80 accepted papers
Cross-modal Knowledge Distillation has demonstrated promising performance on paired modalities with strong semantic connections, referred to as Symmetric Cross-modal Knowledge Distillation (SCKD). However, implementing SCKD becomes exceedingly constrained in real-world scenarios due to the limited a
Large Vision-Language Models (LVLMs) often omit or misrepresent critical visual content in generated image captions. Minimizing such information loss will force LVLMs to focus on image details to generate precise descriptions. However, measuring information loss during modality conversion is inheren
Millimeter-wave (mmWave) radar has attracted significant attention in robotics and autonomous driving due to its robustness in harsh environments. However, the radar point clouds are typically sparse and noisy, which limits its futher development. Traditional mmWave radar enhancement approaches ofte
In recent years, wireless signal recognition (WSR), which leverages artificial intelligence (AI) to identify properties of passively received radio signals, has garnered significant attention due to its broad applications, such as spectrum management. Existing WSR methods typically learn directly fr…
3D understanding has drawn significant attention recently, leveraging Vision-Language Models (VLMs) to enable multi-modal reasoning between point cloud and text data. Current 3D-VLMs directly embed the 3D point clouds into 3D tokens, following large 2D-VLMs with powerful reasoning capabilities. Howe
Data augmentation plays a pivotal role in offline imitation learning (IL) by alleviating covariate shift, yet existing methods remain constrained. Single-step techniques frequently violate underlying system dynamics, whereas trajectory-level approaches are plagued by compounding errors or scalabilit…
Aligning Large Language Models (LLMs) with human preferences is critical, yet traditional fine-tuning methods are computationally expensive and inflexible. While test-time alignment offers a promising alternative, existing approaches often rely on distorted trajectory-level signals or inefficient sa
Human sketches provide a compact and expressive form of visual communication, but their sparse structural cues, while capturing essential object structures, introduce ambiguity because a single sketch can correspond to multiple plausible images, making cross-domain alignment uncertain and unstable.
Optimizing high-degree-of-freedom robotic manipulators requires searching complex, high-dimensional configuration spaces, a task that is computationally challenging for classical methods. This paper introduces a quantum-native framework that integrates Quantum Machine Learning (QML) with Grover's al…
Existing self-evolution methods overlook the influence of fine-grained reasoning steps, which leads to the reasoner-verifier gap. The computational inefficiency of Monte Carlo (MC) process supervision further exacerbates the difficulty in mitigating the gap. Motivated by the Error-Related Negativity
Large reasoning models (LRMs) improve performance at test time by thinking longer, but this often leads to overthinking and high computational cost. To address this, recent reinforcement learning (RL) methods adopt outcome-level rewards, such as rule- or prompt-based signals, that favor shorter corr
Recent studies have demonstrated the efficacy of integrating Group Relative Policy Optimization (GRPO) into flow matching models, particularly for text-to-image and text-to-video generation. However, we find that directly applying these techniques to image-to-video (I2V) models often fails to yield …
Wireless Signal Recognition (WSR) aims to identify the property of received signals using Artificial Intelligence (AI) without any prior knowledge, which has been widely used in civil and military radios. The current AI trend of pre-training and fine-tuning has shown great performance, and the exist…
The accuracy of deep neural networks is significantly influenced by the effectiveness of mini-batch construction during training. In single-label scenarios, such as binary and multi-class classification tasks, it has been demonstrated that batch selection algorithms preferring samples with higher un…
This paper presents the design, modeling, and experimental validation of CapsuleBot, a novel hybrid aerial-ground bi-copter robot designed for long-endurance and low-noise operations. CapsuleBot combines the maneuverability of a bi-copter in the air with the low power consumption and low noise of a
Collaborative perception, fusing information from multiple agents, can extend perception range so as to improve perception performance. However, temporal asynchrony in real-world environments, caused by communication delays, clock misalignment, or sampling configuration differences, can lead to info
Federated learning (FL) enables decentralized clients to collaboratively train a global model under the orchestration of a central server without exposing their individual data. However, the iterative exchange of model parameters between the server and clients imposes heavy communication burdens, ri…
Zero-shot multi-intent detection is capable of capturing multiple intents within a single utterance without any training data, which gains increasing attention. Building on the success of large language models (LLM), dominant approaches in the literature explore prompting techniques to enable zero-s…
In recent years, several robust contrastive text clustering methods have been proposed. While these methods have achieved significant performances, two issues remain. First, the false negative problem is still not fully resolved, and the false positive issue also arises because all in-neighborhood a…
Event cameras have recently been introduced into image semantic segmentation, owing to their high temporal resolution and other advantageous properties. However, existing event-based semantic segmentation methods often fail to fully exploit the complementary information provided by frames and events…
In this paper, we tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs. Current BVSR methods often fail to restore sharp details at high resolutions, resulting in noticeable artifacts and jitter due to insu…
The rapid progress of large language models (LLMs) has catalyzed the emergence of multimodal large language models (MLLMs) that unify visual understanding and image generation within a single framework. However, most existing MLLMs rely on autoregressive (AR) architectures, which impose inherent lim…
Recently, the rapid development of AIGC has significantly boosted the diversities of fake media spread in the Internet, posing unprecedented threats to social security, politics, law, and etc.To detect the ever-increasingly **diverse** malicious fake media in the new era of AIGC, recent studies have…
Recent advancements in knowledge graph question answering (KGQA) have shown promise, yet existing methods often fail to align with human reasoning patterns. This study proposes HD-PORT (hop-level direct preference optimization for knowledge graph reasoning with trees), a novel approach that combines…
Collaborative perception systems overcome single-vehicle limitations in long-range detection and occlusion scenarios by integrating multi-agent sensory data, improving accuracy and safety. However, frequent cooperative interactions and real-time requirements impose stringent bandwidth constraints. P…
Hallucinations in large vision-language models (LVLMs) pose significant challenges for real-world applications, as LVLMs may generate responses that appear plausible yet remain inconsistent with the associated visual content. This issue rarely occurs in human cognition. We argue that this discrepanc…
While image signals are typically defined on a regular 2D grid, there are scenarios where they are only available at irregular positions. In such cases, reconstructing a complete image on regular grid is essential. This paper introduces ISP2HRNet, an end-to-end network designed to reconstruct high r…
3D Visual Grounding (3DVG) faces persistent challenges due to coarse scene-level observations and logically inconsistent annotations, which introduce ambiguities that compromise data quality and hinder effective model supervision. To address these challenges, we introduce Refer-Judge, a novel framew…
Small language models (SLMs) are more efficient, cost-effective, and customizable than large language models (LLMs), though they often underperform in specific areas like reasoning. Past methods for enhancing SLMs’ reasoning, such as supervised fine-tuning and distillation, often depend on costly ex…
The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this ga…
Diffusion models have demonstrated superior performance in portrait animation. However, current approaches relied on either visual or audio modality to control character movements, failing to exploit the potential of mixed-modal control. This challenge arises from the difficulty in balancing the we…
Current neural networks often employ multi-domain-learning or attribute-injecting mechanisms to incorporate non-independent and identically distributed (non-IID) information for text understanding tasks by capturing individual characteristics and the relationships among samples. However, the extent…
Optimizing high-degree-of-freedom robotic manipulators requires searching complex, high-dimensional configuration spaces, a task that is computationally challenging for classical methods. This paper introduces a quantum-native framework that integrates Quantum Machine Learning (QML) with Grover's al
As end-to-end autonomous driving advances toward real-world deployment, ensuring the safety of autonomous vehicles (AVs) has become a critical requirement for their commercial viability. While rule-based AVs have traditionally undergone rigorous testing in both real-world and simulated environments
Recent advancements in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks. This study introduces Reasoning with Trees (RwT), a novel framework that synergistically integrates LLMs with knowledge…
In modern healthcare, the demand for autonomous robotic assistants has grown significantly, particularly in the operating room, where surgical tasks require precision and reliability. Robotic scrub nurses have emerged as a promising solution to improve efficiency and reduce human error during surger
Large language models (LLMs) have achieved outstanding performance in natural language processing, but enormous model sizes and high computational costs limit their practical deployment. Structured pruning can effectively reduce the resource demands for deployment by removing redundant model paramet…
Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class names with generated visual samples (support-set) has shown promising results. However, TPT cannot avoid the semantic gap
Flapping-wing robots offer significant versatility; however, achieving efficient multi-modal locomotion remains challenging. This paper presents the design, modeling, and experimentation of a novel tailless flapping-wing robot with three independently actuated pairs of wings. Inspired by the leg mor
Large language models (LLMs) are increasingly deployed for general problem-solving across various domains yet remain constrained to chaining immediate reasoning steps and depending solely on parametric knowledge. Integrating an information retrieval system directly into the reasoning process of LLMs…
Conventional multi-source domain few-shot adaptation (MFDA) faces the challenge of further reducing the load on edge-side devices in low-resource scenarios. Considering the native language-supervised advantage of CLIP and the plug-and-play nature of prompt to transfer CLIP efficiently, this paper in…
Enabling humanoid robots to perform autonomously loco-manipulation in unstructured environments is crucial and highly challenging for achieving embodied intelligence. This involves robots being able to plan their actions and behaviors in long-horizon tasks while using multi-modality to perceive devi…
Current defenses against graph attacks often rely on certain properties to eliminate structural perturbations by identifying adversarial edges from normal edges. However, this dependence makes defenses vulnerable to adaptive (white-box) attacks from adversaries with the same knowledge. Adversarial t…
Heatmap regression has dominated human pose estimation due to its superior performance and strong generalization. To meet the requirements of traditional explicit neural networks for output form, existing heatmap-based methods discretize the originally continuous heatmap representation into 2D pixel…
Compositional reasoning capabilities are usually considered as fundamental skills to characterize human perception. Recent studies show that current Vision Language Models (VLMs) surprisingly lack sufficient knowledge with respect to such capabilities. To this end, we propose to thoroughly diagnose…
User Simulators play a pivotal role in training and evaluating task-oriented dialogue systems. Traditional user simulators typically rely on human-engineered agendas, resulting in generated responses that often lack diversity and spontaneity. Although large language models (LLMs) exhibit a remarkabl…
Chain of thought (CoT) has proven useful for problems requiring complex reasoning. Many of these problems are both textual and multimodal. Given the inputs in different modalities, a model generates a rationale and then uses it to answer a question. Because of the hallucination issue, the generated…
In the realm of video object segmentation (VOS) the challenge of operating under low-light conditions persists resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation. Event cameras characterized by their high dynamic ran…
"Head pose estimation (HPE) is crucial for various applications, including human-computer interaction, augmented reality, and driver monitoring. However, traditional RGB-based methods struggle in challenging conditions like sudden movement and extreme lighting. Event cameras, as a neuromorphic senso…
Enabling robots to autonomously perform hybrid motions in diverse environments can be beneficial for long-horizon tasks such as material handling, household chores, and work assistance. This requires extensive exploitation of intrinsic motion capabilities, extraction of affordances from rich environ…
Existing studies on personalized sentiment classification consider a document review as an overall text unit and incorporate backgrounds (i.e., user and product information) to learn sentiment representation. However, it is difficult when these methods meet the current pretrained language models (PL…
Aspect-based sentiment analysis (ABSA) identifies sentiment information related to specific aspects and provides deeper market insights to businesses and organizations. With the emergence of large language models (LMs), recent studies have proposed using fixed examples for instruction tuning to refo…
Large Vision-Language Models (LVLMs) show significant strides in general-propose multimodal applications such as visual dialogue and embodied navigation. However, existing multimodal evaluation benchmarks cover a limited number of multimodal tasks testing rudimentary capabilities, falling short in t…
Effectively and efficiently adapting a pre-trained language model (PLM) for human-centered text understanding (HCTU) is challenging since user tokens are million-level in most personalized applications and do not have concrete explicit semantics. A standard and parameter-efficient approach (e.g., Lo…
Few-shot segmentation remains challenging due to the limitations of its labeling information for unseen classes. Most previous approaches rely on extracting high-level feature maps from the frozen visual encoder to compute the pixel-wise similarity as a key prior guidance for the decoder. However su…
The pre-training for language models captures general language understanding but fails to distinguish the affective impact of a particular context to a specific word. Recent works have sought to introduce contrastive learning (CL) for sentiment-aware pre-training in acquiring affective information.…
"It is widely believed that sparse supervision is worse than dense supervision in the field of depth completion, but the underlying reasons for this are rarely discussed. To this end, we revisit the task of radar-camera depth completion and present a new method with sparse LiDAR supervision to outpe…
Multi-camera setups find widespread use across various applications, such as autonomous driving, as they greatly expand sensing capabilities. Despite the fast development of Neural radiance field (NeRF) techniques and their wide applications in both indoor and outdoor scenes, applying NeRF to multi…
Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of Large Language Models (LLMs), attracting increasing attention from researchers. One stream of approaches focuses on the iterative enhancement of LLMs by continuously verifying and refining their reasoning outputs fo…
Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding prompts into language models (LMs). Common methodologies include integrating promp…
In this letter, an aggressive quadrotor ball playing system called Bat is proposed, whose goal is to intercept a flying ball and volley it towards a designated target. Aggressive means Bat operates the quadrotor aggressively to intercept balls that are far away and hit them to distant positions in w
Various gradient compression algorithms have been proposed to alleviate the communication bottleneck in distributed learning, and they have demonstrated effectiveness in terms of high compression ratios and theoretical low communication complexity. However, when it comes to practically training mod…
Applying neural models injected with in-domain user and product information to learn review representations of unseen or anonymous users incurs an obvious obstacle in content-based recommender systems. For the generalization of the in-domain classifier, most existing models train an extra plain-text…
The growing concerns and regulations surrounding the protection of user data privacy have necessitated decentralized training paradigms. To this end, federated learning (FL) is widely studied in user-related natural language processing (NLP). However, it suffers from several critical limitations inc…
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection. We find that the stumbling block to their generalization is caused by the unexpected learned identity representation on images. Termed as the Implicit Identity Leakage, this phenomenon has…
Multimodal named entity recognition (MNER) and multimodal relation extraction (MRE) are two fundamental subtasks in the multimodal knowledge graph construction task. However, the existing methods usually handle two tasks independently, which ignores the bidirectional interaction between them. This p…
Maintaining engagement and consistency is particularly important in dialogue systems. Existing works have improved the performance of dialogue systems by intentionally learning interlocutor personas with sophisticated network structures. One issue with this approach is that it requires more personal…
The Roller-Quadrotor is a novel quadrotor that combines the maneuverability of aerial drones with the endurance of ground vehicles. This work focuses on the design, modeling, and experimental validation of the Roller-Quadrotor. Flight capabilities are achieved through a quadrotor config-uration, wit…
Significant progress has been made in representation learning, especially with recent success on self-supervised contrastive learning. However, for time series with less intuitive or semantic meaning, sampling bias may be inevitably encountered in unsupervised approaches. Although supervised contras…
This paper aims to explain the generalization of deepfake detectors from the novel perspective of multi-order interactions among visual concepts. Specifically, we propose three hypotheses: 1. Deepfake detectors encode multi-order interactions among visual concepts, in which the low-order interacti…
Current unsupervised video deraining methods are inefficient in modeling the intricate spatio-temporal properties of rain, which leads to unsatisfactory results. In this paper, we propose a novel approach by integrating a bio-inspired event camera into the unsupervised video deraining pipeline, whic…
Conditional computation algorithms, such as the early exiting (EE) algorithm, can be applied to accelerate the inference of pretrained language models (PLMs) while maintaining competitive performance on resource-constrained devices. However, this approach is only applied to the vertical architecture…
Natural language spatial video grounding aims to detect the relevant objects in video frames with descriptive sentences as the query. In spite of the great advances, most existing methods rely on dense video frame annotations, which require a tremendous amount of human effort. To achieve effective g…
"This paper aims to interpret how deepfake detection models learn artifact features of images when just supervised by binary labels. To this end, three hypotheses from the perspective of image matching are proposed as follows. 1. Deepfake detection models indicate real/fake images based on visual co…
This paper introduces a novel motion planner, incrementally stochastic and accelerated gradient information mixed optimization (iSAGO), for robotic manipulators in a narrow workspace. Primarily, we propose the overall scheme of iSAGO informed by the mixed momenta for an efficient constrained optimiz
Learning a disentangled representation is still a challenge in the field of the interpretability of generative adversarial networks (GANs). This paper proposes a generic method to modify a traditional GAN into an interpretable GAN, which ensures that filters in an intermediate layer of the generator…
The billions, and sometimes even trillions, of parameters involved in pre-trained language models significantly hamper their deployment in resource-constrained devices and real-time applications. Knowledge distillation (KD) can transfer knowledge from the original model (i.e., teacher) into a compac…
With the growing popularity of deep-learning models, model understanding becomes more important. Much effort has been devoted to demystify deep neural networks for better explainability. Some feature attribution methods have shown promising results in computer vision, especially the gradient-based m…
One of the promising solutions for drilling craniotomy is robot-assisted surgery with human guidance. The present study deals with a piecewise collaborative drilling task assisted by a robot while containing aligning and drilling. It can enable surgeons to complete the operation more efficiently and
Next Point-of-Interest (POI) recommendation plays an important role in location-based services. State-of-the-art methods learn the POI-level sequential patterns in the user's check-in sequence but ignore the subsequence patterns that often represent the socio-economic activities or coherence of pref…