62 accepted papers
Social Law Synthesis (SLS) in strategic environments is a novel multi-unit mechanism design problem, spanning modeling to computational challenges. We derive a method to specify the problem succinctly, reduce payment determination to allocation determination, and design an integer linear programming
Large Language Models (LLMs) often produce hallucinated outputs, which limit their reliability in high-stakes applications. Conformal prediction can provide guarantees on the correctness and factuality of LLM outputs, but existing approaches rely on the exchangeability assumption, which rarely holds…
The rapid advancement of Multimodal Large Language Models (MLLMs) has given rise to sophisticated autonomous agents capable of performing complex, human-like tasks across the web. However, this also introduces significant security risks, particularly from stealthy MLLM agents that can evade conventi
LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introduce silent errors where output quality silently degrades without any explicit error signals. Diagnosing silent errors is notoriously difficult due to …
The reliability of Large Language Models (LLMs) in high-stakes domains such as healthcare, law, and scientific discovery is often compromised by hallucinations. These failures typically stem from two sources: *data-driven hallucinations* and *reasoning-driven hallucinations*. However, existing detec…
Legged robots with egocentric forward-facing depth cameras can couple exteroception and proprioception to achieve robust forward agility on complex terrain. When these robots walk backward, the forward-only field of view provides no preview. Purely proprioceptive controllers can remain stable on mod…
The rapid advancement of large language models (LLMs) has resulted in increasingly sophisticated AI-generated content, posing significant challenges in distinguishing LLM-generated text from human-written language. Existing detection methods, primarily based on lexical heuristics or fine-tuned class
Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead
Large Language Models (LLMs) have achieved remarkable success in complex reasoning tasks, but their inference remains computationally inefficient. We observe a common failure mode in many prevalent LLMs, overthinking, where models generate verbose and tangential reasoning traces even for simple quer…
Despite rapid progress in auto-regressive video diffusion, we identify an emerging system–algorithm bottleneck that limits both deployability and generation quality: KV-cache memory. In auto-regressive video generation models, the KV-cache grows with generation history and quickly dominates GPU memo…
Traversing terrains with sparse footholds like legged animals presents a promising yet challenging task for quadruped robots, as it requires precise environmental perception and agile control to secure safe foot placement while maintaining dynamic stability. Model-based hierarchical controllers exce
Traversing terrains with sparse footholds like legged animals presents a promising yet challenging task for quadruped robots, as it requires precise environmental perception and agile control to secure safe foot placement while maintaining dynamic stability. Model-based hierarchical controllers exce…
Object segmentation is a critical prerequisite for robotic tasks such as grasping and assembly. While high accuracy and reliability typically require extensive real-world data, its collection and annotation are costly. Although synthetic data generated through physically-based rendering mitigates th
Predicting Click-Through Rates is a crucial function within recommendation and advertising platforms, as the output of CTR prediction determines the order of items shown to users. The Embedding and MLP paradigm has become a standard approach for industrial recommendation systems and has been widely…
Causal Inference (CI) plays a crucial role in building unbiased recommender systems. However, most current CI-based debiasing methods only pay attention on either popularity bias or conformity bias. This paper presents a Disentangled Counterfactual Reasoning framework to alleviate dual biases in rec…
The rapid advancement of large-language models (LLMs) has driven extensive research into parameter compression after training has been completed, yet compression during the training phase remains largely unexplored. In this work, we introduce Rate-Constrained Training (BackSlash), a novel training-t…
Recovering 3D geometry and textures of individual objects is crucial for many robotics applications, such as manipulation, pose estimation, and autonomous driving. However, decomposing a target object from a complex background is challenging. Most existing approaches rely on costly manual labels to
In the era of foundation models, Out-of-Distribution (OOD) problems, i.e., the data discrepancy between the training environments and testing environments, hinder AI generalization. Further, relational data like graphs disobeying the Independent and Identically Distributed (IID) condition makes the…
Knowledge Graph Embedding (KGE) methods have achieved great success in predicting missing links in knowledge graphs, a task also known as Knowledge Graph Completion (KGC). Under this task, the Reciprocal Rank (RR) of ground-truth items serve as a key indicator for evaluating the method’s performance…
The proliferation of open-sourced Large Language Models (LLMs) and diverse downstream tasks necessitates efficient model selection, given the impracticality of fine-tuning all candidates due to computational constraints. Despite the recent advances in LLM selection, a fundamental research question l…
Legged robots possess inherent advantages in traversing complex 3D terrains. However, previous work on lowcost quadruped robots with egocentric vision systems has been limited by a narrow front-facing view and exteroceptive noise, restricting omnidirectional mobility in such environments. While buil
Depthwise-separable convolution has emerged as a significant milestone in the lightweight development of Convolutional Neural Networks (CNNs) over the past decade. This technique consists of two key components: depthwise convolution, which captures spatial information, and pointwise convolution, whi…
Recently, camera localization has been widely adopted in autonomous robotic navigation due to its efficiency and convenience. However, autonomous navigation in unknown environments often suffers from scene ambiguity, environmental disturbances, and dynamic object transformation in camera localizatio
Quantum noise constitutes a fundamental obstacle to realizing practical quantum technologies. To address the pivotal challenge of identifying quantum systems least affected by noise, we introduce the purest quantum state identification, which can be used to improve the accuracy of quantum computatio…
Direct Preference Optimization (DPO) is broadly utilized for aligning Large Language Models (LLMs) with human values because of its flexibility. Despite its effectiveness, it has been observed that the capability of DPO to generate human-preferred response is limited and the results of DPO are far f…
Top-one recommendation with anonymous user behaviors, also known as session-based recommendation (SBR), faces challenges of top-one ranking and short anonymous sequences. To this end, we propose a novel objective that combines (1) a reciprocal rank loss to directly optimize the benchmark metric of t…
Transfer learning aims to transfer knowledge or information from a source domain to a relevant target domain. It involves two key challenges: distribution shifts and trustworthiness concerns. Having these challenges in mind, my research focuses on understanding transfer learning from the perspective…
In recent years, advanced U-like networks have demonstrated remarkable performance in medical image segmentation tasks. However, their drawbacks, including excessive parameters, high computational complexity, and slow inference speed, pose challenges for practical implementation in scenarios with li…
In federated learning, most existing robust aggregation rules (AGRs) combat Byzantine attacks in the IID setting, where client data is assumed to be independent and identically distributed. In this paper, we address label skewness, a more realistic and challenging non-IID setting, where each client…
The demand for 4D ( 3D+time ) SLAM system is increasingly urgent, especially for decision-making and scene understanding. However, most of the existing simultaneous localization and mapping ( SLAM ) systems primarily assume static environments. They fail to represent dynamic scenarios due to the cha…
This letter addresses the challenge of open-set instance segmentation (OSIS) which segments both known objects and unknown objects not seen in training, and thus is essential for enabling robots to safely work in the real world. Existing solutions adopt class-agnostic segmentation where all classes
The realm of multi-robot autonomous exploration tasks underscores the critical role of communication in coordinating group activities. This paper introduces an innovative decentralized multi-robot exploration algorithm, meticulously crafted to ensure unbroken communication within robotic groups, a c…
Global trajectory planning is crucial for long-range formation navigation tasks of multi-robot systems in efficiency improvement and energy saving, whose main challenges are the joint space constraints of the whole team and the long-range deployment. To overcome the above difficulties, we reformulat
This paper investigates the bit error rate (BER) minimum precoder design for an orthogonal time frequency space (OTFS)-based integrated sensing and communications (ISAC) system, which is considered as a promising technique for enabling future wireless networks. In particular, the BER minimum problem…
Hashing-based recommendation (HR) methods, whose core idea is mapping users and items into hamming space, are common practice to improve item retrieval efficiency. However, existing HR fails to align optimization objective (i.e., Bayesian Personalized Ranking) and evaluation metric (i.e., Recall), l…
Parkour presents a highly challenging task for legged robots, requiring them to traverse various terrains with agile and smooth locomotion. This necessitates comprehensive understanding of both the robot's own state and the surrounding terrain, despite the inherent unreliability of robot perception
In this paper, we propose a puncturing-based joint source channel coding scheme with a hierarchical down-sampling layer (PJSCC). The proposed hierarchical down-sampling layer fully exploits both frequency and spatial priors. Moreover, to achieve adaptive compression ratio control, PJSCC utilizes a s…
Rotary Position Embedding (RoPE) is an efficient position encoding approach and is widely utilized in numerous large language models (LLMs). Recently, a lot of methods have been put forward to further expand the context window based on RoPE. The core concept of those methods is to predefine or searc…
Current point cloud compression methods based on deep learning cannot guarantee that the reconstructed points are constrained to the surface, resulting in low reconstruction quality at low bitrates. Hence, this paper proposes an efficient deep learning-based point cloud geometry compression algorith…
Accurate state estimation plays a critical role in ensuring the robust control of humanoid robots, particularly in the context of learning-based control policies for legged robots. However, there is a notable gap in analytical research concerning estimations. Therefore, we endeavor to further unders…
Traditional geometric registration based estimation methods only exploit the CAD model implicitly, which leads to their dependence on observation quality and deficiency to occlusion.To address the problem,the letter proposes a bidirectional correspondence prediction network with a point-wise attenti
Transferable graph learning involves knowledge transferability from a source graph to a relevant target graph. The major challenge of transferable graph learning is the distribution shift between source and target graphs induced by individual node attributes and complex graph structures. To solve th…
Transfer learning refers to the transfer of knowledge or information from a relevant source domain to a target domain. However, most existing transfer learning theories and algorithms focus on IID tasks, where the source/target samples are assumed to be independent and identically distributed. Very…
In federated learning (FL), multiple clients collaborate to train machine learning models together while keeping their data decentralized. Through utilizing more training data, FL suffers from the potential negative transfer problem: the global FL model may even perform worse than the models trained…
Traditional Unsupervised Domain Adaptation (UDA) leverages the labeled source domain to tackle the learning tasks on the unlabeled target domain. It can be more challenging when a large domain gap exists between the source and the target domain. A more practical setting is to utilize a large-scale p…
Semi-supervised learning is a promising solution to mitigate data sparsity in review-aware rating regression (RaRR), but it bears the risk of learning with noisy pseudo-labelled data. In this paper, we propose a paradigm called co-training-teaching (CoT2), which integrates the merits of both co-trai…
With the recent advance of deep learning based object recognition and estimation, it is possible to consider object level SLAM where the pose of each object is estimated in the SLAM process. In this letter, based on a novel Lie group structure, a right invariant extended Kalman filter (RI-EKF) for o
Transfer learning refers to the transfer of knowledge or information from a relevant source task to a target task. However, most existing works assume both tasks are sampled from a stationary task distribution, thereby leading to the sub-optimal performance for dynamic tasks drawn from a non-station…
We address the efficiency problem of personalized ranking from implicit feedback by hashing users and items with binary codes, so that top-N recommendation can be fast executed in a Hamming space by bit operations. However, current hashing methods for top-N recommendation fail to align their learnin…
In this paper, we study the problem of domain adaptation regression, which learns a regressor for a target domain by leveraging the knowledge from a relevant source domain. We start by proposing a distribution-informed neural network, which aims to build distribution-aware relationship of inputs and…
The diversified top-k weight clique (DTKWC) search problem is an important generalization of the diversified top-k clique (DTKC) search problem with extensive applications, which extends the DTKC search problem by taking into account the weight of vertices. In this paper, we formulate DTKWC search p…
Current RGB-based 6D object pose estimation methods have achieved noticeable performance on datasets and real world applications. However, predicting 6D pose from single 2D image features is susceptible to disturbance from changing of environment and textureless or resemblant object surfaces. Hence,…
Legged robots, specifically quadruped robots, have good locomotion performance in complex and rugged terrain and are becoming widely used in field exploration and rescue missions. To achieve full autonomy in such scenarios, robots need not only accurate localization but also an accurate understandin…
The threat of data-poisoning backdoor attacks on learning algorithms typically comes from the labeled data. However, in deep semi-supervised learning (SSL), unknown threats mainly stem from the unlabeled data. In this paper, we propose a novel deep hidden backdoor (DeHiB) attack scheme for SSL-based…
Neural architecture search has attracted wide attentions in both academia and industry. To accelerate it, researchers proposed weight-sharing methods which first train a super-network to reuse computation among different operators, from which exponentially many sub-networks can be sampled and effici…
Opening a lock without vision sensors remains a challenge for robots. Inspired by the ability of a human to open a lock through touch and intuition, a peg-in-hole assembly method for recognizing the relative position and inclination angle of a hole is proposed. We use supervised learning to generate…
In this paper, we investigate the adversarial robustness of principal component analysis (PCA) algorithms. In the considered setup, there is a powerful adversary who can add a carefully designed data point to the original data matrix. The goal of the adversary is to maximize the distance between the…
Object 6D pose estimation is a fundamental task in many applications. Conventional methods solve the task by detecting and matching the keypoints, then estimating the pose. Recent efforts bringing deep learning into the problem mainly overcome the vulnerability of conventional methods to environment
In this paper, an approach for automatic peg-in-hole assembly is proposed. The task is divided into two main steps: searching phase and inserting phase. First, a multilayer perceptron network is designed to address the hole search problem and a hybrid force position controller is introduced to ensur…
We consider the problem of structure learning for linear causal models based on observational data. We treat models given by possibly cyclic mixed graphs, which allow for feedback loops and effects of latent confounders. Generalizing related work on bow-free acyclic graphs, we assume that the unde…
Recently, differentiable search methods have made major progress in reducing the computational costs of neural architecture search. However, these approaches often report lower accuracy in evaluating the searched architecture or transferring it to another dataset. This is arguably due to the large g…
This paper introduces a novel approach for sensing the bending deformation on soft robots by leveraging multicolor 3D printing. The measurement of deformation enables to complete the feedback loop of deformation control on soft actuators. The working principle of our approach is based on using compa…