95 accepted papers
Learning representations on graphs is foundational for many downstream tasks, and its synergy with diffusion models has emerged as a promising direction. However, diffusion-based methods for heterogeneous graphs remain underexplored, confronting two principal challenges: (1) The presence of noise an
Generative models, such as diffusion and autoregressive approaches, have demonstrated impressive capabilities in editing natural images. However, applying these tools to scientific charts rests on a flawed assumption: a chart is not merely an arrangement of pixels but a visual representation of stru…
Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they remain constrained by the inherent limitations of performing a…
Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and in…
While neural video codecs (NVCs) have recently demonstrated superior performance over traditional codecs through end-to-end learning, existing approaches primarily focus on architectural enhancements and coding module design, with limited exploration into optimizing hierarchical structures--specific
Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve effective cross-modal collaboration and integration. To address this…
Federated fine-tuning enables Large Language Models (LLMs) to adapt to downstream tasks while preserving data privacy, but its resource-intensive nature severely limits deployment on edge devices. In this paper, we introduce Developmental Federated Tuning (DevFT), a resource-efficient approach inspi…
In highly interactive urban driving, decision making is often naturally multi-stage, and decisions at different stages can lead to different reactions from surrounding vehicles. This calls for stage-wise evaluation and selection. Tree-based planning naturally supports multi-stage search and evaluati
Reinforcement Learning from Human Feedback (RLHF) has achieved considerable success in aligning large language models (LLMs) by modeling human preferences with a learnable reward model and employing a reinforcement learning algorithm to maximize the reward model's scores. However, these reward model…
Federated fine-tuning presents a promising avenue for adapting Large Language Models (LLMs) to downstream tasks while preserving data privacy. However, the prohibitive computational and communication overhead of LLM adaptation inhibits its deployment on resource-constrained edge devices. In this pap…
Subject-driven generation is a critical task in creative AI; yet current state-of-the-art methods present a stark trade-off. They either rely on computationally expensive, per-subject fine-tuning, sacrificing efficiency and zero-shot capability, or employ feed-forward architectures built on diffusio…
Large language models (LLMs) exhibit logically inconsistent hallucinations that appear coherent yet violate reasoning principles, with recent research suggesting an inverse relationship between causal reasoning capabilities and such hallucinations. However, existing reasoning approaches in LLMs, suc
Efficient reference structures are essential in video compression, enabling the exploitation of temporal dependencies across frames to reduce redundancy. In this paper, we delve into the inter-frame reference management mechanism in neural video codecs (NVCs). Previous schemes have inherited the ref
Neural video compression (NVC) has achieved significant progress in recent years. The state-of-the-art (SOTA) NVC schemes, exemplified by the Deep Conditional Video Coding series, have focused on pursuing higher fidelity (e.g., PSNR), but lack sufficient exploitation of deep networks' advantages for
Neural video compression (NVC) technologies have advanced rapidly in recent years, yielding state-of-the-art schemes such as DCVC-RT that offer superior compression efficiency to H.266/VVC and real-time encoding/decoding capabilities. Nonetheless, existing NVC schemes have several limitations, inclu
Feature coding has recently emerged as a key technique for efficient transmission of intermediate representations in distributed AI systems. Existing approaches largely follow a transform-based pipeline inherited from image and video coding, where the transform module is used to remove spatial struc
Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated that such LLM-based Retrieval (LLMR) is vulnerable to adversa…
Anomaly detection (AD) is an important machine learning task with many real-world uses, including fraud detection, medical diagnosis, and industrial monitoring. Within natural language processing (NLP), AD helps detect issues like spam, misinformation, and unusual user activity. Although large langu…
Most Neural Video Codecs (NVCs) only employ temporal references to generate temporal-only contexts and latent prior. These temporal-only NVCs fail to handle large motions or emerging objects due to limited contexts and misaligned latent prior. To relieve the limitations, we propose a Spatially Embed…
Accurate parking slot detection is crucial for autonomous parking and intelligent driving, directly impacting safety and efficiency. However, most existing methods rely on AVM images, making them susceptible to image distortion and vehicle occlusion. Additionally, many approaches independently regre
Although 3D Gaussian Splatting (3DGS) has demonstrated promising results in novel view synthesis, its performance degrades dramatically with sparse inputs and generates undesirable artifacts. As the number of training views decreases, the novel view synthesis task degrades to a highly under-determin…
We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV) maps using only a single spherical camera. This dataset and b
As cyber threats become increasingly automated and sophisticated, novel solutions must be introduced to improve defence of enterprise networks. Deep Reinforcement Learning (DRL) has demonstrated potential in mitigating these advanced threats. Single DRL Agents have proven utility toward execution of…
Learned image compression (LIC) has achieved state-of-the-art rate-distortion performance, deemed promising for next-generation image compression techniques. However, pre-trained LIC models usually suffer from significant performance degradation when applied to out-of-training-domain images, implyin…
Densely structured pruning methods -- which generate pruned models in a fully dense format, allowing immediate compression benefits without additional demands -- are evolving owing to their practical significance. Traditional techniques in this domain mainly revolve around coarser granularities, suc…
Depth completion has played a vital role in enhancing depth perception in various applications such as autonomous driving, robotics, and 3D reconstruction. It is a critical task that involves generating a dense depth map from an RGB image and an aligned sparse depth map. However, many existing studi…
In this paper, we introduce the Generalized Video Moment Retrieval (GVMR) framework, which extends traditional Video Moment Retrieval (VMR) to handle a wider range of query types. Unlike conventional VMR systems, which are often limited to simple, single-target queries, GVMR accommodates both non-ta…
This paper presents a simultaneous localization and mapping (SLAM) system to provide accurate pose estimation and dynamic scene reconstruction. Our approach proposes a Joint Point-Gaussian Splatting representation, which fully integrates the robustness of isotropic feature points in pose estimation
Context modeling is essential in learned image compression for accurately estimating the distribution of latents. While recent advanced methods have expanded context modeling capacity, they still struggle to efficiently exploit long-range dependency and diverse context information across different c…
Adversarial examples, crafted with imperceptible perturbations, reveal a significant vulnerability of Deep Neural Networks (DNNs). More critically, the transferability of adversarial examples allows attackers to induce unreasonable predictions without requiring knowledge about the target model. DNNs…
Backdoor attacks are powerful and effective, but distributing LLMs without a proven track record like ‘meta-llama‘ or ‘qwen‘ rarely gains community traction. We identify LoRA sharing as a unique scenario where users are more willing to try unendorsed assets, since such shared LoRAs allow them to enj
Efficient video coding is highly dependent on exploiting the temporal redundancy, which is usually achieved by extracting and leveraging the temporal context in the emerging conditional coding-based neural video codec (NVC). Although the latest NVC has achieved remarkable progress in improving the c…
Diffusion-based image compression has shown remarkable potential for achieving ultra-low bitrate coding (less than 0.05 bits per pixel) with high realism, by leveraging the generative priors of large pre-trained text-to-image diffusion models. However, current approaches require a large number of de…
Vision-Language Models (VLMs) excel at tasks such as image captioning and visual question answering but frequently produce hallucinated outputs that deviate from the actual visual input or prompt. While prior work links hallucination to biases in data or representation, their causal origins remain u
Large language models (LLMs) face persistent challenges when handling long-context tasks, most notably the “lost in the middle” issue, where information located in the middle of a long input tends to be underutilized. Some existing methods that reduce input have the risk of discarding key informatio
Unsupervised multi-view feature selection involves selecting a subset of crucial features across diverse views to diminish feature dimensionality without leveraging label information. While numerous studies have delved into this area, current solutions predominantly rely on linear multi-view data or…
Diffusion Transformers (DiTs) have recently demonstrated remarkable performance in visual generation tasks, surpassing traditional U-Net-based diffusion models by significantly improving image and video generation quality and scalability. However, the large model size and iterative denoising process…
How to effectively use limited supervised accent data to improve the accented ASR is of paramount importance. In this work, we propose an accent-specific quantization for joint unsupervised and supervised training (AQ-JUST) of end-to-end ASR models to address this issue. Specifically, two variants o…
Effectively modeling the spatio-temporal interactions both internally and externally is a challenge in controlling multi-linked snake robots. This paper presents an effective method based on deep predictive coding: SnakeFormer, to address the aforementioned issue. The main contributions include: 1)
Nighttime photography encounters escalating challenges in extremely low-light conditions, primarily attributable to the ultra-low signal-to-noise ratio. For real-world deployment, a practical solution must not only produce visually appealing results but also require minimal computation. However, mos…
Panoptic Scene Graph Generation (PSG) involves the detection of objects and the prediction of their corresponding relationships (predicates). However, the presence of biased predicate annotations poses a significant challenge for PSG models, as it hinders their ability to establish a clear decision…
Pre-trained language models (LMs) have shown remarkable reasoning performance using explanations or chain-of-thoughts (CoT)) for in-context learning. On the other hand, these reasoning tasks are usually presumed to be more approachable for symbolic programming. To understand the mechanism of reasoni…
Federated Learning faces significant challenges in statistical and system heterogeneity, along with high energy consumption, necessitating efficient client selection strategies. Traditional approaches, including heuristic and learning-based methods, fall short of addressing these complexities holist…
"Synthesizing realistic 3D indoor scenes is a challenging task that traditionally relies on manual arrangement and annotation by expert designers. Recent advances in autoregressive models have automated this process, but they often lack semantic understanding of the relationships and hierarchies pre…
Knowledge tracing (KT) aims to predict students’ responses to given questions based on their historical question-answering interactions. Recent studies have proposed multiple types of KT models, mainly relying on learners’ feedback to capture the evolution of their knowledge states. However, these m…
Inspired by the success of Large Language Models in dealing with new tasks via In-Context Learning (ICL) in NLP researchers have also developed Large Vision-Language Models (LVLMs) with ICL capabilities. However when implementing ICL using these LVLMs researchers usually resort to the simplest way l…
Adapting Large Language Models (LLMs) to new tasks through fine-tuning has been made more efficient by the introduction of Parameter-Efficient Fine-Tuning (PEFT) techniques, such as LoRA. However, these methods often underperform compared to full fine-tuning, particularly in scenarios involving comp…
As a new embodied vision task Instance ImageGoal Navigation (IIN) aims to navigate to a specified object depicted by a goal image in an unexplored environment. The main challenge of this task lies in identifying the target object from different viewpoints while rejecting similar distractors. Existin…
This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios, the Gaussian maps reconstructed lack geometric accuracy and ex
Data-driven trajectory prediction is critical in autonomous vehicles, which requires high-quality data. However, discussions about the compatibility of data collected from different countries remain limited, with a typical issue being the different driving rules in various countries. Therefore, we p
Video compression relies heavily on exploiting the temporal redundancy between video frames, which is usually achieved by estimating and using the motion information. The motion information is represented as optical flows in most of the existing deep video compression networks. Indeed, these network…
Panoptic Scene Graph Generation (PSG) parses objects and predicts their relationships (predicate) to connect human language and visual scenes. However, different language preferences of annotators and semantic overlaps between predicates lead to biased predicate annotations in the dataset, i.e. diff…
Federated Learning (FL) enables multiple devices to collaboratively train a shared model while ensuring data privacy. The selection of participating devices in each training round critically affects both the model performance and training efficiency, especially given the vast heterogeneity in traini…
This paper proposes a domain adaptation method for speech enhancement called Remixed2Remixed. The proposed method adopts Noise2Noise (N2N) learning to adapt models trained on artificially generated (out-of-domain: OOD) noisy-clean pairs of data to better separate real-world recorded (in-domain) nois…
This paper proposes SANet, a small but accurate detector for aerial flying objects. The detector introduces an attention module into the feature extraction module (FEM) for enhancing the accuracy. This FEM with fewer convolutional kernel channels can reduce the parameters, speed up the inference tim…
Computed Tomography (CT) is an advanced imaging technology. To obtain high-resolution (HR) CT images from low-resolution (LR) sinograms, we present a deep-learning (DL) based CT super-resolution (SR) method.The proposed method combines a SR model in the sinogram domain and the iterative framework in…
We propose a lightweight, effective, and efficient anti-drone network, namely ADMNet, for visually detecting and monitoring unfriendly drones with a constrained view field, flying against a complex environment. We merge an SPP module to the first head of YOLOv4 to improve accuracy and perform networ…
Few-shot learning (FSL) requires a model to classify new samples after learning from only a few samples. While remarkable results are achieved in existing methods, the performance of embedding and metrics determines the upper limit of classification accuracy in FSL. The bottleneck is that deep netwo…
Zero-shot Human-Object Interaction (HOI) detection aims to identify both seen and unseen HOI categories. A strong zero-shot HOI detector is supposed to be not only capable of discriminating novel interactions but also robust to positional distribution discrepancy between seen and unseen categories w…
Recent progress in weakly supervised object detection is featured by a combination of multiple instance detection networks (MIDN) and ordinal online refinement. However, with only image-level annotation, MIDN inevitably assigns high scores to some unexpected region proposals when generating pseudo l…
We propose a novel framework to reconstruct accurate appearance and geometry with neural radiance fields (NeRF) for interacting hands, enabling the rendering of photo-realistic images and videos for gesture animation from arbitrary views. Given multi-view images of a single hand or interacting hands…
Whilst the availability of 3D LiDAR point cloud data has significantly grown in recent years, annotation remains expensive and time-consuming, leading to a demand for semi-supervised semantic segmentation methods with application domains such as autonomous driving. Existing work very often employs r…
The emergence of conditional generative adversarial networks (cGANs) has revolutionised the way we approach and control the generation, by means of adversarially learning joint distributions of data and auxiliary information. Despite the success, cGANs have been consistently put under scrutiny due t…
The majority of current research on reinforcement learning (RL) for snake robot control do not sufficiently account for the spatial and temporal dependencies within the robot or its interaction with its environment during movement. To address this issue, we propose an RL based multi-layer Bayesian m…
In fisheye images, rich distinct distortion patterns are regularly distributed in the image plane. These distortion patterns are independent of the visual content and provide informative cues for rectification. To make the best of such rectification cues, we introduce SimFIR, a simple framework for…
Since developing a new multimodal LLM (MLLM) by pre-training on tremendous image-text pairs from scratch can be exceedingly resource-consuming, connecting an existing LLM with a comparatively lightweight visual prompt generator (VPG) becomes a feasible paradigm. However, further tuning the VPG compo…
Instance-dependent label noise (IDN) widely exists in real-world datasets and usually misleads the training of deep neural networks. Noise transition matrix (NTM) (i.e., the probability that clean labels flip into noisy labels) is used to characterize the label noise and can be adopted to bridge the…
Permutation invariant training (PIT) has recently attracted attention as a framework to achieve end-to-end time-domain audio source separation. Its goal is to train a separation network that takes a mixture signal as input and produces the J underlying source signals. Since the order of the output s…
Recent years have witnessed increasing interest in code representation learning, which aims to represent the semantics of source code into distributed vectors. Currently, various works have been proposed to represent the complex semantics of source code from different views, including plain text, Ab…
Two-view structure from motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM (vSLAM). Many existing end-to-end learning-based methods usually formulate it as a brute regression problem. However, the inadequate utilization of traditional geometry model makes the model not robust in un…
Training Graph Neural Networks (GNNs) on large graphs is a fundamental challenge due to the high memory usage, which is mainly occupied by activations (e.g., node embeddings). Previous works usually focus on reducing the number of nodes retained in memory. In parallel, unlike what has been developed…
Steering control is a vital function for autonomous vehicles, whose performance largely determines the driving safety. The widely used feedback steering controllers degrade significantly when vehicles drive at high speeds. This is mainly because these controllers can not effectively exploit nonlinea
Federated learning (FL) allows multiple clients to collectively train a high-performance global model without sharing their private data. However, the key challenge in federated learning is that the clients have significant statistical heterogeneity among their local data distributions, which would…
This paper proposes a method called "Hungarian Block Permutation (HBP)" to solve the block permutation problem in frequency-domain multichannel audio source separation. Many methods for frequency-domain multichannel audio source separation are designed to simultaneously solve frequency-wise source s…
In this paper, we investigate two algorithms for variational autoencoder (VAE)-based underdetermined multichannel source separation. We previously extended the multichannel VAE (MVAE) method for determined multichannel source separation and proposed the generalized MVAE (GMVAE) method for underdeter…
Automatic code summarization, which aims to describe the source code in natural language, has become an essential task in software maintenance. Our fellow researchers have attempted to achieve such a purpose through various machine learning-based approaches. One key challenge keeping these approache…
Glass-free compressive light field (CLF) display gains much attention due to their compatibility in holographic-like and three-dimensional (3D) demonstration. Opposite to other analogous devices, CLF display can provide binocular and motion parallaxes by stacking multiple liquid crystal screens with…
This study is focused on the maneuver planning problem for a tractor-trailer vehicle in a curvy and tiny tunnel. Due to the curse of dimensionality, the prevalent sampling-and- search-based planners used to handle a rigid-body vehicle well become less efficient when the trailer number grows or when
Learning useful interactions between input features is crucial for tabular data modeling. Recent efforts start to explicitly model the feature interactions with graph, where each feature is treated as an individual node. However, the existing graph construction methods either heuristically formula…
Graph neural networks (GNNs) integrate deep architectures and topological structure modeling in an effective way. However, the performance of existing GNNs would decrease significantly when they stack many layers, because of the over-smoothing issue. Node embeddings tend to converge to similar vecto…
It is generally believed that a translation memory (TM) should be beneficial for machine translation tasks. Unfortunately, existing wisdom demonstrates the superiority of TM-based neural machine translation (NMT) only on the TM-specialized translation tasks rather than general tasks, with a non-negl…
The implementation of full-duplex (FD) theoretically doubles the spectral efficiency of cellular communications. We propose a multiuser FD cellular network relying on an intelligent reflecting surface (IRS). The IRS is deployed to cover a dead zone while suppressing user-side self-interference (SI)…
Symbolic techniques based on Satisfiability Modulo Theory (SMT) solvers have been proposed for analyzing and verifying neural network properties, but their usage has been fairly limited owing to their poor scalability with larger networks. In this work, we propose a technique for combining gradient-…
In this paper, we propose SepNet, a deep neural network (DNN) designed to predict separation matrices from multichannel observations. One well-known approach to blind source separation (BSS) involves independent component analysis (ICA). A recently developed method called independent low-rank matrix…
In this paper, we propose a low-latency online extension of wave-U-net for single-channel speech enhancement, which utilizes teacher-student learning to reduce the system latency while keeping the enhancement performance high. Wave-U-net is a recently proposed end-to-end source separation method, wh…
Retrosynthesis is the process of identifying a set of reactants to synthesize a target molecule. It is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. However, the in…
To learn a reliable people counter from crowd images, head center annotations are normally required. Annotating head centers is however a laborious and tedious process in dense crowds. In this paper, we present an active learning framework which enables accurate crowd counting with limited supervisi…
Trained with the standard cross entropy loss, deep neural networks can achieve great performance on correctly labeled data. However, if the training data is corrupted with label noise, deep models tend to overfit the noisy labels, thereby achieving poor generation performance. To remedy this issue,…
This paper addresses the multichannel directional speech enhancement problem with geometrically constrained independent vector analysis (GCIVA), where we aim to combine the high separation performance from blind source separation and the capability of directional focus from beamforming. The proposed…
The increasing demands of high resolution and high quality videos aggravate the burden of limited cluster storage and restricted bandwidth resources. Hence, video de-duplication in storage and transmission is becoming an important feature for video cloud storage and Content Delivery Network (CDN) se…
We consider the problem of multiple robots that must cooperate within a shared environment, but which wish to limit the information they disclose during their coordination efforts. Specifically, we examine the problems of privacy-preserving rendezvous and persistent monitoring. In the former, the ro…
This paper proposes an alternative algorithm for the multi-channel variational autoencoder (MVAE), a recently proposed multichannel source separation approach. While MVAE is notable for its impressive source separation performance, its convergence-guaranteed optimization algorithm and the fact that…
In this paper, we deal with a multichannel source separation problem under a highly reverberant condition. The multichannel variational autoencoder (MVAE) is a recently proposed source separation method that employs the decoder distribution of a conditional VAE (CVAE) as the generative model for the…
In video coding frameworks, the essence of intra coding is leveraging the spatial correlation within a frame to remove redundancy thus achieving compact transmitting data. With modern video acquisition devices improvement, more high-definition videos emerge into people's lives which has set a new ch…
Deep clustering is a recently introduced deep learning-based method for speech separation. The idea is to model and train the mapping from each time-frequency (TF) region of a spectrogram to an embedding space so that the embedding features of the TF regions dominated by the same source are forced t…