149 accepted papers
Loss spikes remain a persistent obstacle in large-scale language model pretraining. While previous research has attempted to identify the root cause of loss spikes by investigating individual factors, we observe that, in practice, such spikes are typically triggered by the confluence of heterogeneou…
Probabilistic forecasting of multivariate time series is challenging due to non-stationarity, inter-variable dependencies, and distribution shifts. While recent diffusion and flow matching models have shown promise, they often ignore informative priors such as conditional means and covariances. In t…
3D multi-human reconstruction from single images holds significant potential for advancing AR/VR applications. While remarkable progress has been made in single-human reconstruction, existing methods face challenges when reconstructing multiple humans. These challenges include: (1) severe inter-occl
The evaluation of discourse-level translation in expert domains remains inadequate, despite its centrality to knowledge dissemination and cross-lingual scholarly communication. While these translations demand discourse-level coherence and strict terminological precision, current evaluation methods p…
This paper studies a fundamental yet often overlooked premise in evolutionary multi-view classification (EMVC): the impact of label noise on EMVC, such as distorting fitness landscapes shaped by individual fitness values (e.g., test accuracy). Traditional EMVC assumes training labels are noise-free,…
The powerful generalization of Vision-Language-Action (VLA) models is bottlenecked by their heavy reliance on massive, redundant, and unevenly valued datasets, hindering their widespread application. Existing model-centric optimization paths, such as model compression (which often leads to performan
Recently, reinforcement learning (RL) has been employed for improving generative image super-resolution (ISR) performance. However, the current efforts are focused on multi-step generative ISR, while one-step generative ISR remains underexplored due to its limited stochasticity. In addition, RL meth
During the video encoding process, the original spatial domain signal is first transformed into the frequency domain, followed by quantization and compression. As a result, the quality degradation in compressed videos primarily stems from distortions in the frequency domain information. However, exi
Generating human motion in complex 3D scenes from text is a challenging task with broad applications. However, existing methods often overlook realistic physical contact, resulting in visually plausible but physically unrealistic motion, e.g., penetration. To alleviate this, we propose IntentMotion,
Referring video object segmentation (RVOS) aims to identify, track and segment the objects in a video based on language descriptions, which has received great attention in recent years. However, existing datasets remain focus on short video clips within several seconds, with salient objects visible
With the rapid advancement of Large Language Models (LLMs) in code generation, human-AI interaction is evolving from static text responses to dynamic, interactive HTML-based applications, which we term **MiniApps**. These applications require models to not only render visual interfaces but also cons…
Diffusion-based motion generation has advanced rapidly, but current methods still struggle with long-horizon consistency, style control, and multi-condition guidance. A major reason is the fused-conditioning design, where semantic, stylistic, and temporal signals share a single pathway, causing inte
Text-to-motion generation aims to generate 3D human motions that are tightly aligned with the input text while remaining physically plausible and rich in fine-grained detail. Although recent approaches can produce complex and natural movements, they usually operate at only one temporal scale, which
Recently, diffusion models have achieved a great performance with a small dataset of size $n$ and a fast optimization process. Despite the impressive performance, the estimation error suffers from the curse of dimensionality $n^{-1/D}$, where $D$ is the data dimension. Since images are usually a un…
Is monolithic scaling the only path to AGI? This paper challenges the dogma that purely scaling a single model is enough to achieve universal super-intelligence. Instead, we identify Agentic AI as the necessary evolution for handling complex, real-world task distributions to achieve AGI in the human…
Offline-to-online reinforcement learning harnesses the stability of offline pretraining and the flexibility of online fine-tuning. A key challenge lies in the non-stationary distribution shift between offline datasets and the evolving online policy. Common approaches often rely on static mixing rati
Understanding complex surgical scenes requires recognizing multiple interdependent entities--such as instruments, actions, and targets--and maintaining their relational consistency across time. Existing surgical triplet recognition methods struggle to jointly model intra-frame label dependencies and
The collaboration between humans and robots is critical in many robotic applications, especially in those requiring physical human-robot interaction (pHRI). Previous research in pHRI has largely focused on robotic manipulators, employing impedance or admittance control to maintain operational safety
Diffusion models are widely used for high-quality generation, but their performance is sensitive to the accuracy of the estimated score. We first develop our main bounds in a Gaussian-mixture setting, where the score admits a closed-form structure and the score Hessian can be controlled explicitly, …
The two-sided matching market problem has attracted extensive research in both computer science and economics due to its wide-ranging applications in multiple fields. In various online matching platforms, market participants often have unclear preferences. As a result, a growing area of research foc
In the domain of merchant-oriented risk control decisions within e-commerce, balancing the effectiveness of risk management with merchant satisfaction remains a critical challenge. Strict risk control strategies, while effectively mitigating risks, often lead to increased merchant dissatisfaction. C…
Dual-arm robots possess exceptional collaborative capabilities and versatility, demonstrating broad application prospects across various fields. As a significant research area for dual-arm robots, the requirements for coordinated motion control are gradually increasing. In practical applications, ro
A rich line of recent works studies how participants in matching markets learn their unknown preferences through iterative interactions with each other. The two sides of participants in the market can be respectively formulated as players and arms in the bandit problem. To ensure market stability, t…
Chain-of-Thought (CoT) has been a widely adopted prompting method, eliciting impressive reasoning abilities of Large Language Models (LLMs). Inspired by the sequential thought structure of CoT, a number of Chain-of-X (CoX) methods have been developed to address challenges across diverse domains and…
Speech-driven 3D talking face method should offer both accurate lip synchronization and controllable expressions. Previous methods solely adopt discrete emotion labels to globally control expressions throughout sequences while limiting flexible fine-grained facial control within the spatiotemporal d…
Conditional independence (CI) testing is a fundamental task in modern statistics and machine learning. The conditional randomization test (CRT) was recently introduced to test whether two random variables, X and Y, are conditionally independent given a potentially high-dimensional set of random vari…
This paper introduces the Convex Potential Mirror Langevin Algorithm (CPMLA), a novel method to improve sampling efficiency for Energy-Based Models (EBMs). CPMLA uses mirror Langevin dynamics with a convex potential flow as a dynamic mirror map for EBM sampling. This dynamic mirror map enables targe…
As virtual experiences grow in popularity, the demand for realistic, personalized, and animatable human avatars increases. Traditional methods, relying on fixed templates, often produce costly avatars that lack expressiveness and realism. To overcome these challenges, we introduce Controllable Avata…
Leveraging the powerful generation capability of large-scale pretrained text-to-image models, training-free methods have demonstrated impressive image editing results. Conventional diffusion-based methods, as well as recent rectified flow (RF)-based methods, typically reverse synthesis trajectories…
Benefiting from pre-trained text-to-image (T2I) diffusion models, real-world image super-resolution (Real-ISR) methods can synthesize rich and realistic details. However, due to the inherent stochasticity of T2I models, different noise inputs often lead to outputs with varying perceptual quality. Al…
This work demonstrates how autonomously learning aspects of robotic operation from sparsely-labeled, real-world data of deployed, engineered solutions at industrial scale can provide with solutions that achieve improved performance. Specifically, it focuses on multi-suction robot picking and perfor…
The application of Large Vision-Language Models (LVLMs) for analyzing images and videos is an exciting and rapidly evolving field. In recent years, we've seen significant growth in high-quality image-text datasets for fine-tuning image understanding, but there is still a lack of comparable datasets…
Second-order Online Kernel Learning (OKL) has attracted considerable research interest due to its promising predictive performance in streaming environments. However, existing second-order OKL approaches suffer from at least quadratic time complexity with respect to the pre-set budget, rendering the
Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine structures, such as small characters and textures, due to the aggre…
Monocular Semantic Scene Completion (MonoSSC) reconstructs and interprets 3D environments from a single image, enabling diverse real-world applications. However, existing methods are often constrained by the local receptive field of Convolutional Neural Networks (CNNs), making it challenging to hand…
Complex Table Question Answering involves providing accurate answers to specific questions based on intricate tables that exhibit complex layouts and flexible header locations. Despite considerable progress having been made in the LLM era, the reasoning processes of existing methods are often implic…
Urban intersections with diverse vehicle types, from small cars to large semi-trailers, pose significant challenges for traffic control. This study explores how robot vehicles (RVs) can enhance heterogeneous traffic flow, particularly at unsignalized intersections where traditional methods fail duri
Consistency models, a new class of one-step generative models, have shown competitive performance with multi-step diffusion models. The most challenging part of consistency models is the training process, which discretizes the continuous diffusion process into $K$ steps and trains a one-step mapping…
Traffic congestion remains a significant challenge in modern urban networks. Autonomous driving technologies have emerged as a potential solution. Among traffic control methods, reinforcement learning has shown superior performance over traffic signals in various scenarios. However, prior research h
We investigate learning approximate Nash equilibrium (NE) policy profiles in two-player zero-sum imperfect information extensive-form games (IIEFGs) with last-iterate convergence guarantees. Existing algorithms either rely on full-information feedback or provide only asymptotic convergence rates. In…
Reinforcement learning (RL) for collaborative agents capable of cooperating with humans to accomplish tasks has long been a central goal in the RL community. While prior approaches have made progress in adapting collaborative agents to diverse human partners, they often focus solely on optimizing ta…
Slip detection and control is critical to achieving stable grasping in robotics. However, accurate and robust slip detection and control remains a challenging task. This letter proposes a learning framework with contrastive learning and feature alignment to improve the accuracy of end-to-end slip de
In this work, we study the logarithmic regret for reinforcement learning (RL) with linear function approximation and adversarial corruptions, in the formulation of linear Markov decision processes (MDPs). Specifically, we consider the case where there exist adversarial corruptions over the reward fu…
This paper presents MetricGrids, a novel grid-based neural representation that combines elementary metric grids in various metric spaces to approximate complex nonlinear signals. While grid-based representations are widely adopted for their efficiency and scalability, the existing feature grids with…
Multi-player multi-armed bandits (MP-MAB) have been extensively studied due to their application in cognitive radio networks. In this setting, multiple players simultaneously select arms and instantly receive feedback. However, in realistic decentralized networks, feedback is often delayed due to se
Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated da…
Reinforcement learning (RL) has shown remarkable success in training agents to achieve high-performing policies, particularly in domains like Game AI where simulation environments enable efficient interactions. However, despite their success in maximizing these returns, such online-trained policies…
Multi-player multi-armed bandit (MP-MAB) has been widely studied owing to its diverse applications across numerous domains. We consider an MP-MAB problem where $N$ players compete for $K$ arms in $T$ rounds. The reward distributions are heterogeneous where each player has a different expected reward…
Point cloud registration is a fundamental task in 3D vision, which plays an important role in various fields but faces challenges in geometrically weak or repetitive scenes. Traditional geometric-based methods struggle in these cases, while recent multimodal approaches improve robustness in weak sce
Federated Distillation (FedKD) relies on lightweight knowledge carriers like logits for efficient client-server communication. Although logit-based methods have demonstrated promise in addressing statistical and architectural heterogeneity in federated learning (FL), current approaches remain const…
Low-precision training is considered an effective strategy for reducing both training and downstream inference costs. Previous scaling laws for precision mainly focus on integer quantization, which pay less attention to the constituents in floating-point (FP) quantization, and thus cannot well fit t…
Predicting future video frames is essential for decision-making systems, yet RGB frames alone often lack the information needed to fully capture the underlying complexities of the real world. To address this limitation, we propose a multi-modal framework for Synchronous Video Prediction (SyncVP) tha…
Recently, variance exploding (VE) diffusion models have achieved state-of-the-art (SOTA) performance in two implementations: (1) the SDE-based implementation and (2) the probability flow ODE (PFODE) implementation. However, only a few works analyze the iteration complexity of VE-based models, and mo…
Despite significant advances in learning imperfect information extensive-form games (IIEFGs), most existing theoretical guarantees are limited to IIEFGs in the tabular case. To permit efficient learning of large-scale IIEFGs, we take the first step in studying two-player zero-sum IIEFGs with linear
Large language models (LLMs) are typically pre-trained on massive-scale data and then fine-tuned on specialized datasets for downstream applications. Determining whether a model has been fine-tuned on a particular dataset is crucial for dataset owners to protect their copyrights. However, there is a…
In Federated Learning (FL) the issue of statistical data heterogeneity has been a significant challenge to the field's ongoing development. This problem is further exacerbated when clients' data vary in modalities. In response to these issues of statistical heterogeneity and modality incompatibility…
Large language models (LLMs) often generate biased outputs containing offensive, toxic, or stereotypical text. Existing LLM alignment methods such as reinforcement learning from human feedback (RLHF) alleviate biases primarily based on reward signals from current model outputs without considering th…
Computer animation's quest to bridge content and style has historically been a challenging venture with previous efforts often leaning toward one at the expense of the other. This paper tackles the inherent challenge of content-style duality ensuring a harmonious fusion where the core narrative of t…
Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks, aided by techniques like chain-of-thought prompting that elicits verbalized reasoning. However, LLMs often generate text with obvious mistakes and contradictions, raising doubts about their ability to…
We introduce a novel framework of combinatorial multi-armed bandits (CMAB) with multivariant and probabilistically triggering arms (CMAB-MT), where the outcome of each arm is a $d$-dimensional multivariant random variable and the feedback follows a general arm triggering process. Compared with exist…
Under-display camera (UDC) systems are the foundation of full-screen display devices in which the lens mounts under the display. The pixel array of light-emitting diodes used for display diffracts and attenuates incident light, causing various degradations as the light intensity changes. Unlike gene…
Few-shot continual learning (FSCL) is a challenging setting as it requires models to learn new knowledge with a few examples over time, and fast adapt to new tasks without forgetting previous knowledge. Prompt-tuning, as an efficient learning approach for language models, has shown competitive perfo…
While diffusion models have demonstrated impressive performance, there is a growing need for generating samples tailored to specific user-defined concepts. The customized requirements promote the development of few-shot diffusion models, which use limited $n_{ta}$ target samples to fine-tune a pre-t…
To date the quest to rapidly and effectively produce human-object interaction (HOI) animations directly from textual descriptions stands at the forefront of computer vision research. The underlying challenge demands both a discriminating interpretation of language and a comprehensive physics-centric…
Large Language Models (LLMs) have shown propensity to generate hallucinated outputs, i.e., texts that are factually incorrect or unsupported. Existing methods for alleviating hallucinations typically require costly human annotations to identify and correct hallucinations in LLM outputs. Moreover, mo…
A rich line of works study the bandit learning problem in two-sided matching markets, where one side of market participants (players) are uncertain about their preferences and hope to find a stable matching during iterative matchings with the other side (arms). The state-of-the-art analysis shows th…
Two-sided matching markets have been widely studied in the literature due to their rich applications. Since participants are usually uncertain about their preferences, online algorithms have recently been adopted to learn them through iterative interactions. An existing work initiates the study of t…
Load transportation (LT) using quadrotor unmanned aerial vehicles (UAVs) has drawn increasing interest from the robotics community in recent years. Two main alternative load carrying modalities have been investigated. Namely, the load is either rigidly attached to the body of the quadrotor (LT-RA),
Transformer-based neural sequence models exhibit a remarkable ability to perform in-context learning. Given some training examples, a pre-trained model can make accurate predictions on an unseen input. This paper studies why transformers can learn different types of function classes in-context. We f…
Masked prediction has emerged as a promising pretraining paradigm in offline reinforcement learning (RL) due to its versatile masking schemes, enabling flexible inference across various downstream tasks with a unified model. Despite the versatility of masked prediction, it remains unclear how to bal…
Variance exploding (VE) based diffusion models, an important class of diffusion models, have shown state-of-the-art (SOTA) performance. However, only a few theoretical works analyze VE-based models, and those works suffer from a worse forward convergence rate $1/\text{poly}(T)$ than the $\exp{(-T)}$…
Eliminating image blur produced by various kinds of motion has been a challenging problem. Dominant approaches rely heavily on model capacity to remove blurring by reconstructing residual from blurry observation in feature space. These practices not only prevent the capture of spatially variable mot…
Proximal policy optimization (PPO) has gained popularity in reinforcement learning (RL). Its PPO-Clip variant is one the most frequently implemented algorithms and is one of the first-to-try algorithms in RL tasks. This variant uses a clipped surrogate objective function not typically found in other…
"The scarcity of large-scale 3D-text paired data poses a great challenge on open vocabulary 3D scene understanding, and hence it is popular to leverage internet-scale 2D data and transfer their open vocabulary capabilities to 3D models through knowledge distillation. However, the existing distillati…
Owe to the powerful generative priors the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However as a consequence of the heavy quality degradation of input low-resolution (LR) images the destruction of local…
Large language models (LLMs) are known for their exceptional performance in natural language processing, making them highly effective in many human life-related tasks. The attention mechanism in the Transformer architecture is a critical component of LLMs, as it allows the model to selectively focus…
In single-incision laparoscopic surgery (SILS), magnetic anchoring and guidance system (MAGS) is a promising technique to prevent clutter in the surgical workspace and provide a larger vision field. Existing camera designs mainly rely on rigid structure design, resulting in risks of losing magnetic…
Despite the recent advances in unified image segmentation (IS) developing a unified video segmentation (VS) model remains a challenge. This is mainly because generic category-specified VS tasks need to detect all objects and track them across consecutive frames while prompt-guided VS tasks require r…
Online learning to rank (OLTR) is a sequential decision-making problem where a learning agent selects an ordered list of items and receives feedback through user clicks. Although potential attacks against OLTR algorithms may cause serious losses in real-world applications, there is limited knowledge…
Communication lays the foundation for cooperation in human society and in multi-agent reinforcement learning (MARL). Humans also desire to maintain their privacy when communicating with others, yet such privacy concern has not been considered in existing works in MARL. We propose the differentially…
Automating warehouse operations can reduce logistics overhead costs, ultimately driving down the final price for consumers, increasing the speed of delivery, and enhancing the resiliency to workforce fluctuations. The past few years have seen increased interest in automating such repeated tasks but…
The representative instance segmentation methods mostly segment different object instances with a mask of the fixed resolution, e.g., 28x 28 grid. However, a low-resolution mask loses rich details, while a high-resolution mask incurs quadratic computation overhead. It is a challenging task to predic…
Conversational contextual bandits elicit user preferences by occasionally querying for explicit feedback on key-terms to accelerate learning. However, there are aspects of existing approaches which limit their performance. First, information gained from key-term-level conversations and arm-level re…
Many weakly supervised semantic segmentation (WSSS) methods employ the class activation map (CAM) to generate the initial segmentation results. However, CAM often fails to distinguish the foreground from its co-occurred background (e.g., train and railroad), resulting in inaccurate activation from t…
Under-display camera (UDC) systems remove the screen notch for bezel-free displays and provide a better interactive experience. The main challenge is that the pixel array of light-emitting diodes used for display diffracts and attenuates the incident light, leading to complex degradation. Existing m…
We study the problem of composition learning for image retrieval, for which we learn to retrieve target images with search queries in the form of a composition of a reference image and a modification text that describes desired modifications of the image. Existing models of composition learning for…
Recent research in offline reinforcement learning (RL) has demonstrated that return-conditioned supervised learning is a powerful paradigm for decision-making problems. While promising, return conditioning is limited to training data labeled with rewards and therefore faces challenges in learning fr…
Due to the difficulty in collecting large-scale and perfectly aligned paired training data for Under-Display Camera (UDC) image restoration, previous methods resort to monitor-based image systems or simulation-based methods, sacrificing the realness of the data and introducing domain gaps. In this w…
Soft prompt tuning achieves superior performances across a wide range of few-shot tasks. However, the performances of prompt tuning can be highly sensitive to the initialization of the prompts. We have also empirically observed that conventional prompt tuning methods cannot encode and learn sufficie…
Conditional independence (CI) testing is a fundamental task in statistics and machine learning, but its effectiveness is hindered by the challenges posed by high-dimensional conditioning variables and limited data samples. This article introduces a novel testing approach to address these challenges…
We study reinforcement learning (RL) with linear function approximation, unknown transition, and adversarial losses in the bandit feedback setting. Specifically, the unknown transition probability function is a linear mixture model \citep{AyoubJSWY20,ZhouGS21,HeZG22} with a given feature mapping, an…
In this work, we study the low-rank MDPs with adversarially changed losses in the full-information feedback setting. In particular, the unknown transition probability kernel admits a low-rank matrix decomposition \citep{REPUCB22}, and the loss functions may change adversarially but are revealed to t…
While impressive progress has been achieved, video instance segmentation (VIS) methods with per-clip input often fail on challenging videos with occluded objects and crowded scenes. This is mainly because instance queries in these methods cannot encode well the discriminative embeddings of instances…
Point cloud sequences are commonly used to accurately detect 3D objects in applications such as autonomous driving. Current top-performing multi-frame detectors mostly follow a Detect-and-Fuse framework, which extracts features from each frame of the sequence and fuses them to detect the objects in…
The conditional randomization test (CRT) was recently proposed to test whether two random variables X and Y are conditionally independent given random variables Z. The CRT assumes that the conditional distribution of X given Z is known under the null hypothesis and then it is compared to the distrib…
One-to-one (o2o) label assignment plays a key role for transformer based end-to-end detection, and it has been recently introduced in fully convolutional detectors for lightweight end-to-end dense detection. However, o2o can largely degrade the feature learning performance due to the limited number…
The contextual linear bandit is an important online learning problem where given arm features, a learning agent selects an arm at each round to maximize the cumulative rewards in the long run. A line of works, called the clustering of bandits (CB), utilize the collaborative effect over user preferen…
In real-world online web systems, multiple users usually arrive sequentially into the system. For applications like click fraud and fake reviews, some users can maliciously perform corrupted (disrupted) behaviors to trick the system. Therefore, it is crucial to design efficient online learning algor…
Weakly supervised instance segmentation using only bounding box annotations has recently attracted much research attention. Most of the current efforts leverage low-level image features as extra supervision without explicitly exploiting the high-level semantic information of the objects, which will…
The intelligent synthesis/generation of daily-life motion sequences is fundamental and urgently needed for many VR/metaverse-related applications. However, existing approaches commonly focus on monotonic motion generation (e.g., walking, jumping, etc.) based on single instruction-like text, which is…
We show that a stochastic version of optimistic mirror descent (OMD), a variant of mirror descent with recency bias, converges fast in general games. More specifically, with our algorithm, the individual regret of each player vanishes at a speed of $O(1/T^{3/4})$ and the sum of all players' regret v…
Self-supervised learning (SSL) has empirically shown its data representation learnability in many downstream tasks. There are only a few theoretical works on data representation learnability, and many of those focus on final data representation, treating the nonlinear neural network as a ``black box…
Label assignment (LA), which aims to assign each training sample a positive (pos) and a negative (neg) loss weight, plays an important role in object detection. Existing LA methods mostly focus on the design of pos weighting function, while the neg weight is directly derived from the pos weight. Suc…
Deep learning based compressed video quality enhancement has raised lots of interest recently. To explore the information over multiple frames, deformable convolution has been used for temporal alignment. However, in the existing methods, the deformable convolution is used in a relatively naïve way,…
This paper studies differential privacy (DP) and local differential privacy (LDP) in cascading bandits. Under DP, we propose a UCB-based algorithm which guarantees ϵ-indistinguishability and a regret of $\mathcal{O}\left( {{{\left( {\frac{{\log T}}{ \in }} \right)}^{1 + \xi }}} \right)$ for an arbit…
Domain adaptive semantic segmentation aims to learn a model with the supervision of source domain data, and produce satisfactory dense predictions on unlabeled target domain. One popular solution to this challenging task is self-training, which selects high-scoring predictions on target samples as p…
Supervised training of existing deep learning models for sequence labeling relies on large scale labeled datasets. Such datasets are generally created with crowd-source labeling. However, crowd-source labeling for tasks of sequence labeling can be expensive and time-consuming. Further, crowd-source…
Large pretrained multilingual language models (ML-LMs) have shown remarkable capabilities of zero-shot cross-lingual transfer, without direct cross-lingual supervision. While these results are promising, follow-up works found that, within the multilingual embedding spaces, there exists strong langua…
Citing and describing related literature are crucial to scientific writing. Many existing approaches show encouraging performance in citation recommendation, but are unable to accomplish the more challenging and onerous task of citation text generation. In this paper, we propose a novel disentangled…
Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and dramatically improve the recommendation quality. Owing to the increasing applica…
Recently, with the rise of high dynamic range (HDR) display devices, there is a great demand to transfer traditional low dynamic range (LDR) images into HDR versions. The key to success is how to solve the many-to-many mapping problem. However, the existing approaches either do not consider constrai…
This paper concerns the problem of multi-object tracking based on the min-cost flow (MCF) formulation, which is conventionally studied as an instance of linear program. Given its computationally tractable inference, the success of MCF tracking largely relies on the learned cost function of underlyin…
Motivated by problems of ranking with partial information, we introduce a variant of the cascading bandit model that considers flexible length sequences with varying rewards and losses. We formulate two generative models for this problem within the generalized linear setting, and design and analyze…
We present PU-Refiner, a generative adversarial network for point cloud upsampling. The generator of our network includes a coarse feature expansion module to create coarse upsampled features, a geometry generation module to regress a coarse point cloud from the coarse upsampled features, and a prog…
Wearable biofeedback systems (WBS) have been proposed to aid physical rehabilitation of individuals with motor impairments. Due to significant inter- and intra-individual differences, the effectiveness of a given biofeedback strategy may vary for different users and across therapeutic sessions, as a
Online learning to rank (OLTR) interactively learns to choose lists of items from a large collection based on certain click models that describe users' click behaviors. Most recent works for this problem focus on the stochastic environment where the item attractiveness is assumed to be invariant dur…
The problem of online learning with graph feedback has been extensively studied in the literature due to its generality and potential to model various learning tasks. Existing works mainly study the adversarial and stochastic feedback separately. If the prior knowledge of the feedback mechanism is u…
The problem of two-sided matching markets has a wide range of real-world applications and has been extensively studied in the literature. A line of recent works have focused on the problem setting where the preferences of one-side market participants are unknown a priori and are learned by iterative…
During the past decades, industrial robot arms have been widely adopted in various fields, like aerospace and medical care. However, an uncalibrated industrial robot arm suffers from its high absolute positioning error, which tremendously restricts its application in high-precision intelligent manuf
Transformer has demonstrated promising performance in many 2D vision tasks. However, it is cumbersome to apply the self-attention underlying transformer on large-scale point cloud data because point cloud is a long sequence and unevenly distributed in 3D space. To solve this issue, existing methods…
Unsupervised domain adaption (UDA) is a promising solution to enhance the generalization ability of a model from a source domain to a target domain without manually annotating labels for target data. Recent works in cross-domain object detection mostly resort to adversarial feature adaptation to mat…
In this paper, the circle formation control problem is addressed for a group of cooperative underactuated fish-like robots involving unknown nonlinear dynamics and disturbances. Based on the reinforcement learning and cognitive consistency theory, we propose a decentralized controller without the kn…
Prior knowledge integration helps identify semantic entities and their relationships in a graphical representation, however, its meaningful abstraction and intervention remain elusive. This paper advocates a knowledge-inspired 3D scene graph prediction method solely based on point clouds. At the mat…
In this paper, we devise a novel semantic completion network, called point cloud semantic scene completion network (PCSSC-Net), for indoor scenes solely based on point clouds. Existing point cloud completion networks still suffer from their inability of fully recovering complex structures and conten…
Recent development of Under-Display Camera (UDC) systems provides a true bezel-less and notch-free viewing experience on smartphones (and TV, laptops, tablets), while allowing images to be captured from the selfie camera embedded underneath. In a typical UDC system, the microstructure of the semi-tr…
The vast majority of community detection algorithms assume that the networks are totally observed. However, in reality many networks cannot be fully observed. On such network is edges-missing network, where some relationships (edges) between two entities are missing. Recently, several works have bee…
Modern one-stage video instance segmentation networks suffer from two limitations. First, convolutional features are neither aligned with anchor boxes nor with ground-truth bounding boxes, reducing the mask sensitivity to spatial location. Second, a video is directly divided into individual frames f…
Thompson sampling (TS) has attracted a lot of interest in the bandit area. It was introduced in the 1930s but has not been theoretically proven until recent years. All of its analysis in the combinatorial multi-armed bandit (CMAB) setting requires an exact oracle to provide optimal solutions with an…
The bandit problem with graph feedback, proposed in [Mannor and Shamir, NeurIPS 2011], is modeled by a directed graph $G=(V,E)$ where $V$ is the collection of bandit arms, and once an arm is triggered, all its incident arms are observed. A fundamental question is how the structure of the graph affec…
The 2D convolutional (Conv2d) layer is the fundamental element to a deep convolutional neural network (CNN). Despite the great success of CNN, the conventional Conv2d is still limited in effectively reducing the spatial and channel-wise redundancy of features. In this paper, we propose to mitigate t…
Online influence maximization (OIM) is a popular problem in social networks to learn influence propagation model parameters and maximize the influence spread at the same time. Most previous studies focus on the independent cascade (IC) model under the edge-level feedback. In this paper, we address O…
We analyze the Gambler's problem, a simple reinforcement learning problem where the gambler has the chance to double or lose their bets until the target is reached. This is an early example introduced in the reinforcement learning textbook by Sutton and Barto (2018), where they mention an interestin…
The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be \emph{$\epsilon$-adversarially robust} (AR); that is, to require the model not to change predict…
In robot-assisted rehabilitation, assist-as-needed (AAN) controllers have been proposed to promote subjects’ active participation, which is thought to lead to better training outcomes. Most of these AAN controllers require a patient-specific manual tuning of the parameters defining the underlying fo…
The design of anchors is critical to the performance of one-stage detectors. Recently, the anchor refinement module (ARM) has been proposed to adjust the initialization of default anchors, providing the detector a better anchor reference. However, this module brings another problem: all pixels at a…
This paper proposes a manipulability optimization control of a 7-DoF robot manipulator for Robot-Assisted Minimally Invasive Surgery (RAMIS), which at the same time guarantees a Remote Center of Motion (RCM). The first degree of redundancy of the manipulator is used to achieve an RCM constraint, the…
We introduce a new model for online ranking in which the click probability factors into an examination and attractiveness function and the attractiveness function is a linear function of a feature vector and an unknown parameter. Only relatively mild assumptions are made on the examination function.…
In this paper, a new adaptive tracking controller with learning ability is proposed for fully-constrained cable-driven parallel robots (CDPRs). For these systems, the necessity of maintaining positive and bounded tensions in all cables while coping with disturbances represents a critical control req…
Recurrent Neural Networks (RNNs) demonstrated advantages on control precision, system robustness and computational efficiency, and have been widely applied to redundant manipulator control optimization. Existing RNN control schemes locally optimize trajectories and are efficient and reliable on obst…
Due to the limitations of the robotic sensors, during a robotic manipulation task, the acquisition of the object's state can be unreliable and noisy. Combining an accurate model of multi-body dynamic system with Bayesian filtering methods has been shown to be able to filter out noise from the object…
Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and exploding problems and hard to learn long-term patterns. Long short-term memory (LSTM) and gated recurrent unit (GRU) were…
Online learning to rank is a sequential decision-making problem where in each round the learning agent chooses a list of items and receives feedback in the form of clicks from the user. Many sample-efficient algorithms have been proposed for this problem that assume a specific click model connecting…
Surgical robot research is driven by the desire of improving surgical outcomes. This paper proposed a Recurrent Neural Network based controller to address two problems: 1) improving control precision, 2) increasing adaptiveness for robot motion (explained in Section I). RNN was adopted in this work…
We investigate a novel cluster-of-bandit algorithm CAB for collaborative recommendation tasks that implements the underlying feedback sharing mechanism by estimating user neighborhoods in a context-dependent manner. CAB makes sharp departures from the state of the art by incorporating collaborative…
A rail yard is a dangerous environment for humans to work in, primarily because of the possibility of serious injuries associated with moving rail cars, locomotives, and uneven terrain. For robots to act autonomously in such environments, there exists a need for a perception system that can act reli…
We propose the contextual combinatorial cascading bandits, a combinatorial online learning game, where at each time step a learning agent is given a set of contextual information, then selects a list of items, and observes stochastic outcomes of a prefix in the selected items by some stopping criter…
We provide two distributed confidence ball algorithms for solving linear bandit problems in peer to peer networks with limited communication capabilities. For the first, we assume that all the peers are solving the same linear bandit problem, and prove that our algorithm achieves the optimal asympto…
We study the contact-aware state estimation (CASE) problem, i.e., the problem of estimating the state of an object while it is being actively manipulated by a robot. Several researchers have developed particle filters for this problem. They estimate the state (pose and velocity) of manipulated objec…
Dynamic system states estimation, such as object pose and contact states estimation, is essential for robots to perform manipulation tasks. In order to make accurate estimation, the state transition model needs to be physically correct. Complementarity formulations of the dynamics are widely used fo…