76 accepted papers
Automatic medical report generation can greatly reduce the workload of doctors, but it is often unreliable for real-world deployment. Current methods can write formally fluent sentences but may be factually flawed, introducing serious medical errors known as clinical hallucinations, which make them
Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and \textbf{\textit{reasoning}}. Despite recent advances of T2I models…
Reinforcement Learning with Verifiable Rewards (RLVR) and Group Relative Policy Optimization (GRPO) have significantly advanced the reasoning capabilities of large language models. Extending these methods to multimodal settings, however, faces a critical challenge: the instability of std-based norma…
Concept Bottleneck Models (CBMs) achieve interpretability by interposing a human-understandable concept layer between perception and label prediction. The foundation of CBMs lies in the many-to-many mapping that translates high-dimensional visual features to a set of discrete concepts. However, we…
In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of geometry-based 3DGS and appearance-driven diffusion models faces inherent challe
Zero-shot anomaly detection (ZSAD) aims to identify unseen anomalies without abnormal supervision, which is essential for open-world scenarios. Recent vision-language models such as CLIP enable anomaly reasoning through shared visual-textual embeddings, but existing methods often rely on coarse prom
The critical challenge of semi-supervised semantic segmentation lies in how to fully exploit a large volume of unlabeled data to improve the model's generalization performance for robust segmentation. However, existing softmax scores-based filtering methods tend to be affected by the overconfidence
Unified interpreting and synthesizing human behaviors within 3D environments is vital for advancing spatial intelligence and humanoid robotics. Despite recent advancements (e.g., HSI-GPT), two fundamental capabilities expected of a unified model--understanding and generation--still lag behind specia
Multi-Exposure Fusion (MEF) seeks to generate a single high-quality image from multiple inputs captured at different exposure levels. Despite substantial progress, most existing approaches depend on statistical metrics that poorly reflect human perceptual preferences. Electroencephalography (EEG) pr
Video Large Language Models (VideoLLMs), which adopt large language models for video understanding, have been demonstrated for single-shot videos. However, they usually struggle in multi-shot videos with frequent shot changes, varying camera angles, etc., which makes VideoLLMs hardly answer question
Human-Object Interaction (HOI) detection with vision-language models (VLMs) has progressed rapidly, yet a trade-off persists between specialization and generalization. Two major challenges remain: (1) the sparsity of supervision, which hampers effective transfer of foundation models to HOI tasks, a…
The transition from image to video understanding requires vision-language models (VLMs) to shift from recognizing static patterns to reasoning over temporal dynamics such as motion trajectories, speed changes, and state transitions. Yet current post-training methods fall short due to two critical li
Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental task to advance the development of legal systems. Traditional methods often rely on statistical analyses or role-based simulations but face challenges with multiple all…
Multimodal large language models have demonstrated impressive capabilities in visual-language understanding, particularly in offline video tasks. More recently, the emergence of online video modeling has introduced early forms of active interaction. However, existing models, typically limited to ten…
Generative sequence modeling faces a fundamental tension between the expressivity of Transformers and the efficiency of linear sequence models. Existing efficient architectures are theoretically bounded by shallow, single-step linear updates, while powerful iterative methods like Test-Time Training …
Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, offensive content, and privacy violations. In scalable applications, fine-tuning-based methods are time-consuming to precisely erase multipl…
Multimodal latent-space reasoning aims to replace explicit “thinking with images” by performing visual reasoning directly in a compact latent space. However, existing approaches largely rely on visual supervision and produce latent representations that lack sufficient semantic richness, limiting the…
Recent advances in vision-language-action (VLA) models have demonstrated impressive generalization for robotic manipulation. However, these models often operate by directly mapping visual and linguistic inputs to subsequent actions, lacking intermediate task planning, along with failure detection an
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general robotic manipulation. However, existing approaches typically omit intermediate reasoning steps and directly regress actions, limiting reasoning interpretability and performance in long-horizon or compositional tasks.
Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality, and text alignment, they often overlook key structural distortions, such as abnormal object appearances and interactio
Recent works have explored reference-based super-resolution (RefSR) to mitigate hallucinations in diffusion-based image restoration. A key challenge is that real-world degradations make correspondences between low-quality (LQ) inputs and reference (Ref) images unreliable, requiring adaptive control…
Video foundation models aim to integrate video understanding, generation, editing, and instruction following within a single framework, making them a central direction for next-generation multimodal systems. However, existing evaluation benchmarks remain fragmented and limited in scope, as they each
In this paper, we propose Unreal Multi-Agent Playground (Unreal-MAP), an MARL general platform based on the Unreal-Engine (UE). Unreal-MAP allows users to freely create multi-agent tasks using the vast visual and physical resources available in the UE community, and deploy state-of-the-art (SOTA) MA
Vision-Language Models (VLMs) often over-rely on linguistic priors even when images are provided, leading to object hallucinations. We revisit object-wise hallucination from the perspective of how visual evidence shapes the model's uncertainty. For each input, we measure decision uncertainty with an
Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement learning from human feedback offers promise for preference al
By virtue of its great utility in solving real-world problems, optimization modeling has been widely employed for optimal decision-making across various sectors, but it requires substantial expertise from operations research professionals. With the advent of large language models (LLMs), new opportu
The critical challenge of semi-supervised semantic segmentation lies in how to fully exploit a large volume of unlabeled data to improve the model's generalization performance for robust segmentation. Existing methods mainly rely on confidence-based scoring functions in the prediction space to filte…
Books, as enduring repositories of cultural heritage as well as knowledge, play a fundamental role in human development. Although advances in embodied AI and robotics revolutionize automation in domains, e.g., manufacturing and logistics, robotic book manipulation remains an underexplored frontier.
While robotic control of catheter motion can improve tip positioning accuracy, hysteresis arising from tendon friction and flexural deformation degrades kinematic modeling accuracy. In this paper, we compare the capabilities of three types of models for representing the forward and inverse kinematic
The paper proposes a novel Economic Model Predictive Control (EMPC) scheme for Autonomous Surface Vehicles (ASVs) to simultaneously address path following accuracy and energy constraints under environmental disturbances. By formulating lateral deviations as energy-equivalent penalties in the cost fu
Cross-Domain Few-Shot Segmentation (CD-FSS) extends the generalization ability of Few-Shot Segmentation (FSS) beyond a single domain, enabling more practical applications. However, directly employing conventional FSS methods suffers from severe performance degradation in cross-domain settings, prima…
Large vision-language models (LVLMs) have recently achieved significant progress, demonstrating strong capabilities in open-world visual understanding. However, it is not yet clear how LVLMs address demographic biases in real life, especially the disparities across attributes such as gender, skin to
Vision-Language models (VLMs) have shown great potential in enhancing open-world visual concept comprehension. Recent researches focus on an optimum multimodal collaboration strategy that significantly advances CLIP-based few-shot tasks. However, existing prompt-based solutions suffer from unidirect…
Knowledge Distillation (KD) has attracted considerable attention as a typical model compression and knowledge transfer paradigm. However, most KD approaches are predicated on the implicit assumption: the deployed student model will exclusively encounter classes that have been seen during training, w…
Generalized few-shot point cloud segmentation (GFS-3DSeg) aims to segment objects of both base and novel classes using abundant base class samples and limited novel class samples. Existing GFS-3DSeg methods encounter bottlenecks due to the scarcity of novel class data and inter-class confusion. In t…
Recent real-time semantic segmentation models, whether single-branch or multi-branch, achieve good performance and speed. However, their speed is limited by multi-path blocks, and some depend on high-performance teacher models for training. To overcome these issues, we propose Golden Cudgel Network…
While flourishing developments have been witnessed in text-to-motion generation, synthesizing physically realistic, controllable, language-conditioned Human Scene Interactions (HSI) remains a relatively underexplored landscape. Current HSI methods naively rely on conditional Variational AutoEncoder…
Human understanding and generation are critical for modeling digital humans and humanoid embodiments. Recently, Human-centric Foundation Models (HcFMs)—inspired by the success of generalist models such as large language and vision models—have emerged to unify diverse human-centric tasks into a singl
3D Vision Grounding (3D-VG) seeks to unravel referential language and identify targets in 3D physical world. Prevailing methods align with the 2D-VG's pipeline to pinpoint the referred object in a categorical multi-modal reasoning manner. However, the geometric complexities of 3D scenes and the nuan…
Personalized federated learning (PFL) studies effective model personalization to address the data heterogeneity issue among clients in traditional federated learning (FL). Existing PFL approaches mainly generate personalized models by relying solely on the clients' latest updated models while ignori…
3D vision-language (3D-VL) reasoning, connecting natural language with 3D physical world, represents a milestone in advancing spatial intelligence. While transformer-based methods dominate 3D-VL research, their quadratic complexity and simplistic positional embedding mechanisms severely limits effec…
The success of text-to-image generation enabled by diffusion models has imposed an urgent need to erase unwanted concepts, e.g., copyrighted, offensive, and unsafe ones, from the pre-trained models in a precise, timely, and low-cost manner. The twofold demand of concept erasure requires a precise re…
Spiking neural networks (SNNs) have shown their competence in handling spatial-temporal event-based data with low energy consumption. Similar to conventional artificial neural networks (ANNs), SNNs are also vulnerable to gradient-based adversarial attacks, wherein gradients are calculated by spatial…
Semi-supervised semantic segmentation has attracted considerable attention as it alleviates the need for extensive pixel-level annotations. However, existing methods often overlook the potential optimization conflict between supervised and unsupervised learning objectives, leading to suboptimal perf…
Accurate localization using visual information is a critical yet challenging task, especially in urban environments where nearby buildings and construction sites significantly degrade GNSS (Global Navigation Satellite System) signal quality. This issue underscores the importance of visual localizati…
Point cloud few-shot semantic segmentation (PC-FSS) aims to segment objects within query samples of new categories given only a handful of annotated support samples. Although PC-FSS demonstrates enhanced category generalization capabilities compared to the fully supervised paradigm, the prevalent…
The performance of Federated Learning (FL) hinges on the effectiveness of utilizing knowledge from distributed datasets. Traditional FL methods adopt an aggregate-then-adapt framework where clients update local models based on a global model aggregated by the server from the previous training round.…
The integration of Large Language Models (LLMs) in information retrieval has raised a critical reevaluation of fairness in the text-ranking models. LLMs, such as GPT models and Llama2, have shown effectiveness in natural language understanding tasks, and prior works such as RankGPT have demonstrated…
Human-Object Interaction (HOI) detection plays a crucial role in visual scene comprehension. In recent advancements two-stage detectors have taken a prominent position. However they are encumbered by two primary challenges. First the misalignment between feature representation and relation reasoning…
Open-Set Recognition (OSR) aims to accurately identify known classes while effectively rejecting unknown classes to guarantee reliability. Most existing OSR methods focus on learning in the spatial domain, where subtle texture and global structure are potentially intertwined. Empirical studies have…
Grounding referred objects in 3D scenes is a burgeoning vision-language task pivotal for propelling Embodied AI as it endeavors to connect the 3D physical world with free-form descriptions. Compared to the 2D counterparts challenges posed by the variability of 3D visual grounding remain relatively u…
Open-vocabulary semantic segmentation (OVS) aims to segment images of arbitrary categories specified by class labels or captions. However most previous best-performing methods whether pixel grouping methods or region recognition methods suffer from false matches between image features and category l…
"Point cloud few-shot semantic segmentation (PC-FSS) aims to segment targets of novel categories in a given query point cloud with only a few annotated support samples. The current top-performing prototypical learning methods employ prototypes originating from support samples to direct the classific…
Artificial intelligence has advanced in Medical Visual Question Answering (Med-VQA), but prevalent research tends to focus on the accuracy of the answers, often overlooking the reasoning paths and interpretability, which are crucial in clinical settings. Besides, current Med-VQA algorithms, typicall…
Byzantine machine learning has garnered considerable attention in light of the unpredictable faults that can occur in large-scale distributed learning systems. The key to secure resilience against Byzantine machines in distributed learning is resilient aggregation mechanisms. Although abundant resil…
Video semantic segmentation has achieved conspicuous achievements attributed to the development of deep learning, but suffers from labor-intensive annotated training data gathering. To alleviate the data-hunger issue, domain adaptation approaches are developed in the hope of adapting the model train…
Due to the advantages of low energy consumption, high robustness and fast inference speed, Spiking Neural Networks (SNNs), with good biological interpretability and the potential to be applied on neuromorphic hardware, are regarded as the third generation of Artificial Neural Networks (ANNs). Despit…
Memory-based methods in semi-supervised video object segmentation task achieve competitive performance by performing dense matching between query and memory frames. However, most of the existing methods neglect the fact that videos carry rich temporal information yet redundant spatial information. I…
With the springing up of face synthesis techniques, it is prominent in need to develop powerful face forgery detection methods due to security concerns. Some existing methods attempt to employ auxiliary frequency-aware information combined with CNN backbones to discover the forged clues. Due to the…
Few-shot segmentation (FSS) aims to segment objects of new categories given only a handful of annotated samples. Previous works focus their efforts on exploring the support information while paying less attention to the mining of the critical query branch. In this paper, we rethink the importance of…
Travelling salesman problem (TSP) is NP-Hard with exponential search space. Recently, the adoption of encoder-decoder models as neural TSP solvers has emerged as an attractive topic because they can instantly obtain near-optimal results for small-scale instances. Nevertheless, their training effici…
Few-shot segmentation (FSS) aims to segment novel objects in a given query image with only a few annotated support images. However, most previous best-performing methods, whether prototypical learning methods or affinity learning methods, neglect to alleviate false matches caused by their own pixel-…
"Few-shot segmentation (FSS) aims to segment objects in a given query image with only a few labelled support images. The limited support information makes it an extremely challenging task. Most previous best-performing methods adopt prototypical learning or affinity learning. Nevertheless, they eith…
We study the relationship between the arrangement of neurons and the complexity of the ReLU-activated neural networks measured by the number of linear regions. More specifically, we provide both theoretical and empirical evidence for the point of view that shallow networks tend to have higher comple…
Dual encoders have been used for question-answering (QA) and information retrieval (IR) tasks with good results. There are two major types of dual encoders, Siamese Dual Encoders (SDE), with parameters shared across two encoders, and Asymmetric Dual Encoder (ADE), with two distinctly parameterized e…
Few-Shot Image Classification (FSIC) aims to recognize novel image classes with limited data, which is significant in practice. In this paper, we consider the FSIC problem in the case of adversarial examples. This is an extremely challenging issue because current deep learning methods are still vuln…
3D facial landmark detection is extensively used in many research fields such as face registration, facial shape analysis, and face recognition. Most existing methods involve traditional features and 3D face models for the detection of landmarks, and their performances are limited by the hand-crafte…
Brain networks constructed from diffusion and functional magnetic resonance imaging (dMRI and fMRI) are typically investigated through graph theoretic models. It has recently been noted that the complexity of brain connectivity may not be sufficiently captured by single-scale models and multi-scale…
Electroencephalography (EEG) is an important neurophysiological modality for understanding brain functions and disorders. Topological data analysis (TDA) can decode patterns in EEG signals that are not captured by standard temporal and spectral features. Gradient filtration is a recently advanced TD…
This paper presents a neural network for robust normal estimation on point clouds, named AdaFit, that can deal with point clouds with noise and density variations. Existing works use a network to learn point-wise weights for weighted least squares surface fitting to estimate the normals, which has d…
Learning continuous representations of discrete objects such as text, users, movies, and URLs lies at the heart of many applications including language and user modeling. When using discrete objects as input to neural networks, we often ignore the underlying structures (e.g., natural groupings and s…
Karaoke machines have become a popular choice for many people’s daily entertainment. In this paper, we address a novel task of recommending a suitable key for a user to sing a given song to meet his or her vocal competence, by proposing the Personalized Competence-based Rating Prediction (PCRP) mode…
This letter proposes three-filters-to-normal (3F2N), an accurate and ultrafast surface normal estimator (SNE), which is designed for structured range sensor data, e.g., depth/disparity images. 3F2N SNE computes surface normals by simply performing three filtering operations (two image gradient filte
We develop a privacy-preserving distributed strategy over multitask diffusion networks, where each agent is interested in not only improving its local inference performance via in-network cooperation, but also protecting its own individual task against privacy leakage. In the proposed strategy, at e…
3D object detection is still an open problem in autonomous driving scenes. When recognizing and localizing key objects from sparse 3D inputs, autonomous vehicles suffer from a larger continuous searching space and higher fore-background imbalance compared to image-based object detection. In this let
Topological data analysis (TDA) extracts hidden topological features in signals that cannot be easily decoded by standard signal processing tools. A key TDA method is persistent homology (PH), which summarizes the changes of connected components in a signal through a multiscale descriptor such as th…