31 accepted papers
Modern autonomous driving systems increasingly rely on mixed camera configurations with pinhole and fisheye cameras for full view perception. However, Bird's-Eye View(BEV) 3D object detection models are predominantly designed for pinhole cameras, leading to performance degradation under fisheye dist…
We propose Contextual History for Adaptive and Simple Exploitation (CHASE), a novel multi-turn method for Large Language Model (LLM) jailbreaking. Rather than directly attack an LLM that may be difficult to jailbreak, CHASE first collects jailbroken histories from an easy-to-jailbreak LLM and then t
*Disentangled representations* seek to recover latent factors of variation underlying observed data, yet their *identifiability* is still not fully understood. We introduce a unified framework in which disentanglement is achieved through *mechanistic independence*, which characterizes latent factors…
Underwater images often exhibit dominant blue-green hues due to wavelength-dependent light attenuation. While existing enhancement methods have achieved promising performance, they typically overlook the subjective nature of visual preferences. To address this gap, we propose SDUIE, a level-aware Se
Automatic Prompt Optimization (APO) enables Large Language Models (LLMs) to adapt to specific tasks while minimizing manual engineering costs. However, since existing APO approaches either rely solely on multi-round iterative procedures or use model-specific generators tailored to optimizing prompts…
Recently, CutMix-based augmentation has emerged as a promising strategy for providing regularization to deep neural networks. However, the randomness in cropping may result in uninformative or non-representative regions being selected, resulting in a synthesized image without the desired features. T…
The technique of data augmentation (DA) is often used in machine learning for regularization purposes to better generalize under i.i.d. settings. In this work, we present a unifying framework with topics in causal inference to make a case for the use of DA beyond just the i.i.d. setting, but for gen…
Smart sensors and Vehicle-To-Everything (V2X) modules are commonly utilized in automotive perception systems, which primarily provide processed object lists rather than raw data. However, high-level fusion approaches suffer from significant information loss and representational misalignment due to t
Embodied multi-agent systems (EMAS) have attracted growing attention for their potential to address complex, real-world challenges in areas such as logistics and robotics. Recent advances in foundation models pave the way for generative agents capable of richer communication and adaptive problem-sol
This paper introduces a wheel-claw quadruped robot named Lywal-X, which is capable of omnidirectional movement as well as grasping actions. Firstly, the mechanical structure of Lywal-X is designed with a three-degree-of-freedom leg transformation mechanism and a two-degree-of-freedom wheel-claw stru
The difficulty of appropriately assigning credit is particularly heightened in cooperative MARL with sparse reward, due to the concurrent time and structural scales involved. Automatic subgoal generation (ASG) has recently emerged as a viable MARL approach inspired by utilizing subgoals in intrinsic…
Autonomous tracking represents a significant advancement in the evolution of unmanned aerial vehicles (UAVs), offering applications in areas such as aerial photography and infrastructure inspection. Despite its potential, many autonomous tracking systems encounter challenges in maintaining consisten
Collaborative exploration is a prevailing trend of autonomous exploration by unmanned aerial vehicles (UAVs). However, most collaborative exploration systems rely on excessively high communication bandwidth for precise map maintenance and efficient task allocation. This letter proposes a low-bandwid
We present a Multi-Stereoscopic Visual-Inertial Odometry (VIO) system capable of integrating an arbitrary number of stereo cameras, exhibiting excellent robustness in the face of visually challenging scenarios. During system initialization, we introduce multi-view keyframes for simultaneous processi
In image denoising networks, feature scaling is widely used to enlarge the receptive field size and reduce computational costs. This practice, however, also leads to the loss of high-frequency information and fails to consider within-scale characteristics. Recently, dynamic convolution has exhibited…
As a popular drone application, autonomous exploration suffers from low efficiency. To address the issue of repeated and unnecessary exploration, especially in a large-scale and cluttered environment, this letter proposes an efficient heuristic viewpoint determination method on frontier-based autono
Contrastive learning has recently emerged as a promising approach for learning data representations that discover and disentangle the explanatory factors of the data. Previous analyses of such approaches have largely focused on individual contrastive losses, such as noise-contrastive estimation (NCE…
In this work, we tackle the problem of learning universal robotic dexterous grasping from a point cloud observation under a table-top setting. The goal is to grasp and lift up objects in high-quality and diverse ways and generalize across hundreds of categories and even the unseen. Inspired by succe…
3D visual grounding aims to locate the referred target object in 3D point cloud scenes according to a free-form language description. Previous methods mostly follow a two-stage paradigm, i.e., language-irrelevant detection and cross-modal matching, which is limited by the isolated architecture. In s…
We present HOI4D, a large-scale 4D egocentric dataset with rich annotations, to catalyze the research of category-level human-object interaction. HOI4D consists of 2.4M RGB-D egocentric video frames over 4000 sequences collected by 9 participants interacting with 800 different object instances from…
Generalizable object manipulation skills are critical for intelligent and multi-functional robots to work in real-world complex scenes. Despite the recent progress in reinforcement learning, it is still very challenging to learn a generalizable manipulation policy that can handle a category of geome
Distance-based dynamic texture recognition is an important research field in multimedia processing with applications ranging from retrieval to segmentation of video data. Based on the conjecture that the most distinctive characteristic of a dynamic texture is the appearance of its individual frames,…
Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Recent methods typically develop sophisticated pipelines to tackle this task. Here, we propose a new video instance segmentation framework built upon…
Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure is often time-consuming, limiting the rollout in some poten…
Camera localization is a fundamental and key component of autonomous driving vehicles and mobile robots to localize themselves globally for further environment perception, path planning and motion control. Recently end-to-end approaches based on convolutional neural network have been much studied to…
Learning depth and ego-motion from unlabeled videos via self-supervision from epipolar projection can improve the robustness and accuracy of the 3D perception and localization of vision-based robots. However, the rigid projection computed by ego-motion cannot represent all scene points, such as poin
In this paper, we propose a single-shot instance segmentation method, which is simple, fast and accurate. There are two main challenges for one-stage instance segmentation: object instances differentiation and pixel-wise feature alignment. Accordingly, we decompose the instance segmentation into two…
This work studies the problem of modeling visual processes by leveraging deep generative architectures for learning linear, Gaussian representations from observed sequences. We propose a joint learning framework, combining a vector autoregressive model and a Variational Autoencoder. This results in…
Training deep neural networks for solving machine learning problems is one great challenge in the field, mainly due to its associated optimisation problem being highly non-convex. Recent developments have suggested that many training algorithms do not suffer from undesired local minima under certain…
This paper presents an algorithm that allows to learn low dimensional representations of images in an unsupervised manner. The core idea is to combine two criteria that play important roles in unsupervised representation learning, namely sparsity and trace quotient. The former is known to be a conve…