96 accepted papers
Narrow passage scenarios pose significant challenges for path planning, especially for tasks requiring real-time performance. Traditional asymptotically converging sampling-based planners (SBPs) often exhibit poor initial path quality and slow convergence, limiting their ability to efficiently const
Agentic vision-language models are increasingly trained to "think with images" by calling image operations. However, we show that high final-answer accuracy often hides unfaithful visual reasoning: models may invoke tools on irrelevant regions or ignore tool outputs entirely, yet still guess the cor
As machine learning (ML) applications grow increasingly complex in recent years, modern ML frameworks often need to address multiple potentially conflicting objectives with coupled decision variables across different layers. This creates a compelling need for multi-objective bilevel learning (MOBL).
The Convolutional Neural Tangent Kernel (CNTK) offers a principled framework for understanding convolutional architectures in the infinite-width regime. However, a comprehensive spectral comparison between CNTK and the classical Neural Tangent Kernel (NTK) remains underexplored. In this work, we pre…
Remote Sensing Image-Text Retrieval (RSITR) aims to achieve precise retrieval between remote sensing images and textual descriptions. However, existing methods neglect the multi-dimensional cognitive attributes inherent in remote sensing data and struggle to handle them simultaneously, leading to su
Automatic sleep staging plays a vital role in assessing sleep quality and diagnosing sleep disorders. Most existing methods rely heavily on long and continuous EEG recordings, which poses significant challenges for data acquisition in resource-constrained systems, such as wearable or home-based moni
Satellite-acquired optical remote sensing imagery is extensively applied in time-critical applications like traffic surveillance and evaluation of natural disasters. However, clouds, as a common atmospheric phenomenon, frequently obscure observation. Current approaches aim to restore visibility in c
Magnitude-based stability proxies such as parameter drift are widely used in narrow-task fine-tuning, yet they do not reliably indicate degradation of broad capabilities. We identify trajectory lock-in: under fixed training conditions for narrow adaptation, the joint evolution of task loss and broad…
Mixture-of-Experts (MoE) has become a dominant architecture for scaling Large Language Models (LLMs) efficiently by decoupling total parameters from computational cost. However, this decoupling creates a critical challenge: predicting the model capacity of a given MoE configurations (e.g., expert ac…
Recent advances in learning rate~(LR) scheduling have demonstrated the effectiveness of decay-free approaches that eliminate the traditional decay phase while maintaining competitive performance. Model merging techniques have emerged as particularly promising solutions in this domain. We present War…
This paper introduces a soft active surface gripper designed to manipulate fragile objects safely. This gripper consists of two fingers, each equipped with two compliant pneumatic actuators and a soft active surface. The gripper utilizes the elastic belt as its soft active surface, which is driven b
The widespread deployment of large language models (LLMs) across critical domains has amplified the societal risks posed by algorithmically generated misinformation. Unlike traditional false content, LLM-generated misinformation can be self-reinforcing, highly plausible, and capable of rapid propaga…
Adapting pre-trained models has become the dominant approach for anomalous sound detection (ASD), where classifying the attributes of machine working status is commonly chosen as the deputy task for fine-tuning. However, attributes might be intractable to collect for some machines, causing the label…
To address the issue that current transformable spoke-wheeled leg-wheel robots cannot simultaneously achieve simple structure, stable locomotion and open step climbing ability, a novel robot design method is proposed. The robot called BiTSpoke is driven by two transformable spoke wheels, with a pass
Decentralized bilevel optimization (DBO) provides a powerful framework for multi-agent systems to solve local bilevel tasks in a decentralized fashion without the need for a central server. However, most existing DBO methods rely on lower-level strong convexity (LLSC) to guarantee unique solutions…
The goal of the acoustic scene classification (ASC) task is to classify recordings into one of the predefined acoustic scene classes. However, in real-world scenarios, ASC systems often encounter challenges such as recording device mismatch, low-complexity constraints, and the limited availability o…
The interpretability of Mixture-of-Experts (MoE) models, especially those with heterogeneous designs, remains underexplored. Existing attribution methods for dense models fail to capture dynamic routing-expert interactions in sparse MoE architectures. To address this issue, we propose a cross-level…
Combinatorial Optimization (CO) addresses many important problems, including the challenging Maximum Independent Set (MIS) problem. Alongside exact and heuristic solvers, differentiable approaches have emerged, often using continuous relaxations of quadratic objectives. Noting that an MIS in a graph…
Continual learning (CL) has gained increasing interest in recent years due to the need for models that can continuously learn new tasks while retaining knowledge from previous ones. However, existing CL methods often require either computationally expensive layer-wise gradient projections or large-s
To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can resul
Multimodal large language models (MLLMs) have recently achieved state-of-the-art performance on tasks ranging from visual question answering to video understanding. However, existing studies have concentrated mainly on visual–textual misalignment, leaving largely unexplored the MLLMs’ ability to pre
Collaborative training methods like Federated Learning (FL) and Split Learning (SL) enable distributed machine learning without sharing raw data. However, FL assumes clients can train entire models, which is infeasible for large-scale models. In contrast, while SL alleviates the client memory const…
Actor-critic methods for decentralized multi-agent reinforcement learning (MARL) facilitate collaborative optimal decision making without centralized coordination, thus enabling a wide range of applications in practice. To date, however, most theoretical convergence studies for existing actor-critic…
Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the learned reward via offline RL. However, accurately modeling s…
Gradient Descent (GD) and Conjugate Gradient (CG) methods are among the most effective iterative algorithms for solving unconstrained optimization problems, particularly in machine learning and statistical modeling, where they are employed to minimize cost functions. In these algorithms, tunable par…
Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) are prone to hallucinations, i.e., the generated content that is nonsensical or unfaithful to input sources. Unlike in LLMs, hallucinations in MLLMs often stem from the sensitivity of text decoder to visual tokens, leadi…
Effectively reconstructing 3D hyperspectral images (HSIs) from 2D measurements presents a significant challenge in Coded Aperture Snapshot Spectral Imaging (CASSI) systems. While recent transformers exhibit potential in HSI reconstruction, they often suffer from inadequate exploration of multi-scale…
Driving decision-making in mixed traffic, characterized by high-dynamic interactions and stochastic behaviors of human-driven vehicles, poses significant challenges for autonomous driving systems. To address these issues, we propose a novel Transformer-based Spatial Temporal Fusion (TSTF) module int
Panoptic segmentation unifies the traditional tasks of instance and semantic segmentation. It plays a crucial role in the field of remote sensing; however, it encounters challenges in recognizing small objects and in the model’s ability to generalize across complex scenes. In this paper, we introduc…
Multi-objective optimization (MOO) lies at the core of many machine learning (ML) applications that involve multiple, potentially conflicting objectives (e.g., multi-task learning, multi-objective reinforcement learning, among many others). Despite the long history of MOO, recent years have witnesse…
Recently, multi-objective optimization (MOO) has gained attention for its broad applications in ML, operations research, and engineering. However, MOO algorithm design remains in its infancy and many existing MOO methods suffer from unsatisfactory convergence rate and sample complexity performance.
As Multimodal Large Language Models (MLLMs) develop, their potential security issues have become increasingly prominent. **Machine Unlearning (MU)**, as an effective strategy for forgetting specific knowledge in training data, has been widely used in privacy protection. However, *MU for safety in ML…
In recent years, Multimodal Large Language Models (MLLM) have achieved notable advancements, demonstrating the feasibility of developing an intelligent biomedical assistant. However, current biomedical MLLMs predominantly focus on image-level understanding and restrict interactions to textual comman…
In this work, we present Patch-Adapter, an effective framework for high-resolution text-guided image inpainting. Unlike existing methods limited to lower resolutions, our approach achieves 4K+ resolution while maintaining precise content consistency and prompt alignment--two critical challenges in i…
Vision-language models demand watermarking solutions that protect intellectual property without compromising multimodal coherence. Existing text watermarking methods disrupt visual-textual alignment through biased token selection and static strategies, leaving semantic-critical concepts vulnerable.
Autonomous driving vehicles play a critical role in intelligent transportation systems and have garnered considerable attention. Currently, the popular approach in autonomous driving systems is to design separate optimal objectives for each independent module. Therefore, a major concern arises from
It is time-saving to build a reading assistant for customer service representations (CSRs) when reading user manuals, especially information-rich ones. Current solutions don’t fit the online custom service scenarios well due to the lack of attention to user questions and possible responses. Hence, w…
In this letter, we address the critical security concerns in multi-agent systems, where illegal infiltration is commonly used to convert agents into malicious entities. Existing research predominantly focuses on explicit malicious attack patterns. Our work introduces a covert deception attack framew
Accurate pose estimation over SE(3) is fundamentally crucial for numerous perception tasks, including camera re-localization. While existing learning-based methods estimated from a series of RGB images have significantly improved the accuracy of pose, the majority of models still face one or two lim…
The combination of electronic health records (EHR) and medical images is crucial for clinicians in making diagnoses and forecasting prognoses. Strategically fusing these two data modalities has great potential to improve the accuracy of machine learning models in clinical prediction tasks. However,…
Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries.While iterative retrieval methods improve performance by gathering additional information, current approaches often rely on multiple calls of large language models (LLMs).In t…
Machine anomalous sound detection is a useful technique for various applications, but it often suffers from poor generalization due to the challenges of data collection and complex acoustic environment. To address this issue, we propose a robust machine anomalous sound detection model that leverages…
Reinforcement learning with multiple, potentially conflicting objectives is pervasive in real-world applications, while this problem remains theoretically under-explored. This paper tackles the multi-objective reinforcement learning (MORL) problem and introduces an innovative actor-critic algorithm…
Multi-agent reinforcement learning (MARL) methods have emerged as a promising solution for multi-agent collaborative driving in the intersection and roundabout scenarios. However, these methods need large amounts of training data obtained from the interaction with the driving simulator, and learning
Existing video-language studies mainly focus on learning short video clips, leaving long-term temporal dependencies rarely explored due to over-high computational cost of modeling long videos. To address this issue, one feasible solution is learning the correspondence between video clips and caption…
Learning an accurate value function for a given policy is a critical step in solving reinforcement learning (RL) problems. So far, however, the convergence speed and sample complexity performances of most existing policy evaluation algorithms remain unsatisfactory, particularly with non-linear funct…
This paper introduces Q-tuning, a novel approach for continual prompt tuning that enables the lifelong learning of a pre-trained language model. When learning a new task, Q-tuning trains a task-specific prompt by adding it to a prompt queue consisting of the prompts from older tasks. To better trans…
Equipping a conversational search engine with strategies regarding when to ask clarification questions is becoming increasingly important across various domains. Attributing to the context understanding capability of LLMs and their access to domain-specific sources of knowledge, LLM-based clarificat…
The good compliance of soft robots provides a reliable safety environment for human-robot interaction; however, it also creates challenges for adding sensors to soft robots. In this letter, we propose a self-sensing origami-inspired soft twisting actuator. The actuator is designed based on the struc
In this paper, we propose SpectralNeRF, an end-to-end Neural Radiance Field (NeRF)-based architecture for high-quality physically based rendering from a novel spectral perspective. We modify the classical spectral rendering into two main steps, 1) the generation of a series of spectrum maps spanning…
We investigate non-collaborative dialogue agents, which are expected to engage in strategic conversations with diverse users, for securing a mutual agreement that leans favorably towards the system’s objectives. This poses two main challenges for existing dialogue agents: 1) The inability to integra…
Existing works in federated learning (FL) often assume either full client or uniformly distributed client participation. However, in reality, some clients may never participate in FL training (aka incomplete client participation) due to various system heterogeneity factors. A popular solution is the…
Magnetically actuated nanoparticle microrobots have great potential for biomedical applications, especially in blood vessels. However, they face a complex bifurcation environment, and magnetic control strategies targeting a single pathway limit the operational efficiency of the targeting task. In th
In recent years, multi-objective optimization (MOO) emerges as a foundational problem underpinning many multi-agent multi-task learning applications. However, existing algorithms in MOO literature remain limited to centralized learning settings, which do not satisfy the distributed nature and data p…
The machine reading comprehension (MRC) of user manuals has huge potential in customer service. However, current methods have trouble answering complex questions. Therefore, we introduce the knowing-how & knowing-that task that requires the model to answer factoid-style, procedure-style, and inconsi…
This work develops analysis and algorithms for solving a class of bilevel optimization problems where the lower-level (LL) problems have linear constraints. Most of the existing approaches for constrained bilevel problems rely on value function-based approximate reformulations, which suffer from iss…
In recent years, decentralized bilevel optimization has gained significant attention thanks to its versatility in modeling a wide range of multi-agent learning problems, such as multi-agent reinforcement learning and multi-agent meta-learning. However, one unexplored and fundamental problem in this…
Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such a process will inevitably introduce mismatched pairs (i.e., Noisy Correspondence) due to i) the unavailable QA pairs in…
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales. However, they have inadvertently overlooked the potential of enhancing model r…
Efficiently retrieving FAQ questions that match users' intent is essential for online customer service. Existing methods aim to fully utilize the dynamic conversation context to enhance the semantic association between the user query and FAQ questions. However, the conversation context contains noi…
Automatic detection of machine anomaly remains challenging for machine learning. We believe the capability of generative adversarial network (GAN) suits the need of machine audio anomaly detection, yet rarely has this been investigated by previous work. In this paper, we propose AEGAN-AD, a totally…
Multi-objective optimization (MOO) and multi-task learning (MTL) have gained much popularity with prevalent use cases such as production model development of regression / classification / ranking models with MOO, and training deep learning models with MTL. Despite the long history of research in MOO…
Bilevel optimization has been shown to be a powerful framework for formulating multi-task machine learning problems, e.g., reinforcement learning (RL) and meta-learning, where the decision variables are coupled in both levels of the minimization problems. In practice, the learning tasks would be loc…
Implicit deep learning has received increasing attention recently due to the fact that it generalizes the recursive prediction rule of many commonly used neural network architectures. Its prediction rule is provided implicitly based on the solution of an equilibrium equation. Although a line of rece…
Present-day federated learning (FL) systems deployed over edge networks consists of a large number of workers with high degrees of heterogeneity in data and/or computing capabilities, which call for flexible worker participation in terms of timing, effort, data heterogeneity, etc. To satisfy the nee…
In this paper, we consider a new multi-armed bandit (MAB) framework motivated by three common complications in online recommender systems in practice: (i) the platform (learning agent) cannot sample an intended product directly and has to incentivize customers to select this product (e.g., promotion…
In this paper, we study the problem of jointly estimating the optical flow and scene flow from synchronized 2D and 3D data. Previous methods either employ a complex pipeline that splits the joint task into independent stages, or fuse 2D and 3D information in an "early-fusion" or "late-fusion" manner…
This work develops a novel framework for communication-efficient distributed learning where the models to be learned are overparameterized. We focus on a class of kernel learning problems (which includes the popular neural tangent kernel (NTK) learning as a special case) and propose a novel {\it mul…
In this paper, we establish the first finite-time convergence result of the actor-critic algorithm for fully decentralized multi-agent reinforcement learning (MARL) problems with average reward. In this problem, a set of $N$ agents work cooperatively to maximize the global average reward through in…
Although explainable artificial intelligence (XAI) has achieved remarkable developments in recent years, there are few efforts have been devoted to the following problems, namely, i) how to develop an explainable method that could explain the black-box in a model-agnostic way? and ii) how to improve…
Accurate absolute pose regression is one of the key challenges in robotics and computer vision. Existing direct regression methods suffer from two limitations. First, some noisy scenarios such as poor illumination conditions are likely to result in the uncertainty of pose estimation. Second, the out…
Fast and accurate pose estimation is essential for many robotic applications such as SLAM, manipulation, and 3D point registration. Existing solutions to this problem suffer from either high computation overhead due to the nonlinear features or accuracy loss due to linear approximation. In this pape…
Federated min-max learning has received increasing attention in recent years thanks to its wide range of applications in various learning paradigms. Similar to the conventional federated learning for empirical risk minimization problems, communication complexity also emerges as one of the most criti…
In recent years, federated learning (FL) has emerged as an important distributed machine learning paradigm to collaboratively learn a global model with multiple clients, while keeping data local and private. However, a key assumption in most existing works on FL algorithms' convergence analysis is t…
Federated learning (FL) is a distributed machine learning architecture that leverages a large number of workers to jointly learn a model with decentralized data. FL has received increasing attention in recent years thanks to its data privacy protection, communication efficiency and a linear speedup…
In this paper, we investigate a new multi-armed bandit (MAB) online learning model that considers real-world phenomena in many recommender systems: (i) the learning agent cannot pull the arms by itself and thus has to offer rewards to users to incentivize arm-pulling indirectly; and (ii) if users wi…
Multi-label text classification (MLTC) is an important task in natural language processing (NLP), which is appealing to researchers in both academia and industry. However, few of studies have been conducted on the relations among the labels. Most of existing methods tend to neglect the semantic info…
We propose a new randomized Bregman (block) coordinate descent (RBCD) method for minimizing a composite problem, where the objective function could be either convex or nonconvex, and the smooth part are freed from the global Lipschitz-continuous (partial) gradient assumption. Under the notion of rel…
Federated Learning (FL) refers to the paradigm where multiple worker nodes (WNs) build a joint model by using local data. Despite extensive research, for a generic non-convex FL problem, it is not clear, how to choose the WNs' and the server's update directions, the minibatch sizes, and the local up…
We study the sample complexity (i.e., the number of comparisons needed) bounds for actively ranking a set of $n$ items from multi-wise comparisons. Here, a multi-wise comparison takes $m$ items as input and returns a (noisy) result about the best item (the winner feedback) or the order of these item…
Cooperative multi-agent reinforcement learning (MARL) has received increasing attention in recent years and has found many scientific and engineering applications. However, a key challenge arising from many cooperative MARL algorithm designs (e.g., the actor-critic framework) is the policy evaluatio…
Untethered, wirelessly controlled microrobots have a broad application prospect from industrial area, to the bioengineering due to their small scales. In a narrow environment containing viscous resistance and friction fluid, rigid body may damage the micro-objects that the microrobots manipulate. In
This paper introduces a lightweight convolutional neural network, called FDDWNet, for real-time accurate semantic segmentation. In contrast to recent advances of lightweight networks that prefer to utilize shallow structure, FDDWNet makes an effort to design more deeper network architecture, while m…
Recently, there have been significant interests in studying the so-called "double-descent" of the generalization error of linear regression models under the overparameterized and overfitting regime, with the hope that such analysis may provide the first step towards understanding why overparameteriz…
Audio tagging aims to predict whether certain acoustic events occur in the audio clips. Due to the difficulty and huge cost of obtaining manually labeled data with high confidence, researchers begin to focus on audio tagging using a small set of manually-labeled data, and a larger set of noisy-label…
This paper studies the sample complexity (aka number of comparisons) bounds for the active best-$k$ items selection from pairwise comparisons. From a given set of items, the learner can make pairwise comparisons on every pair of items, and each comparison returns an independent noisy result about th…
With the rapid growth of internet finance and the booming of financial lending, the intelligent calling for debt collection in FinTech companies has driven increasing attention. Nowadays, the widely used intelligent calling system is based on dialogue flow, namely configuring the interaction flow wi…
This paper studies the problem of identifying any $k$ distinct arms among the top $\rho$ fraction (e.g., top 5%) of arms from a finite or infinite set with a probably approximately correct (PAC) tolerance $\epsilon$. We consider two cases: (i) when the threshold of the top arms’ expected rewards is…
We present Habitat, a platform for research in embodied artificial intelligence (AI). Habitat enables training embodied agents (virtual robots) in highly efficient photorealistic 3D simulation. Specifically, Habitat consists of: (i) Habitat-Sim: a flexible, high-performance 3D simulator with configu…
Most current state-of-the-art text-independent speaker verifi-cation systems take probabilistic linear discriminant analysis (PLDA) as their backend classifiers. The parameters of PL-DA are often estimated by maximizing the objective function, which focuses on increasing the value of log-likelihood…
Soft swimming microrobots that can be powered and guided remotely by magnetic field show greater potential for numerous applications than traditional rigid counterparts, due to their soft and flexible architectures. However, main challenges in closed-loop control remain to be overcome for the soft r
Proxy-word based out of vocabulary (OOV) keyword search has been proven to be quite effective in keyword search. In proxy-word based OOV keyword search, each OOV keyword is assigned several proxies and detections of the proxies are regarded as detections of the OOV keywords. However, the confidence…
Recently, a hybrid deep neural network/i-vector framework has been proved effective for speaker verification, where the DNN trained to predict tied-triphone states (senones) is used to produce frame alignments for sufficient statistics extraction. In this work, in order to better understand the impa…
Magnetically actuated microswimmers have shown great potentials in multiple application scenarios, attracting researchers to investigate their swimming characteristics and controlling methods. However, among those studies, only a small number of closed-loop control schemes have been applied, which i…
Exploiting sparseness in deep neural networks is an important method for reducing the computational cost. In this paper, we study neuron sparseness in deep neural networks for acoustic modeling. For the feed-forward stage, we only activate neurons whose input values are larger than a given threshold…
The OpenKWS14 keyword search evaluation is one of the most challenging and influential evaluations in the field of speech recognition. Its goal is to build a high-performance keyword search system for a minority language with limited training data in a short period of time. We present the system of…