52 accepted papers
Vision-Language-Action (VLA) models have recently shown impressive generalization and language-guided manipulation capabilities. However, their performance degrades on tasks requiring precise spatial reasoning due to limited spatial reasoning inherited from Vision-Language Models (VLMs). Existing VL…
Evolutionary model merging provides a powerful framework for the automated, training-free composition of LLMs through parameter-space search. However, existing methods predominantly rely on stochastic, hand-crafted operators that overlook the underlying performance landscape of the coefficient space…
Autoregressive vision-language-action (VLA) models have recently demonstrated strong capabilities in robotic manipulation. However, their core process of action tokenization often involves a trade-off between reconstruction fidelity and inference efficiency. We introduce \textbf{FASTer}, a unified f…
In real-world time-series modelling, graph structures are widely adopted because they explicitly encode node topology and capture complex network dynamics. In practice, however, a complete graph is often partitioned across multiple parties; each party can access only its local sub-graph and, owing t
We present Galaxy Open-World Dataset, a large-scale, diverse collection of robot behaviors recorded in authentic human living and working environments. All demonstrations are gathered using a consistent robotic embodiment, paired with precise subtask-level language annotations to facilitate both tra…
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve conte
Existing air–ground collaborative systems often rely on passive or reactive coordination, which can cause discontinuous motion and underuse the UAV's ability for anticipatory support. To address these limitations, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://
Multimodal Web Search Agents demonstrate a practically valuable capability by fusing information from diverse modalities (e.g., text and vision), retrieved iteratively from the internet, to address complex user queries. However, the visual modality is prone to information overload, and the noise con
Reliable quadrotor control in dynamic environments remains challenging due to external disturbances and internal uncertainties. While Model Predictive Path Integral (MPPI) control enables agile maneuvers through samplingbased optimization, its performance often degrades under such unmodeled uncertai…
In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across noisy variants via noise or optimal transport, but suffer from…
Post-Training Quantization enables efficient Vision Transformer (ViTs) deployment with a small calibration data, and its prevalent use of uniform quantization harnesses AI accelerator matrix cores for high-speed inference. However, the application of uniform quantization is fundamentally challenged
Wheeled self-reconfigurable robots (WSRRs), a new type of multi-robot system with flexible configurations and task adaptability, have an extensive application prospects in unstructured mission environments. In this paper, based on the nonholonomic constraints and Lagrange method, the combinatorial m
Aiming to address the challenges associated with complex manufacturing processes and the difficulties in batch production of insect-scale robots. A mechatronic origami mechanism applied to an insect-scale parallel-legged structure is designed, manufactured, and tested. The origami mechanism is const
Achieving a real-time precise grasp of a specified target object in densely cluttered environments is an essential capability for autonomous robot operation. Recently, considerable investigations on planar and spatial grasp have been carried out, and significant results have been obtained. However,
Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrot
Piano-playing tasks, which effectively demonstrate bimanual coordination capabilities in humanoid robots, are increasingly becoming a research focus. However, prior research has predominantly focused on Cartesian space trajectory planning without adequately addressing real-world obstacle avoidance c
Training with diverse teammates is the key for learning generalizable agents. Typical approaches aim to generate diverse teammates by utilizing techniques like randomization, designing regularization terms, or reducing policy compatibility, etc. However, such teammates lack semantic information, res…
The increasing parameters and expansive dataset of large lan- guage models (LLMs) highlight the urgent demand for a technical solution to audit the underlying privacy risks and copyright issues associated with LLMs. Existing studies have partially addressed this need through an exploration of the pr…
Scaling the effective context length is essential for advancing large language models (LLMs) toward artificial general intelligence (AGI). However, the quadratic increase in computational complexity inherent in traditional attention mechanisms presents a prohibitive overhead. Existing approaches eit…
Learning from multi-agent expert demonstrations, known as Multi-Agent Imitation Learning (MAIL), provides a promising approach to sequential decision-making. However, existing MAIL methods including Behavior Cloning (BC) and Adversarial Imitation Learning (AIL) face significant challenges: BC suffer…
This paper proposes a precision autonomous landing system for unmanned aerial vehicles (UAVs) targeting high-speed moving platforms. By integrating gimbal-based precise positioning, smooth trajectory generation, and dynamically robust control, the system addresses key challenges in high-speed landin
Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and time-consuming. Current self-supervised and unsupervised approaches typically rely on blind-spot networks or sub-image pairs sampling, resulting in pixel i…
Comprehensive and consistent dynamic scene understanding from camera input is essential for advanced autonomous systems. Traditional camera-based perception tasks like 3D object tracking and semantic occupancy prediction lack either spatial comprehensiveness or temporal consistency. In this work, we
"Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation. This paper introduces CVT-Occ, a novel approach that leverages temporal fusion through the geometric correspondence of voxels over time to improve the accuracy of 3D…
While LLMs demonstrate impressive capabilities in musical knowledge, we find that music reasoning is still an unsolved task.We introduce ChatMusician, an open-source large language model (LLM) that integrates intrinsic musical abilities. It is based on continual pre-training and finetuning LLaMA2 on…
Knowledge distillation (KD) has been applied to various tasks successfully and mainstream methods typically boost the student model via spatial imitation losses. However the consecutive downsamplings induced in the spatial domain of teacher model is a type of corruption hindering the student from an…
The recent success of audio language models (LMs) has revolutionized the field of neural music generation. Among all audio LM approaches, MusicGen has demonstrated the success of a single-stage LMs based music generation framework, without needing to train multiple LMs. Despite its promising perform…
Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker’s voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language model-based TTS models show zero-shot speaker adaptation cap…
Membership Inference Attacks (MIA) aim to infer whether a target data record has been utilized for model training or not. Existing MIAs designed for large language models (LLMs) can be bifurcated into two types: reference-free and reference-based attacks. Although reference-based attacks appear prom…
The shift in dynamics results in significant performance degradation of policies trained in the source domain when deployed in a different target domain, posing a challenge for the practical application of reinforcement learning (RL) in real-world scenarios. Domain transfer methods aim to bridge thi…
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision. While two-stage top-down methods slow down as the number of people in the image increases existing one-stage methods often fail to simultaneously deliver high accuracy and real-time performance.…
Deep learning-based methods have made significant achievements in music source separation. However, obtaining good results while maintaining a low model complexity remains challenging in super wide-band music source separation. Previous works either overlook the differences in subbands or inadequate…
Monocular scene understanding is a foundational component of autonomous systems. Within the spectrum of monocular perception topics, one crucial and useful task for holistic 3D scene understanding is semantic scene completion (SSC), which jointly completes semantic information and geometric details
Mobile self-reconfigurable robots (MSRRs), as a novel multi-robot system with flexible configurations and task adaptability, hold promising applications in unstructured task environments. However, existing autonomous docking strategies are primarily applied in laboratory settings and face numerous c…
Aggressive maneuvering is crucial for aerial vehicles to execute adversarial and penetration missions. However, this challenges the accurate tracking control of drones due to uncertainties induced by high-speed flight. Therefore, firstly, a highly dynamic tracking control framework is proposed to ac…
This paper studies a beam tracking problem in a reconfigurable intelligent surface (RIS)-assisted communication system, in which a single antenna access point (AP) tracks a single-antenna mobile user equipment (UE) through actively reconfiguring the RIS. To maintain beam alignment over time, the mob…
Robotic perception requires the modeling of both 3D geometry and semantics. Existing methods typically focus on estimating 3D bounding boxes, neglecting finer geometric details and struggling to handle general, out-of-vocabulary objects. 3D occupancy prediction, which estimates the detailed occupanc…
Transformer has achieved extraordinary performance in Natural Language Processing and Computer Vision tasks thanks to its powerful self-attention mechanism, and its variant Conformer has become a state-of-the-art architecture in the field of Automatic Speech Recognition (ASR). However, the main-stre…
Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy by independently training local models on each client and then aggregating parameters on a central server, thereby producing an effective global model. Although a variety of FL algorithms hav…
Accurate and real-time LiDAR semantic segmentation is necessary for advanced autonomous driving systems. To guarantee a fast inference speed, previous methods utilize the highly optimized 2D convolutions to extract features on the range view (RV), which is the most compact representation of the LiDA…
Reconfigurable intelligent surface (RIS) is capable of intelligently manipulating the phases of the incident electromagnetic wave to improve the wireless propagation environment between the base station (BS) and the users. This paper addresses the joint user scheduling, RIS configuration, and BS bea…
The versatile nature of agile micro aerial vehicles (MAVs) poses fundamental challenges to the design of robust state estimation in various complex environments. Achieving high-quality performance in textureless scenes is one of the missing pieces in the puzzle. Previously proposed solutions either…
Hyperspectral anomaly detection (HAD) is a challenging task because it explores the intrinsic structure of complex high-dimensional signals without any samples at training time. Deep neural networks (DNNs) can dig out the underlying distribution of hyperspectral data but are limited by the labeling…
LiteSing proposed in this paper is a high-quality singing voice synthesis (SVS) system, which is fast, lightweight and expressive. This model mainly stacks several non-autoregressive WaveNet blocks in the encoder and decoder under a generative adversarial architecture, predicts full conditions from…
Vision-based 3D object detection is a research focus in the field of autonomous driving system. While recently proposed pseudo-LiDAR is a promising solution, its performance is severely restricted by the image-based depth estimator, leading to a considerable performance gap against the LiDAR-based c…
Current state-of-the-art semantic segmentation methods usually require high computational resources for accurate segmentation. One promising way to achieve a good trade-off between segmentation accuracy and efficiency is knowledge distillation. In this paper, different from previous methods performi…
Approaches toward ordinal speech emotion recognition (SER) tasks are commonly based on the categorical classification algorithms, where the rank-order emotions are arbitrarily treated as independent categories. To employ the ordinal information between emotional ranks, we propose to model the ordina…
A major challenge in the pharmaceutical industry is to design novel molecules with specific desired properties, especially when the property evaluation is costly. Here, we propose MNCE-RL, a graph convolutional policy network for molecular optimization with molecular neighborhood-controlled embeddin…
Automatic singing evaluation without reference melody has long been a difficult problem. This paper aims to pilot a novel data driven approach to tackle this artistic problem. We constructed a large scale dataset and designed an innovative Bi-Dense neural network which can address this task efficien…
The huge number of parameters of deep neural network makes it difficult to deploy on embedded devices with limited hardware, computation, storage and energy resources. In this paper, we shall propose a log-sum minimization approach to prune a trained network layer by layer thereby improving the netw…
Dataset reshuffling across mobile devices allows for speeding up on-device distributed machine learning, which however requires significant communication bandwidth. In this paper, we propose a pliable data shuffling approach to significantly reduce the communication cost for on-device distributed le…
Under noisy environments, to achieve the robust performance of speaker recognition is still a challenging task. Motivated by the promising performance of multi-task training in a variety of image processing tasks, we explore the potential of multitask adversarial training for learning a noise-robust…