47 accepted papers
Vision-Language Continual Learning (VLCL) has attracted significant research attention for its robust capabilities, and the adoption of Parameter-Efficient Fine-Tuning (PEFT) strategies is enabling these models to achieve competitive performance with substantially reduced resource consumption. Howev
Though deep neural models adopted to realize the perception of autonomous driving have proven vulnerable to adversarial examples, known attacks often leverage 2D patches and target mostly monocular perception. Therefore, the effectiveness of Physical Adversarial Examples (PAEs) on stereo-based binoc
The emergence of sudden obstacles can significantly reduce the feasible space and may induce locally non-convex or fragmented space, especially in densely clustered scenarios, making vehicle trajectory planning remarkably challenging. Current methods face computational bottlenecks when generating em
Generative data augmentation has created new opportunities for improving image recognition models. Despite these advances, most existing augmentation methods process images holistically, without accounting for the uneven distribution of discriminative information in classification tasks, where foreg
Reinforcement learning-based Multimodal Large Language Models (MLLMs) provide new perspectives for visual grounding, yet face significant challenges in Camouflaged Object Detection (COD) where objects blend seamlessly with backgrounds. This stems primarily from: difficulties in multi-object matching…
Diffusion Large Language Models (dLLMs) have recently emerged as a competitive non-autoregressive paradigm due to their unique training and inference approach. However, there is currently a lack of safety study on this novel architecture. In this paper, we present the first analysis of dLLMs
In product advertising applications, the automated inpainting of backgrounds utilizing AI techniques in product images has emerged as a significant task. However, the techniques still suffer from issues such as inappropriate background and inconsistent product in generated product images, and existi…
Despite substantial efforts in safety alignment, recent research indicates that Large Language Models (LLMs) remain highly susceptible to jailbreak attacks. Among these attacks, finetuning-based ones that compromise LLMs’ safety alignment via fine-tuning stand out due to its stable jailbreak perform…
This study investigates the problem of large-scale swarm robots shape self-assembly problem under conditions of information asymmetry. Existing methods assume complete sharing of global information; however, this assumption has significant limitations in terms of resource consumption and swarm emerg
This paper presents a pioneering exploration of reinforcement learning (RL) via group relative policy optimization for unified multimodal large language models (ULMs), aimed at simultaneously reinforcing generation and understanding capabilities. Through systematic pilot studies, we uncover the sign…
Recent advancements in multimodal large language models (MLLMs) have demonstrated exceptional performance in multimodal perception and understanding. However, leading open-source MLLMs exhibit significant limitations in complex and structured reasoning, particularly in tasks requiring deep reasoning…
The wide adoption of Large Language Models (LLMs) has attracted significant attention from jailbreak attacks, where adversarial prompts crafted through optimization or manual design exploit LLMs to generate malicious contents. However, optimization-based attacks have limited efficiency and transfera
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues. Individuals are particularly sensitive to facial features, and facial image leakage can lead to many malicious activities, suc…
The problem of forecasting spatiotemporal events such as crimes and accidents is crucial to public safety and city management. Besides accuracy, interpretability is also a key requirement for spatiotemporal forecasting models to justify the decisions. Merely presenting predicted scores fails to conv…
Multi-agent reinforcement learning (MARL) has emerged as a powerful framework for modeling autonomous agents that independently optimize their individual objectives. However, in mixed-motive MARL environments, rational self-interested behaviors often lead to collectively suboptimal outcomes situatio…
High-resolution semantic segmentation is essential for applications such as image editing, bokeh imaging, AR/VR, etc. Unfortunately, existing datasets often have limited resolution and lack precise mask details and boundaries. In this work, we build a large-scale, matting-level semantic segmentation…
Federated prompt learning benefits federated learning with CLIP-like Vision-Language Model's (VLM's) robust representation learning ability through prompt learning. However, current federated prompt learning methods are habitually restricted to the traditional FL paradigm, where the participating cl…
Momentum-based optimizers are widely adopted for training neural networks. However, the optimal selection of momentum coefficients remains elusive. This uncertainty impedes a clear understanding of the role of momentum in stochastic gradient methods. In this paper, we present a frequency domain anal…
Online path planning for magnetic microrobots actuated by electromagnetic system in dynamic flow field presents significant challenges due to time-varying fluid dynamics, energy constraints, and collision risks. Traditional path planning approaches, which often rely on static flow assumptions or sim
Large Language Models (LLMs) are increasingly deployed as autonomous agents in multi-agent systems, and promising coordination has been demonstrated in handling complex tasks under predefined roles and scripted workflows. However, significant challenges remain in open-ended environments, where agent…
Deep learning-based semantic segmentation models achieve impressive results yet remain limited in handling distribution shifts between training and test data. In this paper, we present SDGPA (Synthetic Data Generation and Progressive Adaptation), a novel method that tackles zero-shot domain adaptive
In complex unstructured environments, accurate terrain traversability analysis is a fundamental requirement for the successful execution of any movements of ground robots, especially given that terrain traversability often exhibits anisotropy. However, the difficulty in obtaining multi-directional t…
The human hand is capable of executing a wide range of complex movements due to its biomechanical structure and skin sensing system. Designing an anthropomorphic hand that mimics the biomechanical structure of the human and incorporates skin sensing, presents a long-term challenge in the field of ro
The quality of a robot’s environmental perception determines whether it can achieve more intelligent applications, such as semantic interaction with humans. SLAM, on the other hand, is one of the crucial capabilities for a robot to perceive its environment. However, when only a monocular image is pr…
TTransformer models have demonstrated remarkable performance in neural machine translation (NMT). However, their vulnerability to noisy input poses a significant challenge in practical implementation, where generating clean output from noisy input is crucial. The MTNT dataset is widely used as a ben…
In classic reinforcement learning algorithms, agents make decisions at discrete and fixed time intervals. The duration between decisions becomes a crucial hyperparameter, as setting it too short may increase the problem's difficulty by requiring the agent to make numerous decisions to achieve its go…
Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments. Partial model personalization has been proposed to improve the efficiency of PFL by selectively updating local model parameters instead of aggregating all of them. How…
Hand Pose Estimation (HPE) is crucial to many applications, but conventional cameras-based CM-HPE methods are completely subject to Line-of-Sight (LoS), as cameras cannot capture occluded objects. In this paper, we propose to exploit Radio-Frequency-Vision (RF-vision) capable of bypassing obstacles…
Personalized federated learning has received an upsurge of attention due to the mediocre performance of conventional federated learning (FL) over heterogeneous data. Unlike conventional FL which trains a single global consensus model, personalized FL allows different models for different clients. Ho…
Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-$k$ operation's results on samples. In this paper, we show that such a centralized approa…
Conventional federated learning (FL) trains one global model for a federation of clients with decentralized data, reducing the privacy risk of centralized training. However, the distribution shift across non-IID datasets, often poses a challenge to this one-model-fits-all solution. Personalized FL a…
In many real-world cooperative multiagent reinforcement learning (MARL) tasks, teams of agents can rehearse together before deployment, but then communication constraints may force individual agents to execute independently when deployed. Centralized training and decentralized execution (CTDE) is in…
We consider real-world reinforcement learning (RL) of robotic manipulation tasks that involve both visuomotor skills and contact-rich skills. We aim to train a policy that maps multimodal sensory observations (vision and force) to a manipulator's joint velocities under practical considerations. We p…
Prioritized Experience Replay (ER) has been empirically shown to improve sample efficiency across many domains and attracted great attention; however, there is little theoretical understanding of why such prioritized sampling helps and its limitations. In this work, we take a deep look at the priori…
Pedestrian behavior prediction is one of the major challenges for intelligent driving systems. Pedestrians often exhibit complex behaviors influenced by various contextual elements. To address this problem, we propose BiPed, a multitask learning framework that simultaneously predicts trajectories an…
In order to improve climbing performance of the robot in complex environments, the wheel-legged mechanism is gradually being widely used. In this letter, we simplify the previous eccentric paddle mechanism (ePaddle), and propose a 2-DOF ePaddle-based robot which integrates stability and maneuverabil
One of the most crucial yet challenging tasks for autonomous vehicles in urban environments is predicting the future behaviour of nearby pedestrians, especially at points of crossing. Predicting behaviour depends on many social and environmental factors, particularly interactions between road users.…
We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our pr…
Intention prediction is a crucial task for Autonomous Driving (AD). Due to the variety of size and layout of intersections, it is challenging to predict intention of human driver at different intersections, especially unseen and irregular intersections. In this paper, we formulate the prediction of…
In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort. Due to complex interactions among traffic participants, however, it is very hard to achieve accurate prediction for a long horizon. To address this challenge, we propose predictio…
In this paper we propose a system consisting of a modular network and a trajectory planner. The network simultaneously predicts Occupancy Grid Maps (OGMs) and estimates space-time cost maps (CMs) corresponding to the areas around the vehicle. The trajectory planner computes the cost of a set of pred…
Deterministic down-sampling of an unordered point cloud in a deep neural network has not been rigorously studied so far. Existing methods down-sample the points regardless of their importance for the network output and often address down-sampling the raw point cloud before processing. As a result, s…
Whereas adversarial training is employed as the main defence strategy against specific adversarial samples, it has limited generalization capability and incurs excessive time complexity. In this paper, we propose an attack-agnostic defence framework to enhance the intrinsic robustness of neural netw…
Interaction is fundamental in autonomous driving (AD). Despite more than a decade of intensive R&D in AD, how to dynamically interact with diverse road users in various contexts still remains unsolved. Multi-agent learning has recently seen big breakthroughs and has much to offer towards solving rea
Mammalian sperms reorient against fluid flow in the female reproductive tract, known as rheotaxis. Compared to chemotaxis that provides short-distance guidance, rheotaxis provides long-distance guidance for a sperm to find the egg cell. However, only a low number of sperms are capable of rheotaxis a
This paper contributes to the understanding of the fundamental properties of rectilinearly locomotion of an one-dimensional system travelling on the horizontal plane, where dry Coulomb friction acting between it and surface. We discuss an approximate steady-state motion on a simplified two-segment s…
Central catadioptric omnidirectional images exhibit serious nonlinear distortions due to quadratic mirrors involved. Conventional visual features developed based on the perspective model are hard to achieve a satisfactory performance when directly applied to the distorted omnidirectional image. This…