99 accepted papers
Cross-modal hashing (CMH) has achieved remarkable success in large-scale cross-modal retrieval due to its low storage cost and high computational efficiency. However, most existing CMH methods rely on accurately annotated training data, which is often impractical in real-world applications due to th
Undergraduate research experiences are often limited to small-scale apprenticeship models, leaving many students without accessible entry points into research practice. This paper presents the design and evaluation of a semester-long course for undergraduates to gain research experience in Machine L
The rapid advancement of Multimodal Large Language Models (MLLMs) has made aligning them with human preferences a critical challenge. Reward Models (RMs) are a core technology for achieving this goal, but a systematic guide for building state-of-the-art Multimodal Reward Models (MRMs) is currently l…
Model-based reinforcement learning (MBRL) enables efficient decision-making by learning predictive world modelsof environment dynamics. Despite recent advances, existingmodels often struggle to reconcile accurate short-term transitions with coherent long-term planning, especially in partially observ
Incremental Object Detection (IOD) aims to equip detectors with the ability to handle dynamic environments and emerging object categories, and the rise of vision-language models has substantially advanced this goal. However, existing studies often oversimplify real-world scenarios by assuming the in
Multivariate time series (MTS) forecasting critically depends on modeling inter-variable dependencies, yet existing paradigms face a trade-off: channel-isolation strategies can suffer from information fragmentation in strongly coupled systems, whereas channel-interaction methods often introduce spur…
Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms of weak supervision: one-thing-one-click annotations and bou
Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior. Recently, as diffusion language models (DLMs) have become an i…
Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to autoregressive (AR) LLMs for text generation, with the potential to decode multiple tokens in a single iteration. However, none of the existing open-source dLLMs have achieved superior inference speed over AR LLMs of…
Sparse Autoencoders (SAEs) are widely used to steer large language models (LLMs), based on the assumption that their interpretable features naturally enable effective model behavior steering. Yet a fundamental question remains: does higher interpretability imply better steering utility? To answer th…
While 3D Gaussian Splatting (3DGS) achieves real-time photorealistic rendering, its performance degrades significantly when training images contain transient objects that violate multi-view consistency. Existing methods face a circular dependency: accurate transient detection requires a well-reconst
Video-based spatial reasoning -- such as estimating distances, judging directions, or understanding layouts from multiple views -- requires selecting informative frames and, when needed, actively seeking additional viewpoints during inference. Existing multimodal large language models (MLLMs) consum
Generative Flow Networks (GFlowNets) have recently been used to improve diversity and mitigate popularity bias in LLM-based recommender systems, yet most objectives are developed under online-style assumptions. In offline LLM-based recommendation, learning is constrained to a fixed logged dataset, y…
Multimodal learning integrates complementary information from different modalities such as image, text, and audio to improve model performance, but its success relies on large-scale labeled data, which is costly to obtain. Active learning (AL) mitigates this challenge by selectively annotating infor
Recent advancements in Pre-trained Language Models (PLMs) have significantly enhanced performance across various Natural Language Processing (NLP) tasks. However, the variability in data distributions across different domains presents challenges in generalizing these models to unseen domains. Domain
Test-Time Adaptation (TTA) aims to further adapt models to unlabeled test sets arriving in a sequential datastream, thereby progressively strengthening the model's generalization ability. While existing TTA methods for Vision-Language Models (VLMs) are primarily designed and evaluated on (nearly) ba…
Body-surface health conditions, spanning diverse clinical departments, represent some of the most frequent diagnostic scenarios and a primary target for medical multimodal large language models (MLLMs). Yet existing medical benchmarks are either built from publicly available sources with limited ex…
Long-form science fiction generation demands rigorous maintenance of narrative coherence across evolving plots, character dynamics, and speculative world-building. We propose Octopus, an entropy-controlled neural framework with persistent memory-context binding that addresses these challenges throug
Graph Neural Networks (GNNs) have advanced graph classification, yet they remain vulnerable to graph-level imbalance, encompassing class imbalance and topological imbalance. To address both types of imbalance in a unified manner, we propose UniImb, a Unified framework for Imbalanced graph classifica…
Lane-level navigation is critical for geographic information systems and navigation-based tasks, offering finer-grained guidance than road-level navigation by standard definition (SD) maps. However, it currently relies on expansive global HD maps that cannot adapt to dynamic road conditions. Recentl…
While existing multivariate time series forecasting models have advanced significantly in modeling periodicity, they largely neglect the periodic heterogeneity common in real-world data, where variables exhibit distinct and dynamically changing periods. To effectively capture this periodic heterogen…
Real-time 3D reconstruction is crucial for robotics and augmented reality, yet current simultaneous localization and mapping(SLAM) approaches often struggle to maintain structural consistency and robust pose estimation in the presence of depth noise. This work introduces PointSLAM++, a novel RGB-D S
Reconstruction-based multimodal anomaly detection is fundamentally challenged by the one-to-many crossmodal mapping problem, where a single 3D feature may correspond to multiple valid RGB appearances, often leading to collapsed reconstructions and degraded detection performance. We propose *Crossmod…
Panoramic depth estimation enables a complete 360^\circ understanding of 3D environments but faces significant challenges in generalizing to real-world scenes. While recent zero-shot depth models like Depth Anything achieve remarkable generalization on perspective images, their performance sharply d
Accurate weather forecasting is crucial for climate research, disaster mitigation, and societal planning. Despite recent progress with deep learning, global atmospheric data remain uniquely challenging since weather dynamics evolve across heterogeneous spatial and temporal scales ranging from planet…
Cross-modal hashing (CMH) facilitates efficient retrieval across different modalities (e.g., image and text) by encoding data into compact binary representations. While recent methods have achieved remarkable performance, they often rely heavily on fully annotated datasets, which are costly and labo
Stereo disparity estimation is crucial for obtaining depth information in robot-assisted minimally invasive surgery (RAMIS). While current deep learning methods have made significant advancements, challenges remain in achieving an optimal balance between accuracy, robustness, and inference speed. To…
Current mainstream research in multivariate time series (MTS) prediction often assumes that all data is static. However, real-world MTS data typically arrives continuously in a streaming manner, which we refer to as streaming MTS. The statistical characteristics and spatiotemporal graph topology of
Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates severe asynchronous policy conflicts. This issue becomes par
Spiking neural network (SNN) is an event-driven neural network that can greatly reduce the power consumption of the conventional artificial neural networks (ANN). Many ANN models can be converted to SNN models when the activation function is ReLU. For ANN models with other activation functions, such
Generative flow networks (GFlowNets) have been considered as powerful tools for generating candidates with desired properties. Given that evaluating the property of candidates can be complex and time-consuming, existing GFlowNets train proxy models for efficient online evaluation. However, the perfo…
Cross-modal retrieval aims to retrieve relevant data across different modalities. Driven by costly massive labeled data, existing cross-modal retrieval methods achieve encouraging results. To reduce annotation costs while maintaining performance, this paper focuses on an untouched but challenging pr…
In this paper, we propose a distributed-robust sound source localization (D-R-SSL) method in wireless acoustic sensor networks (WASNs). Specifically, the space is first divided into small equal-sized grids, and the local probability of each grid containing the source is calculated by using intra-nod…
Spatiotemporal forecasting (STF) is pivotal in urban computing, yet data scarcity in developing cities hampers robust model training. Addressing this, recent studies leverage transfer learning to migrate knowledge from data-rich (source) to data-poor (target) cities. This strategy, while effective,…
Empathy improves human-machine dialogue systems by enhancing the user’s experience. While traditional models have aimed to detect and express users’ emotions from dialogue history, they neglect the crucial and complex interactions among emotion, emotion causes, and commonsense. To address this, we i…
Combinatorial optimization (CO) is a fundamental tool in many fields. Many neural combinatorial optimization (NCO) methods have been proposed to solve CO problems. However, existing NCO methods typically require significant computational and storage resources, and face challenges in maintaining rob…
Spatiotemporal forecasting facilitates many real world intelligent systems. Combining graph learning with temporal models has recently become popular in spatiotemporal forecasting. Although graph convolution enhances the modeling of spatial correlations, it results in unsatisfactory efficiency and p…
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projection (ERP). Considerable efforts in designing complex spherical convolutions or polyhedron reprojection offer significan…
Large Language Models (LLMs) demonstrate the ability to solve reasoning and mathematical problems using the Chain-of-Thought (CoT) technique. Expanding CoT length, as seen in models such as DeepSeek-R1, significantly enhances this reasoning for complex problems, but requires costly and high-quality
Incremental object detection (IOD) is a challenging task that requires detection models to continuously learn from newly arriving data. This work focuses on incremental learning for vision-language detectors (VLDs), an under explored domain. Existing research typically adopts a local alignment parad…
This paper presents a novel pipeline for estimating room layouts and reconstructing the 3D shapes of indoor objects. This task remains challenging due to occlusions of indoor scenes, which lead to incomplete shape and poor geometric quality manifested as non-smooth meshes. Our key insight is that oc…
The effectiveness of Spatiotemporal Graph Neural Networks (STGNNs) critically hinges on the quality of the underlying graph topology. While end-to-end adaptive graph learning methods have demonstrated promising results in capturing latent spatiotemporal dependencies, they often suffer from high comp…
Sign Language Production (SLP) aims to generate sign videos corresponding to spoken language sentences, where the conversion of sign Glosses to Poses (G2P) is the key step. Due to the cross-modal semantic gap and the lack of word-action correspondence labels for strong supervision alignment, the SLP…
Integrating tools into Large Language Models (LLMs) has facilitated the widespread application. Despite this, in specialized downstream task contexts, reliance solely on tools is insufficient to fully address the complexities of the real world. This particularly restricts the effective deployment of…
Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based fine-tuning and model editing to sparse autoencoder (SAE) steering, e
Position Based Dynamics (PBD) has been widely adopted for interactive simulation, particularly in applications such as virtual surgery and elastodynamics. However, many existing frameworks focus exclusively on interactive deformation, often neglecting the comprehensive analysis of stress distributio
Recent years have witnessed significant advancements in industrial anomaly detection (IAD) thanks to existing anomaly detection datasets. However, the large performance gap between these benchmarks and real industrial practice reveals critical limitations in existing datasets. We argue that the mism…
This paper studies the complex challenge of cross-domain image retrieval under the condition of noisy labels (NCIR), a scenario that not only includes the inherent obstacles of traditional cross-domain image retrieval (CIR) but also requires alleviating the adverse effects of label noise. To address…
Recently, spatiotemporal graph convolutional networks have achieved dominant performance in spatiotemporal prediction tasks. However, most models relying on node-to-node messaging interaction exhibit sensitivity to spatiotemporal shifts, encountering out-of-distribution (OOD) challenges. To address…
Reinforcement Learning (RL) optimizes Traffic Signal Control (TSC) to reduce congestion and emissions, but real-world TSC systems face challenges like adversarial attacks and missing data, leading to incorrect signal decisions and increased congestion. Existing methods, limited to offline data predi…
Role-playing systems powered by large language models (LLMs) have become increasingly influential in emotional communication applications. However, these systems are susceptible to character hallucinations, where the model deviates from predefined character roles and generates responses that are inc…
Discovering regularities from spatiotemporal systems can benefit various scientific and social planning. Current spatiotemporal learners usually train an independent model from a specific source data that leads to limited transferability among sources, where even correlated tasks requires new design…
3D Gaussian Splatting (3D-GS) has exhibited impressive progress in novel view synthesis. When given the sparse views, its performance degrades severely, causing many problems like novel views collapse and excessive floaters. Many recent methods take into account fitting input views, inferring missin…
Current spatio-temporal modeling techniques largely rely on the abundant data and the design of task-specific models. However, many cities lack well-established digital infrastructures, making data scarcity and the high cost of model development significant barriers to application deployment. Theref
Typical spatiotemporal graph forecasting methods process graph-structured spatiotemporal data respectively from spatial and temporal perspectives with the idea of divide and conquer. Existing works are incapable of capturing long-term transdimensional correlations among different spatial points in d…
Long-term time series forecasting (LTSF) has traditionally relied on large parameters to capture extended temporal dependencies, resulting in substantial computational costs and inefficiencies in both memory usage and processing time. However, time series data, unlike high-dimensional images or te…
We present TokenFlow, a novel unified image tokenizer that bridges the long-standing gap between multimodal understanding and generation. Prior research attempt to employ a single reconstruction-targeted Vector Quantization (VQ) encoder for unifying these two tasks. We observe that understanding an…
Despite the significant progress in continual image segmentation, existing arts still strive to balance between stability and plasticity. Additionally, they are specialist to specific tasks and models, which hinders the extension to more general situations. In this work, we present CUE, a novel Cont…
Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit analysis, a popular tool in *Mechanistic Interpretability (MI)*…
Achieving fine-grained control over subject identity and semantic attributes (pose, style, lighting) in text-to-image generation, particularly for multiple subjects, often undermines the editability and coherence of Diffusion Transformers (DiTs). Many approaches introduce artifacts or suffer from at…
Powered knee prostheses promise to improve the mobility of transfemoral amputees by imitating the biomechanics of the missing knee joint. Unfortunately, the heavy weight and short battery life severely limit the application of powered prostheses. Here, we present a lightweight powered knee prosthesi
Robotic picking systems in automated logistics require accurate segmentation and localization of densely stacked cartons. However, the lack of comprehensive and diverse datasets for this task poses a significant challenge. Furthermore, existing instance segmentation methods struggle to meet the accu
Creating expressive, diverse and high-quality 3D avatars from highly customized text descriptions and pose guidance is a challenging task, due to the intricacy of modeling and texturing in 3D that ensure details and various styles (realistic, fictional, etc). We present AvatarVerse, a stable pipelin…
Providing feedback is widely recognized as crucial for refining students’ writing skills. Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-aligned with human-specified attributes. However, it remains unclear whether the fee…
Driven by generative AI and the Internet, there is an increasing availability of a wide variety of images, leading to the significant and popular task of cross-domain image retrieval. To reduce annotation costs and increase performance, this paper focuses on an untouched but challenging problem, i.e…
Spatiotemporal learning has become a pivotal technique to enable urban intelligence. Traditional spatiotemporal models mostly focus on a specific task by assuming a same distribution between training and testing sets. However, given that urban systems are usually dynamic, multi-sourced with imbalanc…
Seeking for generalizable graph representations becomes hot spot in the area of graph learning. Recently, causality theory has been applied for extracting the causal relations between graph data and labels, which are generalizable under distribution shift and result in better OOD generalization. In…
Image Coding for Machine (ICM) aims to compress an image so that the reconstructed one can meet the requirements of both human vision and machine vision. Existing methods apply the constraint from the downstream models to improve machine analytics performance while compromising the visual quality. T…
Real-world tasks are universally associated with training samples that exhibit a long-tailed class distribution, and traditional deep learning models are not suitable for fitting this distribution, thus resulting in a biased trained model. To surmount this dilemma, massive deep long-tailed learning…
Referring 3D Segmentation is a visual-language task that segments all points of the specified object from a 3D point cloud described by a sentence of query. Previous works perform a two-stage paradigm, first conducting language-agnostic instance segmentation then matching with given text query. Howe…
Large Language Models (LLMs) have become integral to a wide spectrum of applications, ranging from traditional computing tasks to advanced artificial intelligence (AI) applications. This widespread adoption has spurred extensive research into LLMs across various disciplines, including the social sci…
One of the most important tasks in ride-hailing is order dispatching, i.e., assigning unserved orders to available drivers. Recent order dispatching has achieved a significant improvement due to the advance of reinforcement learning, which has been approved to be able to effectively address sequenti…
Detecting objects with inherent orientations has numerous applications in the context of livestock reproduction. In this new scenario, the inherent orientations in the range [0, 2π) of target objects are detected alongside their bounding boxes to produce real-oriented bounding boxes. Due to the 0-to…
Intrusion detection acts as a key to in-home security, where WiFi-based systems have gained wide attention due to the ubiquitous nature of WiFi signals. While existing methods achieve impressive performance in specific environments, they are susceptible to environmental changes, especially for compl…
With the progress of urban transportation systems, a significant amount of high-quality traffic data is continuously collected through streaming manners, which has propelled the prosperity of the field of spatial-temporal graph prediction. In this paper, rather than solely focusing on designing pow…
Accuracy and efficiency are pivotal considerations in the field of time series forecasting. Through the integration of meticulously designed temporal components, the Transformer-based models have significantly enhanced the accuracy of time series prediction. However, due to the utilization of attent…
Cross-domain image retrieval aims at retrieving images across different domains to excavate cross-domain classificatory or correspondence relationships. This paper studies a less-touched problem of cross-domain image retrieval, i.e., unsupervised cross-domain image retrieval, considering the followi…
Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios. Prior work attempts to obtain 1-to-1 QA pairs from growing customer service chatlog, w…
Multi-expert ensemble models for long-tailed learning typically either learn diverse generalists from the whole dataset or aggregate specialists on different subsets. However, the former is insufficient for tail classes due to the high imbalance factor of the entire dataset, while the latter may bri…
Object detection is a fundamental task in computer vision, consisting of both classification and localization tasks. Previous works mostly perform classification and localization with shared feature extractor like Convolution Neural Network. However, the tasks of classification and localization exhi…
Graph Neural Networks (GNNs) have shown great promise in various graph learning tasks. However, the computational overheads of fitting GNNs to large-scale graphs grow rapidly, posing obstacles to GNNs from scaling up to real-world applications. To tackle this issue, Graph Lottery Ticket (GLT) hypoth…
The creation of a parameterized stylized character involves careful selection of numerous parameters, also known as the "avatar vectors" that can be interpreted by the avatar engine. Existing unsupervised avatar vector estimation methods that auto-create avatars for users, however, often fail to wor…
Sound event detection(SED) consists of two subtasks: predicting the classes of sound events within an audio clip (audio tagging) and indicating the onset and offset times for each event (localization). One of the common approaches for SED with weak label is multiple instance learning (MIL) method. H…
Few-shot text classification aims to classify the text under the few-shot scenario. Most of the previous methods adopt optimization-based meta learning to obtain task distribution. However, due to the neglect of matching between the few amount of samples and complicated models, as well as the distin…
A hybrid knee prosthesis is proposed in this letter, which consists of a polycentric structure in passive mode for low-torque activities and a single-axis structure in active mode for high-torque activities. A novel mode transition mechanism controls self-holding electromagnets for switching modes b
We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER). In particular, we combine two complementary learning paradigms of NER, i.e., sequence labeling…
Generating precise class-aware pseudo ground-truths, a.k.a, class activation maps (CAMs), is essential for Weakly-Supervised Semantic Segmentation. The original CAM method usually produces incomplete and inaccurate localization maps. To tackle with this issue, this paper proposes an Expansion and Sh…
NLP-powered automatic question generation (QG) techniques carry great pedagogical potential of saving educators’ time and benefiting student learning. Yet, QG systems have not been widely adopted in classrooms to date. In this work, we aim to pinpoint key impediments and investigate how to improve t…
Retinex model-based methods have shown to be effective in layer-wise manipulation with well-designed priors for low-light image enhancement. However, the commonly used hand-crafted priors and optimization-driven solutions lead to the absence of adaptivity and efficiency. To address these issues, in…
Despite the success of neural dialogue systems in achieving high performance on the leader-board, they cannot meet users’ requirements in practice, due to their poor reasoning skills. The underlying reason is that most neural dialogue models only capture the syntactic and semantic information, but f…
Question Answering (QA) models over Knowledge Bases (KBs) are capable of providing more precise answers by utilizing relation information among entities. Although effective, most of these models solely rely on fixed relation representations to obtain answers for different question-related KB subgrap…
The structural information of Knowledge Bases (KBs) has proven effective to Question Answering (QA). Previous studies rely on deep graph neural networks (GNNs) to capture rich structural information, which may not model node relations in particularly long distance due to oversmoothing issue. To addr…
Multi-hop knowledge base question answering (KBQA) aims at finding the answers to a factoid question by reasoning across multiple triples. Note that when human performs multi-hop reasoning, one tends to concentrate on specific relation at different hops and pinpoint a group of entities connected by…
Cross-modal retrieval aims to enable flexible retrieval across different modalities. The core of cross-modal retrieval is how to measure the content similarity between different types of data. In this paper, we present a novel cross-modal retrieval method, called Deep Supervised Cross-modal Retrieva…
In this paper, we propose one novel model for point cloud semantic segmentation,which exploits both the local and global structures within the point cloud based onthe contextual point representations. Specifically, we enrich each point represen-tation by performing one novel gated fusion on the poin…
The Screen Content Coding (SCC) is an extension of High Efficiency Video Coding (HEVC), and it achieves significant improvement on compression ratio. However, the obtained coding efficiency is at the cost of high computational complexity. In this paper, to reduce the computation complexity, we propo…
The human visual system excels at biasing the stereoscopic visual signals by the attention mechanisms. Traditional methods relying on the low-level features and depth relevant information for stereoscopic video saliency prediction have fundamental limitations. For example, it is cumbersome to model…
Video transmission from satellites to terrestrial devices usually requires a large amount of channel resources due to the huge amount of satellite video data. Subject to limited transmission bandwidth in space environment, the video encoder for video satellite calls for higher coding efficiency. In…
This paper advocates a novel framework for segmenting a dataset on a Riemannian manifold M into clusters lying around low-dimensional submanifolds of M. Important examples of M, for which the proposed algorithm is computationally efficient, include the sphere, the set of positive definite matrices,…