65 accepted papers
Controllable generative models have been widely used to improve the realism of synthetic visual content. However, such models must handle control conditions and content generation computational requirements, resulting in generally low generation efficiency. To address this issue, we propose a Hybrid
Federated Reinforcement Learning from Human Feedback (RLHF) enables the collaborative alignment of Large Language Models (LLMs) while preserving privacy, yet it faces critical bottlenecks arising from data heterogeneity. Existing approaches typically rely on rigid client-level clustering, which over
Instruction-based image editing with diffusion models has achieved impressive results, yet existing methods struggle with fine-grained instructions specifying precise attributes such as colors, positions, and quantities. While recent approaches employ Group Relative Policy Optimization (GRPO) for al
End-to-end (E2E) autonomous driving has recently attracted increasing interest in unifying Vision–Language–Action (VLA) with World Models to enhance decision-making and forward-looking imagination. However, existing methods fail to effectively unify future scene evolution and action planning within …
Video generation using recurrent architectures offers compelling efficiency advantages over attention-based transformers, particularly for long-sequence generation. However, chunked processing in recurrent models creates temporal discontinuities that harm long-range consistency. We introduce two com
Driving planning is a critical component of end-to-end (E2E) autonomous driving. However, prevailing Imitative E2E Planners often suffer from multimodal trajectory mode collapse, failing to produce diverse trajectory proposals. Meanwhile, Generative E2E Planners struggle to incorporate crucial safet
While Large Language Models (LLMs) excel in code generation, they remain prone to replicating subtle yet critical vulnerabilities endemic to their training data. Current alignment techniques, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL), typically apply coarse-grained optimiz…
Graph Neural Networks (GNNs) excel at modeling graph data but often amplify biases tied to sensitive attributes like gender and race. Existing causality-based methods use isolated interventions on graph topology or features but struggle to produce representations that balance predictive power with f
Causal representation learning (CRL) has garnered increasing interests from the causal inference and artificial intelligence community, due to its capability of disentangling potentially complex data-generating mechanism into causally interpretable latent features, by leveraging the heterogeneity of…
Diffusion models have recently advanced video editing, yet controllable editing remains challenging due to the need for precise manipulation of diverse object properties. Current methods require different control signal for diverse editing tasks, which complicates model design and demands significan
We propose OMG-Avatar, a novel One-shot method that leverages a Multi-LOD (Level-of-Detail) Gaussian representation for animatable 3D head reconstruction from a single image in 0.2s. Our method enables LOD head avatar modeling using a unified model that accommodates diverse hardware capabilities and
Unified multimodal models significantly improve visual generation by combining vision-language models (VLMs) with diffusion models. However, existing methods struggle to fully balance sufficient interaction and flexible implementation due to vast representation difference. Considering abundant and h
Drought prediction is crucial for disaster mitigation, yet it remains challenging due to the complexity and variability of drought events. Although time series foundation models (TSFMs) have shown great potential in general time series forecasting problems, they struggle to adapt to regional hydrolo
Regional climate prediction presents unique challenges for time series foundation models, which typically process temporal patterns through a single-pass inference. Expert climatologists, in contrast, employ multi-scale temporal analysis and iterative refinement based on systematic error diagnosis. …
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations are not sufficiently adversarial, obscuring critical vulnera…
3D open-world environments with adversarial opponents remain a core challenge for reinforcement learning due to their vast state spaces. Effective reasoning representations are essential in such settings. While existing self-supervised visual foresight reasoning approaches often suffer from multi-st…
Symbolic Regression aims to discover interpretable mathematical expressions from data. Equation Learner (EQL) is a gradient-based method with strong fitting capability and expressive potential, yet it often activates redundant operators as model complexity grows, leading to over-complex expressions …
SP-based synthesis yields two-time-scale control that allows compliant-joint robots to achieve high-quality tracking at low implementation cost. Composite learning enables exact online identification and control of robots without the stringent condition known as persistent excitation (PE). However, …
Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure ( on-premises ) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized access and potential model theft. To address this, prior
Reconstructing atmospheric surface \text CO _2 is crucial for understanding climate dynamics and informing global mitigation strategies. Traditional inversion models achieve precise global \text CO _2 reconstruction but rely heavily on uncertain prior estimates of fluxes and emissions. Inspired by r…
Global Climate Models (GCMs) are crucial for predicting future climate changes by simulating the Earth systems. However, GCM outputs exhibit systematic biases due to model uncertainties, parameterization simplifications, and inadequate representation of complex climate phenomena. Traditional bias co
In high-stakes domains such as healthcare, finance, and law, the need for explainable AI is critical. Traditional methods for generating attribution maps, including white-box approaches relying on gradients and black-box techniques that perturb inputs, face challenges like gradient vanishing, blurre…
End-to-end autonomous driving frameworks enable seamless integration of perception and planning but often rely on one-shot trajectory prediction, which may lead to unstable control and vulnerability to occlusions in single-frame perception. To address this, we propose the Momentum-Aware Driving (Mom…
Prosody transfer in speech synthesis aims to produce natural and expressive speech by replicating the prosody of reference speech. Traditional methods, which rely on same-text, samespeaker references during training, often fail to generalize effectively when applied to different-speaker or different…
Multimodal 3D object detection has garnered considerable interest in autonomous driving. However, multimodal detectors suffer from dimension mismatches that derive from fusing 3D points with 2D pixels coarsely, which leads to suboptimal fusion performance. In this paper, we propose a multimodal fram…
This study proposes a challenging yet practical Federated Few-Shot Class-Incremental Learning (FFSCIL) problem, where clients only hold very few samples for new classes. We develop a novel Unified Optimized Prototype Prompt (UOPP) model to simultaneously handle catastrophic forgetting, over-fitting…
Previous ad auctions predominantly relied on rule-based mechanisms, which selected winning advertisements (ads) at the ad-level and subsequently combined them into page views (PVs), leading to suboptimal allocations in multi-round auctions. This limitation stems from the significant computational bu…
Audio deepfake refers to the technology of synthesizing speech using deep learning or large model algorithms. Compared to human voice, synthetic deepfake speech exhibits artifacts at global and local levels, which can be leveraged by audio deepfake detection (ADD) to distinguish real and fake speech…
It is often challenging to identify a valid instrumental variable (IV), although the IV methods have been regarded as effective tools of addressing the confounding bias introduced by latent variables. To deal with this issue, an Interaction-Data-guided Conditional IV (IDCIV) debiasing method is prop
Large language models (LLMs) have gained increasing attention in recommender systems, but their inherent hallucination issues significantly compromise the accuracy and reliability of recommendation results. Existing LLM-based recommender systems predominantly rely on standard fine-tuning methodologi
This paper presents the development of a multiple-input multiple-output (MIMO) coupling controller for the independent-setup variable stiffness actuator (VSA). The dynamic model of the independent-setup VSA is typically considered decoupled due to the slight coupling between the joint and stiffness
The data privacy constraint in online continual learning (OCL), where the data can be seen only once, complicates the catastrophic forgetting problem in streaming data. A common approach applied by the current SOTAs in OCL is the use of memory-saving exemplars or features from previous classes to be…
Estimating causal effects is crucial for decision-makers in many applications, but it is particularly challenging with observational network data due to peer interactions. Some algorithms have been proposed to estimate causal effects involving network data, particularly peer effects, but they often…
The prompt-based approach has demonstrated its success for continual learning problems. However, it still suffers from catastrophic forgetting due to inter-task vector similarity and unfitted new components of previously learned tasks. On the other hand, the language-guided approach falls short of i…
Generative retrieval (GR) has emerged as a transformative paradigm in search and recommender systems, leveraging numeric-based identifier representations to enhance efficiency and generalization. Notably, methods like TIGER, which employ Residual Quantization-based Semantic Identifiers (RQ-SID), hav…
An essential and challenging problem in causal inference is causal effect estimation from observational data. The problem becomes more difficult with the presence of unobserved confounding variables. The front-door adjustment is an approach for dealing with unobserved confounding variables. However,…
This paper studies the challenging problem of estimating causal effects from observational data, in the presence of unobserved confounders. The two-stage least square (TSLS) method and its variants with a standard instrumental variable (IV) are commonly used to eliminate confounding bias, including…
Semiparametric statistics play a pivotal role in a wide range of domains, including but not limited to missing data, causal inference, and transfer learning, to name a few. In many settings, semiparametric theory leads to (nearly) statistically optimal procedures that yet involve numerically solving…
As an emerging research direction, federated causal structure learning (CSL) aims at learning causal relationships from decentralized data across multiple clients while preserving data privacy. Existing federated CSL algorithms suffer from scalability and accuracy issues, since they require computat…
"Integrating LiDAR and camera information into Bird’s-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate calibration relationship between LiDAR and the camera sensor. Such inaccuracie…
Causal inference from longitudinal observational data is a challenging problem due to the difficulty in correctly identifying the time-dependent confounders, especially in the presence of latent time-dependent confounders. Instrumental variable (IV) is a powerful tool for addressing the latent confo…
As an effective tool for eliciting the power of Large Language Models (LLMs), prompting has recently demonstrated unprecedented abilities across a variety of complex tasks. To further improve the performance, prompt ensemble has attracted substantial interest for tackling the hallucination and insta…
Multi-modal 3D object detectors are dedicated to exploring secure and reliable perception systems for autonomous driving (AD). Although achieving state-of-the-art (SOTA) performance on clean benchmark datasets, they tend to overlook the complexity and harsh conditions of real-world environments. Wit…
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED. Pretrained AST models have recently shown promise on DCASE2022 challenge task4 where t…
The instrumental variable (IV) approach is a widely used way to estimate the causal effects of a treatment on an outcome of interest from observational data with latent confounders. A standard IV is expected to be related to the treatment variable and independent of all other variables in the system…
Many virtual reality applications require massive 3D content, which impels the need for low-cost and efficient modeling tools in terms of quality and quantity. In this paper, we present a Diffusion-augmented Generative model to generate high-fidelity 3D textured meshes that can be directly used in m…
Estimating direct and indirect causal effects from observational data is crucial to understanding the causal mechanisms and predicting the behaviour under different interventions. Causal mediation analysis is a method that is often used to reveal direct and indirect effects. Deep learning shows prom…
Face clustering is a method for unlabeled image annotation and has attracted increasing attention. Existing methods have made significant breakthroughs by introducing Graph Convolutional Networks (GCNs) on the affinity graph. However, such graphs will contain many vertex pairs with inconsistent simi…
The advancement of Offline Reinforcement Learning (RL) and Offline Multi-Agent Reinforcement Learning (MARL) critically depends on the availability of high-quality, pre-collected offline datasets that represent real-world complexities and practical applications. However, existing datasets often fall…
Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the…
The success of the Segment Anything Model (SAM) demonstrates the significance of data-centric machine learning. However, due to the difficulties and high costs associated with annotating Remote Sensing (RS) images, a large amount of valuable RS data remains unlabeled, particularly at the pixel level…
Unobserved confounding is the main obstacle to causal effect estimation from observational data. Instrumental variables (IVs) are widely used for causal effect estimation when there exist latent confounders. With the standard IV method, when a given IV is valid, unbiased estimation can be obtained,…
Causal mediation analysis can unpack the black box of causality and is therefore a powerful tool for disentangling causal pathways in biomedical and social sciences, and also for evaluating machine learning fairness. To reduce bias for estimating Natural Direct and Indirect Effects in mediation anal…
This paper presents a domain robust deep embedding learning method for speaker verification (SV) tasks. Most recent methods utilize deep neural networks (DNN) to learn compact and discriminative speaker embeddings from large-scale labeled datasets such as VoxCeleb and the NIST SRE corpus. Despite th…
Speech emotion recognition (SER) with limited size dataset is a challenging task, since a spoken utterance contains various disturbing attributes besides emotion, including speaker, content, and language. However, due to a close relationship between speaker and emotion attributes, simply fine-tuning…
In this paper, a self-supervised representation learning method is proposed for anomalous sound detection (ASD). ASD has received much research attention in recent DCASE challenges. It aims to identify whether a sound emitted from a machine is anomalous or not, given only normal sound data. This is…
We propose a novel zero-shot multi-frame image restoration method for removing unwanted obstruction elements (such as rains, snow, and moire patterns) that vary in successive frames. It has three stages: transformer pre-training, zero-shot restoration, and hard patch refinement. Using the pre-traine…
"Learning a generalized prior for natural image restoration is an important yet challenging task. Early methods mostly involved handcrafted priors including normalized sparsity, â„“0 gradients, dark channel priors, etc.. Recently, deep neural networks have been used to learn various image priors but…
In this paper, we present an effective end-to-end deep embedding learning method based on Dense-Residual networks, which combine the advantages of a densely connected convolutional network (DenseNet) and a residual network (ResNet), for speaker verification (SV). Unlike a model ensemble strategy whi…
This paper presents an improved mean teacher (MT) based method for large-scale weakly labeled semi-supervised sound event detection (SED), by focusing on learning a better student model. Two main improvements are proposed based on the authors’ previous perturbation based MT method. Firstly, an event…
Much research has been devoted to the problem of estimating treatment effects from observational data; however, most methods assume that the observed variables only contain confounders, i.e., variables that affect both the treatment and the outcome. Unfortunately, this assumption is frequently viola…
Attribute recognition is a crucial but challenging task due to viewpoint changes, illumination variations and appearance diversities, etc. Most of previous work only consider the attribute-level feature embedding, which might perform poorly in complicated heterogeneous conditions. To address this pr…
Usually located at the very early stages of the computational photography pipeline, demosaicing and denoising play important parts in the modern camera image processing. Recently, some neural networks have shown the effectiveness in joint demosaicing and denoising (JDD). Most of them first decompose…
Moiré artifacts are common in digital photography, resulting from the interference between high-frequency scene content and the color filter array of the camera. Existing deep learning-based demoiréing methods trained on large scale datasets are limited in handling various complex moiré patterns, an…
When smartphone cameras are used to take photos of digital screens, usually moire patterns result, severely degrading photo quality. In this paper, we design a wavelet-based dual-branch network (WDNet) with a spatial attention mechanism for image demoireing. Existing image restoration methods workin…