368 accepted papers
As large language models (LLMs) continue to revolutionize AI research, there is a growing interest in building large-scale brain foundation models to advance neuroscience. While most existing brain foundation models are pre-trained on time-series signals or connectome features, we propose a novel gr…
Counterfactual explanations offer an intuitive way to interpret graph neural networks (GNNs) by identifying minimal changes that alter a model’s prediction, thereby answering “what must differ for a different outcome?”. In this work, we propose a novel framework, ATEX-CF that unifies adversarial att…
Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modeling dynamics, existing VAR token reduction methods face three key limitations: heuristic stage partition, non-adaptive sch…
Adjuvants play a critical role in modulating immune responses and are central to the development of vaccines and immunotherapies. Yet progress in this field is constrained by data scarcity and incomplete understanding of mechanisms of action, which limit the transition from experience-based design t…
Abstract— Cross-View Geo-Localization (CVGL) localizes a query image via retrieval from georeferenced satellite imagery,yet severe viewpoint variation remains a central challenge. Recent advances often rely on heavy backbones or add-on modules that achieve high accuracy but are impractical on resour…
We aim to improve the reasoning capabilities of language models via reinforcement learning with verifiable rewards (RLVR). Recent RLVR post-trained models like DeepSeek-R1 have demonstrated reasoning abilities on mathematical and coding tasks. However, prior studies suggest that using RLVR alone to…
Inspired by how humans communicate spatial information, language-guided geo-localization has gained significant traction for its intuitive and practical value. Despite this progress, most methods still rely on a static, one-shot retrieval paradigm, which fails to handle the ambiguity and incompleten
While adversarial fine-tuning can enhance the robustness of vision-language models (VLMs), such approaches are computationally expensive. Adversarial prompt tuning has emerged as a practical alternative. However, existing methods are limited by their reliance on vulnerable continuous image features.…
Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fi
Vision-Language Models (VLMs) have emerged as versatile solutions for zero-shot question answering (QA) across various domains. However, enabling VLMs to effectively comprehend structured graphs and perform accurate, efficient QA remains challenging. Existing approaches typically rely on a single ty
In-context learning (ICL) has emerged as a powerful paradigm for Large Visual Language Models (LVLMs), enabling them to leverage a few examples directly from input contexts. However, the effectiveness of this approach is heavily reliant on the selection of demonstrations, a process that is NP-hard.
Egocentric human pose estimation (HPE) using a head-mounted device is crucial for various VR and AR applications, but it faces significant challenges due to keypoint invisibility. Nevertheless, none of the existing egocentric HPE datasets provide keypoint visibility annotations, and the existing met
Several studies have demonstrated that large language models (LLMs) exhibit positional bias when answering multiple-choice questions (MCQs). Previous methods have identified such bias to be detrimental, leading to the development of techniques to mitigate it. However, we observe that certain permuta
Reward learning via human feedback is a crucial capability for beneficial AI. Current methods are built on decision-making theories that assume a matched dynamics model between the learning agent and the feedback provider. However, humans often form imperfect internal dynamics models, and their feed
Multi-modal large language models (MLLMs) have achieved remarkable success on complex multi-modal tasks. However, it remains insufficiently explored whether they exhibit \textit{modality preference}, a tendency to favor one modality over another when processing multi-modal contexts. To study this qu…
The Minimum Dominating Set (MDS) problem is a well-established combinatorial optimization problem with numerous real-world applications. Its NP-hard nature makes it increasingly difficult to obtain exact solutions as the graph size grows. This paper introduces ParDS, an exact algorithm developed to
The widespread use of mobile devices has created new challenges for vision systems in safety monitoring, workplace productivity assessment, and attention management. Detecting whether a person is using a phone requires not only object recognition but also an understanding of behavioral context, whic…
Existing LLM-as-a-Judge systems suffer from three fundamental limitations: \textbf{limited adaptivity} to task and domain-specific evaluation criteria, \textbf{systematic biases} driven by non-semantic cues such as position, length, format, and model provenance, and \textbf{evaluation inconsistency}…
Diffusion and flow-based models have enabled significant progress in generation tasks across various modalities and have recently found applications in predictive learning. However, unlike typical generation tasks that encourage sample diversity, predictive learning entails different sources of stoc…
Learning on graphs with missing node attributes is a prevalent yet challenging problem in real-world scenarios, as graph neural networks (GNNs) typically rely on complete attribute information. Existing solutions often employ adversarial learning in a shared latent space to align graph structure and…
Recent vision-language models (VLMs) have shown strong generalization and multimodal reasoning abilities in natural domains. However, their application to medical diagnosis remains limited by the lack of comprehensive and structured datasets that capture real clinical workflows. To advance the devel
Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover
SLAM methods based on 3D Gaussian Splatting (3DGS) have demonstrated impressive tracking and mapping performance, but typically require additional geometric information from external depth sensors. Meanwhile, recent SLAM systems that leverage geometric priors from pre-trained feed-forward models ena…
Dynamic graphs are common in real‑world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the full complexity of temporal evolution. They tend to overlook fine‑grained variations in interaction or
Lifelong learning aims to preserve knowledge acquired from previous tasks while incorporating knowledge from a sequence of new tasks. However, most prior work explores only streams of homogeneous tasks (*e.g.*, only classification tasks) and neglects the scenario of learning across heterogeneous tas
Large language models (LLMs) have achieved impressive performance across a wide range of natural language processing tasks, yet they often produce hallucinated content that undermines factual reliability. To address this challenge, we introduce HalluClean, a lightweight and task-agnostic framework f
The existing methods for novel view synthesis depend on dense input images and accurate camera poses, which significantly limits their practical application. We propose a novel framework that enables high-quality sparse-view reconstruction via 3D Gaussian Splatting (3DGS) without knowing camera pose…
Outcome-driven reinforcement learning has advanced reasoning in large language models (LLMs), but prevailing tool-augmented approaches train a single, monolithic policy that interleaves thoughts and tool calls under full context; this scales poorly with long horizons and diverse tools and generalize…
Modeling dynamic dependencies from irregularly sampled event sequences is a fundamental challenge in modern machine learning. In many real-world systems, individual-level states evolve continuously over time while being simultaneously influenced by population-level distributional dynamics. However, …
Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate training. Current frameworks preserve training performance using mixed-granularity quantization, i.e., applying per-group quan…
Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging co
We introduce MoSA, a new parameter-efficient fine-tuning (PEFT) method that replaces low-rank factorization with randomized, fine-grained sharing of weight updates. Each adapted weight matrix is constructed by broadcasting a small set of learned scalars over a fixed tessellation, a pre-defined group…
Diffusion Large Language Models (dLLMs) have emerged as a promising non-autoregressive generative paradigm. Given the prohibitive computational cost of full fine-tuning, Parameter-Efficient Fine-Tuning (PEFT) has become the standard approach. However, existing PEFT methods (e.g., LoRA), originally t…
Hand-object interaction (HOI) reconstruction and synthesis are becoming central to embodied AI and AR/VR. Yet, despite rapid progress, existing HOI generation research remains fragmented across three disjoint tracks: (1) pose-only synthesis that predicts MANO trajectories without producing pixels; (
Multitask genetic programming (MTGP) is one of the primary methods for solving multitask symbolic regression (MTSR), the problem of discovering mathematical expressions for multiple interconnected tasks simultaneously. However, conventional MTGP approaches discard a wealth of valuable knowledge from
Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. Inspired by recent…
Large Vision-Language Models (LVLMs) excel in multimodal reasoning and have shown impressive performance on various multimodal benchmarks. However, most of these benchmarks evaluate models primarily through multiple-choice or short-answer formats, which do not take the reasoning process into account
Robotic ultrasound systems offer significant potential for automated organ coverage scanning, yet acoustic shadows from bone structures can cause incomplete scans and missed diagnoses. This work presents a real-time coverage path planning method for bone-aware robotic ultrasound scanning. A voxel ba
Recent breakthroughs in reasoning language models have significantly advanced text-based reasoning. On the other hand, Multi-modal Large Language Models (MLLMs) still lag behind, hindered by their outdated internal LLMs. Upgrading these is often prohibitively expensive, as it requires complete visio…
Graph Contrastive Learning (GCL) has recently emerged as a powerful paradigm for modeling user–item interactions and learning high-quality representations in recommender systems. While existing GCL-based methods benefit from data augmentation and sampling strategies, they often overlook the inherent
Spatially multimodal omics technologies provide unprecedented opportunities to address cellular heterogeneity within tissue contexts. However, learning robust and informative latent representations from such complex data remains a significant challenge. Existing graph-based methods often rely on sta
Real-time and accurate spatial audio generation is pivotal for delivering an immersive experience. However, existing spatial audio synthesis technologies are often encumbered by a tradeoff between generation quality and high inference latency, as well as difficulty in capturing precise spatial infor…
Cross-modal Visual Geo-localization often aims to retrieve a satellite visible-light image of the same geographic lo cation from a large-scale database using an infrared image cap tured by an unmanned aerial vehicle (UAV), thereby achieving precise localization. This capability is crucial for autono…
Egocentric human pose estimation (HPE) plays a crucial role in immersive applications such as virtual and augmented reality. However, existing methods relying on either visual or sparse inertial data alone often suffer from occlusion or ill-posed problems. In this work, we propose SAME, a novel spat
Fine-tuning large language models often undermines their safety alignment, a problem further amplified by harmful fine-tuning attacks in which adversarial data removes safeguards and induces unsafe behaviors. We propose SPARD, a defense framework that integrates Safety-Projected Alternating optimiza…
The rapid advancement of Large Language Models (LLMs) has driven significant progress in Natural Language Interface to Database (NLIDB). However, the widespread adoption of LLMs has raised critical privacy and security concerns. During interactions, LLMs may unintentionally expose confidential datab
Long video understanding (LVU) remains a core challenge in multimodal learning. Although recent vision-language models (VLMs) have made notable progress, existing benchmarks mainly focus on either fine-grained perception or coarse summarization, offering limited insight into temporal understanding o
Transfer learning aims to facilitate the learning of a target domain by transferring knowledge from a source domain. The source domain typically contains semantically meaningful samples (*e.g.*, images) to facilitate effective knowledge transfer. However, a recent study observes that the noise domai…
This paper addresses the labor-intensive process of converting imprecise hand-drawn sketches into precise, parametric CAD sketches. We present Sketch2CAD, a novel deep learning framework that leverages generative adversarial networks (GANs) to automate this conversion. Our approach consists of two m…
Embodied navigation that adheres to social norms remains an open research challenge. Our SocialNav is a foundational model for socially-aware navigation with a hierarchical "brain-action" architecture, capable of understanding high-level social norms and generating low-level, socially compliant traj
Nowcasting forms the first line of defense against rapidly evolving weather hazards, where even minutes of delay can lead to severe societal impacts. However, existing systems predominantly extrapolate 2D radar reflectivity, which struggles under rapid intensification regimes. We introduce \N, a mul…
Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel unmasking. However, existing block-wise decoding methods typically partition blocks in a rigid and fixed manner, which i…
For an unlabeled dataset containing both known and unknown categories, Generalized Category Discovery (GCD) aims to classify known categories while discovering unknown ones. Although existing methods achieve promising results on coarse-grained datasets, they struggle in fine-grained scenarios. We ob
Large language models (LLMs) continue to struggle with low-resource languages, primarily due to limited training data, translation noise, and unstable cross-lingual alignment. To address these challenges, we propose LiRA (Linguistic Robust Anchoring for LLMs)—a plug-and-play framework that requires …
Video object detection has gained notable progress with the advent of transformers. While transformers excel at modeling long-range contextual dependencies, the quadratic complexity limits their efficiency in long-sequence processing. In contrast, Mamba offers greater efficiency in modeling long seq
Deep learning for human sensing on edge systems presents significant potential for smart applications. However, its training and development are hindered by the limited availability of sensor data and resource constraints of edge systems. While transferring pre-trained models to different sensing ap…
Efficient generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV Cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality…
Entity set expansion, taxonomy expansion, and seed-guided taxonomy construction are three representative tasks that can be applied to automatically populate an existing taxonomy with emerging concepts. Previous studies view them as three separate tasks. Therefore, their proposed techniques usually w…
In this paper, we consider a first step to bridge a gap in coordinating task planning robots. Specifically, we study the automatic construction of languages that are maximally flexible while being sufficiently explicative for coordination. To this end, we view language as a machinery for specifying
Implicit Neural Representation (INR) has shown great potential in constructing the complex nature signal as a continuous implicit function. However, the representation results are incomplete since different components of the signal correspond to different frequencies and neural network inherently te…
Large Language Models (LLMs) with extended context lengths face significant computational challenges during the pre-filling phase, primarily due to the quadratic complexity of self-attention. Existing methods typically employ dynamic pattern matching and block-sparse low-level implementations. Howev
Despite the recent success of two-stage prototypical networks in few-shot named entity recognition (NER), challenges such as over/under-detected false spans in the span detection stage and unaligned entity prototypes in the type classification stage persist. Additionally, LLMs have not proven to be…
Imitation learning based planning tasks on the nuPlan dataset have gained great interest due to their potential to generate human-like driving behaviors. However, open-loop training on the nuPlan dataset tends to cause causal confusion during closed-loop testing, and the dataset also presents a long
Vehicle routing problems (VRPs) are significant combinatorial optimization problems (COPs) holding substantial practical importance. Recently, neural combinatorial optimization (NCO), which involves training deep learning models on extensive data to learn vehicle routing heuristics, has emerged as a…
With the increasing interest in robotic synthesis in the context of organic chemistry, the automated extraction of chemical procedures from literature is critical. However, this task remains challenging due to the inherent ambiguity of chemical language and the high cost of human annotation required…
The advent of single-cell Assay for Transposase-Accessible Chromatin using sequencing (scATAC-seq) offers an innovative perspective for deciphering regulatory mechanisms by assembling a vast repository of single-cell chromatin accessibility data. While foundation models have achieved significant suc…
As the field of robotics evolves, robots become increasingly multi-functional and complex. Currently, there is a need for solutions that enhance flexibility and computational power without compromising real-time performance. The emergence of fog computing and cloud-native approaches addresses these
We propose a Competitive Low-Rank Adaptation (ComLoRA) framework to address the limitations of the LoRA method, which either lacks capacity with a single rank-$r$ LoRA or risks inefficiency and overfitting with a larger rank-$Kr$ LoRA, where $K$ is an integer larger than 1. The proposed ComLoRA meth…
Low-rank adaptation (LoRA) has emerged as a leading parameter-efficient fine-tuning technique for adapting large foundation models, yet it often locks adapters into suboptimal minima near their initialization. This hampers model generalization and limits downstream operators such as adapter merging…
Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), yet its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content, incorrect responses, and poor OCR quality. Previous approaches to address these challenges have focused
Automatically generating questions with controlled difficulty has great application value, especially in the field of education. Although large language models are capable of generating questions of various difficulty levels, the generated questions often fail to align with the given target difficul
Traditional SLAM performs well in static environments, but experiences degeneration of localization accuracy and stability in dynamic settings. To enhance performance in dynamic environments, this letter presents DGO-VINS, a real-time dynamic visual-inertial SLAM system based on geometric constraint
In recent years, deep learning based malicious traffic detection (MTD) systems have demonstrated remarkable success. However, their effectiveness tend to decrease because most malicious traffic datasets are suffered from noisy-labeled and long-tailed problems. While numerous approaches have been dev…
The hybrid aerial-ground robots combine ground mobility and aerial flight capability, which are often designed for executing multi-terrain tasks. However, most of the existing hybrid aerial-ground robots integrate the ground and aerial functionality into one single whole system. This leads to functi
Optimal path planning requires finding a series of feasible states from the starting point to the goal to optimize objectives. Popular path planning algorithms, such as Effort Informed Trees (EIT*), employ effort heuristics to guide the search. Effective heuristics are accurate and computationally e
Continual Semantic Parsing (CSP) enables parsers to generate SQL from natural language questions in task streams, using minimal annotated data to handle dynamically evolving databases in real-world scenarios. Previous works often rely on replaying historical data, which poses privacy concerns. Recen…
Understanding the multimodal documents is essential for accurately extracting relevant evidence and using it for reasoning. Existing document understanding models struggle to focus on key information and tend to generate answers straightforwardly, ignoring evidence from source documents and lacking
Traditional magnetic tactile sensors are highly susceptible to external magnetic field interference, limiting their reliability in practical applications. To address this challenge, we propose a dual-modal soft magnetic skin capable of simultaneously acquiring magnetic and force tactile information
Diffusion models have emerged as powerful generative frameworks by progressively adding noise to data through a forward process and then reversing this process to generate realistic samples. While these models have achieved strong performance across various tasks and modalities, their application to…
GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging…
Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a comprehension defect of complete-text captions. One-fly complete-text input either overlooks critical semantic details or cause…
Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distribution of observations present a significant challenge, resulting in an ill-posed problem with multiple feasible solutions (…
Recently, advancements in video synthesis have attracted significant attention. Video synthesis models have demonstrated the practical applicability of diffusion models in creating dynamic visual content. Despite these advancements, the extension of video lengths remains constrained by computational
Continual Semantic Parsing (CSP) aims to train parsers to convert natural language questions into SQL across tasks with limited annotated examples, adapting to dynamically updated databases in real-world scenarios. Previous studies mitigate this challenge by replaying historical data or employing pa…
Visual Place Recognition (VPR) is aimed at predicting the location of a query image by referencing a database of geotagged images. For VPR task, often fewer discriminative local regions in an image produce important effects while mundane background regions do not contribute or even cause perceptual…
Open-ended event forecasting (OEEF) seeks to predict future events from a given context without being restricted to a predefined scope or format. It plays a crucial role in domains such as risk management and financial decision making. Although large language models show potential for OEEF, existing
Achieving general agile whole-body control on humanoid robots remains a major challenge due to diverse motion demands and data conflicts. While existing frameworks excel in training single motion-specific policies, they struggle to generalize across highly varied behaviors due to conflicting control…
Roadside camera-based perception methods are in high demand for developing efficient vehicle-infrastructure collaborative perception systems. By focusing on object-level depth prediction, we explore the potential benefits of integrating environmental priors into such systems and propose a geometry-b
3D Gaussian Splatting (3DGS) allows flexible adjustments to scene representation, enabling continuous optimization of scene quality during dense visual simultaneous localization and mapping (SLAM) in static environments. However, 3DGS faces challenges in handling environmental disturbances from dyna
Unsupervised domain adaptation (UDA) has been widely studied with the goal of transferring knowledge from a label-rich source domain to a related but unlabeled target domain. Most UDA techniques achieve this by reducing the feature discrepancies between the two domains to learn domain-invariant feat
Large language models (LLMs), through pretraining on extensive corpora, encompass rich semantic knowledge and exhibit the potential for efficient adaptation to diverse downstream tasks. However, the intrinsic mechanisms underlying LLMs remain unexplored, limiting the efficacy of applying these model…
We propose Hadamard High-Rank Adaptation (HiRA), a parameter-efficient fine-tuning (PEFT) method that enhances the adaptability of Large Language Models (LLMs). While Low-rank Adaptation (LoRA) is widely used to reduce resource demands, its low-rank updates may limit its expressiveness for new tasks…
Feature matching between image pairs is a fundamental problem in computer vision that drives many applications, such as SLAM. Recently, semi-dense matching approaches have achieved substantial performance enhancements and established a widely-accepted coarse-to-fine paradigm. However, the majority…
Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large generative models. A critical attribute of watermark techniques is their robustness against various manipulations. In this pap…
Answer Set Programming (ASP) planning can be used to refine the rough solutions generated by Large Language Models (LLMs) to handle specific restrictions of actions, i.e., reconstruct the rough solutions to be executable, for robotic task planning. However, it is still challenging to efficiently sol
Multimodal large language models (MLLMs) have shown remarkable capabilities across various downstream tasks. However, when MLLMs are transferred to the text image machine translation (TiMT) task, preliminary experiments reveal that MLLMs suffer from serious repetition and omission hallucinations. To…
The whisker-inspired tactile sensor is advantageous for enhancing robotic perception in proximate range and darkness via non-intrusive contacts. However, localizing contact along the whisker shaft is challenging due to the non-injective mapping between tangential contacts and the resulting bending m
Conversational aspect-based sentiment quadruple analysis (DiaASQ) is a newly-emergent task aiming to extract quadruples of target-aspect-opinion-sentiment from a conversation text. Existing studies struggle to capture complete dialogue semantics, largely due to inadequate inter-utterance modeling an
We investigate the impacts of NLP research published in top-tier conferences (i.e., ACL, EMNLP, and NAACL) from 1979 to 2024. By analyzing citations from research articles and external sources such as patents, media, and policy documents, we examine how different NLP topics are consumed both within…
LiDAR map matching (LMM) faces two key challenges: the enormous number of point clouds imposes constraints on storage and computation, and traditional two-stage frameworks suffer from initial guess errors during degeneration. This paper presents LHMM, a hybrid-map framework that first compresses the
Large-scale 3D reconstruction is critical in the field of robotics, and the potential of 3D Gaussian Splatting (3DGS) for achieving accurate object-level reconstruction has been demonstrated. However, ensuring geometric accuracy in outdoor and unbounded scenes remains a significant challenge. This s
Aiming to replicate human-like dexterity, perceptual experiences, and motion patterns, we explore learning from human demonstrations using a bimanual system with multifingered hands and visuotactile data. Two significant challenges exist: the lack of an affordable and accessible teleoperation system
Humans rely on multisensory integration to perceive spatial environments, where auditory cues enable sound source localization in three-dimensional space. Despite the critical role of spatial audio in immersive technologies such as VR/AR, most existing multimodal datasets provide only monaural audi…
The Segment Anything Model (SAM), with its remarkable zero-shot capability, has the potential to be a foundation model for multi-task learning. However, adopting SAM to multi-task learning faces two challenges: (a) SAM has difficulty generating task-specific outputs with different channel numbers, a…
As the capabilities of large language models (LLMs) continue to expand, aligning these models with human values remains a significant challenge. Recent studies show that reasoning abilities contribute significantly to model safety, while integrating Mixture-of-Experts (MoE) architectures can further…
Human Activity Recognition (HAR) with wearable sensors is challenged by limited interpretability, which significantly impacts cross-dataset generalization. To address this challenge, we propose Motion-Primitive Transformer (MoPFormer), a novel self-supervised framework that enhances interpretability…
The common matrix completion methods minimize the rank of the matrix to be completed in addition to the Hamming loss between the incomplete and completed matrices. The rank of matrix measures the linear relation among the vectors of matrix, which may introduce ambiguity for data recovery. To cope wi…
Breast cancer remains a leading cause of mortality among women, with millions of new cases diagnosed annually. Early detection through screening is crucial. Using neural networks to improve the accuracy of breast cancer screening has become increasingly important. In accordance with radiologists' pr…
Point-to-point and periodic motions are ubiquitous in the world of robotics. To master these motions, Autonomous Dynamic System (ADS) based algorithms are fundamental in the domain of Learning from Demonstration (LfD). However, these algorithms face the significant challenge of balancing precision i
Few-shot semantic segmentation (FSS) aims to segment objects of novel categories in the query images given only a few annotated support samples. Existing methods primarily build the image-level correlation between the support target object and the entire query image. However, this correlation contai…
Message-passing graph neural networks (MPNNs) and structural features (SFs) are cornerstones for the link prediction task. However, as a common and intuitive mode of understanding, the potential of visual perception has been overlooked in the MPNN community. For the first time, we equip MPNNs with v…
Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline P roactive \underline L ow-rank \underline A llocatio\underline N (PLAN), a framework that extends Low-Rank Adaptation (LoRA) to enable efficient and int…
Effectively utilizing extensive unlabeled high-density EEG data to improve performance in scenarios with limited labeled low-density EEG data presents a significant challenge. In this paper, we address this challenge by formulating it as a graph transfer learning and knowledge distillation problem.…
Protein-specific large language models (ProteinLLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of
Recent advances in robotics have underscored the critical role of colorized point clouds in enhancing environmental perception accuracy. However, conventional multisensor fusion Simultaneous Localization and Mapping (SLAM) systems typically employ all available images indiscriminately for point clou
Codes serve as the fundamental language for human to communicate with machines, and various Transformer-based models are trained to process codes in recent advancements. A unique symmetry of code is its semantic-preserving permutation, which allows certain lines to be rearranged without altering the
Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle significantly with complex problems requiring explicit self-reflection and self-correction, especially compared to their unimodal text-based counterparts. Existing reflection methods are…
Recent breakthroughs in singing voice synthesis (SVS) have heightened the demand for high-quality annotated datasets, yet manual annotation remains prohibitively labor-intensive and resource-intensive. Existing automatic singing annotation (ASA) methods, however, primarily tackle isolated aspects of…
This paper proposes a novel dual-filter architecture utilizing RGB-D camera data and dynamic control barrier functions (D-CBFs) for real-time obstacle avoidance in unstructured environments. The proposed method efficiently handles static, suddenly appearing, and dynamic obstacles, maintaining consis
Black-box optimization algorithms have been widely used in various machine learning problems, including reinforcement learning and prompt fine-tuning. However, directly optimizing the training loss value, as commonly done in existing black-box optimization methods, could lead to suboptimal model qua…
A major breakthrough in 3D reconstruction is the feedforward paradigm to generate pixel-wise 3D points or Gaussian primitives from sparse, unposed images. To further incorporate semantics while avoiding the significant memory and storage costs of high-dimensional semantic features, existing methods…
Detecting a minor average treatment effect is a major challenge in large-scale applications, where even minimal improvements can have a significant economic impact. Traditional methods, reliant on normal distribution-based or expanded statistics, often fail to identify such minor effects because of…
Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limiting their robustness in zero-shot scenarios and producing poor…
Singing voice synthesis has made remarkable progress in generating natural and high-quality voices. However, existing methods rarely provide precise control over vocal techniques such as intensity, mixed voice, falsetto, bubble, and breathy tones, thus limiting the expressive potential of synthetic…
Emotion and Intent Joint Understanding in Multi-modal Conversation is a challenging task in the field of affective computing, aiming to decode the semantic information manifested in the multimodal conversational while simultaneously inferring the emotions and intents of the utterance. To address thi…
Song generation focuses on producing controllable high-quality songs based on various prompts. However, existing methods struggle to generate vocals and accompaniments with prompt-based control and proper alignment. Additionally, they fall short in supporting various tasks. To address these challeng
In many scientific fields, large language models (LLMs) have revolutionized the way text and other modalities of data (e.g., molecules and proteins) are handled, achieving superior performance in various applications and augmenting the scientific discovery process. Nevertheless, previous surveys on…
Multi-objective optimization (MOO) has become an influential framework for various machine learning problems, including reinforcement learning and multi-task learning. In this paper, we study the black-box multi-objective optimization problem, where we aim to optimize multiple potentially conflictin…
Real-time dense reconstruction using Unmanned Aerial Vehicle (UAV) is becoming increasingly popular in large-scale rescue and environmental monitoring tasks. However, due to the energy constraints of a single UAV, the efficiency can be greatly improved through the collaboration of multi-UAVs. Nevert…
Visual object tracking aims to locate a targeted object in a video sequence based on an initial bounding box. Recently, Vision-Language~(VL) trackers have proposed to utilize additional natural language descriptions to enhance versatility in various applications. However, VL trackers are still infer…
Predictive Coding (PC) is a theoretical framework in cognitive science suggesting that the human brain processes cognition through spatiotemporal prediction of visual world. Existing studies have developed spatiotemporal prediction neural networks based on the PC theroy, emulating its two core mecha…
The increasing popularity of Unmanned Aerial Vehicles has led to heightened demand for their ability to interact with the environment along with the large flight envelopes. In this letter, we propose a new spatial symmetric fully actuated multirotor (FAM) that is capable of achieving fast, smooth at
In high-stakes sectors such as network security, IoT security, accurately distinguishing between normal and anomalous data is critical due to the significant implications for operational success and safety in decision-making. The complexity is exacerbated by the presence of unlabeled data and the op…
This paper introduces a novel human pose estimation approach using sparse inertial sensors addressing the shortcomings of previous methods reliant on synthetic data. It leverages a diverse array of real inertial motion capture data from different skeleton formats to improve motion diversity and mode…
Mapping plays a crucial role in location and navigation within automatic systems. However, the presence of dynamic objects in 3D point cloud maps generated from scan sensors can introduce map distortion and long traces, thereby posing challenges for accurate mapping and navigation. To address this i…
Path planning has long been an important and active research area in robotics. To address challenges in high-dimensional motion planning, this study introduces the Force Direction Informed Trees (FDIT*), a sampling-based planner designed to enhance speed and cost-effectiveness in pathfinding. FDIT*…
Far-range perception through roadside sensors is crucial to the effectiveness of intelligent transportation systems. The main challenge of far-range perception is due to the difficulty of performing accurate object detection and tracking under far distances <italic xmlns:mml="http://www.w3.org/1998/
In path planning, anytime almost-surely asymptotically optimal planners dominate the benchmark of sampling-based planners. A notable example is Batch Informed Trees (BIT*), where planners iteratively determine paths to batches of vertices within the exploration area. However, utilizing a consistent…
Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performance by sampling more reasoning chains when saturated. To further boost performance, we introduce backward reasoning to v…
Large Language Models (LLMs) are increasingly used for various tasks with graph structures. Though LLMs can process graph information in a textual format, they overlook the rich vision modality, which is an intuitive way for humans to comprehend structural information and conduct general graph reaso…
The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singers, absence of multi-technique information and real…
Linear attention Transformers and their gated variants, celebrated for enabling parallel training and efficient recurrent inference, still fall short in recall-intensive tasks compared to traditional Transformers and demand significant resources for training from scratch. This paper introduces Gated…
Domain shift degrades classification models on new data distributions. Conventional unsupervised domain adaptation (UDA) aims to learn features that bridge labeled source and unlabeled target domains. In contrast to feature learning, gradual domain adaptation (GDA) leverages extra continuous interme…
Large language models (LLMs), while exhibiting exceptional performance, suffer from hallucinations, especially on knowledge-intensive tasks. Existing works propose to augment LLMs with individual text units retrieved from external knowledge corpora to alleviate the issue. However, in many domains, t…
This paper studies super-resolution harmonic retrieval for strictly non-circular coherent signals. We develop gridless sparse representations of both their covariance and pseudo-covariance matrices over a common matrix-form atom set. This enables the decoupled atomic norm minimization (D-ANM) techni…
In this work we present a novel dense-correspondence method for 6DoF object pose estimation from a single RGB-D image. While many existing data-driven methods achieve impressive performance they tend to be time-consuming due to their reliance on rendering-based refinement approaches. To circumvent t…
As Large Language Models (LLMs) become more capable of handling increasingly complex tasks, the evaluation set must keep pace with these advancements to ensure it remains sufficiently discriminative. Item Discrimination (ID) theory, which is widely used in educational assessment, measures the abilit…
"Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap between models trained with generative and discriminative objectives. In this paper, we aim to narrow this gap by improving…
The first 24 hours’ medication plan is critical to patients with serious or life-threatening illnesses and injuries. An appropriate medication can result in a lower mortality, a shorter length stay and a higher APACHE score. However, in clinical practice, the medication plan is often error-prone, es…
Lake extraction from remote sensing images is challenging due to the complex lake shapes and inherent data noises. Existing methods suffer from blurred segmentation boundaries and poor foreground modeling. This paper proposes a hybrid CNN-Transformer architecture, called LEFormer, for accurate lake…
Autonomous Dynamic System (DS)-based algorithms hold a pivotal and foundational role in the field of Learning from Demonstration (LfD). Nevertheless, they confront the formidable challenge of striking a delicate balance between achieving precision in learning and ensuring the overall stability of th…
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms of *inefficient data utilization*. It relies on a single contrastive supervision for each image-text pair during repres…
"Multi-task dense scene understanding, which learns a model for multiple dense prediction tasks, has a wide range of application scenarios. Modeling long-range dependency and enhancing cross-task interactions are crucial to multi-task dense prediction. In this paper, we propose MTMamba, a novel Mamb…
Spiking neural networks (SNNs) are potential competitors to artificial neural networks (ANNs) due to their high energy-efficiency on neuromorphic hardware. However, SNNs are unfolded over simulation time steps during the training process. Thus, SNNs require much more memory than ANNs, which impedes…
Large language models (LLMs) have pushed the limits of natural language understanding and exhibited excellent problem-solving ability. Despite the great success, most existing open-source LLMs (\eg, LLaMA-2) are still far away from satisfactory for solving mathematical problems due to the complex re…
Recent advancements in large-scale multi-task robot learning offer the potential for deploying robot fleets in household and industrial settings, enabling them to perform diverse tasks across various environments. However, AI-enabled robots often face challenges with generalization and robustness wh…
In the era of large models, the autoregressive nature of decoding often results in latency serving as a significant bottleneck. We propose a non-autoregressive LM-fused ASR system that effectively leverages the parallelization capabilities of accelerator hardware. Our approach combines the Universal…
Spoken language identification refers to the task of automatically predicting the spoken language in a given utterance. Conventionally, it is modeled as a speech-based language identification task. Prior techniques have been constrained to a single modality; however in the case of video data there i…
State-of-the-art neural implicit surface representations have achieved impressive results in indoor scene reconstruction by incorporating monocular geometric priors as additional supervision. However we have observed that multi-view inconsistency between such priors poses a challenge for high-qualit…
With the prevalence of large-scale pretrained vision-language models (VLMs), such as CLIP, soft-prompt tuning has become a popular method for adapting these models to various downstream tasks. However, few works delve into the inherent properties of learnable soft-prompt vectors, specifically the im…
Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. However, the research on fMRI-to-video reconstruction remains limited since decoding the spatiotemporal perception of conti…
This paper proposes a LiDAR-based goal-seeking and exploration framework, addressing the efficiency of online obstacle avoidance in unstructured environments populated with static and moving obstacles. This framework addresses two significant challenges associated with traditional dynamic control ba…
Transformers with linear attention (i.e., linear transformers) and state-space models have recently been suggested as a viable linear-time alternative to transformers with softmax attention. However, these models still underperform transformers especially on tasks that require in-context retrieval.…
Traffic prediction plays an important role in urban computing. However, many cities face data scarcity due to low levels of urban development. Although many approaches transfer knowledge from data-rich cities to data-scarce cities, the centralized training paradigm cannot uphold data privacy. For th…
In the field of education, for better assessment of students’ abilities, generated questions often need to meet experts’ requirements, indicating the need for controllable question generation (CQG). However, current CQG methods mainly focus on difficulty control, neglecting the control of question c…
The increasing demand for automation has led to a rise in the use of low-speed Autonomous guided vehicles (AGVs). However, AGVs rely on batteries for their power source, which limits their operational time and affects their overall performance. To optimize their energy usage and enhance their batter
Knowledge graph question answering (KGQA) involves answering natural language questions by leveraging structured information stored in a knowledge graph. Typically, KGQA initially retrieve a targeted subgraph from a large-scale knowledge graph, which serves as the basis for reasoning models to addre…
Image-goal navigation in unknown environments with sensor error is of considerable difficulty for autonomous robots. In this paper, we propose a drift-resisting topo-metric graph to map the environment and localize the robot using only relative poses. The error-sharing mechanism under this represent…
This paper presents an adaptive online learning framework for systems with uncertain parameters to ensure safety-critical control in non-stationary environments. Our approach consists of two phases. The initial phase is centered on a novel sparse Gaussian process (GP) framework. We first integrate a…
Empirical Risk Minimization (ERM) is fragile in scenarios with insufficient labeled samples. A vanilla extension of ERM to unlabeled samples is Entropy Minimization (EntMin), which employs the soft-labels of unlabeled samples to guide their learning. However, EntMin emphasizes prediction discriminab…
Note-level Automatic Singing Voice Transcription (AST) converts singing recordings into note sequences, facilitating the automatic annotation of singing datasets for Singing Voice Synthesis (SVS) applications. Current AST methods, however, struggle with accuracy and robustness when used for practica…
Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when…
Nowadays, closed-set perception methods for autonomous driving perform well on datasets containing normal scenes. However, they still struggle to handle anomalies in the real world, such as unknown objects that have never been seen while training. The lack of public datasets to evaluate the model pe…
With the widespread application of Large Language Models (LLMs) in Natural Language Interfaces to Databases (NLIDBs), concerns about security issues in NLIDBs have been increasing gradually. However, research on sensitive data leakage in NLIDBs is relatively limited. Therefore, we propose a benchmar…
Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless, collecting such data in highly specialized science and engineering do…
In conversational AI, personalizing dialogues with persona profiles and contextual understanding is essential. Despite large language models’ (LLMs) improved response coherence, effective persona integration remains a challenge. In this work, we first study two common approaches for personalizing LL…
The human shoulder, with its glenohumeral joint, tendons, ligaments, and muscles, allows for the execution of complex tasks with precision and efficiency. However, current robotic shoulder designs lack the compliance and compactness inherent in their biological counterparts. A major limitation of th…
We present SplattingAvatar a hybrid 3D representation of photorealistic human avatars with Gaussian Splatting embedded on a triangle mesh which renders over 300 FPS on a modern GPU and 30 FPS on a mobile device. We disentangle the motion and appearance of a virtual human with explicit mesh geometry…
Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, and articulation skills) derived from reference singing voice samples. However, the endeavor to model the intricate nuanc…
Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunciation) from audio and text prompts. However, the multifaceted nature of singing…
Large-scale diffusion models are adept at generating high-fidelity images and facilitating image editing and interpolation. However, they have limitations when tasked with generating images in dynamic, evolving domains. In this paper, we introduce Terra, a novel Time-varying low-rank adapter that of…
We introduce a multilingual speaker change detection model (USM-SCD) that can simultaneously detect speaker turns and perform ASR for 96 languages. This model is adapted from a speech foundation model trained on a large quantity of supervised and unsupervised data, demonstrating the utility of fine-…
Most lightweight networks adopt simple feature fusion methods, such as element-wise addition, to achieve real-time speed. However, complex background and noise can affect these methods, making it difficult to locate objects accurately. At the same time, if a large number of channel connections are u…
We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios. We project acoustic features based on classical-to-quantum feature encoding. Different from existing quantum convolut…
We propose a novel method to accelerate training and inference process of recurrent neural network transducer (RNN-T) based on the guidance from a co-trained connectionist temporal classification (CTC) model. We made a key assumption that if an encoder embedding frame is classified as a blank frame…
Neural Radiance Fields have shown great potential to synthesize novel views with only a few discrete image observations of the world. However, the requirement of accurate camera parameters to learn scene representations limits its further application. In this paper, we present adaptive positional en…
Sharpness-aware minimization (SAM), which searches for flat minima by min-max optimization, has been shown to be useful in improving model generalization. However, since each SAM update requires computing two gradients, its computational cost and training time are both doubled compared to standard e…
LiDAR and Radar are two complementary sensing approaches in that LiDAR specializes in capturing an object's 3D shape while Radar provides longer detection ranges as well as velocity hints. Though seemingly natural, how to efficiently combine them for improved feature representation is still unclear.…
In recent years, the Convolutional Neural Network (CNN) based deraining methods have achieved remarkable results. However, these methods rarely used the long-range context information, and thus could not effectively restore the regions damaged by dense rain streaks. Moreover, the rain streaks in an…
The retrieval model is an indispensable component for real-world knowledge-intensive tasks, e.g., open-domain question answering (ODQA). As separate retrieval skills are annotated for different datasets, recent work focuses on customized methods, limiting the model transfer- ability and scalability.…
Currently, LiDAR-based 3D detectors are broadly categorized into two groups, namely, BEV-based detectors and cluster-based detectors. BEV-based detectors capture the contextual information from the Bird's Eye View (BEV) and fill their center voxels via feature diffusion with a stack of convolution l…
Knowledge distillation is an effective machine learning technique to transfer knowledge from a teacher model to a smaller student model, especially with unlabeled data. In this paper, we focus on knowledge distillation for the RNN-T model, which is widely used in state-of-the-art (SoTA) automatic sp…
We propose Conditional Adapter (CoDA), a parameter-efficient transfer learning method that also improves inference efficiency. CoDA generalizes beyond standard adapter approaches to enable a new way of balancing speed and accuracy using conditional computation. Starting with an existing dense pretra…
In this paper, we propose a continuous-time-based LiDAR-inertial-vehicle odometry method, which can tightly fuse the data from Light Detection And Ranging (LiDAR), inertial measurement units (IMU), and vehicle measurements. The lateral acceleration constraint is further added to trajectory estimatio…
Quality estimation (QE) aims to assess the quality of machine translations when reference translations are unavailable. QE plays a crucial role in many real-world applications of machine translation. Because labeled QE data are usually limited in scale, recent research, such as DirectQE, pre-trains…
Neural Radiance Fields (NeRF) achieves impressive ren-dering performance by learning volumetric 3D representation from several images of different views. However, it is difficult to reconstruct a sharp NeRF from blurry input as often occurred in the wild. To solve this problem, we propose a novel Ev…
Edges in many real-world social/information networks are associated with rich text information (e.g., user-user communications or user-product reviews). However, mainstream network representation learning models focus on propagating and aggregating node attributes, lacking specific designs to utiliz…
Prompt tuning for pre-trained masked language models (MLM) has shown promising performance in natural language processing tasks with few labeled examples. It tunes a prompt for the downstream task, and a verbalizer is used to bridge the predicted token and label prediction. Due to the limited traini…
Foundation models (FMs), that are trained on broad data at scale and are adaptable to a wide range of downstream tasks, have brought large interest in the research community. Benefiting from the diverse data sources such as different modalities, languages and application domains, foundation models h…