29 accepted papers
The rapid evolution of 3D scene generation has revolutionized content creation across domains such as gaming, film production, and architectural visualization. Within this landscape, interaction techniques serve as the pivotal bridge connecting user intent with generative models, enabling precise co
Magnetic Resonance Imaging (MRI) and its automatic segmentation are pivotal in assisting physicians with clinical diagnosis. In recent years, with the scarcity of labeled data, significant advancements have been made in semi-supervised segmentation. However, the prediction of many current methods is
Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for model compression, techniques developed for general machine l…
SAM3D enables scalable, open-world 3D reconstruction from complex scenes, yet its deployment is hindered by prohibitive inference latency. In this work, we conduct the **first systematic investigation** into its inference dynamics, revealing that generic acceleration strategies are brittle in this c…
With advances in reinforcement learning and imitation learning, quadruped robots can acquire diverse skills within a single policy by imitating multiple skill-specific datasets. However, the lack of datasets on complex terrains limits the ability of such multi-skill policies to generalize effectivel…
Audio-visual deepfake detection (AVD) is increasingly important as modern generators can fabricate convincing speech and video. Most current multimodal detectors are small, task-specific models: they work well on curated tests but scale poorly and generalize weakly across domains. We introduce AV-LM…
Wheeled-legged robots hold promise for traversing complex terrains and offer superior mobility compared to legged robots. However, wheeled-legged robots must effectively balance both wheeled driving and legged control. Furthermore, due to noisy proprioceptive sensing and real-world motor constraints…
Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and attention sparsification are two promising directions for compression, but each alone suffers severe performance degradation…
Learning-based 3D reconstruction models, represented by Visual Geometry Grounded Transformers (VGGTs), have achieved remarkable progress with large-scale transformers. Their prohibitive computational and memory costs severely hinder real-world deployment. Post-Training Quantization (PTQ) has emerged…
Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational efficiency, an essential factor for low-latency speech processing in real-time applications. In this paper, we propose
Diffusion-based world models have shown strong potential for unified world simulation, but the iterative denoising remains too costly for interactive use and long-horizon rollouts. While feature caching can accelerate inference without training, we find that policies designed for single-modal diffus…
Diffusion transformers have emerged as the mainstream paradigm for video generation models. However, the use of up to billions of parameters incurs significant computational costs. Quantization offers a promising solution by reducing memory usage and accelerating inference. Nonetheless, we observe t…
Knowledge Distillation (KD) aims to improve a light-weight student network supervised by a large teacher network. The core idea of KD is to explore valuable knowledge from the teacher. Previous works often extract information from a single sample, but ignore relation modeling among multiple samples…
Diffusion transformer (DiT) architecture catches much attention in image generation, which achieves better fidelity, performance, and diversity. However, most existing DiT-based image generation methods are global-aware synthesis and regional prompt control is less explored. In this paper, we propos…
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…
Spatiotemporal forecasting tasks, such as traffic flow, combustion dynamics, and weather forecasting, often require complex models that suffer from low training efficiency and high memory consumption. This paper proposes a lightweight framework, Spectral Decoupled Knowledge Distillation, which trans…
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…
The primary challenges in visible-infrared person re-identification arise from the differences between visible (vis) and infrared (ir) images, including inter-modal and intra-modal variations. These challenges are further complicated by varying viewpoints and irregular movements. Existing methods of…
In the realm of DeepFake detection, the challenge of adapting to various synthesis methodologies such as Faceswap, Deepfakes, Face2Face, and NeuralTextures significantly impacts the performance of traditional machine learning models. These models often suffer from static feature representation, whic…
This paper presents SpecWav-Attack, an adversarial model for detecting speakers in anonymized speech. It leverages Wav2Vec2 for feature extraction [1] and incorporates spectrogram resizing and incremental training for improved performance. Evaluated on librispeech-dev and librispeech-test, SpecWav-A…
Recent state-of-the-art zero-shot cross-lingual spoken language understanding (SLU) models utilize contrastive learning to achieve multilingual semantics alignment between the original utterance and code-switched counterpart. Despite achieving promising results, we discover that they still suffer fr…
Battery degradation remains a pivotal concern in the energy storage domain, with machine learning emerging as a potent tool to drive forward insights and solutions. However, this intersection of electrochemical science and machine learning poses complex challenges. Machine learning experts often gra…
The vision transformer (ViT) has recently emerged as a leading approach in various domains, outperforming other methods. Therefore, it is logical to explore the possibility of transferring the superior knowledge from ViT to more compact and cost-effective convolutional neural networks (CNNs). Howeve…
We propose Multi-spectral Neural Radiance Fields(Spec-NeRF) for jointly reconstructing a multispectral radiance field and spectral sensitivity functions(SSFs) of the camera from a set of color images filtered by different filters. The proposed method focuses on modeling the physical imaging process,…
In tiny object detection, the main challenges are tiny objects’ weak feature responses and possible semantic disappearance in deep networks. To address the problems, we proposed an Instance-level, Scale-adaptive, Shape-preserved, and Semantic-consistent Supervision (I4S) module for better locating t…
Neural network pruning offers a promising prospect to compress and accelerate modern deep convolution networks. The stripe-wise pruning method with a finer granularity than traditional methods has become the focus of research. Inspired by the previous work, a new balanced stripe-wise pruning, includ…
This paper examines the problem of illumination spectra estimation in multispectral images. We cast the problem into a constrained matrix factorization problem and present a method for both single-global and multiple illumination estimation in which a deep unrolling network is constructed from the a…
Imaging depth and spectrum have been extensively studied in isolation from each other for decades. Recently, hyperspectral-depth (HS-D) imaging emerges to capture both information simultaneously by combining two different imaging systems; one for depth, the other for spectrum. While being accurate,…
A Generative Adversarial Network (GAN) with generator G trained to model the prior of images has been shown to perform better than sparsity-based regularizers in ill-posed inverse problems. Here, we propose a new method of deploying a GAN-based prior to solve linear inverse problems using projected…