves (GWs) at nanohertz based on pulsar timing arrays has underscored the growing significance of searching for new pulsars, which serve as valuable probes for GWs. However, one of the challenges in this endeavor is the lack of labeled data, which ca…
In this work, we aim to teach robots to manipulate various thin-shell materials. Prior works studying thin-shell object manipulation mostly rely on heuristic policies or learn policies from real-world video demonstrations, and only focus on limited material types and tasks (e.g., cloth unfolding).…
The problem of signal detection and classification of multiple UAVs can be solved using object detection techniques in computer vision. However, this requires collecting and labeling a large amount of reliable raw data. Since the UAV signal dataset cannot be directly applied to object detection, we…
In this work, we use recent developments in the field of adaptive robust Model Predictive Control (MPC) to build a controller for bilateral teleoperation systems. To guarantee robust constraint satisfaction, we incorporate polytopic tube controllers in the MPC design. In addition, we use online lear…
Recently, word enhancement has become very popular for Chinese Named Entity Recognition (NER), reducing segmentation errors and increasing the semantic and boundary information of Chinese words. However, these methods tend to ignore the semantic relationship before and after the sentence after integ…
We demonstrate how off-the-shelf single-image depth estimation methods can be augmented with guidance from optical flow to achieve consistent and accurate online depth estimation using video sequences of static scenes. While previous work has successfully leveraged the complementary nature of optica…
Task-oriented dialogue systems have become overwhelmingly popular in recent researches. Spoken Language Understanding (SLU) is widely used to extract the semantics frame of user queries and comprehend users’ intent/emotion/dialogue state in task-oriented dialogue systems. Most previous works on such…
The cooperation of a human pilot with an autonomous agent during flight control realizes parallel autonomy. We propose an air-guardian system that facilitates cooperation between a pilot with eye tracking and a parallel end-to-end neural control system. Our vision-based air-guardian system combines…
This paper introduces ActionSense, a multimodal dataset and recording framework with an emphasis on wearable sensing in a kitchen environment. It provides rich, synchronized data streams along with ground truth data to facilitate learning pipelines that could extract insights about how humans inter…
Aspect-based sentiment analysis (ABSA) has received increasing attention recently. ABSA can be divided into multiple tasks according to the different extracted elements. Existing generative methods usually treat the output as a whole string rather than the combination of different elements and only…
Acoustic target tracking has shown significant potential for contactless human-computer interaction. However, most existing acoustic 2-D tracking approaches for portable devices require at least one speaker and two microphones, incapable for universal devices. In this paper, we propose NearTracker,…
Astronomical interferometry enables a collection of telescopes to achieve angular resolutions comparable to that of a single, much larger telescope. This is achieved by combining simultaneous observations from pairs of telescopes such that the signal is mathematically equivalent to sampling the Four…
In order to obtain a high-precision contact model that can properly describe the target soft tissue, this paper proposes a hybrid soft contact model based on a clustering algorithm ART-II, which selects the most suitable soft contact model according to the surgical environment. The least-square meth…
Knowledge graph embedding methods are important for the knowledge graph completion (or link prediction) task.One state-of-the-art method, PairRE, leverages two separate vectors to model complex relations (i.e., 1-to-N, N-to-1, and N-to-N) in knowledge graphs. However, such a method strictly restrict…
While recent pre-training tasks on 2D images have proven very successful for transfer learning, pre-training for 3D data remains challenging. In this work, we introduce a general method for 3D self-supervised representation learning that 1) remains agnostic to the underlying neural network architect…
Low-light image enhancement is a complex and vital task including, recovering color and texture details from low-light images. For automated driving, low-light scenarios will have severe implications for vision-based applications. To address this problem, we propose a real-time unsupervised generati…
The Variable Topology Truss (VTT) is a new class of self-reconfigurable robot that can reconfigure its truss shape and topology depending on the task or environment requirements. Motion planning and avoiding self-collision are difficult as these systems usually have dozens of degrees-of-freedom with…
Self-reconfigurable modular robots are composed of many modules that can be rearranged into various structures with respect to different activities and tasks. The variable topology truss (VTT) is a class of modular truss robot. These robots are able to change their shape by not only controlling join…
Self-reconfigurable modular robots are usually composed of multiple modules with uniform docking interfaces that can be transformed into different configurations by themselves. The reconfiguration planning problem is finding what sequence of reconfiguration actions are required for one arrangement o
Microrobots capable of performing targeted delivery are promising for biomedical applications. Due to the restriction of their small size and volume, however, the real-time <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in vivo</i> imaging strategy
Depth sensing is crucial for 3D reconstruction and scene understanding. Active depth sensors provide dense metric measurements, but often suffer from limitations such as restricted operating ranges, low spatial resolution, sensor interference, and high power consumption. In this paper, we propose a…
This paper presents an algorithm to do motion planning for a new class of self-reconfigurable modular robot: the variable topology truss (VTT). Modular robots consist of many modules that can be configured into various structures, and motion planning problem for modular robots with many degrees of f…
This paper presents a novel manipulator for aerial vehicles to perform grasping and manipulation tasks. The goal is to design a low-cost, relatively light but strong manipulator with a large workspace and compact storage space that can be mounted on an unmanned aerial system. A novel design solution…
This paper is an initial step toward the realization of an aerial robot that can perform lateral physical work, such as drilling a hole or fastening a screw in a wall. Aerial robots are capable of high maneuverability and can provide access to locations that would be difficult or impossible for grou…
Thin structures such as fence, grass and vessels are common in photography and scientific imaging. They exhibit complex 3D structures with sharp depth variations/discontinuities and mutual occlusions. In this paper, we develop a method to estimate the occlusion matte and depths of thin structures fr…
The PaintPot manufacturing process is a new way to create low-cost, low-profile, highly customizable potentiometers for position sensing in robotic applications. It uses widely accessible materials, requires no special expertise, and creates custom potentiometers in a variety of shapes and sizes, in…
We present the EP-Face connector, a novel connector for hybrid chain-lattice type modular robots that is high-strength (88.4N), compact, fast, power efficient, and robust to position errors.
Microcirculatory monitoring plays an important role in diagnosis and treatment of critical care patients. Sidestream Dark Field (SDF) imaging devices have been used to visualize and support interpretation of the micro-vascular blood flow. However, due to subsurface scattering within the tissue that…
In this paper, we propose a scalable clustering paradigm to address the problems of excessive computational load and limited clustering performance in large-scale data. The proposed method employs the enhanced splitting merging awareness tactics (E-SMART) algorithm. The large-scale dataset is divide…