73 accepted papers
Navigating Linked Multi-Component Robotic Systems (L-MCRS)---robot pairs tethered by passive flexible hoses---through dynamic pedestrian environments is fundamentally harder than rigid multi-robot coordination, as the uncontrollable hose creates a variable-geometry collision footprint spanning 118 p…
Recent reinforcement-learning frameworks for visual perception policy usually incorporate intermediate reasoning chains expressed in natural language. Empirical observations indicate that such purely linguistic intermediate reasoning often reduces performance on perception tasks. We argue that the c…
Diagrams represent a form of visual language that encodes abstract concepts and relationships through structured symbols and their spatial arrangements. Unlike natural images, they are inherently symbolic, and entirely artificial. They thus pose unique challenges for Multimodal Large Language Model…
Monocular 3D object detection from a single RGB image remains challenging due to two fundamental challenges: the ill-posed nature of 3D localization, where multiple plausible configurations can correspond to the same 2D observation, and unreliable confidence estimation that fails to reflect true loc
Reinforcement learning with verifiable rewards has shown notable effectiveness in enhancing large language models (LLMs) reasoning performance, especially in mathematics tasks. However, such improvements often come with reduced outcome diversity, where the model concentrates probability mass on a na…
Spoken named entity recognition (NER) aims to identify named entities from speech, playing an important role in speech processing. New named entities appear every day, however, annotating their Spoken NER data is costly. In this paper, we demonstrate that existing Spoken NER systems perform poorly w…
Pancreatic NEuroendocrine Tumors (pNETs) are very rare endocrine neoplasms that account for less than 5% of all pancreatic malignancies, with an incidence of only 1–1.5 cases per 100,000. Early detection of pNETs is critical for improving patient survival, but the rarity of pNETs makes segmenting th…
Existing video captioning methods merely provide shallow or simplistic representations of object behaviors, resulting in superficial and ambiguous descriptions. However, object behavior is dynamic and complex. To comprehensively capture the essence of object behavior, we propose a dynamic action sem…
Palms are ecologically and economically indicators of tropical forest health, biodiversity, and human impact that support local economies and global forest product supply chains. While palm detection in plantations is well-studied, efforts to map naturally occurring palms in dense forests remain lim
This paper introduces a Dual Evaluation Framework to comprehensively assess the multilingual capabilities of LLMs. By decomposing the evaluation along the dimensions of linguistic medium and cultural context, this framework enables a nuanced analysis of LLMs’ ability to process questions within both…
Document-level context is crucial for handling discourse challenges in text-to-text document-level machine translation (MT). Despite the increased discourse challenges introduced by noise from automatic speech recognition (ASR), the integration of document-level context in speech translation (ST) re…
Knowledge utilization is a critical aspect of LLMs, and understanding how they adapt to evolving knowledge is essential for their effective deployment. However, existing benchmarks are predominantly static, failing to capture the evolving nature of LLMs and knowledge, leading to inaccuracies and vul…
Multi-instance partial-label learning (MIPL) is a paradigm where each training example is encapsulated as a multi-instance bag associated with the candidate label set, which includes one true label and several false positives. Current MIPL algorithms typically assume that all instances are independ…
Robotic manipulation in high-precision tasks is essential for numerous industrial and real-world applications where accuracy and speed are required. Yet current diffusion-based policy learning methods generally suffer from low computational efficiency due to the iterative denoising process during in…
Dynamic grasping of moving objects in complex, continuous motion scenarios remains challenging. Reinforcement Learning (RL) has been applied in various robotic manipulation tasks, benefiting from its closed-loop property. However, existing RL-based methods do not fully explore the potential for enha
The inaccurate translation of numbers can lead to significant security issues, ranging from financial setbacks to medical inaccuracies. While large language models (LLMs) have made significant advancements in machine translation, their capacity for translating numbers has not been thoroughly explore…
Large language models (LLMs) can enhance automatic speech recognition (ASR) systems through generative error correction (GEC). In this paper, we propose Pinyin-enhanced GEC (PY-GEC), which leverages Pinyin—the phonetic representation of Mandarin Chinese—as supplementary information to improve Chines…
Reconstructing the 3D shape of an object from a single-view image is a fundamental task in computer vision. Recent advances in differentiable rendering have enabled 3D reconstruction from image collections using only 2D annotations. However, these methods mainly focus on whole-object reconstruction…
Automated bidding to optimize online advertising with various constraints, e.g. ROI constraints and budget constraints, is widely adopted by advertisers. A key challenge lies in designing algorithms for non-truthful mechanisms with ROI constraints. While prior work has addressed truthful auctions or…
Robotic manipulation based on visual observations and natural language instructions is a long-standing challenge in robotics. Yet prevailing approaches model action distribution by adopting explicit or implicit representations, which often struggle to achieve a trade-off between accuracy and efficie…
Robotic grasping, serving as the cornerstone of robot manipulation, is fundamental for embodied intelligence. Manipulation in challenging scenarios demands grasp detection algorithms with higher efficiency and generalizability. However, for general 6-Dof grasp detection, most data-driven methods dir
Entity alignment (EA) is crucial for integrating multi-source knowledge graphs (KGs), aiming to identify equivalent entities across different graphs. However, most existing EA decoding methods rely on both entity and relation embeddings, limiting their generalizability and efficiency, especially in…
Road space and lane line segmentation are vital tasks in intelligent traffic surveillance, yet they receive less attention compared to similar tasks in autonomous driving. In highway surveillance, segmenting occluded road areas and lane lines is crucial for comprehensive perception, though it adds c…
World models allow agents to simulate the consequences of actions in imagined environments for planning, control, and long-horizon decision-making. However, existing autoregressive world models struggle with visually coherent predictions due to disrupted spatial structure, inefficient decoding, and…
Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a microscopic perspective, there has been limited research on how to be…
Embodied localization based on vision and natural language dialogues presents a persistent challenge in embodied intelligence. Existing methods often approach this task as an image translation problem, leveraging encoder-decoder architectures to predict heatmaps. However, these methods frequently ex…
Retrieval-Augmented Generation (RAG) is an effective solution to supplement necessary knowledge to large language models (LLMs). Targeting its bottleneck of retriever performance, “generate-then-read” pipeline is proposed to replace the retrieval stage with generation from the LLM itself. Although p…
Large language models (LLMs) have achieved impressive performance across various natural language benchmarks, prompting a continual need to curate more difficult datasets for larger LLMs, which is costly and time-consuming. In this paper, we propose to automate dataset updating and provide systemati…
Central Pattern Generators (CPG) nonlinear oscillation network is being increasingly used in the control of multi-joint collaborative robots. The motion attitude of robots can be effectively adjusted by tuning parameters of the CPG neural network. However, the mapping from CPG parameters to motion a…
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…
Multi-instance partial-label learning (MIPL) addresses scenarios where each training sample is represented as a multi-instance bag associated with a candidate label set containing one true label and several false positives. Existing MIPL algorithms have primarily focused on mapping multi-instance ba…
Prophet inequality concerns a basic optimal stopping problem and states that simple threshold stopping policies --- i.e., accepting the first reward larger than a certain threshold --- can achieve tight $\frac{1}{2}$-approximation to the optimal prophet value. Motivated by its economic applications,…
3D point cloud has been wildly used in security crucial domains, such as self-driving and 3D face recognition. Backdoor attack is a serious threat that usually destroy Deep Neural Networks (DNN) in the training stage. Though a few 3D backdoor attacks are designed to achieve guaranteed attack efficie…
This paper introduces the innovative “LLMs-as-Instructors” framework, which leverages the advanced Large Language Models (LLMs) to autonomously enhance the training of smaller target models. Inspired by the theory of “Learning from Errors”, this framework employs an instructor LLM to meticulously an…
"Unsupervised video anomaly detection (UVAD) aims to detect abnormal events in videos without any annotations. It remains challenging because anomalies are rare, diverse, and usually not well-defined. Existing UVAD methods are purely data-driven and perform unsupervised learning by identifying vario…
Multi-instance partial-label learning (MIPL) is an emerging learning framework where each training sample is represented as a multi-instance bag associated with a candidate label set. Existing MIPL algorithms often overlook the margins for attention scores and predicted probabilities, leading to sub…
Performative prediction, as introduced by Perdomo et al., is a framework for studying social prediction in which the data distribution itself changes in response to the deployment of a model. Existing work in this field usually hinges on three assumptions that are easily violated in practice: that t…
In this letter, we present a novel portable strategy for the autonomous exploration of highly unstructured three-dimensional environments using ground robots. The proposed planner leverages elevation mapping to estimate traversability, enabling efficient environment mapping while conserving computat
While LLMs have made notable advancements in natural language processing, they continue to struggle with processing extensive text. Memory mechanisms offer a flexible solution for managing long contexts, utilizing techniques such as compression, summarization, and structuring to facilitate nuanced a…
A series of region-based methods succeed in extracting regional features and enhancing grasp detection quality. However, faced with a cluttered scene with potential collision, the definition of the grasp-relevant region stays inconsistent. In this paper, we propose Normalized Grasp Space (NGS) from…
Multi-Object Tracking (MOT) encompasses various tracking scenarios each characterized by unique traits. Effective trackers should demonstrate a high degree of generalizability across diverse scenarios. However existing trackers struggle to accommodate all aspects or necessitate hypothesis and experi…
Recent advancements in multimodal foundation models (e.g., CLIP) have excelled in zero-shot generalization. Prompt tuning involved in the knowledge transfer from foundation models to downstream tasks has gained significant attention recently. Existing prompt-tuning methods in cross-modal learning, h…
In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and several false positive labels. Multi-instance partial-label learning (MIPL) is a learning paradigm to deal with such tasks an…
We consider a novel dynamic pricing and learning setting where in addition to setting prices of products in sequential rounds, the seller also ex-ante commits to ‘advertising schemes’. That is, in the beginning of each round the seller can decide what kind of signal they will provide to the buyer ab…
Fast and robust object grasping in clutter is a crucial component of robotics. Most current works resort to the whole observed point cloud for 6-Dof grasp generation, ignoring the guidance information excavated from global semantics, thus limiting high-quality grasp generation and real-time performa
We initiate the study of $\textit{behavioral information design}$ through deep learning. In information design, a $\textit{sender}$ aims to persuade a $\textit{receiver}$ to take certain actions by strategically revealing information. We address scenarios in which the receiver might exhibit differen…
Fake news causes cognitive misperception among the audience and spreads panic to the public. It is crucial to detect fake news and prevent its spread early. Previous methods focus on excavating distinguishable features from news contents in a single domain with deep models, which are difficult to ge…
Semi-Supervised Temporal Action Localization (SS-TAL) aims to improve the generalization ability of action detectors with large-scale unlabeled videos. Albeit the recent advancement, one of the major challenges still remains: noisy pseudo labels hinder efficient learning on abundant unlabeled videos…
The main challenge of Multi-Object Tracking (MOT) lies in maintaining a continuous trajectory for each target. Existing methods often learn reliable motion patterns to match the same target between adjacent frames and discriminative appearance features to re-identify the lost targets after a long pe…
Forecasting the future trajectory of pedestrians is an important task in computer vision with a range of applications, from security cameras to autonomous driving. It is very challenging because pedestrians not only move individually across time but also interact spatially, and the spatial and tempo…
A common approach to Temporal Action Localization (TAL) is to generate action proposals and then perform action classification and localization on them. For each proposal, existing methods universally use a shared proposal-level representation for both tasks. However, our analysis indicates that thi…
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e.g., context and background, in an untrimmed video. While prior approaches have achieved substantial progress through devising advanced action detectors, they still suffer f…
In this letter, we address the path planning of multi-robot systems (i.e., a team of identical mobile robots) with a global high-level specification that is given as a Boolean formula over some regions of the environment. The task is composed of logical requirements on the trajectories and the final
Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations. Existing works suffer from 1) heterogeneous representations of entities and relations, and 2) heterogeneous modeling of entity-entity interactions and entity-relation interac…
The object of Weakly-supervised Temporal Action Localization (WS-TAL) is to localize all action instances in an untrimmed video with only video-level supervision. Due to the lack of frame-level annotations during training, current WS-TAL methods rely on attention mechanisms to localize the foregroun…
This paper reports a novel optical localization method, including both the hardware design and algorithm design, to track mobile Unmanned Aerial Vehicles (UAVs). The method relies on a circle-shaped blinking LED marker installed on the UAV and uses a single Dynamic Vision Sensing (DVS) camera to sen…
We consider a stochastic multi-armed bandit (MAB) problem with delayed impact of actions. In our setting, actions taken in the past impact the arm rewards in the subsequent future. This delayed impact of actions is prevalent in the real world. For example, the capability to pay back a loan for peopl…
Effectively tackling the problem of temporal action localization (TAL) necessitates a visual representation that jointly pursues two confounding goals, i.e., fine-grained discrimination for temporal localization and sufficient visual invariance for action classification. We address this challenge by…
Dependency relations among visual entities are ubiquity because both objects and scenes are highly structured. They provide prior knowledge about the real world that can help improve the generalization ability of deep learning approaches. Different from contextual reasoning which focuses on feature…
There is an increasing use of algorithms to inform decisions in many settings, from student evaluations, college admissions, to credit scoring. These decisions are made by applying a decision rule to individual’s observed features. Given the impacts of these decisions on individuals, decision makers…
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels. Existing methods often rely on estimated pseudo labels via iterative clustering and classification, and they are unfortunately highly susceptible to performance penalties incurred by the inaccur…
The graph convolutional network (GCN) has recently achieved promising performance of 3D human pose estimation (HPE) by modeling the relationship among body parts. However, most prior GCN approaches suffer from two main drawbacks. First, they share a feature transformation for each node within a grap…
Understanding complex social interactions among agents is a key challenge for trajectory prediction. Most existing methods consider the interactions between pairwise traffic agents or in a local area, while the nature of interactions is unlimited, involving an uncertain number of agents and non-loca…
Weakly-supervised Temporal Action Localization (WS-TAL) methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. Existing WS-TAL methods rely on deep features learned for action recognition. However, due to the mismatch between classificat…
Graph convolutional networks (GCNs) have been applied to 3D human pose estimation (HPE) from 2D body joint detections and have shown encouraging performance. One limitation of the vanilla graph convolution is that it models the relationships between neighboring nodes via a shared weight matrix. This…
Soft fluid-driven robots have great potential for safe interaction with humans, and for adaptation to complex and unpredictable environments with the compliance brought about by soft materials. However, the respective complex structure and massive use of nonlinear and viscoelastic soft materials, an
We study the \emph{secure} stochastic convex optimization problem: a learner aims to learn the optimal point of a convex function through sequentially querying a (stochastic) gradient oracle, in the meantime, there exists an adversary who aims to free-ride and infer the learning outcome of the learn…
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision. However, without frame-level annotations, it is challenging for W-TAL methods to identify false positive action proposals and generate a…
Human pose estimation (HPE) is inherently a homogeneous multi-task learning problem, with the localization of each body part as a different task. Recent HPE approaches universally learn a shared representation for all parts, from which their locations are linearly regressed. However, our statistical…
Moments are a kind of classical feature descriptors for image analysis. Orthogonal moments, due to their computation efficiency and numerical stability, have been widely developed. We propose a set of orthogonal polynomials which are derived from the parity of Hermite polynomials. The new orthogonal…
Compositional models represent patterns with hierarchies of meaningful parts and subparts. Their ability to characterize high-order relationships among body parts helps resolve low-level ambiguities in human pose estimation (HPE). However, prior compositional models make unrealistic assumptions on s…
Many existing person re-identification (PRID) methods typically attempt to train a faithful global metric offline to cover the enormous visual appearance variations, so as to directly use it online on various probes for identity matching. However, their need for a huge set of positive training pairs…
Compositional models represent visual patterns as hierarchies of meaningful and reusable parts. They are attractive to vision modeling due to their ability to decompose complex patterns into simpler ones and resolve the low-level ambiguities in high-level image interpretations. However, current comp…