70 accepted papers
Retrieving real-time information is a fundamental capability for search-integrated agents in real-world applications. However, existing benchmarks are predominantly static and therefore fail to capture the temporal dynamics of information and the continuously evolving nature of real-world knowledge.
Exoskeletons, as wearable human–robot collaborative devices, can effectively reduce muscle fatigue caused by prolonged material handling and overhead tasks. However, most existing active exoskeletons adopt tightly coupled serial structures, which generally suffer from insufficient wearing comfort, l…
Modern autonomous navigation systems predominantly rely on lidar and depth cameras. However, a fundamental question remains: Can flying robots navigate in clutter using solely monocular RGB images? Given the prohibitive costs of real-world data collection, learning policies in simulation offers a pr
Scene-level point cloud understanding remains challenging due to diverse geometries, imbalanced category distributions, and highly varied spatial layouts. Existing methods improve object-level performance but rely on static network parameters during inference, limiting their adaptability to dynamic
Federated recommendations (FRs), facilitating multiple local clients to collectively learn a global model without disclosing user private data, have emerged as a prevalent on-device service. In conventional FRs, a dominant paradigm is to utilize discrete identities to represent clients and items, wh
Sound separation (SS) and target sound extraction (TSE) are fundamental techniques for addressing complex acoustic scenarios. While existing SS methods struggle with determining the unknown number of sound sources, TSE approaches require precisely specified clues to achieve optimal performance. This
We present UniFuture, a unified 4D Driving World Model designed to simulate the dynamic evolution of the 3D physical world. Unlike existing driving world models that focus solely on 2D pixel-level video generation (lacking geometry) or static perception (lacking temporal dynamics), our approach brid…
With the great advancement of video generation models, a growing number of content creators and researchers are leveraging these technologies to produce large volumes of human-centric videos for content creation and customized data generation for specific tasks. Although existing video generation mo
Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA, a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsi
This study introduces a multimodal large language model capable of not only accomplishing various heart sound tasks but also providing reasoning, marking an advancement in the field of medical diagnostics. The model’s innovation stems from a collaboration with experts to collect a novel dataset desi…
Cascade ranking architecture, composed of matching, pre-ranking, ranking and re-ranking stages, is usually adopted to balance the efficiency and effectiveness in real-world recommendation system (RS). As the middle stage of RS, pre-ranking aims to quickly filter out the low-quality items selected at…
We introduce ESGenius , a comprehensive benchmark for evaluating and enhancing the proficiency of Large Language Models (LLMs) in Environmental, Social, and Governance (ESG) and sustainability-focused question answering. ESGenius comprises two key components: (i) ESGenius-QA , a collection of 1,136
While large language models (LLMs) have shown remarkable capabilities in natural language processing, they struggle with complex, multi-step reasoning tasks involving knowledge graphs (KGs). Existing approaches that integrate LLMs and KGs either underutilize the reasoning abilities of LLMs or suffer…
Active Speaker Detection (ASD) aims to determine whether each candidate in a video frame is speaking. The egocentric dataset Ego4D introduces unique challenges for this task, such as dynamic shooting angles that cause candidates to frequently leave the sight, leading to temporal discontinuities. Add…
Coordinate initialization is the first step in accomplishing collaborative tasks within robot swarms, determining the quality of tasks. However, fast and robust coordinate initialization in vision-based drone swarms remains elusive. To this end, our letter proposes a complete system for initial rela
Addressing the challenge of limited labels in Specific Emitter Identification (SEI), various Semi-Supervised Learning (SSL) approaches have been explored. However, these methods often neglect pervasive unknown signals in the real electromagnetic environment, thus restricting the model’s practical ad…
Training Large Language Models (LLMs) with synthetic data is a prevalent practice in code generation. A key approach is self-training, where LLMs are iteratively trained on self-generated correct code snippets. In this case, the self-generated codes are drawn from a conditional distribution, conditi…
Driving World Models (DWMs) have become essential for autonomous driving by enabling future scene prediction. However, existing DWMs are limited to scene generation and fail to incorporate scene understanding, which involves interpreting and reasoning about the driving environment. In this paper, we…
Keyframe insertion is critical for the performance and robustness of SLAM systems. However, traditional heuristic-based methods often lead to suboptimal keyframe selection, compromising the accuracy of localization and mapping. To address this, we propose KINND, a lightweight neural network-based fr
Generative depth estimation methods leverage the rich visual priors stored in pretrained text-to-image diffusion models, demonstrating astonishing zero-shot capability. However, parameter updates during training lead to catastrophic degradation in the image generation capability of the pretrained mo…
Recent studies have demonstrated the effectiveness of LLM test-time scaling. However, existing approaches to incentivize LLMs’ deep thinking abilities generally require large-scale data or significant training efforts. Meanwhile, it remains unclear how to improve the thinking abilities of less power…
Generalizable algorithms for tactile sensing remain underexplored, primarily due to the diversity of sensor modalities. Recently, many methods for cross-sensor transfer between optical (vision-based) tactile sensors have been investigated, yet little work focus on non-optical tactile sensors. To add
Dexterous in-hand manipulation (IHM) for arbitrary objects is challenging due to the rich and subtle contact process. Variable-friction manipulation is an alternative approach to dexterity, previously demonstrating robust and versatile 2D IHM capabilities with only two single-joint fingers. However,
Continual learning aims to learn new tasks sequentially without forgetting previously acquired knowledge. However, catastrophic forgetting remains a significant challenge. In this paper, we introduce kNN-CL, a simple yet effective approach that harnesses k-nearest neighbors (kNN) to mitigate forgett…
Surface electromyography (sEMG) has demonstrated significant potential in simultaneous and proportional control (SPC). However, existing algorithms for predicting joint angles based on sEMG often suffer from high inference costs or are limited to specific subjects rather than multi-subject scenarios
We propose UniSeg3D, a unified 3D scene understanding framework that achieves panoptic, semantic, instance, interactive, referring, and open-vocabulary segmentation tasks within a single model. Most previous 3D segmentation approaches are typically tailored to a specific task, limiting their underst…
Modern large language models (LLMs) exhibit a remarkable capacity for role-playing, enabling them to embody not only human characters but also non-human entities. This versatility allows them to simulate complex human-like interactions and behaviors within various contexts, as well as to emulate spe…
Recent advances in sequential recommendation models have demonstrated the efficacy of integrating pre-trained text embeddings with item ID embeddings to achieve superior performance. However, our study takes a unique perspective by exclusively focusing on the untapped potential of text embeddings, o…
Point cloud analysis has achieved outstanding performance by transferring point cloud pre-trained models. However existing methods for model adaptation usually update all model parameters i.e. full fine-tuning paradigm which is inefficient as it relies on high computational costs (e.g. training GPU…
The bokeh effect is an artistic technique that blurs out-of-focus areas in a photograph and has gained interest due to recent developments in text-to-image synthesis and the ubiquity of smartphone cameras and photo sharing apps. Prior work on rendering bokeh effects have focused on manipulating phot…
Heart sound auscultation holds significant importance in the diagnosis of congenital heart disease. However, existing methods for Heart Sound Diagnosis (HSD) tasks are predominantly limited to a few fixed categories, framing the HSD task as a rigid classification problem that does not fully align wi…
Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention’s quadratic computational demands. Many sought to mitigate this by restricting the attenti…
Large language models (LLMs) have shown great potential to empower various domains and are often customized by fine-tuning for the requirements of different applications. However, the powerful learning ability of LLMs not only enables them to learn new tasks but also makes them vulnerable to learnin…
Transformers have become one of the foundational architectures in point cloud analysis tasks due to their excellent global modeling ability. However, the attention mechanism has quadratic complexity, making the design of a linear complexity method with global modeling appealing. In this paper, we pr…
Relative state estimation is crucial for vision-based swarms to estimate and compensate for the unavoidable drift of visual odometry. For autonomous drones equipped with the most compact sensor setting — a stereo camera that provides a limited field of view (FoV), the demand for mutual observation f…
In code search, the Generation-Augmented Retrieval (GAR) framework, which generates exemplar code snippets to augment queries, has emerged as a promising strategy to address the principal challenge of modality misalignment between code snippets and natural language queries, particularly with the dem…
Retrieval-Augmented Generation (RAG) significantly improved the ability of Large Language Models (LLMs) to solve knowledge-intensive tasks. While existing research seeks to enhance RAG performance by retrieving higher-quality documents or designing RAG-specific LLMs, the internal mechanisms within L…
Recently, Few-shot Named Entity Recognition has received wide attention with the growing need for NER models to learn new classes with minimized annotation costs. However, one common yet understudied situation is to transfer a model trained with coarse-grained classes to recognize fine-grained class…
Multi-stream signals are increasingly being used in robot-assisted rehabilitation training, where the timely and accurate prediction of a patient's motor intentions is frequently required to provide simultaneous and proportional control strategies. However, existing methods for motion intent predict
We propose a simple and novel method for generating 3D human motion from complex natural language sentences, which describe different velocity, direction and composition of all kinds of actions. Different from existing methods that use classical generative architecture, we apply the Denoising Diffus…
Recurrent neural network (RNN) and self-attention mechanism (SAM) are the de facto methods to extract spatial-temporal information for temporal graph learning. Interestingly, we found that although both RNN and SAM could lead to a good performance, in practice neither of them is always necessary. In…
Fabricating existing and popular open-source adaptive robotic grippers commonly involves using multiple professional machines, purchasing a wide range of parts, and tedious, time-consuming assembly processes. This poses a significant barrier to entry for some robotics researchers and drives others t…
As the categories of named entities rapidly increase, the deployed NER models are required to keep updating toward recognizing more entity types, creating a demand for class-incremental learning for NER. Considering the privacy concerns and storage constraints, the standard paradigm for class-increm…
Planar object tracking is a critical computer vision problem and has drawn increasing interest owing to its key roles in robotics, augmented reality, etc. Despite rapid progress, its further development, especially in the deep learning era, is largely hindered due to the lack of large-scale challeng…
Normalizing flow models using invertible neural networks (INN) have been widely investigated for successful generative image super-resolution (SR) by learning the transformation between the normal distribution of latent variable z and the conditional distribution of high-resolution (HR) images gave…
Recently, contrastive learning has become a key component in fine-tuning code search models for software development efficiency and effectiveness. It pulls together positive code snippets while pushing negative samples away given search queries. Among contrastive learning, InfoNCE is the most widely…
With the goal of providing an alternative to optical and other tactile sensors, we set out to stress test the object shape identification capabilities of barometric tactile arrays in robotic manipulation tasks. These sensors are superior to optical devices in terms of form factor, ease of fabricatio…
Pre-trained language models (PLMs) are often deployed as cloud services, enabling users to upload textual data and perform inference remotely. However, users' personal text often contains sensitive information, and sharing such data directly with the service providers can lead to serious privacy l…
In real-world applications, pre-trained language models are typically deployed on the cloud, allowing clients to upload data and perform compute-intensive inference remotely. To avoid sharing sensitive data directly with service providers, clients can upload numerical representations rather than pla…
Recently, many studies have illustrated the robustness problem of Named Entity Recognition (NER) systems: the NER models often rely on superficial entity patterns for predictions, without considering evidence from the context. Consequently, even state-of-the-art NER models generalize poorly to out-o…
Lower-limb exoskeleton robots can support hemiplegic patients’ affected limbs and assist in their rehabilitation. In order to set effective control strategies, it is necessary to obtain the user’s motion intention accurately and timeously. These requirements pose many challenges. The surface electro
Weakly-supervised temporal action localization aims to recognize and localize action segments in untrimmed videos given only video-level action labels for training. Without the boundary information of action segments, existing methods mostly rely on multiple instance learning (MIL), where the predic…
Online trajectory planners enable quadrotors to safely and smoothly navigate in unknown cluttered environments. However, tuning parameters is challenging since modern planners have become too complex to mathematically model and predict their interaction with unstructured environments. This work take…
Robotic tactile sensing provides a method of recognizing objects and their properties where vision fails. Prior work on tactile perception in robotic manipulation has frequently focused on exploratory procedures (EPs). However, the also-human-inspired technique of in-hand-manipulation can glean rich…
Designing autonomous aerial robot team systems remains a grand challenge in robotics. Existing works in this field can be categorized as centralized and decentralized. Centralized methods suffer from scale dilemmas, while decentralized ones often lead to poor planning quality. In this paper, we prop
Question generation over knowledge bases (KBQG) aims at generating natural questions about a subgraph, which can be answered by a given answer entity. Existing KBQG models still face two main challenges: (1) Most models often focus on the most relevant part of the answer entity, while neglecting the…
Large pre-trained language models (PLMs) have demonstrated superior performance in industrial applications. Recent studies have explored parameter-efficient PLM tuning, which only updates a small amount of task-specific parameters while achieving both high efficiency and comparable performance again…
Proof generation focuses on deductive reasoning: given a hypothesis and a set of theories, including some supporting facts and logical rules expressed in natural language, the model generates a proof tree indicating how to deduce the hypothesis from given theories.Current models with state-of-the-ar…
Input distribution shift is one of the vital problems in unsupervised domain adaptation (UDA). The most popular UDA approaches focus on domain-invariant representation learning, trying to align the features from different domains into a similar feature distribution. However, these approaches ignore…
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would be time-consuming to enumerate the template queries over all…
Recently, more and more pre-trained language models are released as a cloud service. It allows users who lack computing resources to perform inference with a powerful model by uploading data to the cloud. The plain text may contain private information, as the result, users prefer to do partial compu…
In order to solve the dual-objective path optimization problem of arc welding robot, a complete and novel methodology is proposed, including modeling, collision-free path search and global path optimization. First of all, the grid method is utilized to accurately model the welding workpieces and sur
Gradient-based planners are widely used for quadrotor local planning, in which a Euclidean Signed Distance Field (ESDF) is crucial for evaluating gradient magnitude and direction. Nevertheless, computing such a field has much redundancy since the trajectory optimization procedure only covers a very
This paper presents a decentralized and asynchronous systematic solution for multi-robot autonomous navigation in unknown obstacle-rich scenes using merely onboard resources. The planning system is formulated under gradient-based local planning framework, where collision avoidance is achieved by for…
Interactions with either environments or expert policies during training are needed for most of the current imitation learning (IL) algorithms. For IL problems with no interactions, a typical approach is Behavior Cloning (BC). However, BC-like methods tend to be affected by distribution shift. To mi…
In this letter, we propose a lightweight yet effective Topology Guided Kinodynamic planner (TGK-Planner) for quadrotor aggressive flights with limited onboard computing resources. The proposed system follows the traditional hierarchical planning workflow, with novel designs to improve the robustness
With much research has been conducted into trajectory planning for quadrotors, planning with spatial and temporal optimal trajectories in real-time is still challenging. In this letter, we propose a framework for large-scale waypoint-based polynomial trajectory generation, with highlights on its sup
A large-scale video quality dataset called the VideoSet has been constructed recently to measure human subjective experience of H.264 coded video in terms of the just-noticeable-difference (JND). It measures the first three JND points of 5-second video of resolution 1080p, 720p, 540p and 360p. Based…
Acoustic source localization in sensor network is a challenging task because of severe constraints on cost, energy, and effective range of sensor devices. To overcome these limitations in existing solutions, this paper formally describes, designs, implements, and evaluates a Half Plane Intersection…
Firstly, an implementation-friendly interpolation filter algorithm is proposed in this paper. It can save 19.6% processing time on average with negligible coding quality degradation. Then based on the proposed algorithm, an optimized interpolation filter VLSI architecture, composed of the reused dat…