Since videos record objects moving coherently, adjacent video frames have commonness (similar object appearances) and uniqueness (slightly changed postures). To prevent redundant modeling of common video signals, we propose a novel diffusion-based framework, named COMUNI, which decomposes the COMmon and UNIque video signals to enable efficient video generation. Our approach separates the decomposition of video signals from the task of video generation, thus reducing the computation complexity of generative models. In particular, we introduce CU-VAE to decompose video signals and encode them into latent features. To train CU-VAE in a self-supervised manner, we employ a cascading merge module to reconstitute video signals and a time-agnostic video decoder to reconstruct video frames. Then we propose CU-LDM to model latent features for video generation, which adopts two specific diffusion streams to simultaneously model the common and unique latent features. We further utilize additional joint modules for cross modeling of the common and unique latent features, and a novel position embedding method to ensure the content consistency and motion coherence of generated videos. The position embedding method incorporates spatial and temporal absolute position information into the joint modules. Extensive experiments demonstrate the necessity of decomposing common and unique video signals for video generation and the effectiveness and efficiency of our proposed method.
相關內容
AI companions based on large language models can role-play and converse very naturally. When value conflicts arise between the AI companion and the user, it may offend or upset the user. Yet, little research has examined such conflicts. We first conducted a formative study that analyzed 151 user complaints about conflicts with AI companions, providing design implications for our study. Based on these, we created Minion, a technology probe to help users resolve human-AI value conflicts. Minion applies a user-empowerment intervention method that provides suggestions by combining expert-driven and user-driven conflict resolution strategies. We conducted a technology probe study, creating 40 value conflict scenarios on Character.AI and Talkie. 22 participants completed 274 tasks and successfully resolved conflicts 94.16% of the time. We summarize user responses, preferences, and needs in resolving value conflicts, and propose design implications to reduce conflicts and empower users to resolve them more effectively.
Selective state space models (SSMs) represented by Mamba have demonstrated their computational efficiency and promising outcomes in various tasks, including automatic speech recognition (ASR). Mamba has been applied to ASR task with the attention-based encoder-decoder framework, where the cross-attention mechanism between encoder and decoder remains. This paper explores the capability of Mamba as the decoder-only architecture in ASR task. Our MAmba-based DEcoder-ONly approach (MADEON) consists of a single decoder that takes speech tokens as a condition and predicts text tokens in an autoregressive manner. To enhance MADEON, we further propose speech prefixing that performs bidirectional processing on speech tokens, which enriches the contextual information in the hidden states. Our experiments show that MADEON significantly outperforms a non-selective SSM. The combination of speech prefixing and the recently proposed Mamba-2 yields comparable performance to Transformer-based models on large datasets.
Large language models (LLMs) have received increasing attention. However, due to the complexity of its capabilities, how to rationally evaluate the capabilities of LLMs is still a task to be solved. We propose the RoCar method, which utilizes the defined basic schemas to randomly construct a task graph and generates natural language evaluation tasks based on the task graph to evaluate the reasoning and memory abilities of LLMs respectively. Due to the very large randomness of the task construction process, it is possible to ensure that none of the LLMs to be tested has directly learned the evaluation tasks, guaranteeing the fairness of the evaluation method.
Medical brain imaging relies heavily on image registration to accurately curate structural boundaries of brain features for various healthcare applications. Deep learning models have shown remarkable performance in image registration in recent years. Still, they often struggle to handle the diversity of 3D brain volumes, challenged by their structural and contrastive variations and their imaging domains. In this work, we present NeuReg, a Neuro-inspired 3D image registration architecture with the feature of domain invariance. NeuReg generates domain-agnostic representations of imaging features and incorporates a shifting window-based Swin Transformer block as the encoder. This enables our model to capture the variations across brain imaging modalities and species. We demonstrate a new benchmark in multi-domain publicly available datasets comprising human and mouse 3D brain volumes. Extensive experiments reveal that our model (NeuReg) outperforms the existing baseline deep learning-based image registration models and provides a high-performance boost on cross-domain datasets, where models are trained on 'source-only' domain and tested on completely 'unseen' target domains. Our work establishes a new state-of-the-art for domain-agnostic 3D brain image registration, underpinned by Neuro-inspired Transformer-based architecture.
The efficacy of diffusion models in generating a spectrum of data modalities, including images, text, and videos, has spurred inquiries into their utility in molecular generation, yielding significant advancements in the field. However, the molecular generation process with diffusion models involves multiple autoregressive steps over a finite time horizon, leading to exposure bias issues inherently. To address the exposure bias issue, we propose a training framework named GapDiff. The core idea of GapDiff is to utilize model-predicted conformations as ground truth probabilistically during training, aiming to mitigate the data distributional disparity between training and inference, thereby enhancing the affinity of generated molecules. We conduct experiments using a 3D molecular generation model on the CrossDocked2020 dataset, and the vina energy and diversity demonstrate the potency of our framework with superior affinity. GapDiff is available at \url{//github.com/HUGHNew/gapdiff}.
The transition from monolithic architecture to microservices has enhanced flexibility in application design and its scalable execution. This approach often involves using a computing cluster managed by a container orchestration platform, which supports the deployment of microservices. However, this shift introduces significant challenges, particularly in the efficient scheduling of containerized services. These challenges are compounded by unpredictable scenarios such as dynamic incoming workloads with various execution traffic and variable communication delays among cluster nodes. Existing works often overlook the real-time traffic impacts of dynamic requests on running microservices, as well as the varied communication delays across cluster nodes. Consequently, even optimally deployed microservices could suffer from significant performance degradation over time. To address these issues, we introduce a network and traffic-aware adaptive scheduling framework, TraDE. This framework can adaptively redeploy microservice containers to maintain desired performance amid changing traffic and network conditions within the hosting cluster. We have implemented TraDE as an extension to the Kubernetes platform. Additionally, we deployed realistic microservice applications in a real compute cluster and conducted extensive experiments to assess our framework's performance in various scenarios. The results demonstrate the effectiveness of TraDE in rescheduling running microservices to enhance end-to-end performance while maintaining a high goodput ratio. Compared with the existing method NetMARKS, TraDE outperforms it by reducing the average response time of the application by up to 48.3\%, and improving the throughput by up to 1.4x while maintaining a goodput ratio of 95.36\% and showing robust adaptive capability under sustained workloads.
The development of large language models (LLMs) has expanded to multi-modal systems capable of processing text, images, and speech within a unified framework. Training these models demands significantly larger datasets and computational resources compared to text-only LLMs. To address the scaling challenges, we introduce Mixture-of-Transformers (MoT), a sparse multi-modal transformer architecture that significantly reduces pretraining computational costs. MoT decouples non-embedding parameters of the model by modality -- including feed-forward networks, attention matrices, and layer normalization -- enabling modality-specific processing with global self-attention over the full input sequence. We evaluate MoT across multiple settings and model scales. In the Chameleon 7B setting (autoregressive text-and-image generation), MoT matches the dense baseline's performance using only 55.8\% of the FLOPs. When extended to include speech, MoT reaches speech performance comparable to the dense baseline with only 37.2\% of the FLOPs. In the Transfusion setting, where text and image are trained with different objectives, a 7B MoT model matches the image modality performance of the dense baseline with one third of the FLOPs, and a 760M MoT model outperforms a 1.4B dense baseline across key image generation metrics. System profiling further highlights MoT's practical benefits, achieving dense baseline image quality in 47.2\% of the wall-clock time and text quality in 75.6\% of the wall-clock time (measured on AWS p4de.24xlarge instances with NVIDIA A100 GPUs).
Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive fine-tuning process. In response, TIP-Adapter and SuS-X have introduced training-free methods aimed at bolstering the efficacy of downstream tasks. While these approaches incorporate support sets to maintain data distribution consistency between knowledge cache and test sets, they often fall short in terms of generalization on the test set, particularly when faced with test data exhibiting substantial distributional variations. In this work, we present CapS-Adapter, an innovative method that employs a caption-based support set, effectively harnessing both image and caption features to exceed existing state-of-the-art techniques in training-free scenarios. CapS-Adapter adeptly constructs support sets that closely mirror target distributions, utilizing instance-level distribution features extracted from multimodal large models. By leveraging CLIP's single and cross-modal strengths, CapS-Adapter enhances predictive accuracy through the use of multimodal support sets. Our method achieves outstanding zero-shot classification results across 19 benchmark datasets, improving accuracy by 2.19\% over the previous leading method. Our contributions are substantiated through extensive validation on multiple benchmark datasets, demonstrating superior performance and robust generalization capabilities. Our code is made publicly available at //github.com/WLuLi/CapS-Adapter.
Scientists are increasingly leveraging advances in instruments, automation, and collaborative tools to scale up their experiments and research goals, leading to new bursts of discovery. Various scientific disciplines, including neuroscience, have adopted key technologies to enhance collaboration, reproducibility, and automation. Drawing inspiration from advancements in the software industry, we present a roadmap to enhance the reliability and scalability of scientific operations for diverse research teams tackling large and complex projects. We introduce a five-level Capability Maturity Model describing the principles of rigorous scientific operations in projects ranging from small-scale exploratory studies to large-scale, multi-disciplinary research endeavors. Achieving higher levels of operational maturity necessitates the adoption of new, technology-enabled methodologies, which we refer to as SciOps. This concept is derived from the DevOps methodologies that have revolutionized the software industry. SciOps involves digital research environments that seamlessly integrate computational, automation, and AI-driven efforts throughout the research cycle-from experimental design and data collection to analysis and dissemination, ultimately leading to closed-loop discovery. This maturity model offers a framework for assessing and improving operational practices in multidisciplinary research teams, guiding them towards greater efficiency and effectiveness in scientific inquiry.
InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions
Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences. ConvE, a recently proposed approach, applies convolutional filters on 2D reshapings of entity and relation embeddings in order to capture rich interactions between their components. However, the number of interactions that ConvE can capture is limited. In this paper, we analyze how increasing the number of these interactions affects link prediction performance, and utilize our observations to propose InteractE. InteractE is based on three key ideas -- feature permutation, a novel feature reshaping, and circular convolution. Through extensive experiments, we find that InteractE outperforms state-of-the-art convolutional link prediction baselines on FB15k-237. Further, InteractE achieves an MRR score that is 9%, 7.5%, and 23% better than ConvE on the FB15k-237, WN18RR and YAGO3-10 datasets respectively. The results validate our central hypothesis -- that increasing feature interaction is beneficial to link prediction performance. We make the source code of InteractE available to encourage reproducible research.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191