22 accepted papers
When designing interventions to promote desired actions, two-stage agent heterogeneity -- encompassing both engagement with the intervention and completion of the desired action -- creates significant challenges in identifying optimal intervention policies. While this two-dimensional heterogeneity c…
Legal reasoning is a fundamental component of legal analysis and decision-making. Existing computational approaches to legal reasoning predominantly rely on generic reasoning frameworks such as syllogism, which do not comprehensively examine the nuanced process of legal reasoning. Moreover, current
Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely encountered in everyday indoor environments. Errors under such contriv
Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, long-tail situations such as subtle human behaviors, traffic accidents, and non-compliant driving patterns. Given the demon…
Inertial navigation enables self-contained localization using only Inertial Measurement Units (IMUs), making it widely applicable in various domains such as navigation, augmented reality, and robotics. However, existing methods suffer from drift accumulation due to the sensor noise and difficulty ca
In the evolving landscape of machine learning, a pivotal challenge lies in deciphering the internal representations harnessed by neural networks and Transformers. Building on recent progress toward comprehending how networks execute distinct target functions, our study embarks on an exploration of t…
We investigate the statistical and computational limits of prompt tuning for transformer-based foundation models. Our key contributions are that prompt tuning on *single-head* transformers with only a *single* self-attention layer: (i) is universal, and (ii) supports efficient (even almost-linear…
Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however, these methods often overlook the distinct characteristics of dif…
MetaDesigner introduces a transformative framework for artistic typography synthesis, powered by Large Language Models (LLMs) and grounded in a user-centric design paradigm. Its foundation is a multi-agent system comprising the Pipeline, Glyph, and Texture agents, which collectively orchestrate the…
Open-world specific emitter identification (SEI) is a practical but challenging task, because it requires accurate identification of both known and unknown emitters in open environments with channel variations. However, traditional closed-set SEI methods suffer from severe performance degradation in…
Node tokenized graph Transformers (GTs) have shown promising performance in node classification. The generation of token sequences is the key module in existing tokenized GTs which transforms the input graph into token sequences, facilitating the node representation learning via Transformer. In this…
Precise needle alignment is essential for percutaneous needle insertion in robotic ultrasound-guided procedures. However, inherent challenges such as speckle noise, needle-like artifacts, and low image resolution complicate robust needle detection, which is essential for alignment in ultrasound imag
The weighted low-rank approximation problem is a fundamental numerical linear algebra problem and has many applications in machine learning. Given a $n \times n$ weight matrix $W$ and a $n \times n$ matrix $A$, the goal is to find two low-rank matrices $U, V \in \mathbb{R}^{n \times k}$ such that th…
Due to the complementary properties between sensors, multi-sensor fusion can effectively promote accuracy and tackle the challenging scenes in simultaneous localization and mapping (SLAM) tasks. To this end, we propose a novel LiDAR-camera fused method for odometry and mapping using dense colored po
Iris images captured in real-world scenarios are often occluded, which leads to a significant degradation for the iris recognition system. Therefore, it is necessary to propose an effective iris inpainting method. While generative adversarial network (GAN)-based image inpainting methods have shown p…
Extrinsic calibration is an essential prerequisite for the applications of camera-LiDAR fusion. Existing methods either suffer from the complex offline setting of man-made targets or tend to produce suboptimal and unrobust results. In this paper, we propose an online two-stage calibration method tha…
In the realm of autonomous driving, real-time perception or streaming perception remains under-explored. This research introduces DAMO-StreamNet, a novel framework that merges the cutting-edge elements of the YOLO series with a detailed examination of spatial and temporal perception techniques. DAMO…
Streaming perception is a fundamental task in autonomous driving that requires a careful balance between the latency and accuracy of the autopilot system. However, current methods for streaming perception are limited as they rely only on the current and adjacent two frames to learn movement patterns…
Existing Visual Object Tracking (VOT) only takes the target area in the first frame as a template. This causes tracking to inevitably fail in fast-changing and crowded scenes, as it cannot account for changes in object appearance between frames. To this end, we revamped the tracking framework with P…
Autonomous ultrasound (US) imaging has gained increased interest recently, and it has been seen as a potential solution to overcome the limitations of free-hand US exami-nations, such as inter-operator variations. However, it is still challenging to accurately map planned paths from a generic atlas…
One main challenge in building task-oriented dialogue systems is the limited amount of supervised training data available. In this work, we present a method for training retrieval-based dialogue systems using a small amount of high-quality, annotated data and a larger, unlabeled dataset. We show tha…
In this paper, a parallel system together with an adaptive workload balancing algorithm is proposed for view synthesis on multi-core platforms. Based on system level data parallelism, an adaptive workload balancing method is proposed for depth image based rendering by evaluating the number of non-ho…