102 accepted papers
Sound source localization (SSL) demonstrates remarkable results in controlled settings but struggles in real-world deployment due to dual imbalance challenges: intra-task imbalance arising from long-tailed direction-of-arrival (DoA) distributions, and inter-task imbalance induced by cross-task skews…
Despite significant strides in statement autoformalization, a critical gap remains in the development of automated evaluation metrics capable of assessing formal translation quality. Existing metrics often fail to balance semantic and structural information: string-based methods neglect semantics, w…
Audio-visual sound source localization (AV-SSL) estimates the position of sound sources by fusing auditory and visual cues. Current AV-SSL methodologies typically require spatially-paired audio-visual data and cannot selectively localize specific target sources. To address these limitations, we intr
Automated essay scoring (AES) is a challenging task in cross-prompt settings due to the diversity of scoring criteria. While previous studies have focused on the output of large language models (LLMs) to improve scoring accuracy, we believe activations from intermediate layers may also provide valua
For many complex tasks, multi-finger robot hands are poised to revolutionize how we interact with the world, but reliably grasping objects remains a significant challenge. We focus on the problem of synthesizing grasps for multi-finger robot hands that, given an target object's geometry and pose, co…
Generative models for financial time series often create data that look realistic and even reproduce stylized facts such as fat tails or volatility clustering. However, these apparent successes break down under trading backtests: models like GANs or WGAN-GP frequently collapse, yielding extreme and…
We investigate episodic Markov Decision Processes with heavy-tailed feedback (HTMDPs). Existing approaches for HTMDPs are conservative in stochastic environments and lack adaptivity in adversarial regimes. In this work, we propose algorithms ```HT-FTRL-OM``` and ```HT-FTRL-UOB``` for HTMDPs that ach…
Stochastic interpolants offer a robust framework for continuously transforming samples between arbitrary data distributions via ordinary or stochastic differential equations (ODEs/SDEs), holding significant promise for generative modeling. While previous studies have analyzed the finite-time converg…
Many popular practical reinforcement learning (RL) algorithms employ evolving reward functions—through techniques such as reward shaping, entropy regularization, or curriculum learning—yet their theoretical foundations remain underdeveloped. This paper provides the first finite-time convergence anal…
The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are typically sparse and discrete. Conversely, synthetic data sc
Prior dual-stream methods with the feature interaction mechanism have achieved remarkable performance in single image reflection removal (SIRR). However, they often struggle with (1) semantic understanding gap between the features of pre-trained models and those of reflection removal models, and (2)
Memory is a core capability of autonomous agents, yet existing benchmarks evaluate it primarily in constrained settings such as short dialogues or synthetic tasks, failing to reflect realistic agent deployments. We present \textbf{Memoria-Bench}, a benchmark for evaluating agent memory grounded in c…
This paper explores traversability estimation for robot navigation. A key bottleneck in traversability estimation lies in efficiently achieving reliable and robust predictions while accurately encoding both geometric and semantic information across diverse environments. We introduce Navigation via M…
Recent advances in multimodal large language models (MLLMs) have demonstrated substantial potential in video understanding. However, existing benchmarks fail to comprehensively evaluate synergistic reasoning capabilities across audio and visual modalities, often neglecting either one of the modaliti…
While CLIP has achieved strong performance across vision–language tasks, fine-grained image–text alignment remains challenging. Recent efforts improve textual granularity by leveraging long, detailed descriptions and replacing CLIP’s text encoder with LLM, but often overlook the visual-side bottlene…
Unsupervised Reinforcement Learning from Internal Feedback (RLIF) has emerged as a promising paradigm for eliciting the latent capabilities of Large Language Models (LLMs) without external supervision. However, current methods rely on heuristic intrinsic rewards, which often lack a well-defined theo…
Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationally expensive and memory-intensive, especially in resource-constrained environments. Existing parameter-efficient fine-tun…
Text-to-video diffusion models have enabled open-ended video synthesis, but often struggle with generating the correct number of objects specified in a prompt. We introduce NUMINA, a training-free identify-then-guide framework for improved numerical alignment. NUMINA identifies prompt-layout inconsi
Event cameras are bio-inspired vision sensors that encode visual information with high dynamic range, high temporal resolution, and low latency. Current state-of-the-art event stream processing methods rely on end-to-end deep learning techniques. However, these models are heavily dependent on data s…
Time-series forecasting is crucial across various domains, including finance, healthcare, and energy. Transformer models, originally developed for natural language processing, have demonstrated significant potential in addressing challenges associated with time-series data. These models utilize diff…
Simulating fuel sloshing within aircraft tanks during flight is crucial for aircraft safety research. Traditional methods based on Navier-Stokes equations are computationally expensive. In this paper, we treat fluid motion as point cloud transformation and propose the first neural network method spe…
Autoformalization, the automatic translation of mathematical content from natural language into machine-verifiable formal languages, has seen significant progress driven by advances in large language models (LLMs). Nonetheless, a primary barrier to further improvements is the limited availability of…
Our team developed a riding ballbot (called PURE) that is dynamically stable, omnidirectional, and driven by lean-to-steer control. A hands-free admittance control scheme (HACS) was previously integrated to allow riders with different torso functions to control the robot's movements via torso leanin
Label prototype learning has emerged as an effective paradigm in Partial Multi-Label Learning (PML), providing a distinctive framework for modeling structured representations of label semantics while naturally filtering noise through prototype-based label confidence estimation. However, existing pro…
Neural radiance fields (NeRF) and 3D Gaussian Splatting (3DGS) are popular techniques to reconstruct and render photorealistic images. However, the prerequisite of running Structure-from-Motion (SfM) to get camera poses limits their completeness. Although previous methods can reconstruct a few unpos…
This paper presents an experiential learning pedagogy that teaches undergraduate business management information systems students hands-on AI skills through the lens of sustainability. The learning modules aim to empower undergraduate business students to gain interest and confidence in AI knowledge…
The stochastic interpolant framework offers a powerful approach for constructing generative models based on ordinary differential equations (ODEs) or stochastic differential equations (SDEs) to transform arbitrary data distributions. However, prior analyses of this framework have primarily focused o…
The Transformer architecture serves as the foundation of modern AI systems, powering recent advances in Large Language Models (LLMs) and Large Multimodal Models (LMMs). Central to these models, attention mechanisms capture contextual dependencies via token interactions. Beyond inference, attention h…
LiDAR sensors are integral to autonomous driving and augmented reality applications, providing essential depth information. However, managing the substantial volume of LiDAR point cloud data is crucial for practical application, necessitating efficient compression algorithms. Similar to other data c
Existing full-reference image quality assessment (FR-IQA) methods often fail to capture the complex causal mechanisms that underlie human perceptual responses to image distortions, limiting their ability to generalize across diverse scenarios. In this paper, we propose an FR-IQA method based on abdu…
Control Barrier Functions (CBFs) have emerged as an effective and non-invasive safety filter for ensuring the safety of autonomous systems in dynamic environments with formal guarantees. However, most existing works on CBF synthesis focus on fully known settings. Synthesizing CBFs online based on pe
This paper focuses on the motion planning problem for serial articulated robots with revolute joints under kinematic constraints. Many motion planners leverage iterative local optimization methods but are often trapped in local minima due to non-convexity of the problem. A key reason for the non-con
In Partial Multi-Label Learning (PML), each instance is associated with a candidate label set containing multiple relevant labels along with other false positive labels. Currently, most PML methods directly extract instance correlation from instance features while ignoring the candidate labels, whic
Applying deep learning techniques to Electroencephalogram (EEG) data has shown great potential in the field of depression detection. However, existing EEG-based depression detection models face challenges: they struggle to capture the complex spatiotemporal dependencies and the complementary nature…
Despite the success of adversarial training on small datasets, applying it to large-scale datasets like ImageNet remains challenging. Previous attempts using synthetic data show limited improvements. This work investigates the impact of synthetic data scaling, model scaling, and training strategies…
Vulnerability detection remains a critical challenge in the field of security. Many existing approaches extract code representations for vulnerability detection. However, these methods often focus on the overall semantics of the code, neglecting to specifically target vulnerability-related semantics…
In this paper, we present a novel algorithm, `uniINF`, for the Heavy-Tailed Multi-Armed Bandits (HTMAB) problem, demonstrating robustness and adaptability in both stochastic and adversarial environments. Unlike the stochastic MAB setting where loss distributions are stationary with time, our study e…
The recent advances in 3D Gaussian Splatting (3DGS) show promising results on the novel view synthesis (NVS) task. With its superior rendering performance and high-fidelity rendering quality, 3DGS is excelling at its previous NeRF counterparts. The most recent 3DGS method focuses either on improving…
This paper introduces the Fair Fairness Benchmark (FFB), a benchmarking framework for in-processing group fairness methods. Ensuring fairness in machine learning is important for ethical compliance. However, there exist challenges in comparing and developing fairness methods due to inconsistencies i…
In this paper we explore a novel challenging generation task i.e. Handwritten Mathematical Expression Generation (HMEG) from symbolic sequences. Since symbolic sequences are naturally graph-structured data we formulate HMEG as a graph-to-image (G2I) generation problem. Unlike the generation of natur…
Robots designed for in-pipe navigation, inspection, and repair require flexibility for intricate pipeline traversal and the strength to carry payloads. However, conventional wheeled in-pipe robots face challenges in simultaneously achieving both substantial flexibility and payload-carrying capacity.
Today’s large language models (LLMs) typically train on short text segments (e.g., <4K tokens) due to the quadratic complexity of their Transformer architectures. As a result, their performance suffers drastically on inputs longer than those encountered during training, substantially limiting their…
The prevailing noise-resistant and reverberation-resistant localization algorithms primarily emphasize separating and providing directional output for each speaker in multi-speaker scenarios, without association with the identity of speakers. In this paper, we present a target speaker localization a…
Lossless compression of large-scale scientific floating-point data is critical yet challenging due to the presence of high-order information and noise that arises from model truncation and discretization errors. Existing entropy coding techniques fail to effectively leverage the mechanisms underlyin…
Global localization is a challenging task for intelligent robots, as its accuracy directly contributes to the performance of downstream navigation and planning tasks. However, existing literature focus more on the place retrieval and the success rate of localization, with limited attention given to…
3D Gaussians have recently emerged as a highly efficient representation for 3D reconstruction and rendering. Despite its high rendering quality and speed at high resolutions they both deteriorate drastically when rendered at lower resolutions or from far away camera position. During low resolution o…
In textual backdoor attacks, attackers insert poisoned samples with triggered inputs and target labels into training datasets to manipulate model behavior, threatening the model’s security and reliability. Current defense methods can generally be categorized into inference-time and training-time one…
Low back pain is a widespread issue that affects people worldwide and can lead to serious conditions such as herniated discs, spinal stenosis, or lumbar radiculopathy. Improper posture while lifting heavy weights is a common cause of back pain, especially among laborers. However, current back exoske…
In the realm of reinforcement learning (RL), accounting for risk is crucial for making decisions under uncertainty, particularly in applications where safety and reliability are paramount. In this paper, we introduce a general framework on Risk-Sensitive Distributional Reinforcement Learning (RS-Dis…
Risk-sensitive reinforcement learning (RL) aims to optimize policies that balance the expected reward and risk. In this paper, we present a novel risk-sensitive RL framework that employs an Iterated Conditional Value-at-Risk (CVaR) objective under both linear and general function approximations, enr…
This work pioneers regret analysis of risk-sensitive reinforcement learning in partially observable environments with hindsight observation, addressing a gap in theoretical exploration. We introduce a novel formulation that integrates hindsight observations into a Partially Observable Markov Decisio…
Diffusion models have become the go-to method for large-scale generative models in real-world applications. These applications often involve data distributions confined within bounded domains, typically requiring ad-hoc thresholding techniques for boundary enforcement. Reflected diffusion models aim…
A typical application of upper-limb exoskeleton robots is deployment in rehabilitation training, helping patients to regain manipulative abilities. However, as the patient is not always capable of following the robot, safety issues may arise during the training. Due to the bias in different patients…
Time series data consists of a temporal dimension and features associated with each timestamp. Anomaly detection in this context necessitates the consideration of both temporal and spatial features. However, existing work focuses on separately addressing temporal and spatial features, neglecting the…
Tremors, which are prevalent symptoms in both Parkinson’s disease (PD) and essential tremor (ET), substantially diminish the quality of life for those affected. Traditional treatments, including pharmaceutical medications and invasive surgical procedures, often come with limitations and side effects…
Schrödinger bridge (SB) has emerged as the go-to method for optimizing transportation plans in diffusion models. However, SB requires estimating the intractable forward score functions, inevitably resulting in the (costly) implicit training loss based on simulated trajectories. To improve the scalab…
Despite the impressive results achieved by many existing Structure from Motion (SfM) approaches, there is still a need to improve the robustness, accuracy, and efficiency on large-scale scenes with many outlier matches and sparse view graphs. In this paper, we propose AdaSfM: a coarse-to-fine adapti…
Contrastively trained vision-language models have achieved remarkable progress in vision and language representation learning. However, recent research has highlighted severe limitations of these models in their ability to perform compositional reasoning over objects, attributes, and relations. Scen…
Recent works such as BARF and GARF can bundle adjust camera poses with neural radiance fields (NeRF) which is based on coordinate-MLPs. Despite the impressive results, these methods cannot be applied to Generalizable NeRFs (GeNeRFs) which require image feature extractions that are often based on mor…
Although Neural Radiance Fields (NeRF) is popular in the computer vision community recently, registering multiple NeRFs has yet to gain much attention. Unlike the existing work, NeRF2NeRF, which is based on traditional optimization methods and needs human annotated keypoints, we propose DReg-NeRF to…
Many kinds of simultaneously-observed
Noisy Student Training (NST) has recently demonstrated extremely strong performance in Automatic Speech Recognition (ASR). In this paper, we propose a data selection strategy named LM Filter to improve the performance of NST on non-target domain data in ASR tasks. Hypotheses with and without a Langu…
Point processes often have a natural interpretation with respect to a continuous process. We propose a point process construction that describes arrival time observations in terms of the state of a latent diffusion process. In this framework, we relate the return times of a diffusion in a continuous…
Information-theoretic clustering is one of the most promising and principled approaches to finding clusters with minimal apriori assumptions. The key criterion therein is to maximize the mutual information between the data points and their cluster labels. Such an approach, however, does not explicit…
Persuasive dialogue aims to persuade users to achieve some targets by conversations. While previous persuasion models have achieved notable successes, they mostly base themselves on utterance semantic matching, and an important aspect has been ignored, that is, the strategy of the conversations, for…
Learning-based video compression has been extensively studied over the past years, but it still has limitations in adapting to various motion patterns and entropy models. In this paper, we propose multi-mode video compression (MMVC), a block wise mode ensemble deep video compression framework that s…
The task of product attribute value extraction is to identify values of an attribute from product information. Product attributes are important features, which help improve online shopping experience of customers, such as product search, recommendation and comparison. Most existing works only focus…
Exoskeleton robots provide assistive forces to suit the human subject via physical human-robot interaction. During the closely-coupled interaction, a mismatch between the wearer and the robot may result in physical conflict, which could affect assistance efficiency or even compromise safety. Therefo…
The Schrödinger bridge problem (SBP) is gaining increasing attention in generative modeling and showing promising potential even in comparison with the score-based generative models (SGMs). SBP can be interpreted as an entropy-regularized optimal transport problem, which conducts projections onto ev…
Recent deep learning based visual-inertial odometry (VIO) systems achieve impressive performance in various applications and challenging scenarios. However, it is difficult to deploy such VIO models directly on energy-constrained mobile platforms in real-time due to the extensive complexity of exist…
We study reward-free reinforcement learning with linear function approximation for episodic Markov decision processes (MDPs). In this setting, an agent first interacts with the environment without accessing the reward function in the exploration phase. In the subsequent planning phase, it is given a…
The advantages of cable-driven exoskeleton robots with series elastic actuators can be summarized in twofold: 1) the inertia of the robot joint is relatively low, which is more friendly for human-robot interaction; 2) the elastic element is tolerant to impacts and hence provides structural safety. A…
Sound source separation and localization for situational awareness enables a wide range of applications such as hearing enhancement and audio beam-forming. We present an end-to-end deep learning framework to separate and localize multiple audio sources from the mixture of multi-channels. The propose…
"In recent years, deep learning-based approaches for visual-inertial odometry (VIO) have shown remarkable performance outperforming traditional geometric methods. Yet, all existing methods use both the visual and inertial measurements for every pose estimation incurring potential computational redun…
Estimating Transfer Entropy (TE) between time series is a highly impactful problem in fields such as finance and neuroscience. The well-known nearest neighbor estimator of TE potentially fails if temporal dependencies are noisy and long ranged, primarily because it estimates TE indirectly relying o…
Laser-driven micro-tools are formulated by treating highly-focused laser beams as actuators, to control the tool's motion to contact then manipulate a micro object, which allows it to manipulate opaque micro objects, or large cells without causing photodamage. However, most existing laser-driven too…
Leveraging line features to improve the accuracy of the SLAM system has been studied in many works. However, making full use of the characteristics of different line features (parallel, non-parallel) to improve the SLAM system is rarely mentioned. In this paper, we designed a VIO system based on poi
We study reinforcement learning with linear function approximation where the transition probability and reward functions are linear with respect to a feature mapping $\boldsymbol{\phi}(s,a)$. Specifically, we consider the episodic inhomogeneous linear Markov Decision Process (MDP), and propose a nov…
The ability for ground vehicles to identify terrain types and characteristics can help provide more accurate localization and information-rich mapping solutions. Previous studies have shown the possibility of classifying terrain types based on proprioceptive sensors that monitor wheel-terrain intera
Learning-based video compression has achieved substantial progress during recent years. The most influential approaches adopt deep neural networks (DNNs) to remove spatial and temporal redundancies by finding the appropriate lower-dimensional representations of frames in the video. We propose a nove…
The perceptual loss has been widely used as an effective loss term in image synthesis tasks including image super-resolution [16], and style transfer [14]. It was believed that the success lies in the high-level perceptual feature representations extracted from CNNs pretrained with a large set of im…
We address rotation averaging (RA) and its application to real-world 3D reconstruction. Local optimisation based approaches are the de facto choice, though they only guarantee a local optimum. Global optimisers ensure global optimality in low noise conditions, but they are inefficient and may easily…
Source code summarization aims to generate natural language summaries from structured code snippets for better understanding code functionalities. However, automatic code summarization is challenging due to the complexity of the source code and the language gap between the source code and natural la…
Venipuncture is an indispensable procedure for both diagnosis and treatment. In this paper, unlike existing solutions that fully or partially rely on professional assistance, a compact robotic system integrating both novel hardware and software developments is introduced. The hardware consists of a…
In an order-driven financial market, the price of a financial asset is discovered through the interaction of orders - requests to buy or sell at a particular price - that are posted to the public limit order book (LOB). Therefore, LOB data is extremely valuable for modelling market dynamics. However…
For personalized recommendations, collaborative filtering (CF) methods aim to recommend items to users based on data of historical user-item interactions. Deep learning has indicated success in improving performance of CF methods in recent works. However, to generate an item recommendation list for…
Conversational machine comprehension (MC) has proven significantly more challenging compared to traditional MC since it requires better utilization of conversation history. However, most existing approaches do not effectively capture conversation history and thus have trouble handling questions invo…
In this paper, we propose an end-to-end graph learning framework, namely \textbf{I}terative \textbf{D}eep \textbf{G}raph \textbf{L}earning (\alg), for jointly and iteratively learning graph structure and graph embedding. The key rationale of \alg is to learn a better graph structure based on better…
Efficient construction of checkpoints/snapshots is a critical tool for training and diagnosing deep learning models. In this paper, we propose a lossy compression scheme for checkpoint constructions (called LC-Checkpoint). LC-Checkpoint simultaneously maximizes the compression rate and optimizes the…
Natural question generation (QG) aims to generate questions from a passage and an answer. Previous works on QG either (i) ignore the rich structure information hidden in text, (ii) solely rely on cross-entropy loss that leads to issues like exposure bias and inconsistency between train/test measurem…
Item Response Theory (IRT) aims to assess latent abilities of respondents based on the correctness of their answers in aptitude test items with different difficulty levels. In this paper, we propose the $\beta^3$-IRT model, which models continuous responses and can generate a much enriched family o…
Although opinion-unaware (OA) blind image quality assessment (BIQA) is the most difficult task, it is still very attractive because of its great potential for good generalization capability and practical usage. In this paper, a novel OA-BIQA algorithm is proposed. This algorithm is based on the cons…
Visual loop closure detection, which can be considered as an image retrieval task, is an important problem in SLAM (Simultaneous Localization and Mapping) systems. The frequently used bag-of-words (BoW) models can achieve high precision and moderate recall. However, the requirement for lower time co…
Maximum Likelihood Estimators (MLE) has many good properties. For example, the asymptotic variance of MLE solution attains equality of the asymptotic Cram{\'e}r-Rao lower bound (efficiency bound), which is the minimum possible variance for an unbiased estimator. However, obtaining such MLE solution…
The rapidly increasing surveillance video data has challenged the existing video coding standards. Even though knowledge based video coding scheme proposed for moving objects so far has achieved high efficiency, it does not take full advantages of local information and highly relies on the accuracy…
We present SELL-CORPUS, a multiple accented speech corpus for L2 English learning in China, aiming at the potential research of multiple accented acoustic model, mispronunciation detection and pronunciation assessment for future nationwide oral English tests. Our corpus contains 31.6 hour speech rec…
In this paper, we present a conceptually novel framework for vehicle pose estimation from given RGB images. Our approach extends Mask R-CNN by adding two branches for coarse viewpoint estimation and keypoint detection, in parallel with the existing branches for mask segmentation and 2D object detect…
Face Super-Resolution (SR) is a domain-specific superresolution problem. The facial prior knowledge can be leveraged to better super-resolve face images. We present a novel deep end-to-end trainable Face Super-Resolution Network (FSRNet), which makes use of the geometry prior, i.e., facial landmark…
For human pose estimation in monocular images, joint occlusions and overlapping upon human bodies often result in deviated pose predictions. Under these circumstances, bi- ologically implausible pose predictions may be produced. In contrast, human vision is able to predict poses by exploiting geomet…
In this paper machine learning and human learning are applied jointly to optimize the training of linear regression. Human learning is exploited to label extra training data so as to resolve problems such as insufficient training and over-fitting. Considering the inevitable human errors in labeling,…
Traditional Exemplar-SVMs (ESVM) require millions of negative samples to establish a linear exemplar detector. However, Exemplar Linear Discriminant Analysis (ELDA) can achieve similar performance while avoid negative samples mining. To construct a strong object classifier, Multiple Instance Learnin…