59 accepted papers
Augmented large language models (LLMs) that invoke external calls are increasingly prevalent in inference serving. However, such augmentations pose significant challenges to inference efficiency under strict Service-Level Objectives (SLOs). Existing inference systems are agnostic to the dynamic exec…
Despite the rapid progress of Vision Language Models (VLMs), existing benchmarks still concentrate on coarse-grained object recognition or simple relational reasoning, leaving the fine-grained and higher-order reasoning abilities of these systems largely unexamined. To bridge this critical evaluati
Multimodal Large Language Models (MLLMs) demonstrate impressive cross-modal capabilities, yet their substantial size poses significant deployment challenges. Knowledge distillation (KD) is a promising solution for compressing these models, but existing methods primarily rely on static next-token ali…
Knowledge-based visual question answering (KB-VQA) demonstrates significant potential for handling knowledge-intensive tasks. However, conflicts arise between static parametric knowledge in vision language models (VLMs) and dynamically retrieved information due to the static model knowledge from pre
Instruction-based image editing (IIE) is a vital tool for iterative content creation, enabling multi-round interactions that refine visual details while preserving cross-round consistency. However, this workflow is constrained by the compute-bound nature of Diffusion Transformers (DiTs): because DiT…
We study the fair allocation of indivisible items to groups of agents from the perspectives of both the agents and a centralized allocator. In our setting, the centralized allocator aims to ensure that the allocation is fair both among the groups and between individual agents. This setting applies t
Cytological images originate from exfoliated cells, collected via liquid-based slides and digitized into whole slide images (WSIs). Unlike histological WSIs that exhibit continuous and well-structured tissue, cytological WSIs are sparse in spatial distribution and unstructured in cellular relationsh
Reasoning abilities of large language models (LLMs) require explicit derivations compared to general question-answering, supervised fine-tuning (SFT) can empower multiple reasoning abilities in LLMs via learning from various datasets. However, neither training the datasets jointly (mix-up) nor conti…
Recent advances in multimodal large language models (MLLMs) have led to impressive progress across various benchmarks. However, their capability in understanding infrared images remains unexplored. To address this gap, we introduce **IF-Bench**, the first high-quality benchmark designed for evaluati
Rectification flow Transformers (RFTs) have shown promising performance in diffusion-based image synthesis but are typically confined to lower-resolution scenarios, limiting their ability to generate high-resolution images. Existing resolution extrapolation approaches often suffer from excessive co
Accurate reconstruction of 3D vehicle pose and shape from monocular images is challenging, particularly for distant objects in autonomous driving. Existing methods often suffer from geometric ambiguity in depth estimation and structural hollowness in shape recovery, primarily due to inadequate multi
Automated auscultation advances the detection of respiratory diseases, especially in areas with limited resources where traditional diagnostic methods are unavailable. On the other hand, the scarcity of auscultation datasets limits the automation performance, prompting the needs for data augmentatio
Recent advances in Large Language Models (LLMs) have enabled impressive capabilities across diverse reasoning and generation tasks. However, their ability to understand and operate on real-world engineering problems—such as Printed Circuit Board (PCB) placement and routing—remains underexplored due…
Frequency Modulated Continuous Wave (FMCW) radars can measure subtle chest wall oscillations to enable non-contact heartbeat sensing. However, traditional radar-based heartbeat sensing methods face performance degradation due to noise. Learning-based radar methods achieve better noise robustness but
Cognitive diagnosis aims to infer students’ concept-level mastery from exercise response logs and exercise-concept associations. Fully leveraging heterogeneous relations and modeling large mastery-difficulty variations remain challenging, especially with a single predictor. To address these challeng
Reliable medical audio diagnosis demands models that are not only accurate but also honest about their uncertainty. However, fine-tuned models based on small, imbalanced datasets often become overconfident due to norm bias, whereby they rely on feature magnitude rather than semantic alignment. As a …
Learning good representations is essential for latent planning with world models. While pretrained visual encoders provide strong visual features, they are not tailored to planning and contain substantial information which is irrelevant to planning. Inspired by the perceptual straightening hypothesi…
3D dense captioning aims to describe the crucial regions in 3D visual scenes in the form of natural language. Recent prevailing approaches achieve promising results by leveraging complicated structures incorporated with large-scale models, which necessitate abundant parameters and pose challenges re
Quantum Neural Networks (QNNs) offer promising capabilities for complex data tasks, but are often constrained by limited qubit resources and high entanglement, which can hinder scalability and efficiency. In this paper, we introduce Adaptive Threshold Pruning (ATP), an encoding method that reduces e…
One-shot post-training pruning enhances the deployment of billion-scale large language models (LLMs), with the pruning metric playing a pivotal role in determining which weights to remove. However, existing metrics underperform due to their reliance on a simple symbolic combination of weights and ac…
Designing crystal materials with desired physicochemical properties remains a fundamental challenge in materials science. While large language models (LLMs) have demonstrated strong in-context learning (ICL) capabilities, existing LLM-based crystal generation approaches are limited to zero-shot scen
Dynamic pruning leverage the feature information of each input sample to dynamically adjust the network structure, generating multiple subnetworks suitable for different sample complexity. However, it inevitably introduces higher computational complexity and increased memory consumption. In addition…
Existing graph neural network (GNN) methods are typically built upon the i.i.d. assumption, emphasizing the enhancement of the test performance for in-distribution (ID) data. However, there has been limited exploration of their adaptability to scenarios involving unknown distribution data. On the on
Traditional knowledge graphs (KGs) provide each entity with a unique embedding as a representation, which contains a lot of redundant information. Meanwhile, the space complexities of the KGs are positively related to the number of entities. In this work, we propose a hierarchical representation lea
The task of Knowlegde-Based Visual Question Answering (KB-VQA) requires the model to understand visual features and retrieve external knowledge. Retrieval-Augmented Generation (RAG) have been employed to address this problem through knowledge base querying. However, existing work demonstrate two lim…
Drone-based multi-object tracking is essential yet highly challenging due to small targets, severe occlusions, and cluttered backgrounds. Existing RGB-based multi-object tracking algorithms heavily depend on spatial appearance cues such as color and texture, which often degrade in aerial views, comp…
Open set anomaly detection (OSAD) is a crucial task that aims to identify abnormal patterns or behaviors in data sets, especially when the anomalies observed during training do not represent all possible classes of anomalies. The recent advances in quantum computing in handling complex data structur…
Variational quantum Eigensolver (VQE) is a leading candidate for harnessing quantum computers to advance quantum chemistry and materials simulations, yet its training efficiency deteriorates rapidly for large Hamiltonians. Two issues underlie this bottleneck: (i) the no-cloning theorem imposes a lin…
To build safe and reliable graph machine learning systems, unsupervised graph-level anomaly detection (GLAD) and unsupervised graph-level out-of-distribution (OOD) detection (GLOD) have received significant attention in recent years. Though these two lines of research share the same objective, they…
Human-like social bias of pre-trained language models (PLMs) on downstream tasks have attracted increasing attention. The potential flaws in the training data are the main factor that causes unfairness in PLMs. Existing data-centric debiasing strategies mainly leverage explicit bias words (defined a…
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation. However, SAM requires two sequential gradient computations during the optimization o…
Zero-shot Chain-of-Thought (CoT) prompting emerges as a simple and effective strategy for enhancing the performance of large language models (LLMs) in real-world reasoning tasks. Nonetheless, the efficacy of a singular, task-level prompt uniformly applied across the whole of instances is inherently…
Although pre-trained language models (PLMs) have been widely used in natural language understandings (NLU), they are still exposed to fairness issues. Most existing extrinsic debiasing methods rely on manually curated word lists for each sensitive groups to modify training data or to add regular con…
Scaling up model and data size has been quite successful for the evolution of LLMs. However the scaling law for the diffusion based text-to-image (T2I) models is not fully explored. It is also unclear how to efficiently scale the model for better performance at reduced cost. The different training s…
Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learning simply sums up cross-entropy losses of the independent training nodes and ap…
We propose a generalized method for boosting the generalization ability of pre-trained vision-language models (VLMs) while fine-tuning on downstream few-shot tasks. The idea is realized by exploiting out-of-distribution (OOD) detection to predict whether a sample belongs to a base distribution or a…
As the representation capability of Pre-trained Language Models (PLMs) improve, there is growing concern that they will inherit social biases from unprocessed corpora. Most previous debiasing techniques used Counterfactual Data Augmentation (CDA) to balance the training corpus. However, CDA slightly…
Visual loop closure detection is an essential backend task for long-term vSLAM applications. However, prior works cannot simultaneously meet the requirements of high recall and low computing and memory overhead, which prohibits their applicability to resource-constrained platforms. In this work we p
Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability. To improve the interpretability of vision-language models such as CLIP, we propose a multi-modal information bottleneck (M2IB) approach that…
Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years. Panorama images maintain the complete spatial information but introduce distortion with equirectangular projection. In this paper, we propose an ACDNet based on the adaptively combined dilated convolution…
Corrupted labels and class imbalance are commonly encountered in practically collected training data, which easily leads to over-fitting of deep neural networks (DNNs). Existing approaches alleviate these issues by adopting a sample re-weighting strategy, which is to re-weight sample by designing…
Existing multiple object tracking methods usually strengthen data association by discriminative identity embeddings. However, many works treat object detection and association as two individual tasks, thus gaining limited benefits. In this paper, we follow the joint detection and tracking paradigm t…
3D object detection from the LiDAR point cloud is fundamental to autonomous driving. Large-scale outdoor scenes usually feature significant variance in instance scales, thus requiring features rich in long-range and fine-grained information to support accurate detection. Recent detectors leverage th…
Geometric constraints are shown to enforce scale consistency and remedy the scale ambiguity issue in self-supervised monocular depth estimation. Meanwhile, scale-invariant losses focus on learning relative depth, leading to accurate relative depth prediction. To combine the best of both worlds, we l…
In this work, we propose an efficient retrieval method for human motion capture (MoCap) data based on supervised deep hash code learning. Raw Mocap data is represented into three 2D images, which encode the trajectories, velocities and self-similarity of joints respectively. Such image-based represe…
We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. This plug-in loss term complements the cross-entropy loss in capturing boundary tr…
With the thriving of deep learning, CNN-based object detectors have made great progress in the past decade. However, the domain gap between training and testing data leads to a prominent performance degradation and thus hinders their application in the real world. To alleviate this problem, Knowledg…
Ego-motion estimation with 3D perception using visual odometry (VO) is known to be robust and economical among the existing odometry techniques. However, existing VO solutions are typically both computation intensive and memory intensive, which dramatically inhibits their deployment in IoT platforms…
Accurately ranking the vast number of candidate detections is crucial for dense object detectors to achieve high performance. Prior work uses the classification score or a combination of classification and predicted localization scores to rank candidates. However, neither option results in a reliabl…
We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization. Bayesian Bits employs a novel decomposition of the quantization operation, which sequentially considers doubling the bit width. At each new bit width, the residual e…
Skeleton-based gesture recognition is very challenging, as the high-level information in gesture is expressed by a sequence of complexly composite motions. Previous works often learn all the motions with a single model. In this paper, we propose to decouple the gesture into hand posture variations a…
We present a differentiable joint pruning and quantization (DJPQ) scheme. We frame neural network compression as a joint gradient-based optimization problem, trading off between model pruning and quantization automatically for hardware efficiency. DJPQ incorporates variational information bottleneck…
In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection. A binary signature image can be obtained for each point cloud after several LoG-Gabor filtering and thresholding operations on the LiDAR-Iris image representation.…
With the proliferation of specialized neural network processors that operate on low-precision integers, the performance of Deep Neural Network inference becomes increasingly dependent on the result of quantization. Despite plenty of prior work on the quantization of weights or activations for neural…
The ambiguity in image matching is one of main factors decreasing the quality of the 3D model reconstructed by PatchMatch based multiple view stereo. In this paper, we present a novel method, matching ambiguity reduced multiple view stereo (MARMVS) to address this issue. The MARMVS handles the ambig…
In this work, we propose a novel paradigm to design a hybrid thermal/EO (Electro-Optical or visible-light) camera, whose thermal and RGB frames are pixel-wisely aligned and temporally synchronized. Compared with the existing schemes, we innovate in three ways in order to make it more compact in dime…
One major difficulty in medical image segmentation is intensity inhomogeneity, which manifests itself with a slow intensity variation over the whole image domain. Recently, a local binary fitting (LBF) model has been proposed to solve this problem within level set segmentation framework. However, th…
We investigate the max-min weighted downlink signal- to-interference ratio (SINR) problem under uplink SINR constraints and practical per-antenna constraints in full- duplex systems. The successive convex approximation (SCA) method is adopted to iteratively deal with this non-convex problem. Within…
This paper presents an algorithm for fully reconstructing a 3D face from a single image. This task is still highly challenging as most current methods only care about the frontal face, ignoring side face, such as the neck, ears etc. In our algorithm, to get the more detailed texture, we deal with th…